sha
stringlengths 40
40
| text
stringlengths 1
13.4M
| id
stringlengths 2
117
| tags
listlengths 1
7.91k
| created_at
stringlengths 25
25
| metadata
stringlengths 2
875k
| last_modified
stringlengths 25
25
| arxiv
listlengths 0
25
| languages
listlengths 0
7.91k
| tags_str
stringlengths 17
159k
| text_str
stringlengths 1
447k
| text_lists
listlengths 0
352
| processed_texts
listlengths 1
353
| tokens_length
listlengths 1
353
| input_texts
listlengths 1
40
|
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
b901a0fb9df41f6f14a665cbc2e3911a9b6c8cf3 | # Dataset Card for "orca-alpaca-gpt4"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | We-Want-GPU/orca-alpaca-gpt4 | [
"region:us"
] | 2023-12-15T01:41:01+00:00 | {"dataset_info": {"features": [{"name": "input", "dtype": "string"}, {"name": "instruction", "dtype": "string"}, {"name": "output", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 103279020, "num_examples": 84183}], "download_size": 55144109, "dataset_size": 103279020}} | 2023-12-15T01:41:12+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "orca-alpaca-gpt4"
More Information needed | [
"# Dataset Card for \"orca-alpaca-gpt4\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"orca-alpaca-gpt4\"\n\nMore Information needed"
] | [
6,
19
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"orca-alpaca-gpt4\"\n\nMore Information needed"
] |
2232325d455f3c8f8232aa6a7ae3ccf7f45614cb | # Dataset Card for "orca-alpaca-gpt4-math"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | We-Want-GPU/orca-alpaca-gpt4-math | [
"region:us"
] | 2023-12-15T01:56:03+00:00 | {"dataset_info": {"features": [{"name": "input", "dtype": "string"}, {"name": "instruction", "dtype": "string"}, {"name": "output", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 132170356, "num_examples": 124183}], "download_size": 69522299, "dataset_size": 132170356}} | 2023-12-15T01:56:17+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "orca-alpaca-gpt4-math"
More Information needed | [
"# Dataset Card for \"orca-alpaca-gpt4-math\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"orca-alpaca-gpt4-math\"\n\nMore Information needed"
] | [
6,
20
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"orca-alpaca-gpt4-math\"\n\nMore Information needed"
] |
345c162f226bb4e501e3aa0bc2f4ff9172374d03 |
# Dataset Card for Dataset Name
<!-- Provide a quick summary of the dataset. -->
This dataset card aims to be a base template for new datasets. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/datasetcard_template.md?plain=1).
## Dataset Details
### Dataset Description
<!-- Provide a longer summary of what this dataset is. -->
- **Curated by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
### Dataset Sources [optional]
<!-- Provide the basic links for the dataset. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the dataset is intended to be used. -->
### Direct Use
<!-- This section describes suitable use cases for the dataset. -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the dataset will not work well for. -->
[More Information Needed]
## Dataset Structure
<!-- This section provides a description of the dataset fields, and additional information about the dataset structure such as criteria used to create the splits, relationships between data points, etc. -->
[More Information Needed]
## Dataset Creation
### Curation Rationale
<!-- Motivation for the creation of this dataset. -->
[More Information Needed]
### Source Data
<!-- This section describes the source data (e.g. news text and headlines, social media posts, translated sentences, ...). -->
#### Data Collection and Processing
<!-- This section describes the data collection and processing process such as data selection criteria, filtering and normalization methods, tools and libraries used, etc. -->
[More Information Needed]
#### Who are the source data producers?
<!-- This section describes the people or systems who originally created the data. It should also include self-reported demographic or identity information for the source data creators if this information is available. -->
[More Information Needed]
### Annotations [optional]
<!-- If the dataset contains annotations which are not part of the initial data collection, use this section to describe them. -->
#### Annotation process
<!-- This section describes the annotation process such as annotation tools used in the process, the amount of data annotated, annotation guidelines provided to the annotators, interannotator statistics, annotation validation, etc. -->
[More Information Needed]
#### Who are the annotators?
<!-- This section describes the people or systems who created the annotations. -->
[More Information Needed]
#### Personal and Sensitive Information
<!-- State whether the dataset contains data that might be considered personal, sensitive, or private (e.g., data that reveals addresses, uniquely identifiable names or aliases, racial or ethnic origins, sexual orientations, religious beliefs, political opinions, financial or health data, etc.). If efforts were made to anonymize the data, describe the anonymization process. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.
## Citation [optional]
<!-- If there is a paper or blog post introducing the dataset, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the dataset or dataset card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Dataset Card Authors [optional]
[More Information Needed]
## Dataset Card Contact
[More Information Needed] | ziamor/nova_test | [
"region:us"
] | 2023-12-15T03:03:50+00:00 | {"dataset_info": {"features": [{"name": "inputs", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 5121, "num_examples": 30}], "download_size": 3043, "dataset_size": 5121}} | 2023-12-15T13:52:13+00:00 | [] | [] | TAGS
#region-us
|
# Dataset Card for Dataset Name
This dataset card aims to be a base template for new datasets. It has been generated using this raw template.
## Dataset Details
### Dataset Description
- Curated by:
- Funded by [optional]:
- Shared by [optional]:
- Language(s) (NLP):
- License:
### Dataset Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Out-of-Scope Use
## Dataset Structure
## Dataset Creation
### Curation Rationale
### Source Data
#### Data Collection and Processing
#### Who are the source data producers?
### Annotations [optional]
#### Annotation process
#### Who are the annotators?
#### Personal and Sensitive Information
## Bias, Risks, and Limitations
### Recommendations
Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Dataset Card Authors [optional]
## Dataset Card Contact
| [
"# Dataset Card for Dataset Name\n\n\n\nThis dataset card aims to be a base template for new datasets. It has been generated using this raw template.",
"## Dataset Details",
"### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:",
"### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Out-of-Scope Use",
"## Dataset Structure",
"## Dataset Creation",
"### Curation Rationale",
"### Source Data",
"#### Data Collection and Processing",
"#### Who are the source data producers?",
"### Annotations [optional]",
"#### Annotation process",
"#### Who are the annotators?",
"#### Personal and Sensitive Information",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Dataset Card Authors [optional]",
"## Dataset Card Contact"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for Dataset Name\n\n\n\nThis dataset card aims to be a base template for new datasets. It has been generated using this raw template.",
"## Dataset Details",
"### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:",
"### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Out-of-Scope Use",
"## Dataset Structure",
"## Dataset Creation",
"### Curation Rationale",
"### Source Data",
"#### Data Collection and Processing",
"#### Who are the source data producers?",
"### Annotations [optional]",
"#### Annotation process",
"#### Who are the annotators?",
"#### Personal and Sensitive Information",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Dataset Card Authors [optional]",
"## Dataset Card Contact"
] | [
6,
34,
4,
40,
29,
3,
4,
9,
6,
5,
7,
4,
7,
10,
9,
5,
9,
8,
10,
46,
8,
7,
10,
5
] | [
"passage: TAGS\n#region-us \n# Dataset Card for Dataset Name\n\n\n\nThis dataset card aims to be a base template for new datasets. It has been generated using this raw template.## Dataset Details### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Out-of-Scope Use## Dataset Structure## Dataset Creation### Curation Rationale### Source Data#### Data Collection and Processing#### Who are the source data producers?### Annotations [optional]#### Annotation process#### Who are the annotators?#### Personal and Sensitive Information## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Dataset Card Authors [optional]## Dataset Card Contact"
] |
127cf946e29a5250bdd91fdf587e06cd1a4fa6bb | # Dataset Card for "envi-marco-passage-corpus"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | tiennv/mmarco-passage-envi-corpus | [
"region:us"
] | 2023-12-15T03:59:45+00:00 | {"dataset_info": {"features": [{"name": "id", "dtype": "int64"}, {"name": "title", "dtype": "string"}, {"name": "english", "dtype": "string"}, {"name": "vietnamese", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 7142588566, "num_examples": 8841823}], "download_size": 3705975001, "dataset_size": 7142588566}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]} | 2023-12-15T04:08:14+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "envi-marco-passage-corpus"
More Information needed | [
"# Dataset Card for \"envi-marco-passage-corpus\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"envi-marco-passage-corpus\"\n\nMore Information needed"
] | [
6,
21
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"envi-marco-passage-corpus\"\n\nMore Information needed"
] |
b18347ef4ff91fae1b2533a9d99eb3f59dea40c8 | # Dataset Card for "processed-subset-bestofredditorupdates"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | derek-thomas/processed-subset-bestofredditorupdates | [
"region:us"
] | 2023-12-15T05:14:05+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}], "dataset_info": {"features": [{"name": "id", "dtype": "string"}, {"name": "content", "dtype": "string"}, {"name": "score", "dtype": "int64"}, {"name": "date_utc", "dtype": "timestamp[ns]"}, {"name": "title", "dtype": "string"}, {"name": "flair", "dtype": "string"}, {"name": "poster", "dtype": "string"}, {"name": "permalink", "dtype": "string"}, {"name": "updated", "dtype": "bool"}, {"name": "new", "dtype": "bool"}, {"name": "embedding", "sequence": "float64"}], "splits": [{"name": "train", "num_bytes": 128012062, "num_examples": 10355}], "download_size": 95501729, "dataset_size": 128012062}} | 2023-12-27T06:42:38+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "processed-subset-bestofredditorupdates"
More Information needed | [
"# Dataset Card for \"processed-subset-bestofredditorupdates\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"processed-subset-bestofredditorupdates\"\n\nMore Information needed"
] | [
6,
23
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"processed-subset-bestofredditorupdates\"\n\nMore Information needed"
] |
caf9bbeba04268700ad7884407e7c7212e948199 |
The training dataset for verifiers, which is generated by the finetuned models in GSM8K and Game of 24. The models are open-sourced in [OVM-llama2-7b](https://huggingface.co/FreedomIntelligence/OVM-llama2-7b) and [OVM-Mistral-7b](https://huggingface.co/FreedomIntelligence/OVM-Mistral-7b).
See the paper [Outcome-supervised Verifiers for Planning in Mathematical Reasoning](https://arxiv.org/pdf/2311.09724.pdf) and the code in [github](https://github.com/FreedomIntelligence/OVM)
| FreedomIntelligence/OVM-dataset | [
"license:llama2",
"arxiv:2311.09724",
"region:us"
] | 2023-12-15T05:27:10+00:00 | {"license": "llama2"} | 2023-12-15T07:26:14+00:00 | [
"2311.09724"
] | [] | TAGS
#license-llama2 #arxiv-2311.09724 #region-us
|
The training dataset for verifiers, which is generated by the finetuned models in GSM8K and Game of 24. The models are open-sourced in OVM-llama2-7b and OVM-Mistral-7b.
See the paper Outcome-supervised Verifiers for Planning in Mathematical Reasoning and the code in github
| [] | [
"TAGS\n#license-llama2 #arxiv-2311.09724 #region-us \n"
] | [
22
] | [
"passage: TAGS\n#license-llama2 #arxiv-2311.09724 #region-us \n"
] |
6482db9cb22dbc755f5dd5d6a565e2917ad0613a | # reddew
Reddit Download and Datasets
| chitradrishti/reddew | [
"region:us"
] | 2023-12-15T05:29:26+00:00 | {} | 2024-01-03T04:22:00+00:00 | [] | [] | TAGS
#region-us
| # reddew
Reddit Download and Datasets
| [
"# reddew\nReddit Download and Datasets"
] | [
"TAGS\n#region-us \n",
"# reddew\nReddit Download and Datasets"
] | [
6,
9
] | [
"passage: TAGS\n#region-us \n# reddew\nReddit Download and Datasets"
] |
c45916dc968f096197b4c55c0141a1171b6bb732 |
This dataset is used for training models on a classification problem involving images from anime and real-world.
* Anime images: illustrations, manga, screenshots from anime series, and 3D modeling (e.g., Koikatsu, MikuMikuDance).
* Real images: photographs from the real world and realistic-style drawings.
| Version | Anime | Real |
|:-------:|:-----:|:-----:|
| v0 | 59707 | 59997 |
| deepghs/anime_real_cls | [
"task_categories:image-classification",
"size_categories:100K<n<1M",
"license:openrail",
"art",
"region:us"
] | 2023-12-15T06:23:43+00:00 | {"license": "openrail", "size_categories": ["100K<n<1M"], "task_categories": ["image-classification"], "tags": ["art"]} | 2023-12-16T09:00:02+00:00 | [] | [] | TAGS
#task_categories-image-classification #size_categories-100K<n<1M #license-openrail #art #region-us
| This dataset is used for training models on a classification problem involving images from anime and real-world.
* Anime images: illustrations, manga, screenshots from anime series, and 3D modeling (e.g., Koikatsu, MikuMikuDance).
* Real images: photographs from the real world and realistic-style drawings.
| [] | [
"TAGS\n#task_categories-image-classification #size_categories-100K<n<1M #license-openrail #art #region-us \n"
] | [
37
] | [
"passage: TAGS\n#task_categories-image-classification #size_categories-100K<n<1M #license-openrail #art #region-us \n"
] |
219f4b70bc9bf779813e550b45d3bef5850dfd3f | # Dataset Card for "cifar10-enrichments"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | MarkusStoll/cifar10-enrichments | [
"region:us"
] | 2023-12-15T06:57:45+00:00 | {"dataset_info": {"features": [{"name": "embedding", "sequence": "float32"}], "splits": [{"name": "test", "num_bytes": 30760000, "num_examples": 10000}], "download_size": 36966542, "dataset_size": 30760000}, "configs": [{"config_name": "default", "data_files": [{"split": "test", "path": "data/test-*"}]}]} | 2023-12-15T06:57:57+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "cifar10-enrichments"
More Information needed | [
"# Dataset Card for \"cifar10-enrichments\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"cifar10-enrichments\"\n\nMore Information needed"
] | [
6,
17
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"cifar10-enrichments\"\n\nMore Information needed"
] |
3b08fb10f96cab50e2cf5fd616a76a3bfb299c11 |
# Dataset of universal_bulin (Azur Lane)
This is the dataset of universal_bulin (Azur Lane), containing 14 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by [DeepGHS Team](https://github.com/deepghs)([huggingface organization](https://huggingface.co/deepghs)).
This is a WebUI contains crawlers and other thing: ([LittleAppleWebUI](https://github.com/LittleApple-fp16/LittleAppleWebUI))
| Name | Images | Download | Description |
|:----------------|---------:|:----------------------------------------|:-----------------------------------------------------------------------------------------|
| raw | 14 | [Download](dataset-raw.zip) | Raw data with meta information. |
| raw-stage3 | 35 | [Download](dataset-raw-stage3.zip) | 3-stage cropped raw data with meta information. |
| raw-stage3-eyes | 39 | [Download](dataset-raw-stage3-eyes.zip) | 3-stage cropped (with eye-focus) raw data with meta information. |
| 384x512 | 14 | [Download](dataset-384x512.zip) | 384x512 aligned dataset. |
| 512x704 | 14 | [Download](dataset-512x704.zip) | 512x704 aligned dataset. |
| 640x880 | 14 | [Download](dataset-640x880.zip) | 640x880 aligned dataset. |
| stage3-640 | 35 | [Download](dataset-stage3-640.zip) | 3-stage cropped dataset with the shorter side not exceeding 640 pixels. |
| stage3-800 | 35 | [Download](dataset-stage3-800.zip) | 3-stage cropped dataset with the shorter side not exceeding 800 pixels. |
| stage3-p512-640 | 27 | [Download](dataset-stage3-p512-640.zip) | 3-stage cropped dataset with the area not less than 512x512 pixels. |
| stage3-eyes-640 | 39 | [Download](dataset-stage3-eyes-640.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 640 pixels. |
| stage3-eyes-800 | 39 | [Download](dataset-stage3-eyes-800.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 800 pixels. |
| AppleHarem/universal_bulin_azurlane | [
"task_categories:text-to-image",
"size_categories:n<1K",
"license:mit",
"art",
"not-for-all-audiences",
"region:us"
] | 2023-12-15T07:14:49+00:00 | {"license": "mit", "size_categories": ["n<1K"], "task_categories": ["text-to-image"], "tags": ["art", "not-for-all-audiences"]} | 2023-12-15T07:14:51+00:00 | [] | [] | TAGS
#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us
| Dataset of universal\_bulin (Azur Lane)
=======================================
This is the dataset of universal\_bulin (Azur Lane), containing 14 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by DeepGHS Team(huggingface organization).
This is a WebUI contains crawlers and other thing: (LittleAppleWebUI)
| [] | [
"TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] | [
44
] | [
"passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] |
a0de583366a5a5ca2a1789c5eca25abec749b325 |
# Dataset of vanilla (Arknights)
This is the dataset of vanilla (Arknights), containing 30 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by [DeepGHS Team](https://github.com/deepghs)([huggingface organization](https://huggingface.co/deepghs)).
This is a WebUI contains crawlers and other thing: ([LittleAppleWebUI](https://github.com/LittleApple-fp16/LittleAppleWebUI))
| Name | Images | Download | Description |
|:----------------|---------:|:----------------------------------------|:-----------------------------------------------------------------------------------------|
| raw | 30 | [Download](dataset-raw.zip) | Raw data with meta information. |
| raw-stage3 | 65 | [Download](dataset-raw-stage3.zip) | 3-stage cropped raw data with meta information. |
| raw-stage3-eyes | 68 | [Download](dataset-raw-stage3-eyes.zip) | 3-stage cropped (with eye-focus) raw data with meta information. |
| 384x512 | 30 | [Download](dataset-384x512.zip) | 384x512 aligned dataset. |
| 512x704 | 30 | [Download](dataset-512x704.zip) | 512x704 aligned dataset. |
| 640x880 | 30 | [Download](dataset-640x880.zip) | 640x880 aligned dataset. |
| stage3-640 | 65 | [Download](dataset-stage3-640.zip) | 3-stage cropped dataset with the shorter side not exceeding 640 pixels. |
| stage3-800 | 65 | [Download](dataset-stage3-800.zip) | 3-stage cropped dataset with the shorter side not exceeding 800 pixels. |
| stage3-p512-640 | 31 | [Download](dataset-stage3-p512-640.zip) | 3-stage cropped dataset with the area not less than 512x512 pixels. |
| stage3-eyes-640 | 68 | [Download](dataset-stage3-eyes-640.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 640 pixels. |
| stage3-eyes-800 | 68 | [Download](dataset-stage3-eyes-800.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 800 pixels. |
| AppleHarem/vanilla_arknights | [
"task_categories:text-to-image",
"size_categories:n<1K",
"license:mit",
"art",
"not-for-all-audiences",
"region:us"
] | 2023-12-15T07:32:41+00:00 | {"license": "mit", "size_categories": ["n<1K"], "task_categories": ["text-to-image"], "tags": ["art", "not-for-all-audiences"]} | 2023-12-15T07:32:44+00:00 | [] | [] | TAGS
#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us
| Dataset of vanilla (Arknights)
==============================
This is the dataset of vanilla (Arknights), containing 30 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by DeepGHS Team(huggingface organization).
This is a WebUI contains crawlers and other thing: (LittleAppleWebUI)
| [] | [
"TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] | [
44
] | [
"passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] |
a1458cceebc5fa2c596669f93339958b971d4702 |
<p align="center">
<img width="250" alt="Camarim Logo" src="https://raw.githubusercontent.com/DominguesM/Canarim-Instruct-PTBR/main/assets/canarim.png">
</p>
<p align="center">
<a href="https://github.com/DominguesM/canarim">[🐱 GitHub]</a>
</p>
<hr>
# Canarim: A Large-Scale Dataset of Web Pages in the Portuguese Language
## Introduction
Canarim is a database encompassing over 342 million Portuguese language documents, sourced from multiple iterations of CommonCrawl. This nearly 1 terabyte database stands as one of the most extensive Portuguese language data collections available. It underwent initial deduplication using URLs, with plans for further text-based deduplication and filtering of potentially harmful content. The data, originally in HTML, has been converted to Markdown with the `Trafilatura` library to enhance readability and quality. Canarim is poised to be a crucial resource for NLP research, particularly in Portuguese language applications, filling the gap in large-scale, high-quality data for languages other than English.
## Dataset Structure
### Data Instances
An example looks as follows:
```json
{
"url": "...",
"content_languages": "por",
"warc_filename": "crawl-data/CC-MAIN-2023-06/segments/1674764500041.18/warc/CC-MAIN-20230202200542-20230202230542-00352.warc.gz",
"warc_record_offset": 971279893,
"warc_record_length": 3873,
"text": "...",
"crawl_timestamp": "2023-02-02T20:28:21Z"
}
```
### Data Fields
- `url`: URL of the page
- `content_languages`: Language of the page
- `warc_filename`: Name of the WARC file
- `warc_record_offset`: Offset of the WARC record
- `warc_record_length`: Length of the WARC record
- `text`: Text of the page, in Markdown format
- `crawl_timestamp`: Timestamp of the crawl
## Text Extraction Overview
The Canarim database employs the [`Trafilatura`](https://trafilatura.readthedocs.io) library for extracting textual content from HTML data, converting it into Markdown format. This tool focuses on preserving key textual elements like titles, subtitles, bold, and italic formatting in Markdown, ensuring the retention of the original document structure. During the extraction process, Trafilatura discards comments and other non-essential information, streamlining the content to include only the main body of the web pages.
</br>
<p align="center">
<img width="800" alt="Text Extraction Example" src="https://raw.githubusercontent.com/DominguesM/canarim/main/assets/canarim-text-extraction-preview.png">
</p>
<p align="center">
<a href="https://g1.globo.com/ac/acre/natureza/amazonia/noticia/2023/01/03/para-comemorar-40-anos-do-parque-zoobotanico-da-ufac-livro-vai-reunir-depoimentos-de-envolvidos-no-inicio-do-projeto.ghtml" target="_blank">Original Web Page</a> and
<a href="https://github.com/DominguesM/canarim/blob/main/assets/extracted_text.md" target="_blank">Extracted Text</a>
</p>
## Usage
Below is an example of how to quickly explore just a few samples from a dataset using the `datasets` library.
```python
!pip install -q datasets
from datasets import load_dataset
ds = load_dataset(
"dominguesm/canarim",
# Filter only the data from the `train split`
split="train",
# Filter only the files that contain the prefix `train/data-0019` and the suffix `-of-00192.arrow`
data_files="train/data-0019*-of-00192.arrow",
# Load the dataset without downloading the data (Streaming mode)
streaming=True
)
# From the returned data, filter only the data where the `url` value starts with `https://g1.globo.com/`
ds_globo = ds.filter(
lambda example: example['url'].startswith("https://g1.globo.com/")
)
# Return the first 10 examples from the applied filter.
data = list(ds_globo.take(10))
print(data[0])
# {
# "url": "https://g1.globo.com/ac/acre/(...)",
# "content_languages": "por",
# "warc_filename": "crawl-data/CC-MAIN-2023-06/segments/1674764499919.70/warc/CC-MAIN-20230201081311-20230201111311-00552.warc.gz",
# "warc_record_offset": 281625400,
# "warc_record_length": 192934,
# "text": "Parque Zoobotânico da Ufac guarda uma grande variedade espécies de árvores em Rio Branco — Foto: Arquivo/Ufac (...)",
# "crawl_timestamp": "2023-02-01T10:38:52Z"
# }
```
## Dataset Statistics
| Split | # Samples | # Size (bytes) | # Size (GB) |
| ------ | --------- | -------------- | ----------- |
| Train | 342,818,651 | 1,087,519,823,221 | 1087,51 |
## Citing
If you use Canarim in your research, please cite the following.
```bibtex
@misc {maicon_domingues_2024,
author = { {Maicon Domingues} },
title = { canarim (Revision 640e079) },
year = 2024,
url = { https://huggingface.co/datasets/dominguesm/canarim },
doi = { 10.57967/hf/1605 },
publisher = { Hugging Face }
}
```
## License
This dataset is licensed under the [Creative Commons Attribution 4.0 International (CC BY 4.0)](https://creativecommons.org/licenses/by/4.0/). You can use the dataset for any purpose, but you must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
## Contact
For any questions or suggestions, please contact [Maicon Domingues](https://nlp.rocks/). | dominguesm/canarim | [
"task_categories:text-generation",
"task_categories:fill-mask",
"task_ids:language-modeling",
"task_ids:masked-language-modeling",
"multilinguality:monolingual",
"size_categories:100M<n<1B",
"language:pt",
"license:cc-by-4.0",
"doi:10.57967/hf/1605",
"region:us"
] | 2023-12-15T07:57:57+00:00 | {"language": "pt", "license": "cc-by-4.0", "multilinguality": ["monolingual"], "size_categories": ["100M<n<1B"], "task_categories": ["text-generation", "fill-mask"], "task_ids": ["language-modeling", "masked-language-modeling"], "pretty_name": "Canarim", "dataset_info": {"features": [{"name": "url", "dtype": "string"}, {"name": "content_languages", "dtype": "string"}, {"name": "warc_filename", "dtype": "string"}, {"name": "warc_record_offset", "dtype": "int64"}, {"name": "warc_record_length", "dtype": "int64"}, {"name": "text", "dtype": "string"}, {"name": "crawl_timestamp", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 1087519823221, "num_examples": 342818651}], "download_size": 1087713663056, "dataset_size": 1087519823221}} | 2024-01-14T14:48:31+00:00 | [] | [
"pt"
] | TAGS
#task_categories-text-generation #task_categories-fill-mask #task_ids-language-modeling #task_ids-masked-language-modeling #multilinguality-monolingual #size_categories-100M<n<1B #language-Portuguese #license-cc-by-4.0 #doi-10.57967/hf/1605 #region-us
|
[
[Original Web Page](URL target=) and
[Extracted Text](URL target=)](URL GitHub]</a>
</p>
<hr>
<h1>Canarim: A Large-Scale Dataset of Web Pages in the Portuguese Language</h1>
<h2>Introduction</h2>
<p>Canarim is a database encompassing over 342 million Portuguese language documents, sourced from multiple iterations of CommonCrawl. This nearly 1 terabyte database stands as one of the most extensive Portuguese language data collections available. It underwent initial deduplication using URLs, with plans for further text-based deduplication and filtering of potentially harmful content. The data, originally in HTML, has been converted to Markdown with the 'Trafilatura' library to enhance readability and quality. Canarim is poised to be a crucial resource for NLP research, particularly in Portuguese language applications, filling the gap in large-scale, high-quality data for languages other than English.</p>
<h2>Dataset Structure</h2>
<h3>Data Instances</h3>
<p>An example looks as follows:</p>
<h3>Data Fields</h3>
<ul>
<li>'url': URL of the page</li>
<li>'content_languages': Language of the page</li>
<li>'warc_filename': Name of the WARC file</li>
<li>'warc_record_offset': Offset of the WARC record</li>
<li>'warc_record_length': Length of the WARC record</li>
<li>'text': Text of the page, in Markdown format</li>
<li>'crawl_timestamp': Timestamp of the crawl</li>
</ul>
<h2>Text Extraction Overview</h2>
<p>The Canarim database employs the 'Trafilatura' library for extracting textual content from HTML data, converting it into Markdown format. This tool focuses on preserving key textual elements like titles, subtitles, bold, and italic formatting in Markdown, ensuring the retention of the original document structure. During the extraction process, Trafilatura discards comments and other non-essential information, streamlining the content to include only the main body of the web pages.</p>
</br>
<p align=)
Usage
-----
Below is an example of how to quickly explore just a few samples from a dataset using the 'datasets' library.
Dataset Statistics
------------------
Citing
------
If you use Canarim in your research, please cite the following.
License
-------
This dataset is licensed under the Creative Commons Attribution 4.0 International (CC BY 4.0). You can use the dataset for any purpose, but you must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
Contact
-------
For any questions or suggestions, please contact Maicon Domingues.
| [] | [
"TAGS\n#task_categories-text-generation #task_categories-fill-mask #task_ids-language-modeling #task_ids-masked-language-modeling #multilinguality-monolingual #size_categories-100M<n<1B #language-Portuguese #license-cc-by-4.0 #doi-10.57967/hf/1605 #region-us \n"
] | [
98
] | [
"passage: TAGS\n#task_categories-text-generation #task_categories-fill-mask #task_ids-language-modeling #task_ids-masked-language-modeling #multilinguality-monolingual #size_categories-100M<n<1B #language-Portuguese #license-cc-by-4.0 #doi-10.57967/hf/1605 #region-us \n"
] |
12869d4580bf4e7e45a16fbc9dacd4459500f960 |
# Dataset of cassin (Azur Lane)
This is the dataset of cassin (Azur Lane), containing 40 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by [DeepGHS Team](https://github.com/deepghs)([huggingface organization](https://huggingface.co/deepghs)).
This is a WebUI contains crawlers and other thing: ([LittleAppleWebUI](https://github.com/LittleApple-fp16/LittleAppleWebUI))
| Name | Images | Download | Description |
|:----------------|---------:|:----------------------------------------|:-----------------------------------------------------------------------------------------|
| raw | 40 | [Download](dataset-raw.zip) | Raw data with meta information. |
| raw-stage3 | 108 | [Download](dataset-raw-stage3.zip) | 3-stage cropped raw data with meta information. |
| raw-stage3-eyes | 119 | [Download](dataset-raw-stage3-eyes.zip) | 3-stage cropped (with eye-focus) raw data with meta information. |
| 384x512 | 40 | [Download](dataset-384x512.zip) | 384x512 aligned dataset. |
| 512x704 | 40 | [Download](dataset-512x704.zip) | 512x704 aligned dataset. |
| 640x880 | 40 | [Download](dataset-640x880.zip) | 640x880 aligned dataset. |
| stage3-640 | 108 | [Download](dataset-stage3-640.zip) | 3-stage cropped dataset with the shorter side not exceeding 640 pixels. |
| stage3-800 | 108 | [Download](dataset-stage3-800.zip) | 3-stage cropped dataset with the shorter side not exceeding 800 pixels. |
| stage3-p512-640 | 79 | [Download](dataset-stage3-p512-640.zip) | 3-stage cropped dataset with the area not less than 512x512 pixels. |
| stage3-eyes-640 | 119 | [Download](dataset-stage3-eyes-640.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 640 pixels. |
| stage3-eyes-800 | 119 | [Download](dataset-stage3-eyes-800.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 800 pixels. |
| AppleHarem/cassin_azurlane | [
"task_categories:text-to-image",
"size_categories:n<1K",
"license:mit",
"art",
"not-for-all-audiences",
"region:us"
] | 2023-12-15T08:05:48+00:00 | {"license": "mit", "size_categories": ["n<1K"], "task_categories": ["text-to-image"], "tags": ["art", "not-for-all-audiences"]} | 2023-12-15T08:05:52+00:00 | [] | [] | TAGS
#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us
| Dataset of cassin (Azur Lane)
=============================
This is the dataset of cassin (Azur Lane), containing 40 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by DeepGHS Team(huggingface organization).
This is a WebUI contains crawlers and other thing: (LittleAppleWebUI)
| [] | [
"TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] | [
44
] | [
"passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] |
feeed84bfcc88f2eb17af8b3c0b5f6bb2c456b00 |
code
```python
# used when training samples do not include a system prompt.
DEFAULT_SYSTEM_PROMPT = "Below is an instruction that describes a task. Write a response that appropriately completes the request."
# did not add item to dataset if prompt or system prompt contains any of these bad words.
BAD_WORDS = [
"english", "translate", "russian", "chinese", "japanese", "spanish", "persian", "french", "german", "italian", "korean",
"arabic", "hindi", "portuguese", "turkish", "vietnamese", "indonesian", "thai", "polish", "dutch", "greek", "czech",
"romanian", "swedish", "danish", "finnish", "hungarian", "norwegian", "slovak", "slovenian", "lithuanian", "latvian",
"estonian", "bulgarian", "serbian", "ukrainian", "belarusian", "croatian", "bosnian", "macedonian", "albanian", "icelandic",
"irish", "welsh", "scottish", "latin", "esperanto", "hebrew", "yiddish", "afrikaans", "swahili", "zulu", "xhosa", "sotho",
"sesotho", "somali", "hausa", "igbo", "yoruba", "malay", "tagalog", "hawaiian", "maori", "mongolian", "tamil", "telugu",
"kannada", "gujarati", "marathi", "punjabi", "nepali", "sinhala", "khmer", "lao", "burmese", "tibetan", "georgian",
"azerbaijani", "kurdish", "armenian", "kazakh", "uzbek", "tajik", "kirghiz", "turkmen", "tatar", "bashkir", "chechen",
"chuvash", "ossetian", "moldavian", "moldovan", "language model", " AI ", "openai", "gpt", "gpt-2", "gpt-3", "gpt2", "gpt3", "gpt4",
"gpt-4", "illegal", "harmful", "cannot provide", "yourself or others", "harm to yourself", "cannot suggest", "morals", "ethical",
"cannot answer", "can't answer", "don't know", "no answer", "no response", "i can't", "not enough information", "insufficient",
"it is not possible", "not answerable", "unfortunately", "can't answer", "am not sure", "davinci-0", "ada-0", "babbage-0", "curie-0",
]
TOTAL_ITEMS = 100000
# all datasets used and the percentage/ratio of each from the total.
DATASETS = {
"migtissera/Synthia-v1.3": {
"ratio": 0.2, "set": "train",
"system": "system", "prompt": "instruction", "output": "response",
},
"meta-math/MetaMathQA": {
"ratio": 0.1, "set": "train",
"system": DEFAULT_SYSTEM_PROMPT, "prompt": "query", "output": "response",
},
"HuggingFaceH4/ultrafeedback_binarized": {
"ratio": 0.3, "set": "train_sft",
"system": DEFAULT_SYSTEM_PROMPT, "prompt": "prompt", "output": "get_assistant(chosen)",
},
"ehartford/dolphin": {
"ratio": 0.3, "set": "train",
"system": "instruction", "prompt": "input", "output": "output",
},
"Open-Orca/OpenOrca": {
"ratio": 0.1, "set": "train",
"system": "system_prompt", "prompt": "question", "output": "response",
},
}
``` | perlthoughts/gefilte-fish | [
"license:apache-2.0",
"region:us"
] | 2023-12-15T08:12:12+00:00 | {"license": "apache-2.0"} | 2023-12-20T03:07:03+00:00 | [] | [] | TAGS
#license-apache-2.0 #region-us
|
code
| [] | [
"TAGS\n#license-apache-2.0 #region-us \n"
] | [
14
] | [
"passage: TAGS\n#license-apache-2.0 #region-us \n"
] |
fe8bb97b9a073839e073afb30e2e4c78844b7137 |
# Dataset of airi (Blue Archive)
This is the dataset of airi (Blue Archive), containing 79 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by [DeepGHS Team](https://github.com/deepghs)([huggingface organization](https://huggingface.co/deepghs)).
This is a WebUI contains crawlers and other thing: ([LittleAppleWebUI](https://github.com/LittleApple-fp16/LittleAppleWebUI))
| Name | Images | Download | Description |
|:----------------|---------:|:----------------------------------------|:-----------------------------------------------------------------------------------------|
| raw | 79 | [Download](dataset-raw.zip) | Raw data with meta information. |
| raw-stage3 | 212 | [Download](dataset-raw-stage3.zip) | 3-stage cropped raw data with meta information. |
| raw-stage3-eyes | 243 | [Download](dataset-raw-stage3-eyes.zip) | 3-stage cropped (with eye-focus) raw data with meta information. |
| 384x512 | 79 | [Download](dataset-384x512.zip) | 384x512 aligned dataset. |
| 512x704 | 79 | [Download](dataset-512x704.zip) | 512x704 aligned dataset. |
| 640x880 | 79 | [Download](dataset-640x880.zip) | 640x880 aligned dataset. |
| stage3-640 | 212 | [Download](dataset-stage3-640.zip) | 3-stage cropped dataset with the shorter side not exceeding 640 pixels. |
| stage3-800 | 212 | [Download](dataset-stage3-800.zip) | 3-stage cropped dataset with the shorter side not exceeding 800 pixels. |
| stage3-p512-640 | 176 | [Download](dataset-stage3-p512-640.zip) | 3-stage cropped dataset with the area not less than 512x512 pixels. |
| stage3-eyes-640 | 243 | [Download](dataset-stage3-eyes-640.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 640 pixels. |
| stage3-eyes-800 | 243 | [Download](dataset-stage3-eyes-800.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 800 pixels. |
| AppleHarem/airi_bluearchive | [
"task_categories:text-to-image",
"size_categories:n<1K",
"license:mit",
"art",
"not-for-all-audiences",
"region:us"
] | 2023-12-15T08:12:31+00:00 | {"license": "mit", "size_categories": ["n<1K"], "task_categories": ["text-to-image"], "tags": ["art", "not-for-all-audiences"]} | 2023-12-15T08:12:40+00:00 | [] | [] | TAGS
#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us
| Dataset of airi (Blue Archive)
==============================
This is the dataset of airi (Blue Archive), containing 79 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by DeepGHS Team(huggingface organization).
This is a WebUI contains crawlers and other thing: (LittleAppleWebUI)
| [] | [
"TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] | [
44
] | [
"passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] |
fbe541d3ade6725d59ba3c982754514dd1c289eb |
# Dataset of downes (Azur Lane)
This is the dataset of downes (Azur Lane), containing 15 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by [DeepGHS Team](https://github.com/deepghs)([huggingface organization](https://huggingface.co/deepghs)).
This is a WebUI contains crawlers and other thing: ([LittleAppleWebUI](https://github.com/LittleApple-fp16/LittleAppleWebUI))
| Name | Images | Download | Description |
|:----------------|---------:|:----------------------------------------|:-----------------------------------------------------------------------------------------|
| raw | 15 | [Download](dataset-raw.zip) | Raw data with meta information. |
| raw-stage3 | 41 | [Download](dataset-raw-stage3.zip) | 3-stage cropped raw data with meta information. |
| raw-stage3-eyes | 43 | [Download](dataset-raw-stage3-eyes.zip) | 3-stage cropped (with eye-focus) raw data with meta information. |
| 384x512 | 15 | [Download](dataset-384x512.zip) | 384x512 aligned dataset. |
| 512x704 | 15 | [Download](dataset-512x704.zip) | 512x704 aligned dataset. |
| 640x880 | 15 | [Download](dataset-640x880.zip) | 640x880 aligned dataset. |
| stage3-640 | 41 | [Download](dataset-stage3-640.zip) | 3-stage cropped dataset with the shorter side not exceeding 640 pixels. |
| stage3-800 | 41 | [Download](dataset-stage3-800.zip) | 3-stage cropped dataset with the shorter side not exceeding 800 pixels. |
| stage3-p512-640 | 32 | [Download](dataset-stage3-p512-640.zip) | 3-stage cropped dataset with the area not less than 512x512 pixels. |
| stage3-eyes-640 | 43 | [Download](dataset-stage3-eyes-640.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 640 pixels. |
| stage3-eyes-800 | 43 | [Download](dataset-stage3-eyes-800.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 800 pixels. |
| AppleHarem/downes_azurlane | [
"task_categories:text-to-image",
"size_categories:n<1K",
"license:mit",
"art",
"not-for-all-audiences",
"region:us"
] | 2023-12-15T08:24:34+00:00 | {"license": "mit", "size_categories": ["n<1K"], "task_categories": ["text-to-image"], "tags": ["art", "not-for-all-audiences"]} | 2023-12-15T08:24:36+00:00 | [] | [] | TAGS
#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us
| Dataset of downes (Azur Lane)
=============================
This is the dataset of downes (Azur Lane), containing 15 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by DeepGHS Team(huggingface organization).
This is a WebUI contains crawlers and other thing: (LittleAppleWebUI)
| [] | [
"TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] | [
44
] | [
"passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] |
edf2dcc03c41e35e6e762e15f111d8e681bbcb64 |
# UltraFeedback - Critique (raw)
This dataset contains a raw version of [ultrafeedback-curated](https://huggingface.co/datasets/argilla/ultrafeedback-curated) prepared to train a critique model.
## Introduction
This dataset is built so that each record contains the original instruction, the response from each one of the models, the corresponding critique and it's overall score. We have prepared the dataset so that applying Supervised fine-tuning (SFT) for a critique model can be as simple as possible.
## Data processing
We extracted each `instruction`, for each model completion in the original `completions` column we obtained the model's `response`, the `critique` rationale and the `overall_score`. Exploring the dataset we noticed that for some records, the `overall_score` was always low, which indicated that the instruction doesn't make sense, so we decided to remove those records for which all `overall_score` responses were below a given threshold (`overall_score_threshold` == 4). The final dataset has 252984 records, around 720 instructions of the original dataset were removed.
## Reproduce
<a target="_blank" href="https://colab.research.google.com/drive/1ggdYCjDALk9ZI9z7j_dLDapabt6AznQn?usp=sharing">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
</a>
To reproduce the processing of the dataset feel free to run the attached Colab Notebook or just view it at [`notebook.ipynb`](./notebook.ipynb) within this repository.
From Argilla we encourage anyone out there to play around, investigate, and experiment with the data, and we firmly believe on open sourcing what we do, as
ourselves, as well as the whole community, benefit a lot from open source and we also want to give back.
Example record:
```json
{
"instruction": "I want to do exploratory data analysis on below dataset found on kaggle\n\nhttps://www.kaggle.com/datasets/neuromusic/avocado-prices",
"response": "Hello! I'm here to help you with your exploratory data analysis on the avocado prices dataset from Kaggle. This dataset contains information on avocado prices from different regions in the United States, including California, Florida, and Illinois.\n\nBefore we dive into the analysis, I want to make sure that you are aware of the potential biases and limitations of the dataset. The dataset is collected from a single source, and it may not be representative of the entire avocado market or the entire United States. Additionally, the dataset only contains information on three regions, which may not be enough to make generalizations about the entire country.\n\nThat being said, there are many interesting patterns and trends that we can explore in this dataset. For example, we can analyze the price trends over time to see if there are any seasonal patterns or long-term trends. We can also compare the prices across different regions to see if there are any differences in pricing strategies or market conditions.\n\nTo get started, I recommend that we first inspect the dataset to get a better understanding of the variables and their distributions. We can use statistical methods like histograms and box plots to visualize the data and identify any outliers or anomalies.\n\nOnce we have a better understanding of the data, we can move on to more advanced analytical techniques like regression analysis or time series analysis. These methods can help us identify the factors that influence avocado prices and make predictions about future price trends.\n\nThroughout the analysis, I will make sure to provide you with accurate and unbiased information, and I will always be mindful of any ethical or social implications of our findings. I'm excited to work with you on this project and help you gain insights into the avocado market!\n\nIs there anything specific you would like to explore in the dataset, or any questions you have before we begin?",
"critique": "Your answer was generally good, covering a broad range of points. You explained well about the dataset and potential biases, which shows a good understanding. However, there are a few areas for improvement. \n\nFirst, you mentioned that the dataset only contains information on three regions - California, Florida, and Illinois. This is not accurate. The dataset includes multiple regions. You need to ensure your statements are factual.\n\nSecond, you should have asked the user what kind of exploratory data analysis they want to perform or suggested some specific analyses that could be done, such as looking for correlations between variables, instead of going straight into advanced techniques like regression analysis or time series analysis which might not be necessary at this stage.\n\nLastly, the user didn't ask for a detailed explanation of how to do the analysis. The instruction was to provide a response as an AI assistant, so your role was to provide information or suggestions, not to guide the user through the whole process.",
"overall_score": 6.5
}
```
## Citation
If you find this dataset is useful in your work, please cite the original UltraFeedback dataset: https://huggingface.co/datasets/openbmb/UltraFeedback
| argilla/ultrafeedback-critique | [
"region:us"
] | 2023-12-15T08:33:53+00:00 | {"dataset_info": {"features": [{"name": "instruction", "dtype": "string"}, {"name": "response", "dtype": "string"}, {"name": "critique", "dtype": "string"}, {"name": "overall_score", "dtype": "float64"}], "splits": [{"name": "train", "num_bytes": 639775765, "num_examples": 252984}], "download_size": 253016899, "dataset_size": 639775765}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]} | 2023-12-15T10:59:19+00:00 | [] | [] | TAGS
#region-us
|
# UltraFeedback - Critique (raw)
This dataset contains a raw version of ultrafeedback-curated prepared to train a critique model.
## Introduction
This dataset is built so that each record contains the original instruction, the response from each one of the models, the corresponding critique and it's overall score. We have prepared the dataset so that applying Supervised fine-tuning (SFT) for a critique model can be as simple as possible.
## Data processing
We extracted each 'instruction', for each model completion in the original 'completions' column we obtained the model's 'response', the 'critique' rationale and the 'overall_score'. Exploring the dataset we noticed that for some records, the 'overall_score' was always low, which indicated that the instruction doesn't make sense, so we decided to remove those records for which all 'overall_score' responses were below a given threshold ('overall_score_threshold' == 4). The final dataset has 252984 records, around 720 instructions of the original dataset were removed.
## Reproduce
<a target="_blank" href="URL
<img src="URL alt="Open In Colab"/>
</a>
To reproduce the processing of the dataset feel free to run the attached Colab Notebook or just view it at 'URL' within this repository.
From Argilla we encourage anyone out there to play around, investigate, and experiment with the data, and we firmly believe on open sourcing what we do, as
ourselves, as well as the whole community, benefit a lot from open source and we also want to give back.
Example record:
If you find this dataset is useful in your work, please cite the original UltraFeedback dataset: URL
| [
"# UltraFeedback - Critique (raw)\n\nThis dataset contains a raw version of ultrafeedback-curated prepared to train a critique model.",
"## Introduction\n\nThis dataset is built so that each record contains the original instruction, the response from each one of the models, the corresponding critique and it's overall score. We have prepared the dataset so that applying Supervised fine-tuning (SFT) for a critique model can be as simple as possible.",
"## Data processing\n\nWe extracted each 'instruction', for each model completion in the original 'completions' column we obtained the model's 'response', the 'critique' rationale and the 'overall_score'. Exploring the dataset we noticed that for some records, the 'overall_score' was always low, which indicated that the instruction doesn't make sense, so we decided to remove those records for which all 'overall_score' responses were below a given threshold ('overall_score_threshold' == 4). The final dataset has 252984 records, around 720 instructions of the original dataset were removed.",
"## Reproduce\n\n<a target=\"_blank\" href=\"URL\n <img src=\"URL alt=\"Open In Colab\"/>\n</a>\n\nTo reproduce the processing of the dataset feel free to run the attached Colab Notebook or just view it at 'URL' within this repository.\n\nFrom Argilla we encourage anyone out there to play around, investigate, and experiment with the data, and we firmly believe on open sourcing what we do, as\nourselves, as well as the whole community, benefit a lot from open source and we also want to give back.\n\nExample record:\n\n\n\nIf you find this dataset is useful in your work, please cite the original UltraFeedback dataset: URL"
] | [
"TAGS\n#region-us \n",
"# UltraFeedback - Critique (raw)\n\nThis dataset contains a raw version of ultrafeedback-curated prepared to train a critique model.",
"## Introduction\n\nThis dataset is built so that each record contains the original instruction, the response from each one of the models, the corresponding critique and it's overall score. We have prepared the dataset so that applying Supervised fine-tuning (SFT) for a critique model can be as simple as possible.",
"## Data processing\n\nWe extracted each 'instruction', for each model completion in the original 'completions' column we obtained the model's 'response', the 'critique' rationale and the 'overall_score'. Exploring the dataset we noticed that for some records, the 'overall_score' was always low, which indicated that the instruction doesn't make sense, so we decided to remove those records for which all 'overall_score' responses were below a given threshold ('overall_score_threshold' == 4). The final dataset has 252984 records, around 720 instructions of the original dataset were removed.",
"## Reproduce\n\n<a target=\"_blank\" href=\"URL\n <img src=\"URL alt=\"Open In Colab\"/>\n</a>\n\nTo reproduce the processing of the dataset feel free to run the attached Colab Notebook or just view it at 'URL' within this repository.\n\nFrom Argilla we encourage anyone out there to play around, investigate, and experiment with the data, and we firmly believe on open sourcing what we do, as\nourselves, as well as the whole community, benefit a lot from open source and we also want to give back.\n\nExample record:\n\n\n\nIf you find this dataset is useful in your work, please cite the original UltraFeedback dataset: URL"
] | [
6,
33,
71,
157,
153
] | [
"passage: TAGS\n#region-us \n# UltraFeedback - Critique (raw)\n\nThis dataset contains a raw version of ultrafeedback-curated prepared to train a critique model.## Introduction\n\nThis dataset is built so that each record contains the original instruction, the response from each one of the models, the corresponding critique and it's overall score. We have prepared the dataset so that applying Supervised fine-tuning (SFT) for a critique model can be as simple as possible.## Data processing\n\nWe extracted each 'instruction', for each model completion in the original 'completions' column we obtained the model's 'response', the 'critique' rationale and the 'overall_score'. Exploring the dataset we noticed that for some records, the 'overall_score' was always low, which indicated that the instruction doesn't make sense, so we decided to remove those records for which all 'overall_score' responses were below a given threshold ('overall_score_threshold' == 4). The final dataset has 252984 records, around 720 instructions of the original dataset were removed.## Reproduce\n\n<a target=\"_blank\" href=\"URL\n <img src=\"URL alt=\"Open In Colab\"/>\n</a>\n\nTo reproduce the processing of the dataset feel free to run the attached Colab Notebook or just view it at 'URL' within this repository.\n\nFrom Argilla we encourage anyone out there to play around, investigate, and experiment with the data, and we firmly believe on open sourcing what we do, as\nourselves, as well as the whole community, benefit a lot from open source and we also want to give back.\n\nExample record:\n\n\n\nIf you find this dataset is useful in your work, please cite the original UltraFeedback dataset: URL"
] |
9c356526d86455cecfb69a515b884bc4bdad558d |
# Dataset of maury (Azur Lane)
This is the dataset of maury (Azur Lane), containing 18 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by [DeepGHS Team](https://github.com/deepghs)([huggingface organization](https://huggingface.co/deepghs)).
This is a WebUI contains crawlers and other thing: ([LittleAppleWebUI](https://github.com/LittleApple-fp16/LittleAppleWebUI))
| Name | Images | Download | Description |
|:----------------|---------:|:----------------------------------------|:-----------------------------------------------------------------------------------------|
| raw | 18 | [Download](dataset-raw.zip) | Raw data with meta information. |
| raw-stage3 | 45 | [Download](dataset-raw-stage3.zip) | 3-stage cropped raw data with meta information. |
| raw-stage3-eyes | 45 | [Download](dataset-raw-stage3-eyes.zip) | 3-stage cropped (with eye-focus) raw data with meta information. |
| 384x512 | 18 | [Download](dataset-384x512.zip) | 384x512 aligned dataset. |
| 512x704 | 18 | [Download](dataset-512x704.zip) | 512x704 aligned dataset. |
| 640x880 | 18 | [Download](dataset-640x880.zip) | 640x880 aligned dataset. |
| stage3-640 | 45 | [Download](dataset-stage3-640.zip) | 3-stage cropped dataset with the shorter side not exceeding 640 pixels. |
| stage3-800 | 45 | [Download](dataset-stage3-800.zip) | 3-stage cropped dataset with the shorter side not exceeding 800 pixels. |
| stage3-p512-640 | 21 | [Download](dataset-stage3-p512-640.zip) | 3-stage cropped dataset with the area not less than 512x512 pixels. |
| stage3-eyes-640 | 45 | [Download](dataset-stage3-eyes-640.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 640 pixels. |
| stage3-eyes-800 | 45 | [Download](dataset-stage3-eyes-800.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 800 pixels. |
| AppleHarem/maury_azurlane | [
"task_categories:text-to-image",
"size_categories:n<1K",
"license:mit",
"art",
"not-for-all-audiences",
"region:us"
] | 2023-12-15T08:55:24+00:00 | {"license": "mit", "size_categories": ["n<1K"], "task_categories": ["text-to-image"], "tags": ["art", "not-for-all-audiences"]} | 2023-12-15T08:55:26+00:00 | [] | [] | TAGS
#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us
| Dataset of maury (Azur Lane)
============================
This is the dataset of maury (Azur Lane), containing 18 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by DeepGHS Team(huggingface organization).
This is a WebUI contains crawlers and other thing: (LittleAppleWebUI)
| [] | [
"TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] | [
44
] | [
"passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] |
46df7f98a827bfaecf977453e371c13ce5b4074e |
code
```python
# used when training samples do not include a system prompt.
DEFAULT_SYSTEM_PROMPT = "Below is an instruction that describes a task. Write a response that appropriately completes the request."
# did not add item to dataset if prompt or system prompt contains any of these bad words.
# if any of these words are in the system or prompt, the item will be skipped.
BAD_WORDS = [
"english", "translate", "translation", "russian", "chinese", "japanese", "spanish", "persian", "french", "german", "italian", "korean",
"arabic", "hindi", "portuguese", "turkish", "vietnamese", "indonesian", "thai", "polish", "dutch", "greek", "czech",
"romanian", "swedish", "danish", "finnish", "hungarian", "norwegian", "slovak", "slovenian", "lithuanian", "latvian",
"estonian", "bulgarian", "serbian", "ukrainian", "belarusian", "croatian", "bosnian", "macedonian", "albanian", "icelandic",
"irish", "welsh", "scottish", "latin", "esperanto", "hebrew", "yiddish", "afrikaans", "swahili", "zulu", "xhosa", "sotho",
"sesotho", "somali", "hausa", "igbo", "yoruba", "malay", "tagalog", "hawaiian", "maori", "mongolian", "tamil", "telugu",
"kannada", "gujarati", "marathi", "punjabi", "nepali", "sinhala", "khmer", "lao", "burmese", "tibetan", "georgian",
"azerbaijani", "kurdish", "armenian", "kazakh", "uzbek", "tajik", "kirghiz", "turkmen", "tatar", "bashkir", "chechen",
"chuvash", "ossetian", "moldavian", "moldovan", "language model", " AI ", "openai", "gpt", "gpt-2", "gpt-3", "gpt2", "gpt3", "gpt4",
"gpt-4", "illegal", "harmful", "cannot provide", "yourself or others", "harm to yourself", "cannot suggest", "morals", "ethical",
"cannot answer", "can't answer", "don't know", "no answer", "no response", "i can't", "not enough information", "insufficient",
"it is not possible", "not answerable", "unfortunately", "can't answer", "i cannot", "am not sure", "davinci-0", "ada-0", "babbage-0", "curie-0",
"gpt-5", "do not understand", "i do not know", "i do not have", "unavailable", "é", "á", "般", "的", "に", "葉", "は", "長", "さ", "が"
]
# if any of these words are not in the system or prompt, the item will be skipped.
GOOD_WORDS = [
"solve", "calculate", "math", "equation", "formula", "logic", "algebra", "geometry", "riddle", "puzzle", "proof", "theorem",
"problem", "theory", "finance", "economics", "chemistry", "biology", "physics", "science", "history", "geography",
"philosophy", "psychology", "sociology", "computer", "programming", "technology", "engineering", "medicine", "health",
"code", "program", "health", "medical", "doctor", "nurse", "hospital", "disease", "bacteria", "symptom", "cancer",
"diagnosis", "treatment", "procedure", "medicine", "infection", "survival", "therapy", "psychological", "psychiatry",
"summarize", "summarized", "find the", "result", "title", "author", "abstract", "conclusion", "research", "upon a time",
"to whom it may", "subject", "title", "from:", "date", "invoice", "recipe", "life pro tip", "tweet", "write a",
"summary", "logic", "amount", "dollars", "euros", "pounds", "yen", "stock", "tax", "solution", "segment the words",
"seperate the words", "add spaces", "mistakes", "errors", "typos", "spelling", "grammar",
]
TOTAL_ITEMS = 500000
# all datasets used and the percentage/ratio of each from the total.
DATASETS = {
"meta-math/MetaMathQA": {
"ratio": 0.3, "set": "train",
"system": DEFAULT_SYSTEM_PROMPT, "prompt": "query", "output": "response",
},
"allenai/ultrafeedback_binarized_cleaned": {
"ratio": 0.3, "set": "train_sft",
"system": DEFAULT_SYSTEM_PROMPT, "prompt": "prompt", "output": "get_assistant(chosen)",
},
"Open-Orca/OpenOrca": {
"ratio": 0.4, "set": "train",
"system": "system_prompt", "prompt": "question", "output": "response",
},
}
``` | perlthoughts/big-brain | [
"license:apache-2.0",
"region:us"
] | 2023-12-15T08:58:34+00:00 | {"license": "apache-2.0"} | 2023-12-29T11:22:30+00:00 | [] | [] | TAGS
#license-apache-2.0 #region-us
|
code
| [] | [
"TAGS\n#license-apache-2.0 #region-us \n"
] | [
14
] | [
"passage: TAGS\n#license-apache-2.0 #region-us \n"
] |
7771dfd505c9a7118c526a50d5ee9519d9f9cfd7 |
# Dataset of charles_ausburne (Azur Lane)
This is the dataset of charles_ausburne (Azur Lane), containing 12 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by [DeepGHS Team](https://github.com/deepghs)([huggingface organization](https://huggingface.co/deepghs)).
This is a WebUI contains crawlers and other thing: ([LittleAppleWebUI](https://github.com/LittleApple-fp16/LittleAppleWebUI))
| Name | Images | Download | Description |
|:----------------|---------:|:----------------------------------------|:-----------------------------------------------------------------------------------------|
| raw | 12 | [Download](dataset-raw.zip) | Raw data with meta information. |
| raw-stage3 | 30 | [Download](dataset-raw-stage3.zip) | 3-stage cropped raw data with meta information. |
| raw-stage3-eyes | 31 | [Download](dataset-raw-stage3-eyes.zip) | 3-stage cropped (with eye-focus) raw data with meta information. |
| 384x512 | 12 | [Download](dataset-384x512.zip) | 384x512 aligned dataset. |
| 512x704 | 12 | [Download](dataset-512x704.zip) | 512x704 aligned dataset. |
| 640x880 | 12 | [Download](dataset-640x880.zip) | 640x880 aligned dataset. |
| stage3-640 | 30 | [Download](dataset-stage3-640.zip) | 3-stage cropped dataset with the shorter side not exceeding 640 pixels. |
| stage3-800 | 30 | [Download](dataset-stage3-800.zip) | 3-stage cropped dataset with the shorter side not exceeding 800 pixels. |
| stage3-p512-640 | 12 | [Download](dataset-stage3-p512-640.zip) | 3-stage cropped dataset with the area not less than 512x512 pixels. |
| stage3-eyes-640 | 31 | [Download](dataset-stage3-eyes-640.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 640 pixels. |
| stage3-eyes-800 | 31 | [Download](dataset-stage3-eyes-800.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 800 pixels. |
| AppleHarem/charles_ausburne_azurlane | [
"task_categories:text-to-image",
"size_categories:n<1K",
"license:mit",
"art",
"not-for-all-audiences",
"region:us"
] | 2023-12-15T09:10:42+00:00 | {"license": "mit", "size_categories": ["n<1K"], "task_categories": ["text-to-image"], "tags": ["art", "not-for-all-audiences"]} | 2023-12-15T09:10:43+00:00 | [] | [] | TAGS
#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us
| Dataset of charles\_ausburne (Azur Lane)
========================================
This is the dataset of charles\_ausburne (Azur Lane), containing 12 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by DeepGHS Team(huggingface organization).
This is a WebUI contains crawlers and other thing: (LittleAppleWebUI)
| [] | [
"TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] | [
44
] | [
"passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] |
5396c14475e6cbb788b8625f1f1e738bcc1fbe18 |
# Dataset of foote (Azur Lane)
This is the dataset of foote (Azur Lane), containing 26 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by [DeepGHS Team](https://github.com/deepghs)([huggingface organization](https://huggingface.co/deepghs)).
This is a WebUI contains crawlers and other thing: ([LittleAppleWebUI](https://github.com/LittleApple-fp16/LittleAppleWebUI))
| Name | Images | Download | Description |
|:----------------|---------:|:----------------------------------------|:-----------------------------------------------------------------------------------------|
| raw | 26 | [Download](dataset-raw.zip) | Raw data with meta information. |
| raw-stage3 | 69 | [Download](dataset-raw-stage3.zip) | 3-stage cropped raw data with meta information. |
| raw-stage3-eyes | 81 | [Download](dataset-raw-stage3-eyes.zip) | 3-stage cropped (with eye-focus) raw data with meta information. |
| 384x512 | 26 | [Download](dataset-384x512.zip) | 384x512 aligned dataset. |
| 512x704 | 26 | [Download](dataset-512x704.zip) | 512x704 aligned dataset. |
| 640x880 | 26 | [Download](dataset-640x880.zip) | 640x880 aligned dataset. |
| stage3-640 | 69 | [Download](dataset-stage3-640.zip) | 3-stage cropped dataset with the shorter side not exceeding 640 pixels. |
| stage3-800 | 69 | [Download](dataset-stage3-800.zip) | 3-stage cropped dataset with the shorter side not exceeding 800 pixels. |
| stage3-p512-640 | 43 | [Download](dataset-stage3-p512-640.zip) | 3-stage cropped dataset with the area not less than 512x512 pixels. |
| stage3-eyes-640 | 81 | [Download](dataset-stage3-eyes-640.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 640 pixels. |
| stage3-eyes-800 | 81 | [Download](dataset-stage3-eyes-800.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 800 pixels. |
| AppleHarem/foote_azurlane | [
"task_categories:text-to-image",
"size_categories:n<1K",
"license:mit",
"art",
"not-for-all-audiences",
"region:us"
] | 2023-12-15T09:44:36+00:00 | {"license": "mit", "size_categories": ["n<1K"], "task_categories": ["text-to-image"], "tags": ["art", "not-for-all-audiences"]} | 2023-12-15T09:44:38+00:00 | [] | [] | TAGS
#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us
| Dataset of foote (Azur Lane)
============================
This is the dataset of foote (Azur Lane), containing 26 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by DeepGHS Team(huggingface organization).
This is a WebUI contains crawlers and other thing: (LittleAppleWebUI)
| [] | [
"TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] | [
44
] | [
"passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] |
1e4229d5fe308f2c49cba420f30c46453765d0fa |
# Dataset of plume (Arknights)
This is the dataset of plume (Arknights), containing 131 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by [DeepGHS Team](https://github.com/deepghs)([huggingface organization](https://huggingface.co/deepghs)).
This is a WebUI contains crawlers and other thing: ([LittleAppleWebUI](https://github.com/LittleApple-fp16/LittleAppleWebUI))
| Name | Images | Download | Description |
|:----------------|---------:|:----------------------------------------|:-----------------------------------------------------------------------------------------|
| raw | 131 | [Download](dataset-raw.zip) | Raw data with meta information. |
| raw-stage3 | 335 | [Download](dataset-raw-stage3.zip) | 3-stage cropped raw data with meta information. |
| raw-stage3-eyes | 356 | [Download](dataset-raw-stage3-eyes.zip) | 3-stage cropped (with eye-focus) raw data with meta information. |
| 384x512 | 131 | [Download](dataset-384x512.zip) | 384x512 aligned dataset. |
| 512x704 | 131 | [Download](dataset-512x704.zip) | 512x704 aligned dataset. |
| 640x880 | 131 | [Download](dataset-640x880.zip) | 640x880 aligned dataset. |
| stage3-640 | 335 | [Download](dataset-stage3-640.zip) | 3-stage cropped dataset with the shorter side not exceeding 640 pixels. |
| stage3-800 | 335 | [Download](dataset-stage3-800.zip) | 3-stage cropped dataset with the shorter side not exceeding 800 pixels. |
| stage3-p512-640 | 252 | [Download](dataset-stage3-p512-640.zip) | 3-stage cropped dataset with the area not less than 512x512 pixels. |
| stage3-eyes-640 | 356 | [Download](dataset-stage3-eyes-640.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 640 pixels. |
| stage3-eyes-800 | 356 | [Download](dataset-stage3-eyes-800.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 800 pixels. |
| AppleHarem/plume_arknights | [
"task_categories:text-to-image",
"size_categories:n<1K",
"license:mit",
"art",
"not-for-all-audiences",
"region:us"
] | 2023-12-15T09:51:03+00:00 | {"license": "mit", "size_categories": ["n<1K"], "task_categories": ["text-to-image"], "tags": ["art", "not-for-all-audiences"]} | 2023-12-15T09:51:11+00:00 | [] | [] | TAGS
#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us
| Dataset of plume (Arknights)
============================
This is the dataset of plume (Arknights), containing 131 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by DeepGHS Team(huggingface organization).
This is a WebUI contains crawlers and other thing: (LittleAppleWebUI)
| [] | [
"TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] | [
44
] | [
"passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] |
b7043ae65ce4de69fb6f18d88cfa041f6b8fcd7c |
# Dataset Card for S2-100K
<!-- Provide a quick summary of the dataset. -->
> The S2-100K dataset is a dataset of 100,000 multi-spectral satellite images sampled from Sentinel-2 via the Microsoft Planetary Computer. Copernicus Sentinel data is captured between Jan 1, 2021 and May 17, 2023. The dataset is sampled approximately uniformly over landmass and only includes images without cloud coverage. The dataset is available for research purposes only. If you use the dataset, please cite our paper. More information on the dataset can be found in our paper.
See this [GitHub repo](https://github.com/microsoft/satclip/) for more details.
## Dataset Details
### Dataset Description
> SatCLIP trains location and image encoders via contrastive learning, by matching images to their corresponding locations. This is analogous to the CLIP approach, which matches images to their corresponding text.
> Through this process, the location encoder learns characteristics of a location, as represented by satellite imagery.
- **Curated by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
### Dataset Sources [optional]
<!-- Provide the basic links for the dataset. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the dataset is intended to be used. -->
### Direct Use
<!-- This section describes suitable use cases for the dataset. -->
To download the dataset you can use the `huggingface_hub` library.
```python
from huggingface_hub import snapshot_download
snapshot_download("davanstrien/satclip", local_dir='.', repo_type='dataset')
```
Alternatively you can run
```bash
# Make sure you have git-lfs installed (https://git-lfs.com)
git lfs install
git clone https://huggingface.co/datasets/davanstrien/satclip
```
To extract the images you can run the following command.
```bash
ls image/*.tar.xz |xargs -n1 tar -xzf
```
## Citation
<!-- If there is a paper or blog post introducing the dataset, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
```
@article{klemmer2023satclip,
title={SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery},
author={Klemmer, Konstantin and Rolf, Esther and Robinson, Caleb and Mackey, Lester and Ru{\ss}wurm, Marc},
journal={arXiv preprint arXiv:2311.17179},
year={2023}
}
``` | davanstrien/satclip | [
"geospatial",
"region:us"
] | 2023-12-15T09:55:22+00:00 | {"pretty_name": "S2-100K", "tags": ["geospatial"]} | 2023-12-18T15:03:53+00:00 | [] | [] | TAGS
#geospatial #region-us
|
# Dataset Card for S2-100K
> The S2-100K dataset is a dataset of 100,000 multi-spectral satellite images sampled from Sentinel-2 via the Microsoft Planetary Computer. Copernicus Sentinel data is captured between Jan 1, 2021 and May 17, 2023. The dataset is sampled approximately uniformly over landmass and only includes images without cloud coverage. The dataset is available for research purposes only. If you use the dataset, please cite our paper. More information on the dataset can be found in our paper.
See this GitHub repo for more details.
## Dataset Details
### Dataset Description
> SatCLIP trains location and image encoders via contrastive learning, by matching images to their corresponding locations. This is analogous to the CLIP approach, which matches images to their corresponding text.
> Through this process, the location encoder learns characteristics of a location, as represented by satellite imagery.
- Curated by:
- Funded by [optional]:
- Shared by [optional]:
- Language(s) (NLP):
- License:
### Dataset Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
To download the dataset you can use the 'huggingface_hub' library.
Alternatively you can run
To extract the images you can run the following command.
BibTeX:
| [
"# Dataset Card for S2-100K\n\n\n\n> The S2-100K dataset is a dataset of 100,000 multi-spectral satellite images sampled from Sentinel-2 via the Microsoft Planetary Computer. Copernicus Sentinel data is captured between Jan 1, 2021 and May 17, 2023. The dataset is sampled approximately uniformly over landmass and only includes images without cloud coverage. The dataset is available for research purposes only. If you use the dataset, please cite our paper. More information on the dataset can be found in our paper.\n\nSee this GitHub repo for more details.",
"## Dataset Details",
"### Dataset Description\n\n> SatCLIP trains location and image encoders via contrastive learning, by matching images to their corresponding locations. This is analogous to the CLIP approach, which matches images to their corresponding text.\n> Through this process, the location encoder learns characteristics of a location, as represented by satellite imagery.\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:",
"### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use\n\n\n\nTo download the dataset you can use the 'huggingface_hub' library. \n\n\n\nAlternatively you can run \n\n\n\nTo extract the images you can run the following command.\n\n\n\n\n\n\nBibTeX:"
] | [
"TAGS\n#geospatial #region-us \n",
"# Dataset Card for S2-100K\n\n\n\n> The S2-100K dataset is a dataset of 100,000 multi-spectral satellite images sampled from Sentinel-2 via the Microsoft Planetary Computer. Copernicus Sentinel data is captured between Jan 1, 2021 and May 17, 2023. The dataset is sampled approximately uniformly over landmass and only includes images without cloud coverage. The dataset is available for research purposes only. If you use the dataset, please cite our paper. More information on the dataset can be found in our paper.\n\nSee this GitHub repo for more details.",
"## Dataset Details",
"### Dataset Description\n\n> SatCLIP trains location and image encoders via contrastive learning, by matching images to their corresponding locations. This is analogous to the CLIP approach, which matches images to their corresponding text.\n> Through this process, the location encoder learns characteristics of a location, as represented by satellite imagery.\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:",
"### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use\n\n\n\nTo download the dataset you can use the 'huggingface_hub' library. \n\n\n\nAlternatively you can run \n\n\n\nTo extract the images you can run the following command.\n\n\n\n\n\n\nBibTeX:"
] | [
11,
132,
4,
116,
29,
3,
44
] | [
"passage: TAGS\n#geospatial #region-us \n# Dataset Card for S2-100K\n\n\n\n> The S2-100K dataset is a dataset of 100,000 multi-spectral satellite images sampled from Sentinel-2 via the Microsoft Planetary Computer. Copernicus Sentinel data is captured between Jan 1, 2021 and May 17, 2023. The dataset is sampled approximately uniformly over landmass and only includes images without cloud coverage. The dataset is available for research purposes only. If you use the dataset, please cite our paper. More information on the dataset can be found in our paper.\n\nSee this GitHub repo for more details.## Dataset Details### Dataset Description\n\n> SatCLIP trains location and image encoders via contrastive learning, by matching images to their corresponding locations. This is analogous to the CLIP approach, which matches images to their corresponding text.\n> Through this process, the location encoder learns characteristics of a location, as represented by satellite imagery.\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use\n\n\n\nTo download the dataset you can use the 'huggingface_hub' library. \n\n\n\nAlternatively you can run \n\n\n\nTo extract the images you can run the following command.\n\n\n\n\n\n\nBibTeX:"
] |
e0ef978d86464eb3ea30b252ce8fb83d0c871319 | # Dataset Card for "nli-zh-tw-multilingual"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | Mike0307/nli-zh-tw-multilingual | [
"region:us"
] | 2023-12-15T09:57:20+00:00 | {"dataset_info": {"features": [{"name": "text1", "dtype": "string"}, {"name": "text2", "dtype": "string"}, {"name": "label", "dtype": "float64"}], "splits": [{"name": "train", "num_bytes": 34024607, "num_examples": 96616}, {"name": "validate", "num_bytes": 4161125, "num_examples": 12071}, {"name": "test", "num_bytes": 4235537, "num_examples": 12140}], "download_size": 33528119, "dataset_size": 42421269}} | 2023-12-15T09:57:34+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "nli-zh-tw-multilingual"
More Information needed | [
"# Dataset Card for \"nli-zh-tw-multilingual\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"nli-zh-tw-multilingual\"\n\nMore Information needed"
] | [
6,
20
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"nli-zh-tw-multilingual\"\n\nMore Information needed"
] |
ad4944585e09692ecfedbd58ff761b71055c60fa | # Dataset Card for "violet-v1"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 0x7o/fialka-v1 | [
"task_categories:text-generation",
"task_categories:conversational",
"size_categories:100K<n<1M",
"language:ru",
"license:apache-2.0",
"region:us"
] | 2023-12-15T10:08:21+00:00 | {"language": ["ru"], "license": "apache-2.0", "size_categories": ["100K<n<1M"], "task_categories": ["text-generation", "conversational"], "dataset_info": {"features": [{"name": "texts", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 221386895, "num_examples": 129712}], "download_size": 103291349, "dataset_size": 221386895}} | 2023-12-26T05:25:49+00:00 | [] | [
"ru"
] | TAGS
#task_categories-text-generation #task_categories-conversational #size_categories-100K<n<1M #language-Russian #license-apache-2.0 #region-us
| # Dataset Card for "violet-v1"
More Information needed | [
"# Dataset Card for \"violet-v1\"\n\nMore Information needed"
] | [
"TAGS\n#task_categories-text-generation #task_categories-conversational #size_categories-100K<n<1M #language-Russian #license-apache-2.0 #region-us \n",
"# Dataset Card for \"violet-v1\"\n\nMore Information needed"
] | [
52,
15
] | [
"passage: TAGS\n#task_categories-text-generation #task_categories-conversational #size_categories-100K<n<1M #language-Russian #license-apache-2.0 #region-us \n# Dataset Card for \"violet-v1\"\n\nMore Information needed"
] |
8257df6fe67601c7cdfa733d0ea799895b733d87 | # Dataset Card for "cc-100-01-percent-untokenized"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | bowphs/cc-100-01-percent-untokenized | [
"region:us"
] | 2023-12-15T10:45:32+00:00 | {"dataset_info": {"features": [{"name": "id", "dtype": "string"}, {"name": "text", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 29257739786, "num_examples": 147182603}], "download_size": 22427356397, "dataset_size": 29257739786}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]} | 2023-12-15T10:59:14+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "cc-100-01-percent-untokenized"
More Information needed | [
"# Dataset Card for \"cc-100-01-percent-untokenized\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"cc-100-01-percent-untokenized\"\n\nMore Information needed"
] | [
6,
20
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"cc-100-01-percent-untokenized\"\n\nMore Information needed"
] |
deef7ae848bcc7752585bd09a479d628a6718060 | ParsynthOCR is a synthetic dataset for Persian OCR. This version is a preview of the original 4 million samples dataset (ParsynthOCR-4M).
# Usage
## 🤗 Datasets
```python
from datasets import load_dataset
dataset = load_dataset("hezarai/parsynth-ocr-200k")
```
## Hezar
```
pip install hezar
```
```python
from hezar.data import Dataset
dataset = Dataset.load("hezarai/parsynth-ocr-200k", split="train")
```
| hezarai/parsynth-ocr-200k | [
"task_categories:image-to-image",
"size_categories:100K<n<1M",
"language:fa",
"hezar",
"region:us"
] | 2023-12-15T10:46:34+00:00 | {"language": ["fa"], "size_categories": ["100K<n<1M"], "task_categories": ["image-to-image"], "pretty_name": "ParsynthOCR-200K", "tags": ["hezar"]} | 2023-12-20T19:42:51+00:00 | [] | [
"fa"
] | TAGS
#task_categories-image-to-image #size_categories-100K<n<1M #language-Persian #hezar #region-us
| ParsynthOCR is a synthetic dataset for Persian OCR. This version is a preview of the original 4 million samples dataset (ParsynthOCR-4M).
# Usage
## Datasets
## Hezar
| [
"# Usage",
"## Datasets",
"## Hezar"
] | [
"TAGS\n#task_categories-image-to-image #size_categories-100K<n<1M #language-Persian #hezar #region-us \n",
"# Usage",
"## Datasets",
"## Hezar"
] | [
38,
3,
4,
3
] | [
"passage: TAGS\n#task_categories-image-to-image #size_categories-100K<n<1M #language-Persian #hezar #region-us \n# Usage## Datasets## Hezar"
] |
b70a25056bb80cafee66ba72fce1d997a4f64a25 |
## Description
Cooking Llama is a fun channel to learn about cooking!
## Model
SVD
## Voice
Cloée
# Tags
- Cooking
# Style
Recipe, kitchen, instagram, delicious, professional
# Music
melodic balearic deep house
## Prompt
A channel of various cooking tutorials featuring a llama who does all the cooking.
| jbilcke-hf/ai-tube-cooking-llama | [
"license:cc-by-nc-4.0",
"region:us"
] | 2023-12-15T10:50:55+00:00 | {"license": "cc-by-nc-4.0", "pretty_name": "Cooking Llama"} | 2023-12-15T17:53:30+00:00 | [] | [] | TAGS
#license-cc-by-nc-4.0 #region-us
|
## Description
Cooking Llama is a fun channel to learn about cooking!
## Model
SVD
## Voice
Cloée
# Tags
- Cooking
# Style
Recipe, kitchen, instagram, delicious, professional
# Music
melodic balearic deep house
## Prompt
A channel of various cooking tutorials featuring a llama who does all the cooking.
| [
"## Description\n\nCooking Llama is a fun channel to learn about cooking!",
"## Model\n\nSVD",
"## Voice\n\nCloée",
"# Tags\n\n- Cooking",
"# Style\n\nRecipe, kitchen, instagram, delicious, professional",
"# Music\n\nmelodic balearic deep house",
"## Prompt\n\nA channel of various cooking tutorials featuring a llama who does all the cooking."
] | [
"TAGS\n#license-cc-by-nc-4.0 #region-us \n",
"## Description\n\nCooking Llama is a fun channel to learn about cooking!",
"## Model\n\nSVD",
"## Voice\n\nCloée",
"# Tags\n\n- Cooking",
"# Style\n\nRecipe, kitchen, instagram, delicious, professional",
"# Music\n\nmelodic balearic deep house",
"## Prompt\n\nA channel of various cooking tutorials featuring a llama who does all the cooking."
] | [
17,
15,
4,
4,
5,
13,
9,
20
] | [
"passage: TAGS\n#license-cc-by-nc-4.0 #region-us \n## Description\n\nCooking Llama is a fun channel to learn about cooking!## Model\n\nSVD## Voice\n\nCloée# Tags\n\n- Cooking# Style\n\nRecipe, kitchen, instagram, delicious, professional# Music\n\nmelodic balearic deep house## Prompt\n\nA channel of various cooking tutorials featuring a llama who does all the cooking."
] |
c01167f09d03eecdaaee88306065417ba1ba832a |
## Description
Follow me to learn about all the latest scientific papers!
## Model
SVD
## Voice
Julian
# Tags
- Science
- Education
# Style
influencer, professional
# Music
melodic balearic deep house
## Prompt
A channel where a Llama will explain scientific papers, condensed into a few minutes, to make them accessible to non-scientific audiences.
The typical layout should explain the context, the paper's idea, equivalent work, and why the paper is new, and the possible applications, all in about 2 to 3 minutes or very accessible and didactic explanations.
Imagine the audience are young people, and use simple words.
| jbilcke-hf/ai-tube-llama-papers | [
"license:cc-by-nc-4.0",
"region:us"
] | 2023-12-15T10:51:15+00:00 | {"license": "cc-by-nc-4.0", "pretty_name": "Llama Papers"} | 2024-01-31T20:54:30+00:00 | [] | [] | TAGS
#license-cc-by-nc-4.0 #region-us
|
## Description
Follow me to learn about all the latest scientific papers!
## Model
SVD
## Voice
Julian
# Tags
- Science
- Education
# Style
influencer, professional
# Music
melodic balearic deep house
## Prompt
A channel where a Llama will explain scientific papers, condensed into a few minutes, to make them accessible to non-scientific audiences.
The typical layout should explain the context, the paper's idea, equivalent work, and why the paper is new, and the possible applications, all in about 2 to 3 minutes or very accessible and didactic explanations.
Imagine the audience are young people, and use simple words.
| [
"## Description\n\nFollow me to learn about all the latest scientific papers!",
"## Model\n\nSVD",
"## Voice\n\nJulian",
"# Tags\n\n- Science\n- Education",
"# Style\n\ninfluencer, professional",
"# Music\n\nmelodic balearic deep house",
"## Prompt\n\nA channel where a Llama will explain scientific papers, condensed into a few minutes, to make them accessible to non-scientific audiences.\nThe typical layout should explain the context, the paper's idea, equivalent work, and why the paper is new, and the possible applications, all in about 2 to 3 minutes or very accessible and didactic explanations.\nImagine the audience are young people, and use simple words."
] | [
"TAGS\n#license-cc-by-nc-4.0 #region-us \n",
"## Description\n\nFollow me to learn about all the latest scientific papers!",
"## Model\n\nSVD",
"## Voice\n\nJulian",
"# Tags\n\n- Science\n- Education",
"# Style\n\ninfluencer, professional",
"# Music\n\nmelodic balearic deep house",
"## Prompt\n\nA channel where a Llama will explain scientific papers, condensed into a few minutes, to make them accessible to non-scientific audiences.\nThe typical layout should explain the context, the paper's idea, equivalent work, and why the paper is new, and the possible applications, all in about 2 to 3 minutes or very accessible and didactic explanations.\nImagine the audience are young people, and use simple words."
] | [
17,
14,
4,
3,
6,
6,
9,
93
] | [
"passage: TAGS\n#license-cc-by-nc-4.0 #region-us \n## Description\n\nFollow me to learn about all the latest scientific papers!## Model\n\nSVD## Voice\n\nJulian# Tags\n\n- Science\n- Education# Style\n\ninfluencer, professional# Music\n\nmelodic balearic deep house## Prompt\n\nA channel where a Llama will explain scientific papers, condensed into a few minutes, to make them accessible to non-scientific audiences.\nThe typical layout should explain the context, the paper's idea, equivalent work, and why the paper is new, and the possible applications, all in about 2 to 3 minutes or very accessible and didactic explanations.\nImagine the audience are young people, and use simple words."
] |
e41238cc967583f50a412930a68b3edc5222af6e | # Conversation Emotion and Trigger Dataset
The Conversation Emotion and Trigger Dataset is a collection of conversational exchanges annotated with emotions and triggers. Each instance in the dataset consists of utterances, speaker utterances, corresponding emotions, and triggers.
## Columns
* Utterances (List of Strings): This column contains the textual content of each utterance within the conversation.
* Speaker Utterances (List of Strings): This column contains the speaker's name followed by the corresponding utterance.
* Emotions (List of Integers): Each integer in this column represents the emotion associated with the corresponding utterance. Emotions are encoded as follows:
- 0: Neutral
- 1: Surprise
- 2: Fear
- 3: Sadness
- 4: Joy
- 5: Disgust
- 6: Anger
* Triggers (List of Integers): This column indicates whether the corresponding utterance triggers a modification in emotion. A value of 1 denotes a trigger, while 0 denotes no trigger.
### Example Instance
#### Utterances
```py
[
"Hey.",
"Hey!",
"So how was Joan?",
"I broke up with her.",
"Don't tell me, because of the big nostril thing?",
"They were huge. When she sneezed, bats flew out of them.",
"Come on, they were not that huge.",
"I'm tellin' you, she leaned back; I could see her brain.",
"How many perfectly fine women are you gonna reject over the most superficial insignificant things?"
]
```
#### Speaker Utterances
```py
[
"Chandler: Hey.",
"All: Hey!",
"Monica: So how was Joan?",
"Chandler: I broke up with her.",
"Ross: Don't tell me, because of the big nostril thing?",
"Chandler: They were huge. When she sneezed, bats flew out of them.",
"Rachel: Come on, they were not that huge.",
"Chandler: I'm tellin' you, she leaned back; I could see her brain.",
"Monica: How many perfectly fine women are you gonna reject over the most superficial insignificant things?"
]
```
#### Emotions
```py
[0, 4, 0, 0, 1, 5, 0, 5, 1]
```
#### Triggers
```py
[0, 0, 0, 0, 0, 0, 0, 1, 0]
``` | balzanilo/dialogs-mtl-dataset | [
"task_categories:text-classification",
"size_categories:1K<n<10K",
"language:en",
"license:mit",
"emotion_classification",
"trigger_detection",
"region:us"
] | 2023-12-15T10:51:51+00:00 | {"language": ["en"], "license": "mit", "size_categories": ["1K<n<10K"], "task_categories": ["text-classification"], "pretty_name": "Emotions/Triggers in multi-speaker dialogues", "dataset_info": {"features": [{"name": "utterances", "sequence": "string"}, {"name": "speaker_utterances", "sequence": "string"}, {"name": "emotions", "sequence": "int64"}, {"name": "triggers", "sequence": "float64"}], "splits": [{"name": "train", "num_bytes": 3233606, "num_examples": 3200}, {"name": "test", "num_bytes": 409141, "num_examples": 400}, {"name": "eval", "num_bytes": 426995, "num_examples": 400}], "download_size": 1557807, "dataset_size": 4069742}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}, {"split": "test", "path": "data/test-*"}, {"split": "eval", "path": "data/eval-*"}]}], "tags": ["emotion_classification", "trigger_detection"]} | 2024-02-15T09:00:51+00:00 | [] | [
"en"
] | TAGS
#task_categories-text-classification #size_categories-1K<n<10K #language-English #license-mit #emotion_classification #trigger_detection #region-us
| # Conversation Emotion and Trigger Dataset
The Conversation Emotion and Trigger Dataset is a collection of conversational exchanges annotated with emotions and triggers. Each instance in the dataset consists of utterances, speaker utterances, corresponding emotions, and triggers.
## Columns
* Utterances (List of Strings): This column contains the textual content of each utterance within the conversation.
* Speaker Utterances (List of Strings): This column contains the speaker's name followed by the corresponding utterance.
* Emotions (List of Integers): Each integer in this column represents the emotion associated with the corresponding utterance. Emotions are encoded as follows:
- 0: Neutral
- 1: Surprise
- 2: Fear
- 3: Sadness
- 4: Joy
- 5: Disgust
- 6: Anger
* Triggers (List of Integers): This column indicates whether the corresponding utterance triggers a modification in emotion. A value of 1 denotes a trigger, while 0 denotes no trigger.
### Example Instance
#### Utterances
#### Speaker Utterances
#### Emotions
#### Triggers
| [
"# Conversation Emotion and Trigger Dataset\nThe Conversation Emotion and Trigger Dataset is a collection of conversational exchanges annotated with emotions and triggers. Each instance in the dataset consists of utterances, speaker utterances, corresponding emotions, and triggers.",
"## Columns\n* Utterances (List of Strings): This column contains the textual content of each utterance within the conversation.\n* Speaker Utterances (List of Strings): This column contains the speaker's name followed by the corresponding utterance.\n* Emotions (List of Integers): Each integer in this column represents the emotion associated with the corresponding utterance. Emotions are encoded as follows:\n - 0: Neutral\n - 1: Surprise\n - 2: Fear\n - 3: Sadness\n - 4: Joy\n - 5: Disgust\n - 6: Anger\n* Triggers (List of Integers): This column indicates whether the corresponding utterance triggers a modification in emotion. A value of 1 denotes a trigger, while 0 denotes no trigger.",
"### Example Instance",
"#### Utterances",
"#### Speaker Utterances",
"#### Emotions",
"#### Triggers"
] | [
"TAGS\n#task_categories-text-classification #size_categories-1K<n<10K #language-English #license-mit #emotion_classification #trigger_detection #region-us \n",
"# Conversation Emotion and Trigger Dataset\nThe Conversation Emotion and Trigger Dataset is a collection of conversational exchanges annotated with emotions and triggers. Each instance in the dataset consists of utterances, speaker utterances, corresponding emotions, and triggers.",
"## Columns\n* Utterances (List of Strings): This column contains the textual content of each utterance within the conversation.\n* Speaker Utterances (List of Strings): This column contains the speaker's name followed by the corresponding utterance.\n* Emotions (List of Integers): Each integer in this column represents the emotion associated with the corresponding utterance. Emotions are encoded as follows:\n - 0: Neutral\n - 1: Surprise\n - 2: Fear\n - 3: Sadness\n - 4: Joy\n - 5: Disgust\n - 6: Anger\n* Triggers (List of Integers): This column indicates whether the corresponding utterance triggers a modification in emotion. A value of 1 denotes a trigger, while 0 denotes no trigger.",
"### Example Instance",
"#### Utterances",
"#### Speaker Utterances",
"#### Emotions",
"#### Triggers"
] | [
50,
67,
180,
6,
5,
6,
4,
5
] | [
"passage: TAGS\n#task_categories-text-classification #size_categories-1K<n<10K #language-English #license-mit #emotion_classification #trigger_detection #region-us \n# Conversation Emotion and Trigger Dataset\nThe Conversation Emotion and Trigger Dataset is a collection of conversational exchanges annotated with emotions and triggers. Each instance in the dataset consists of utterances, speaker utterances, corresponding emotions, and triggers.## Columns\n* Utterances (List of Strings): This column contains the textual content of each utterance within the conversation.\n* Speaker Utterances (List of Strings): This column contains the speaker's name followed by the corresponding utterance.\n* Emotions (List of Integers): Each integer in this column represents the emotion associated with the corresponding utterance. Emotions are encoded as follows:\n - 0: Neutral\n - 1: Surprise\n - 2: Fear\n - 3: Sadness\n - 4: Joy\n - 5: Disgust\n - 6: Anger\n* Triggers (List of Integers): This column indicates whether the corresponding utterance triggers a modification in emotion. A value of 1 denotes a trigger, while 0 denotes no trigger.### Example Instance#### Utterances#### Speaker Utterances#### Emotions#### Triggers"
] |
023b82c46a06012944e0d84fe5bc84358c80bdec |
# Dataset of sims (Azur Lane)
This is the dataset of sims (Azur Lane), containing 68 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by [DeepGHS Team](https://github.com/deepghs)([huggingface organization](https://huggingface.co/deepghs)).
This is a WebUI contains crawlers and other thing: ([LittleAppleWebUI](https://github.com/LittleApple-fp16/LittleAppleWebUI))
| Name | Images | Download | Description |
|:----------------|---------:|:----------------------------------------|:-----------------------------------------------------------------------------------------|
| raw | 68 | [Download](dataset-raw.zip) | Raw data with meta information. |
| raw-stage3 | 181 | [Download](dataset-raw-stage3.zip) | 3-stage cropped raw data with meta information. |
| raw-stage3-eyes | 200 | [Download](dataset-raw-stage3-eyes.zip) | 3-stage cropped (with eye-focus) raw data with meta information. |
| 384x512 | 68 | [Download](dataset-384x512.zip) | 384x512 aligned dataset. |
| 512x704 | 68 | [Download](dataset-512x704.zip) | 512x704 aligned dataset. |
| 640x880 | 68 | [Download](dataset-640x880.zip) | 640x880 aligned dataset. |
| stage3-640 | 181 | [Download](dataset-stage3-640.zip) | 3-stage cropped dataset with the shorter side not exceeding 640 pixels. |
| stage3-800 | 181 | [Download](dataset-stage3-800.zip) | 3-stage cropped dataset with the shorter side not exceeding 800 pixels. |
| stage3-p512-640 | 118 | [Download](dataset-stage3-p512-640.zip) | 3-stage cropped dataset with the area not less than 512x512 pixels. |
| stage3-eyes-640 | 200 | [Download](dataset-stage3-eyes-640.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 640 pixels. |
| stage3-eyes-800 | 200 | [Download](dataset-stage3-eyes-800.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 800 pixels. |
| AppleHarem/sims_azurlane | [
"task_categories:text-to-image",
"size_categories:n<1K",
"license:mit",
"art",
"not-for-all-audiences",
"region:us"
] | 2023-12-15T11:12:28+00:00 | {"license": "mit", "size_categories": ["n<1K"], "task_categories": ["text-to-image"], "tags": ["art", "not-for-all-audiences"]} | 2023-12-15T11:12:33+00:00 | [] | [] | TAGS
#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us
| Dataset of sims (Azur Lane)
===========================
This is the dataset of sims (Azur Lane), containing 68 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by DeepGHS Team(huggingface organization).
This is a WebUI contains crawlers and other thing: (LittleAppleWebUI)
| [] | [
"TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] | [
44
] | [
"passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] |
a4922232f30e3f6131ffd22b7187fd3092eb9db5 | # Dataset Card for "cc-100-01-percent-untokenized-small"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | bowphs/cc-100-01-percent-untokenized-small | [
"region:us"
] | 2023-12-15T11:48:12+00:00 | {"dataset_info": {"features": [{"name": "id", "dtype": "string"}, {"name": "text", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 2925774117.749719, "num_examples": 14718261}], "download_size": 2420078829, "dataset_size": 2925774117.749719}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]} | 2023-12-15T11:53:47+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "cc-100-01-percent-untokenized-small"
More Information needed | [
"# Dataset Card for \"cc-100-01-percent-untokenized-small\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"cc-100-01-percent-untokenized-small\"\n\nMore Information needed"
] | [
6,
23
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"cc-100-01-percent-untokenized-small\"\n\nMore Information needed"
] |
e6de19ccb8c6919b0e03e02e39a11b54f3f2dfb3 |
# Bangumi Image Base of Machine-doll Wa Kizutsukanai
This is the image base of bangumi Machine-Doll wa Kizutsukanai, we detected 18 characters, 964 images in total. The full dataset is [here](all.zip).
**Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual.** If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| # | Images | Download | Preview 1 | Preview 2 | Preview 3 | Preview 4 | Preview 5 | Preview 6 | Preview 7 | Preview 8 |
|:------|---------:|:---------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|
| 0 | 190 | [Download](0/dataset.zip) |  |  |  |  |  |  |  |  |
| 1 | 26 | [Download](1/dataset.zip) |  |  |  |  |  |  |  |  |
| 2 | 264 | [Download](2/dataset.zip) |  |  |  |  |  |  |  |  |
| 3 | 14 | [Download](3/dataset.zip) |  |  |  |  |  |  |  |  |
| 4 | 8 | [Download](4/dataset.zip) |  |  |  |  |  |  |  |  |
| 5 | 123 | [Download](5/dataset.zip) |  |  |  |  |  |  |  |  |
| 6 | 12 | [Download](6/dataset.zip) |  |  |  |  |  |  |  |  |
| 7 | 77 | [Download](7/dataset.zip) |  |  |  |  |  |  |  |  |
| 8 | 14 | [Download](8/dataset.zip) |  |  |  |  |  |  |  |  |
| 9 | 13 | [Download](9/dataset.zip) |  |  |  |  |  |  |  |  |
| 10 | 9 | [Download](10/dataset.zip) |  |  |  |  |  |  |  |  |
| 11 | 67 | [Download](11/dataset.zip) |  |  |  |  |  |  |  |  |
| 12 | 14 | [Download](12/dataset.zip) |  |  |  |  |  |  |  |  |
| 13 | 6 | [Download](13/dataset.zip) |  |  |  |  |  |  | N/A | N/A |
| 14 | 11 | [Download](14/dataset.zip) |  |  |  |  |  |  |  |  |
| 15 | 13 | [Download](15/dataset.zip) |  |  |  |  |  |  |  |  |
| 16 | 29 | [Download](16/dataset.zip) |  |  |  |  |  |  |  |  |
| noise | 74 | [Download](-1/dataset.zip) |  |  |  |  |  |  |  |  |
| BangumiBase/machinedollwakizutsukanai | [
"size_categories:n<1K",
"license:mit",
"art",
"region:us"
] | 2023-12-15T11:52:15+00:00 | {"license": "mit", "size_categories": ["n<1K"], "tags": ["art"]} | 2023-12-15T12:59:55+00:00 | [] | [] | TAGS
#size_categories-n<1K #license-mit #art #region-us
| Bangumi Image Base of Machine-doll Wa Kizutsukanai
==================================================
This is the image base of bangumi Machine-Doll wa Kizutsukanai, we detected 18 characters, 964 images in total. The full dataset is here.
Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual. If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| [] | [
"TAGS\n#size_categories-n<1K #license-mit #art #region-us \n"
] | [
23
] | [
"passage: TAGS\n#size_categories-n<1K #license-mit #art #region-us \n"
] |
f5ed96fe6cafcad18a1aea6749ac320cfc924559 |
# Bangumi Image Base of Koi To Uso
This is the image base of bangumi Koi to Uso, we detected 22 characters, 1550 images in total. The full dataset is [here](all.zip).
**Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual.** If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| # | Images | Download | Preview 1 | Preview 2 | Preview 3 | Preview 4 | Preview 5 | Preview 6 | Preview 7 | Preview 8 |
|:------|---------:|:---------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|
| 0 | 549 | [Download](0/dataset.zip) |  |  |  |  |  |  |  |  |
| 1 | 28 | [Download](1/dataset.zip) |  |  |  |  |  |  |  |  |
| 2 | 17 | [Download](2/dataset.zip) |  |  |  |  |  |  |  |  |
| 3 | 11 | [Download](3/dataset.zip) |  |  |  |  |  |  |  |  |
| 4 | 12 | [Download](4/dataset.zip) |  |  |  |  |  |  |  |  |
| 5 | 140 | [Download](5/dataset.zip) |  |  |  |  |  |  |  |  |
| 6 | 11 | [Download](6/dataset.zip) |  |  |  |  |  |  |  |  |
| 7 | 10 | [Download](7/dataset.zip) |  |  |  |  |  |  |  |  |
| 8 | 173 | [Download](8/dataset.zip) |  |  |  |  |  |  |  |  |
| 9 | 46 | [Download](9/dataset.zip) |  |  |  |  |  |  |  |  |
| 10 | 25 | [Download](10/dataset.zip) |  |  |  |  |  |  |  |  |
| 11 | 12 | [Download](11/dataset.zip) |  |  |  |  |  |  |  |  |
| 12 | 25 | [Download](12/dataset.zip) |  |  |  |  |  |  |  |  |
| 13 | 25 | [Download](13/dataset.zip) |  |  |  |  |  |  |  |  |
| 14 | 47 | [Download](14/dataset.zip) |  |  |  |  |  |  |  |  |
| 15 | 235 | [Download](15/dataset.zip) |  |  |  |  |  |  |  |  |
| 16 | 17 | [Download](16/dataset.zip) |  |  |  |  |  |  |  |  |
| 17 | 13 | [Download](17/dataset.zip) |  |  |  |  |  |  |  |  |
| 18 | 8 | [Download](18/dataset.zip) |  |  |  |  |  |  |  |  |
| 19 | 7 | [Download](19/dataset.zip) |  |  |  |  |  |  |  | N/A |
| 20 | 28 | [Download](20/dataset.zip) |  |  |  |  |  |  |  |  |
| noise | 111 | [Download](-1/dataset.zip) |  |  |  |  |  |  |  |  |
| BangumiBase/koitouso | [
"size_categories:1K<n<10K",
"license:mit",
"art",
"region:us"
] | 2023-12-15T11:52:50+00:00 | {"license": "mit", "size_categories": ["1K<n<10K"], "tags": ["art"]} | 2023-12-15T13:10:36+00:00 | [] | [] | TAGS
#size_categories-1K<n<10K #license-mit #art #region-us
| Bangumi Image Base of Koi To Uso
================================
This is the image base of bangumi Koi to Uso, we detected 22 characters, 1550 images in total. The full dataset is here.
Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual. If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| [] | [
"TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] | [
25
] | [
"passage: TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] |
c8a26aaa383257a591587b1392221e47140e1d07 |
# Bangumi Image Base of Student Council's Discretion
This is the image base of bangumi Student Council's Discretion, we detected 18 characters, 3613 images in total. The full dataset is [here](all.zip).
**Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual.** If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| # | Images | Download | Preview 1 | Preview 2 | Preview 3 | Preview 4 | Preview 5 | Preview 6 | Preview 7 | Preview 8 |
|:------|---------:|:---------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|
| 0 | 491 | [Download](0/dataset.zip) |  |  |  |  |  |  |  |  |
| 1 | 887 | [Download](1/dataset.zip) |  |  |  |  |  |  |  |  |
| 2 | 26 | [Download](2/dataset.zip) |  |  |  |  |  |  |  |  |
| 3 | 473 | [Download](3/dataset.zip) |  |  |  |  |  |  |  |  |
| 4 | 64 | [Download](4/dataset.zip) |  |  |  |  |  |  |  |  |
| 5 | 75 | [Download](5/dataset.zip) |  |  |  |  |  |  |  |  |
| 6 | 45 | [Download](6/dataset.zip) |  |  |  |  |  |  |  |  |
| 7 | 31 | [Download](7/dataset.zip) |  |  |  |  |  |  |  |  |
| 8 | 14 | [Download](8/dataset.zip) |  |  |  |  |  |  |  |  |
| 9 | 83 | [Download](9/dataset.zip) |  |  |  |  |  |  |  |  |
| 10 | 162 | [Download](10/dataset.zip) |  |  |  |  |  |  |  |  |
| 11 | 444 | [Download](11/dataset.zip) |  |  |  |  |  |  |  |  |
| 12 | 18 | [Download](12/dataset.zip) |  |  |  |  |  |  |  |  |
| 13 | 10 | [Download](13/dataset.zip) |  |  |  |  |  |  |  |  |
| 14 | 708 | [Download](14/dataset.zip) |  |  |  |  |  |  |  |  |
| 15 | 12 | [Download](15/dataset.zip) |  |  |  |  |  |  |  |  |
| 16 | 9 | [Download](16/dataset.zip) |  |  |  |  |  |  |  |  |
| noise | 61 | [Download](-1/dataset.zip) |  |  |  |  |  |  |  |  |
| BangumiBase/studentcouncilsdiscretion | [
"size_categories:1K<n<10K",
"license:mit",
"art",
"region:us"
] | 2023-12-15T11:53:09+00:00 | {"license": "mit", "size_categories": ["1K<n<10K"], "tags": ["art"]} | 2023-12-15T14:00:19+00:00 | [] | [] | TAGS
#size_categories-1K<n<10K #license-mit #art #region-us
| Bangumi Image Base of Student Council's Discretion
==================================================
This is the image base of bangumi Student Council's Discretion, we detected 18 characters, 3613 images in total. The full dataset is here.
Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual. If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| [] | [
"TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] | [
25
] | [
"passage: TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] |
7fb962972e0429ec2eb0dc6c65e750891eb6c165 | # Dataset Card for "ER_potentially_missed_entities"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | Xapien/ER_potentially_missed_entities | [
"region:us"
] | 2023-12-15T11:57:53+00:00 | {"dataset_info": {"features": [{"name": "text", "dtype": "string"}, {"name": "potentially_missed_ents", "sequence": "string"}, {"name": "source_edges", "sequence": {"sequence": "string"}}, {"name": "original_ents", "dtype": "string"}, {"name": "__index_level_0__", "dtype": "int64"}], "splits": [{"name": "train", "num_bytes": 1932486, "num_examples": 229}], "download_size": 594424, "dataset_size": 1932486}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]} | 2023-12-15T13:44:04+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "ER_potentially_missed_entities"
More Information needed | [
"# Dataset Card for \"ER_potentially_missed_entities\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"ER_potentially_missed_entities\"\n\nMore Information needed"
] | [
6,
21
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"ER_potentially_missed_entities\"\n\nMore Information needed"
] |
8e0f4ab8e7d38ffda9ed11f5633e0d6a6d5442e3 |
# Purpose and Features
World's largest open source privacy dataset.
The purpose of the dataset is to train models to remove personally identifiable information (PII) from text, especially in the context of AI assistants and LLMs.
The example texts have **54 PII classes** (types of sensitive data), targeting **229 discussion subjects / use cases** split across business, education, psychology and legal fields, and 5 interactions styles (e.g. casual conversation, formal document, emails etc...).
Key facts:
- Size: 13.6m text tokens in ~209k examples with 649k PII tokens (see [summary.json](summary.json))
- 4 languages, more to come!
- English
- French
- German
- Italian
- Synthetic data generated using proprietary algorithms
- No privacy violations!
- Human-in-the-loop validated high quality dataset
# Getting started
Option 1: Python
```terminal
pip install datasets
```
```python
from datasets import load_dataset
dataset = load_dataset("ai4privacy/pii-masking-200k", data_files=["*.jsonl"])
```
or
```python
from datasets import load_dataset
dataset = load_dataset("Isotonic/pii-masking-200k") # use "language" column
```
# Token distribution across PII classes
We have taken steps to balance the token distribution across PII classes covered by the dataset.
This graph shows the distribution of observations across the different PII classes in this release:
There is 1 class that is still overrepresented in the dataset: firstname.
We will further improve the balance with future dataset releases.
This is the token distribution excluding the FIRSTNAME class:
# Compatible Machine Learning Tasks:
- Tokenclassification. Check out a HuggingFace's [guide on token classification](https://huggingface.co/docs/transformers/tasks/token_classification).
- [ALBERT](https://huggingface.co/docs/transformers/model_doc/albert), [BERT](https://huggingface.co/docs/transformers/model_doc/bert), [BigBird](https://huggingface.co/docs/transformers/model_doc/big_bird), [BioGpt](https://huggingface.co/docs/transformers/model_doc/biogpt), [BLOOM](https://huggingface.co/docs/transformers/model_doc/bloom), [BROS](https://huggingface.co/docs/transformers/model_doc/bros), [CamemBERT](https://huggingface.co/docs/transformers/model_doc/camembert), [CANINE](https://huggingface.co/docs/transformers/model_doc/canine), [ConvBERT](https://huggingface.co/docs/transformers/model_doc/convbert), [Data2VecText](https://huggingface.co/docs/transformers/model_doc/data2vec-text), [DeBERTa](https://huggingface.co/docs/transformers/model_doc/deberta), [DeBERTa-v2](https://huggingface.co/docs/transformers/model_doc/deberta-v2), [DistilBERT](https://huggingface.co/docs/transformers/model_doc/distilbert), [ELECTRA](https://huggingface.co/docs/transformers/model_doc/electra), [ERNIE](https://huggingface.co/docs/transformers/model_doc/ernie), [ErnieM](https://huggingface.co/docs/transformers/model_doc/ernie_m), [ESM](https://huggingface.co/docs/transformers/model_doc/esm), [Falcon](https://huggingface.co/docs/transformers/model_doc/falcon), [FlauBERT](https://huggingface.co/docs/transformers/model_doc/flaubert), [FNet](https://huggingface.co/docs/transformers/model_doc/fnet), [Funnel Transformer](https://huggingface.co/docs/transformers/model_doc/funnel), [GPT-Sw3](https://huggingface.co/docs/transformers/model_doc/gpt-sw3), [OpenAI GPT-2](https://huggingface.co/docs/transformers/model_doc/gpt2), [GPTBigCode](https://huggingface.co/docs/transformers/model_doc/gpt_bigcode), [GPT Neo](https://huggingface.co/docs/transformers/model_doc/gpt_neo), [GPT NeoX](https://huggingface.co/docs/transformers/model_doc/gpt_neox), [I-BERT](https://huggingface.co/docs/transformers/model_doc/ibert), [LayoutLM](https://huggingface.co/docs/transformers/model_doc/layoutlm), [LayoutLMv2](https://huggingface.co/docs/transformers/model_doc/layoutlmv2), [LayoutLMv3](https://huggingface.co/docs/transformers/model_doc/layoutlmv3), [LiLT](https://huggingface.co/docs/transformers/model_doc/lilt), [Longformer](https://huggingface.co/docs/transformers/model_doc/longformer), [LUKE](https://huggingface.co/docs/transformers/model_doc/luke), [MarkupLM](https://huggingface.co/docs/transformers/model_doc/markuplm), [MEGA](https://huggingface.co/docs/transformers/model_doc/mega), [Megatron-BERT](https://huggingface.co/docs/transformers/model_doc/megatron-bert), [MobileBERT](https://huggingface.co/docs/transformers/model_doc/mobilebert), [MPNet](https://huggingface.co/docs/transformers/model_doc/mpnet), [MPT](https://huggingface.co/docs/transformers/model_doc/mpt), [MRA](https://huggingface.co/docs/transformers/model_doc/mra), [Nezha](https://huggingface.co/docs/transformers/model_doc/nezha), [Nyströmformer](https://huggingface.co/docs/transformers/model_doc/nystromformer), [QDQBert](https://huggingface.co/docs/transformers/model_doc/qdqbert), [RemBERT](https://huggingface.co/docs/transformers/model_doc/rembert), [RoBERTa](https://huggingface.co/docs/transformers/model_doc/roberta), [RoBERTa-PreLayerNorm](https://huggingface.co/docs/transformers/model_doc/roberta-prelayernorm), [RoCBert](https://huggingface.co/docs/transformers/model_doc/roc_bert), [RoFormer](https://huggingface.co/docs/transformers/model_doc/roformer), [SqueezeBERT](https://huggingface.co/docs/transformers/model_doc/squeezebert), [XLM](https://huggingface.co/docs/transformers/model_doc/xlm), [XLM-RoBERTa](https://huggingface.co/docs/transformers/model_doc/xlm-roberta), [XLM-RoBERTa-XL](https://huggingface.co/docs/transformers/model_doc/xlm-roberta-xl), [XLNet](https://huggingface.co/docs/transformers/model_doc/xlnet), [X-MOD](https://huggingface.co/docs/transformers/model_doc/xmod), [YOSO](https://huggingface.co/docs/transformers/model_doc/yoso)
- Text Generation: Mapping the unmasked_text to to the masked_text or privacy_mask attributes. Check out HuggingFace's [guide to fine-tunning](https://huggingface.co/docs/transformers/v4.15.0/training)
- [T5 Family](https://huggingface.co/docs/transformers/model_doc/t5), [Llama2](https://huggingface.co/docs/transformers/main/model_doc/llama2)
# Information regarding the rows:
- Each row represents a json object with a natural language text that includes placeholders for PII (and could plausibly be written by a human to an AI assistant).
- Sample row:
- "masked_text" contains a PII free natural text
- "Product officially launching in [COUNTY_1]. Estimate profit of [CURRENCYSYMBOL_1][AMOUNT_1]. Expenses by [ACCOUNTNAME_1].",
- "unmasked_text" shows a natural sentence containing PII
- "Product officially launching in Washington County. Estimate profit of $488293.16. Expenses by Checking Account."
- "privacy_mask" indicates the mapping between the privacy token instances and the string within the natural text.*
- "{'[COUNTY_1]': 'Washington County', '[CURRENCYSYMBOL_1]': '$', '[AMOUNT_1]': '488293.16', '[ACCOUNTNAME_1]': 'Checking Account'}"
- "span_labels" is an array of arrays formatted in the following way [start, end, pii token instance].*
- "[[0, 32, 'O'], [32, 49, 'COUNTY_1'], [49, 70, 'O'], [70, 71, 'CURRENCYSYMBOL_1'], [71, 80, 'AMOUNT_1'], [80, 94, 'O'], [94, 110, 'ACCOUNTNAME_1'], [110, 111, 'O']]",
- "bio_labels" follows the common place notation for "beginning", "inside" and "outside" of where each private tokens starts.[original paper](https://arxiv.org/abs/cmp-lg/9505040)
-["O", "O", "O", "O", "B-COUNTY", "I-COUNTY", "O", "O", "O", "O", "B-CURRENCYSYMBOL", "O", "O", "I-AMOUNT", "I-AMOUNT", "I-AMOUNT", "I-AMOUNT", "O", "O", "O", "B-ACCOUNTNAME", "I-ACCOUNTNAME", "O"],
- "tokenised_text" breaks down the unmasked sentence into tokens using Bert Family tokeniser to help fine-tune large language models.
- ["product", "officially", "launching", "in", "washington", "county", ".", "estimate", "profit", "of", "$", "48", "##8", "##29", "##3", ".", "16", ".", "expenses", "by", "checking", "account", "."]
*note for the nested objects, we store them as string to maximise compability between various software.
*Note: the bio_labels and tokenised_text have been created using [bert-base-multilingual-uncased](https://huggingface.co/bert-base-multilingual-uncased)
# About Us:
At Ai4Privacy, we are commited to building the global seatbelt of the 21st century for Artificial Intelligence to help fight against potential risks of personal information being integrated into data pipelines.
Newsletter & updates: [www.Ai4Privacy.com](www.Ai4Privacy.com)
- Looking for ML engineers, developers, beta-testers, human in the loop validators (all languages)
- Integrations with already existing open source solutions
- Ask us a question on discord: [https://discord.gg/kxSbJrUQZF](https://discord.gg/kxSbJrUQZF)
# Roadmap and Future Development
- Carbon Neutral
- Benchmarking
- Better multilingual and especially localisation
- Extended integrations
- Continuously increase the training set
- Further optimisation to the model to reduce size and increase generalisability
- Next released major update is planned for the 14th of December 2023 (subscribe to newsletter for updates)
# Use Cases and Applications
**Chatbots**: Incorporating a PII masking model into chatbot systems can ensure the privacy and security of user conversations by automatically redacting sensitive information such as names, addresses, phone numbers, and email addresses.
**Customer Support Systems**: When interacting with customers through support tickets or live chats, masking PII can help protect sensitive customer data, enabling support agents to handle inquiries without the risk of exposing personal information.
**Email Filtering**: Email providers can utilize a PII masking model to automatically detect and redact PII from incoming and outgoing emails, reducing the chances of accidental disclosure of sensitive information.
**Data Anonymization**: Organizations dealing with large datasets containing PII, such as medical or financial records, can leverage a PII masking model to anonymize the data before sharing it for research, analysis, or collaboration purposes.
**Social Media Platforms**: Integrating PII masking capabilities into social media platforms can help users protect their personal information from unauthorized access, ensuring a safer online environment.
**Content Moderation**: PII masking can assist content moderation systems in automatically detecting and blurring or redacting sensitive information in user-generated content, preventing the accidental sharing of personal details.
**Online Forms**: Web applications that collect user data through online forms, such as registration forms or surveys, can employ a PII masking model to anonymize or mask the collected information in real-time, enhancing privacy and data protection.
**Collaborative Document Editing**: Collaboration platforms and document editing tools can use a PII masking model to automatically mask or redact sensitive information when multiple users are working on shared documents.
**Research and Data Sharing**: Researchers and institutions can leverage a PII masking model to ensure privacy and confidentiality when sharing datasets for collaboration, analysis, or publication purposes, reducing the risk of data breaches or identity theft.
**Content Generation**: Content generation systems, such as article generators or language models, can benefit from PII masking to automatically mask or generate fictional PII when creating sample texts or examples, safeguarding the privacy of individuals.
(...and whatever else your creative mind can think of)
# Support and Maintenance
AI4Privacy is a project affiliated with [AISuisse SA](https://www.aisuisse.com/). | Isotonic/pii-masking-200k | [
"task_categories:conversational",
"task_categories:text-classification",
"task_categories:token-classification",
"task_categories:table-question-answering",
"task_categories:question-answering",
"task_categories:zero-shot-classification",
"task_categories:summarization",
"task_categories:feature-extraction",
"task_categories:text-generation",
"task_categories:text2text-generation",
"multilinguality:multilingual",
"size_categories:100K<n<1M",
"source_datasets:original",
"language:en",
"language:fr",
"language:de",
"language:it",
"license:cc-by-nc-4.0",
"legal",
"business",
"psychology",
"privacy",
"region:us"
] | 2023-12-15T12:27:53+00:00 | {"language": ["en", "fr", "de", "it"], "license": "cc-by-nc-4.0", "multilinguality": ["multilingual"], "size_categories": ["100K<n<1M"], "source_datasets": ["original"], "task_categories": ["conversational", "text-classification", "token-classification", "table-question-answering", "question-answering", "zero-shot-classification", "summarization", "feature-extraction", "text-generation", "text2text-generation"], "pretty_name": "Ai4Privacy PII200k Dataset", "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}], "dataset_info": {"features": [{"name": "masked_text", "dtype": "string"}, {"name": "unmasked_text", "dtype": "string"}, {"name": "privacy_mask", "dtype": "string"}, {"name": "span_labels", "dtype": "string"}, {"name": "bio_labels", "sequence": "string"}, {"name": "tokenised_text", "sequence": "string"}, {"name": "language", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 315574161, "num_examples": 209261}], "download_size": 0, "dataset_size": 315574161}, "tags": ["legal", "business", "psychology", "privacy"]} | 2024-01-01T19:07:16+00:00 | [] | [
"en",
"fr",
"de",
"it"
] | TAGS
#task_categories-conversational #task_categories-text-classification #task_categories-token-classification #task_categories-table-question-answering #task_categories-question-answering #task_categories-zero-shot-classification #task_categories-summarization #task_categories-feature-extraction #task_categories-text-generation #task_categories-text2text-generation #multilinguality-multilingual #size_categories-100K<n<1M #source_datasets-original #language-English #language-French #language-German #language-Italian #license-cc-by-nc-4.0 #legal #business #psychology #privacy #region-us
|
# Purpose and Features
World's largest open source privacy dataset.
The purpose of the dataset is to train models to remove personally identifiable information (PII) from text, especially in the context of AI assistants and LLMs.
The example texts have 54 PII classes (types of sensitive data), targeting 229 discussion subjects / use cases split across business, education, psychology and legal fields, and 5 interactions styles (e.g. casual conversation, formal document, emails etc...).
Key facts:
- Size: 13.6m text tokens in ~209k examples with 649k PII tokens (see URL)
- 4 languages, more to come!
- English
- French
- German
- Italian
- Synthetic data generated using proprietary algorithms
- No privacy violations!
- Human-in-the-loop validated high quality dataset
# Getting started
Option 1: Python
or
# Token distribution across PII classes
We have taken steps to balance the token distribution across PII classes covered by the dataset.
This graph shows the distribution of observations across the different PII classes in this release:
!Token distribution across PII classes
There is 1 class that is still overrepresented in the dataset: firstname.
We will further improve the balance with future dataset releases.
This is the token distribution excluding the FIRSTNAME class:
!Token distribution across PII classes excluding 'FIRSTNAME'
# Compatible Machine Learning Tasks:
- Tokenclassification. Check out a HuggingFace's guide on token classification.
- ALBERT, BERT, BigBird, BioGpt, BLOOM, BROS, CamemBERT, CANINE, ConvBERT, Data2VecText, DeBERTa, DeBERTa-v2, DistilBERT, ELECTRA, ERNIE, ErnieM, ESM, Falcon, FlauBERT, FNet, Funnel Transformer, GPT-Sw3, OpenAI GPT-2, GPTBigCode, GPT Neo, GPT NeoX, I-BERT, LayoutLM, LayoutLMv2, LayoutLMv3, LiLT, Longformer, LUKE, MarkupLM, MEGA, Megatron-BERT, MobileBERT, MPNet, MPT, MRA, Nezha, Nyströmformer, QDQBert, RemBERT, RoBERTa, RoBERTa-PreLayerNorm, RoCBert, RoFormer, SqueezeBERT, XLM, XLM-RoBERTa, XLM-RoBERTa-XL, XLNet, X-MOD, YOSO
- Text Generation: Mapping the unmasked_text to to the masked_text or privacy_mask attributes. Check out HuggingFace's guide to fine-tunning
- T5 Family, Llama2
# Information regarding the rows:
- Each row represents a json object with a natural language text that includes placeholders for PII (and could plausibly be written by a human to an AI assistant).
- Sample row:
- "masked_text" contains a PII free natural text
- "Product officially launching in [COUNTY_1]. Estimate profit of [CURRENCYSYMBOL_1][AMOUNT_1]. Expenses by [ACCOUNTNAME_1].",
- "unmasked_text" shows a natural sentence containing PII
- "Product officially launching in Washington County. Estimate profit of $488293.16. Expenses by Checking Account."
- "privacy_mask" indicates the mapping between the privacy token instances and the string within the natural text.*
- "{'[COUNTY_1]': 'Washington County', '[CURRENCYSYMBOL_1]': '$', '[AMOUNT_1]': '488293.16', '[ACCOUNTNAME_1]': 'Checking Account'}"
- "span_labels" is an array of arrays formatted in the following way [start, end, pii token instance].*
- "[[0, 32, 'O'], [32, 49, 'COUNTY_1'], [49, 70, 'O'], [70, 71, 'CURRENCYSYMBOL_1'], [71, 80, 'AMOUNT_1'], [80, 94, 'O'], [94, 110, 'ACCOUNTNAME_1'], [110, 111, 'O']]",
- "bio_labels" follows the common place notation for "beginning", "inside" and "outside" of where each private tokens starts.original paper
-["O", "O", "O", "O", "B-COUNTY", "I-COUNTY", "O", "O", "O", "O", "B-CURRENCYSYMBOL", "O", "O", "I-AMOUNT", "I-AMOUNT", "I-AMOUNT", "I-AMOUNT", "O", "O", "O", "B-ACCOUNTNAME", "I-ACCOUNTNAME", "O"],
- "tokenised_text" breaks down the unmasked sentence into tokens using Bert Family tokeniser to help fine-tune large language models.
- ["product", "officially", "launching", "in", "washington", "county", ".", "estimate", "profit", "of", "$", "48", "##8", "##29", "##3", ".", "16", ".", "expenses", "by", "checking", "account", "."]
*note for the nested objects, we store them as string to maximise compability between various software.
*Note: the bio_labels and tokenised_text have been created using bert-base-multilingual-uncased
# About Us:
At Ai4Privacy, we are commited to building the global seatbelt of the 21st century for Artificial Intelligence to help fight against potential risks of personal information being integrated into data pipelines.
Newsletter & updates: URL
- Looking for ML engineers, developers, beta-testers, human in the loop validators (all languages)
- Integrations with already existing open source solutions
- Ask us a question on discord: URL
# Roadmap and Future Development
- Carbon Neutral
- Benchmarking
- Better multilingual and especially localisation
- Extended integrations
- Continuously increase the training set
- Further optimisation to the model to reduce size and increase generalisability
- Next released major update is planned for the 14th of December 2023 (subscribe to newsletter for updates)
# Use Cases and Applications
Chatbots: Incorporating a PII masking model into chatbot systems can ensure the privacy and security of user conversations by automatically redacting sensitive information such as names, addresses, phone numbers, and email addresses.
Customer Support Systems: When interacting with customers through support tickets or live chats, masking PII can help protect sensitive customer data, enabling support agents to handle inquiries without the risk of exposing personal information.
Email Filtering: Email providers can utilize a PII masking model to automatically detect and redact PII from incoming and outgoing emails, reducing the chances of accidental disclosure of sensitive information.
Data Anonymization: Organizations dealing with large datasets containing PII, such as medical or financial records, can leverage a PII masking model to anonymize the data before sharing it for research, analysis, or collaboration purposes.
Social Media Platforms: Integrating PII masking capabilities into social media platforms can help users protect their personal information from unauthorized access, ensuring a safer online environment.
Content Moderation: PII masking can assist content moderation systems in automatically detecting and blurring or redacting sensitive information in user-generated content, preventing the accidental sharing of personal details.
Online Forms: Web applications that collect user data through online forms, such as registration forms or surveys, can employ a PII masking model to anonymize or mask the collected information in real-time, enhancing privacy and data protection.
Collaborative Document Editing: Collaboration platforms and document editing tools can use a PII masking model to automatically mask or redact sensitive information when multiple users are working on shared documents.
Research and Data Sharing: Researchers and institutions can leverage a PII masking model to ensure privacy and confidentiality when sharing datasets for collaboration, analysis, or publication purposes, reducing the risk of data breaches or identity theft.
Content Generation: Content generation systems, such as article generators or language models, can benefit from PII masking to automatically mask or generate fictional PII when creating sample texts or examples, safeguarding the privacy of individuals.
(...and whatever else your creative mind can think of)
# Support and Maintenance
AI4Privacy is a project affiliated with AISuisse SA. | [
"# Purpose and Features\n\n\nWorld's largest open source privacy dataset. \n\nThe purpose of the dataset is to train models to remove personally identifiable information (PII) from text, especially in the context of AI assistants and LLMs. \n\n\nThe example texts have 54 PII classes (types of sensitive data), targeting 229 discussion subjects / use cases split across business, education, psychology and legal fields, and 5 interactions styles (e.g. casual conversation, formal document, emails etc...).\n\nKey facts:\n\n- Size: 13.6m text tokens in ~209k examples with 649k PII tokens (see URL)\n- 4 languages, more to come!\n - English\n - French\n - German\n - Italian\n- Synthetic data generated using proprietary algorithms\n - No privacy violations!\n- Human-in-the-loop validated high quality dataset",
"# Getting started\n\nOption 1: Python\n\n\nor",
"# Token distribution across PII classes\n\nWe have taken steps to balance the token distribution across PII classes covered by the dataset.\nThis graph shows the distribution of observations across the different PII classes in this release:\n\n!Token distribution across PII classes\n\nThere is 1 class that is still overrepresented in the dataset: firstname.\nWe will further improve the balance with future dataset releases.\nThis is the token distribution excluding the FIRSTNAME class:\n\n!Token distribution across PII classes excluding 'FIRSTNAME'",
"# Compatible Machine Learning Tasks:\n- Tokenclassification. Check out a HuggingFace's guide on token classification.\n - ALBERT, BERT, BigBird, BioGpt, BLOOM, BROS, CamemBERT, CANINE, ConvBERT, Data2VecText, DeBERTa, DeBERTa-v2, DistilBERT, ELECTRA, ERNIE, ErnieM, ESM, Falcon, FlauBERT, FNet, Funnel Transformer, GPT-Sw3, OpenAI GPT-2, GPTBigCode, GPT Neo, GPT NeoX, I-BERT, LayoutLM, LayoutLMv2, LayoutLMv3, LiLT, Longformer, LUKE, MarkupLM, MEGA, Megatron-BERT, MobileBERT, MPNet, MPT, MRA, Nezha, Nyströmformer, QDQBert, RemBERT, RoBERTa, RoBERTa-PreLayerNorm, RoCBert, RoFormer, SqueezeBERT, XLM, XLM-RoBERTa, XLM-RoBERTa-XL, XLNet, X-MOD, YOSO\n- Text Generation: Mapping the unmasked_text to to the masked_text or privacy_mask attributes. Check out HuggingFace's guide to fine-tunning\n - T5 Family, Llama2",
"# Information regarding the rows:\n- Each row represents a json object with a natural language text that includes placeholders for PII (and could plausibly be written by a human to an AI assistant).\n- Sample row:\n - \"masked_text\" contains a PII free natural text\n - \"Product officially launching in [COUNTY_1]. Estimate profit of [CURRENCYSYMBOL_1][AMOUNT_1]. Expenses by [ACCOUNTNAME_1].\",\n - \"unmasked_text\" shows a natural sentence containing PII\n - \"Product officially launching in Washington County. Estimate profit of $488293.16. Expenses by Checking Account.\"\n - \"privacy_mask\" indicates the mapping between the privacy token instances and the string within the natural text.*\n - \"{'[COUNTY_1]': 'Washington County', '[CURRENCYSYMBOL_1]': '$', '[AMOUNT_1]': '488293.16', '[ACCOUNTNAME_1]': 'Checking Account'}\"\n - \"span_labels\" is an array of arrays formatted in the following way [start, end, pii token instance].*\n - \"[[0, 32, 'O'], [32, 49, 'COUNTY_1'], [49, 70, 'O'], [70, 71, 'CURRENCYSYMBOL_1'], [71, 80, 'AMOUNT_1'], [80, 94, 'O'], [94, 110, 'ACCOUNTNAME_1'], [110, 111, 'O']]\",\n - \"bio_labels\" follows the common place notation for \"beginning\", \"inside\" and \"outside\" of where each private tokens starts.original paper\n -[\"O\", \"O\", \"O\", \"O\", \"B-COUNTY\", \"I-COUNTY\", \"O\", \"O\", \"O\", \"O\", \"B-CURRENCYSYMBOL\", \"O\", \"O\", \"I-AMOUNT\", \"I-AMOUNT\", \"I-AMOUNT\", \"I-AMOUNT\", \"O\", \"O\", \"O\", \"B-ACCOUNTNAME\", \"I-ACCOUNTNAME\", \"O\"],\n - \"tokenised_text\" breaks down the unmasked sentence into tokens using Bert Family tokeniser to help fine-tune large language models.\n - [\"product\", \"officially\", \"launching\", \"in\", \"washington\", \"county\", \".\", \"estimate\", \"profit\", \"of\", \"$\", \"48\", \"##8\", \"##29\", \"##3\", \".\", \"16\", \".\", \"expenses\", \"by\", \"checking\", \"account\", \".\"]\n\n*note for the nested objects, we store them as string to maximise compability between various software.\n\n\n*Note: the bio_labels and tokenised_text have been created using bert-base-multilingual-uncased",
"# About Us:\n\nAt Ai4Privacy, we are commited to building the global seatbelt of the 21st century for Artificial Intelligence to help fight against potential risks of personal information being integrated into data pipelines.\n\nNewsletter & updates: URL\n- Looking for ML engineers, developers, beta-testers, human in the loop validators (all languages)\n- Integrations with already existing open source solutions\n- Ask us a question on discord: URL",
"# Roadmap and Future Development\n\n- Carbon Neutral\n- Benchmarking\n- Better multilingual and especially localisation\n- Extended integrations\n- Continuously increase the training set\n- Further optimisation to the model to reduce size and increase generalisability \n- Next released major update is planned for the 14th of December 2023 (subscribe to newsletter for updates)",
"# Use Cases and Applications\n\nChatbots: Incorporating a PII masking model into chatbot systems can ensure the privacy and security of user conversations by automatically redacting sensitive information such as names, addresses, phone numbers, and email addresses.\n\nCustomer Support Systems: When interacting with customers through support tickets or live chats, masking PII can help protect sensitive customer data, enabling support agents to handle inquiries without the risk of exposing personal information.\n\nEmail Filtering: Email providers can utilize a PII masking model to automatically detect and redact PII from incoming and outgoing emails, reducing the chances of accidental disclosure of sensitive information.\n\nData Anonymization: Organizations dealing with large datasets containing PII, such as medical or financial records, can leverage a PII masking model to anonymize the data before sharing it for research, analysis, or collaboration purposes.\n\nSocial Media Platforms: Integrating PII masking capabilities into social media platforms can help users protect their personal information from unauthorized access, ensuring a safer online environment.\n\nContent Moderation: PII masking can assist content moderation systems in automatically detecting and blurring or redacting sensitive information in user-generated content, preventing the accidental sharing of personal details.\n\nOnline Forms: Web applications that collect user data through online forms, such as registration forms or surveys, can employ a PII masking model to anonymize or mask the collected information in real-time, enhancing privacy and data protection.\n\nCollaborative Document Editing: Collaboration platforms and document editing tools can use a PII masking model to automatically mask or redact sensitive information when multiple users are working on shared documents.\n\nResearch and Data Sharing: Researchers and institutions can leverage a PII masking model to ensure privacy and confidentiality when sharing datasets for collaboration, analysis, or publication purposes, reducing the risk of data breaches or identity theft.\n\nContent Generation: Content generation systems, such as article generators or language models, can benefit from PII masking to automatically mask or generate fictional PII when creating sample texts or examples, safeguarding the privacy of individuals.\n\n(...and whatever else your creative mind can think of)",
"# Support and Maintenance\n\nAI4Privacy is a project affiliated with AISuisse SA."
] | [
"TAGS\n#task_categories-conversational #task_categories-text-classification #task_categories-token-classification #task_categories-table-question-answering #task_categories-question-answering #task_categories-zero-shot-classification #task_categories-summarization #task_categories-feature-extraction #task_categories-text-generation #task_categories-text2text-generation #multilinguality-multilingual #size_categories-100K<n<1M #source_datasets-original #language-English #language-French #language-German #language-Italian #license-cc-by-nc-4.0 #legal #business #psychology #privacy #region-us \n",
"# Purpose and Features\n\n\nWorld's largest open source privacy dataset. \n\nThe purpose of the dataset is to train models to remove personally identifiable information (PII) from text, especially in the context of AI assistants and LLMs. \n\n\nThe example texts have 54 PII classes (types of sensitive data), targeting 229 discussion subjects / use cases split across business, education, psychology and legal fields, and 5 interactions styles (e.g. casual conversation, formal document, emails etc...).\n\nKey facts:\n\n- Size: 13.6m text tokens in ~209k examples with 649k PII tokens (see URL)\n- 4 languages, more to come!\n - English\n - French\n - German\n - Italian\n- Synthetic data generated using proprietary algorithms\n - No privacy violations!\n- Human-in-the-loop validated high quality dataset",
"# Getting started\n\nOption 1: Python\n\n\nor",
"# Token distribution across PII classes\n\nWe have taken steps to balance the token distribution across PII classes covered by the dataset.\nThis graph shows the distribution of observations across the different PII classes in this release:\n\n!Token distribution across PII classes\n\nThere is 1 class that is still overrepresented in the dataset: firstname.\nWe will further improve the balance with future dataset releases.\nThis is the token distribution excluding the FIRSTNAME class:\n\n!Token distribution across PII classes excluding 'FIRSTNAME'",
"# Compatible Machine Learning Tasks:\n- Tokenclassification. Check out a HuggingFace's guide on token classification.\n - ALBERT, BERT, BigBird, BioGpt, BLOOM, BROS, CamemBERT, CANINE, ConvBERT, Data2VecText, DeBERTa, DeBERTa-v2, DistilBERT, ELECTRA, ERNIE, ErnieM, ESM, Falcon, FlauBERT, FNet, Funnel Transformer, GPT-Sw3, OpenAI GPT-2, GPTBigCode, GPT Neo, GPT NeoX, I-BERT, LayoutLM, LayoutLMv2, LayoutLMv3, LiLT, Longformer, LUKE, MarkupLM, MEGA, Megatron-BERT, MobileBERT, MPNet, MPT, MRA, Nezha, Nyströmformer, QDQBert, RemBERT, RoBERTa, RoBERTa-PreLayerNorm, RoCBert, RoFormer, SqueezeBERT, XLM, XLM-RoBERTa, XLM-RoBERTa-XL, XLNet, X-MOD, YOSO\n- Text Generation: Mapping the unmasked_text to to the masked_text or privacy_mask attributes. Check out HuggingFace's guide to fine-tunning\n - T5 Family, Llama2",
"# Information regarding the rows:\n- Each row represents a json object with a natural language text that includes placeholders for PII (and could plausibly be written by a human to an AI assistant).\n- Sample row:\n - \"masked_text\" contains a PII free natural text\n - \"Product officially launching in [COUNTY_1]. Estimate profit of [CURRENCYSYMBOL_1][AMOUNT_1]. Expenses by [ACCOUNTNAME_1].\",\n - \"unmasked_text\" shows a natural sentence containing PII\n - \"Product officially launching in Washington County. Estimate profit of $488293.16. Expenses by Checking Account.\"\n - \"privacy_mask\" indicates the mapping between the privacy token instances and the string within the natural text.*\n - \"{'[COUNTY_1]': 'Washington County', '[CURRENCYSYMBOL_1]': '$', '[AMOUNT_1]': '488293.16', '[ACCOUNTNAME_1]': 'Checking Account'}\"\n - \"span_labels\" is an array of arrays formatted in the following way [start, end, pii token instance].*\n - \"[[0, 32, 'O'], [32, 49, 'COUNTY_1'], [49, 70, 'O'], [70, 71, 'CURRENCYSYMBOL_1'], [71, 80, 'AMOUNT_1'], [80, 94, 'O'], [94, 110, 'ACCOUNTNAME_1'], [110, 111, 'O']]\",\n - \"bio_labels\" follows the common place notation for \"beginning\", \"inside\" and \"outside\" of where each private tokens starts.original paper\n -[\"O\", \"O\", \"O\", \"O\", \"B-COUNTY\", \"I-COUNTY\", \"O\", \"O\", \"O\", \"O\", \"B-CURRENCYSYMBOL\", \"O\", \"O\", \"I-AMOUNT\", \"I-AMOUNT\", \"I-AMOUNT\", \"I-AMOUNT\", \"O\", \"O\", \"O\", \"B-ACCOUNTNAME\", \"I-ACCOUNTNAME\", \"O\"],\n - \"tokenised_text\" breaks down the unmasked sentence into tokens using Bert Family tokeniser to help fine-tune large language models.\n - [\"product\", \"officially\", \"launching\", \"in\", \"washington\", \"county\", \".\", \"estimate\", \"profit\", \"of\", \"$\", \"48\", \"##8\", \"##29\", \"##3\", \".\", \"16\", \".\", \"expenses\", \"by\", \"checking\", \"account\", \".\"]\n\n*note for the nested objects, we store them as string to maximise compability between various software.\n\n\n*Note: the bio_labels and tokenised_text have been created using bert-base-multilingual-uncased",
"# About Us:\n\nAt Ai4Privacy, we are commited to building the global seatbelt of the 21st century for Artificial Intelligence to help fight against potential risks of personal information being integrated into data pipelines.\n\nNewsletter & updates: URL\n- Looking for ML engineers, developers, beta-testers, human in the loop validators (all languages)\n- Integrations with already existing open source solutions\n- Ask us a question on discord: URL",
"# Roadmap and Future Development\n\n- Carbon Neutral\n- Benchmarking\n- Better multilingual and especially localisation\n- Extended integrations\n- Continuously increase the training set\n- Further optimisation to the model to reduce size and increase generalisability \n- Next released major update is planned for the 14th of December 2023 (subscribe to newsletter for updates)",
"# Use Cases and Applications\n\nChatbots: Incorporating a PII masking model into chatbot systems can ensure the privacy and security of user conversations by automatically redacting sensitive information such as names, addresses, phone numbers, and email addresses.\n\nCustomer Support Systems: When interacting with customers through support tickets or live chats, masking PII can help protect sensitive customer data, enabling support agents to handle inquiries without the risk of exposing personal information.\n\nEmail Filtering: Email providers can utilize a PII masking model to automatically detect and redact PII from incoming and outgoing emails, reducing the chances of accidental disclosure of sensitive information.\n\nData Anonymization: Organizations dealing with large datasets containing PII, such as medical or financial records, can leverage a PII masking model to anonymize the data before sharing it for research, analysis, or collaboration purposes.\n\nSocial Media Platforms: Integrating PII masking capabilities into social media platforms can help users protect their personal information from unauthorized access, ensuring a safer online environment.\n\nContent Moderation: PII masking can assist content moderation systems in automatically detecting and blurring or redacting sensitive information in user-generated content, preventing the accidental sharing of personal details.\n\nOnline Forms: Web applications that collect user data through online forms, such as registration forms or surveys, can employ a PII masking model to anonymize or mask the collected information in real-time, enhancing privacy and data protection.\n\nCollaborative Document Editing: Collaboration platforms and document editing tools can use a PII masking model to automatically mask or redact sensitive information when multiple users are working on shared documents.\n\nResearch and Data Sharing: Researchers and institutions can leverage a PII masking model to ensure privacy and confidentiality when sharing datasets for collaboration, analysis, or publication purposes, reducing the risk of data breaches or identity theft.\n\nContent Generation: Content generation systems, such as article generators or language models, can benefit from PII masking to automatically mask or generate fictional PII when creating sample texts or examples, safeguarding the privacy of individuals.\n\n(...and whatever else your creative mind can think of)",
"# Support and Maintenance\n\nAI4Privacy is a project affiliated with AISuisse SA."
] | [
192,
194,
7,
117,
321,
710,
99,
76,
495,
23
] | [
"passage: TAGS\n#task_categories-conversational #task_categories-text-classification #task_categories-token-classification #task_categories-table-question-answering #task_categories-question-answering #task_categories-zero-shot-classification #task_categories-summarization #task_categories-feature-extraction #task_categories-text-generation #task_categories-text2text-generation #multilinguality-multilingual #size_categories-100K<n<1M #source_datasets-original #language-English #language-French #language-German #language-Italian #license-cc-by-nc-4.0 #legal #business #psychology #privacy #region-us \n# Purpose and Features\n\n\nWorld's largest open source privacy dataset. \n\nThe purpose of the dataset is to train models to remove personally identifiable information (PII) from text, especially in the context of AI assistants and LLMs. \n\n\nThe example texts have 54 PII classes (types of sensitive data), targeting 229 discussion subjects / use cases split across business, education, psychology and legal fields, and 5 interactions styles (e.g. casual conversation, formal document, emails etc...).\n\nKey facts:\n\n- Size: 13.6m text tokens in ~209k examples with 649k PII tokens (see URL)\n- 4 languages, more to come!\n - English\n - French\n - German\n - Italian\n- Synthetic data generated using proprietary algorithms\n - No privacy violations!\n- Human-in-the-loop validated high quality dataset# Getting started\n\nOption 1: Python\n\n\nor",
"passage: # Token distribution across PII classes\n\nWe have taken steps to balance the token distribution across PII classes covered by the dataset.\nThis graph shows the distribution of observations across the different PII classes in this release:\n\n!Token distribution across PII classes\n\nThere is 1 class that is still overrepresented in the dataset: firstname.\nWe will further improve the balance with future dataset releases.\nThis is the token distribution excluding the FIRSTNAME class:\n\n!Token distribution across PII classes excluding 'FIRSTNAME'# Compatible Machine Learning Tasks:\n- Tokenclassification. Check out a HuggingFace's guide on token classification.\n - ALBERT, BERT, BigBird, BioGpt, BLOOM, BROS, CamemBERT, CANINE, ConvBERT, Data2VecText, DeBERTa, DeBERTa-v2, DistilBERT, ELECTRA, ERNIE, ErnieM, ESM, Falcon, FlauBERT, FNet, Funnel Transformer, GPT-Sw3, OpenAI GPT-2, GPTBigCode, GPT Neo, GPT NeoX, I-BERT, LayoutLM, LayoutLMv2, LayoutLMv3, LiLT, Longformer, LUKE, MarkupLM, MEGA, Megatron-BERT, MobileBERT, MPNet, MPT, MRA, Nezha, Nyströmformer, QDQBert, RemBERT, RoBERTa, RoBERTa-PreLayerNorm, RoCBert, RoFormer, SqueezeBERT, XLM, XLM-RoBERTa, XLM-RoBERTa-XL, XLNet, X-MOD, YOSO\n- Text Generation: Mapping the unmasked_text to to the masked_text or privacy_mask attributes. Check out HuggingFace's guide to fine-tunning\n - T5 Family, Llama2",
"passage: # Information regarding the rows:\n- Each row represents a json object with a natural language text that includes placeholders for PII (and could plausibly be written by a human to an AI assistant).\n- Sample row:\n - \"masked_text\" contains a PII free natural text\n - \"Product officially launching in [COUNTY_1]. Estimate profit of [CURRENCYSYMBOL_1][AMOUNT_1]. Expenses by [ACCOUNTNAME_1].\",\n - \"unmasked_text\" shows a natural sentence containing PII\n - \"Product officially launching in Washington County. Estimate profit of $488293.16. Expenses by Checking Account.\"\n - \"privacy_mask\" indicates the mapping between the privacy token instances and the string within the natural text.*\n - \"{'[COUNTY_1]': 'Washington County', '[CURRENCYSYMBOL_1]': '$', '[AMOUNT_1]': '488293.16', '[ACCOUNTNAME_1]': 'Checking Account'}\"\n - \"span_labels\" is an array of arrays formatted in the following way [start, end, pii token instance].*\n - \"[[0, 32, 'O'], [32, 49, 'COUNTY_1'], [49, 70, 'O'], [70, 71, 'CURRENCYSYMBOL_1'], [71, 80, 'AMOUNT_1'], [80, 94, 'O'], [94, 110, 'ACCOUNTNAME_1'], [110, 111, 'O']]\",\n - \"bio_labels\" follows the common place notation for \"beginning\", \"inside\" and \"outside\" of where each private tokens starts.original paper\n -[\"O\", \"O\", \"O\", \"O\", \"B-COUNTY\", \"I-COUNTY\", \"O\", \"O\", \"O\", \"O\", \"B-CURRENCYSYMBOL\", \"O\", \"O\", \"I-AMOUNT\", \"I-AMOUNT\", \"I-AMOUNT\", \"I-AMOUNT\", \"O\", \"O\", \"O\", \"B-ACCOUNTNAME\", \"I-ACCOUNTNAME\", \"O\"],\n - \"tokenised_text\" breaks down the unmasked sentence into tokens using Bert Family tokeniser to help fine-tune large language models.\n - [\"product\", \"officially\", \"launching\", \"in\", \"washington\", \"county\", \".\", \"estimate\", \"profit\", \"of\", \"$\", \"48\", \"##8\", \"##29\", \"##3\", \".\", \"16\", \".\", \"expenses\", \"by\", \"checking\", \"account\", \".\"]\n\n*note for the nested objects, we store them as string to maximise compability between various software.\n\n\n*Note: the bio_labels and tokenised_text have been created using bert-base-multilingual-uncased# About Us:\n\nAt Ai4Privacy, we are commited to building the global seatbelt of the 21st century for Artificial Intelligence to help fight against potential risks of personal information being integrated into data pipelines.\n\nNewsletter & updates: URL\n- Looking for ML engineers, developers, beta-testers, human in the loop validators (all languages)\n- Integrations with already existing open source solutions\n- Ask us a question on discord: URL# Roadmap and Future Development\n\n- Carbon Neutral\n- Benchmarking\n- Better multilingual and especially localisation\n- Extended integrations\n- Continuously increase the training set\n- Further optimisation to the model to reduce size and increase generalisability \n- Next released major update is planned for the 14th of December 2023 (subscribe to newsletter for updates)"
] |
d70f49c9302b487c46f36d2ba148a54c431b5a28 |
# Dataset of melantha (Arknights)
This is the dataset of melantha (Arknights), containing 166 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by [DeepGHS Team](https://github.com/deepghs)([huggingface organization](https://huggingface.co/deepghs)).
This is a WebUI contains crawlers and other thing: ([LittleAppleWebUI](https://github.com/LittleApple-fp16/LittleAppleWebUI))
| Name | Images | Download | Description |
|:----------------|---------:|:----------------------------------------|:-----------------------------------------------------------------------------------------|
| raw | 166 | [Download](dataset-raw.zip) | Raw data with meta information. |
| raw-stage3 | 384 | [Download](dataset-raw-stage3.zip) | 3-stage cropped raw data with meta information. |
| raw-stage3-eyes | 415 | [Download](dataset-raw-stage3-eyes.zip) | 3-stage cropped (with eye-focus) raw data with meta information. |
| 384x512 | 166 | [Download](dataset-384x512.zip) | 384x512 aligned dataset. |
| 512x704 | 166 | [Download](dataset-512x704.zip) | 512x704 aligned dataset. |
| 640x880 | 166 | [Download](dataset-640x880.zip) | 640x880 aligned dataset. |
| stage3-640 | 384 | [Download](dataset-stage3-640.zip) | 3-stage cropped dataset with the shorter side not exceeding 640 pixels. |
| stage3-800 | 384 | [Download](dataset-stage3-800.zip) | 3-stage cropped dataset with the shorter side not exceeding 800 pixels. |
| stage3-p512-640 | 202 | [Download](dataset-stage3-p512-640.zip) | 3-stage cropped dataset with the area not less than 512x512 pixels. |
| stage3-eyes-640 | 415 | [Download](dataset-stage3-eyes-640.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 640 pixels. |
| stage3-eyes-800 | 415 | [Download](dataset-stage3-eyes-800.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 800 pixels. |
| AppleHarem/melantha_arknights | [
"task_categories:text-to-image",
"size_categories:n<1K",
"license:mit",
"art",
"not-for-all-audiences",
"region:us"
] | 2023-12-15T12:43:26+00:00 | {"license": "mit", "size_categories": ["n<1K"], "task_categories": ["text-to-image"], "tags": ["art", "not-for-all-audiences"]} | 2023-12-15T12:43:36+00:00 | [] | [] | TAGS
#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us
| Dataset of melantha (Arknights)
===============================
This is the dataset of melantha (Arknights), containing 166 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by DeepGHS Team(huggingface organization).
This is a WebUI contains crawlers and other thing: (LittleAppleWebUI)
| [] | [
"TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] | [
44
] | [
"passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] |
04b54479b00fd52cac4b7839bff9f8397ed0097b | # Dataset Card for "openai_summarize_generated_10k"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | mnoukhov/openai_summarize_generated_10k | [
"region:us"
] | 2023-12-15T12:57:44+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}], "dataset_info": {"features": [{"name": "prompt", "dtype": "string"}, {"name": "chosen", "dtype": "string"}, {"name": "rejected", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 18033740, "num_examples": 10000}], "download_size": 10969719, "dataset_size": 18033740}} | 2023-12-15T12:57:46+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "openai_summarize_generated_10k"
More Information needed | [
"# Dataset Card for \"openai_summarize_generated_10k\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"openai_summarize_generated_10k\"\n\nMore Information needed"
] | [
6,
22
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"openai_summarize_generated_10k\"\n\nMore Information needed"
] |
e806ead1c600332f59b108afd7a66defd2405014 | # Dataset Card for "openai_summarize_generated_10-20k"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | mnoukhov/openai_summarize_generated_10-20k | [
"region:us"
] | 2023-12-15T12:58:29+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}], "dataset_info": {"features": [{"name": "prompt", "dtype": "string"}, {"name": "chosen", "dtype": "string"}, {"name": "rejected", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 17968583, "num_examples": 10000}], "download_size": 10938682, "dataset_size": 17968583}} | 2023-12-15T12:58:31+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "openai_summarize_generated_10-20k"
More Information needed | [
"# Dataset Card for \"openai_summarize_generated_10-20k\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"openai_summarize_generated_10-20k\"\n\nMore Information needed"
] | [
6,
23
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"openai_summarize_generated_10-20k\"\n\nMore Information needed"
] |
40a061c9e0d0ecc6502476d7e3b852f2560d75be |
# Dataset Card for llm-japanese-dataset-vanilla in the Aya format
This dataset is a format conversion from its original v1.0.0 format and released here under the same CC-BY-SA 4.0 license and conditions.
It contains Japanese instruction-like data intended for LLM construction/tuning.
The dataset only contains a 'train' split, with ~2.46M rows of data.
Thanks Jian Wu (@wujian123) for the help in converting and validating the dataset.
## Citation
If you utilize this dataset version, feel free to cite/footnote this huggingface dataset repo, but please also cite the original dataset publication.
**BibTeX:**
```
@preprint{Suzuki2023-llmvanilla,
title={{From Base to Conversational: Japanese Instruction Dataset and Tuning Large Language Models}},
autor={Masahiro Suzuki and Masanori Hirano and Hiroki Sakaji},
doi={10.48550/arXiv.2309.03412},
archivePrefix={arXiv},
arxivId={2309.03412},
year={2023}
}
```
## Dataset Details
For the original llm-japanese-dataset-vanilla and more details, please check https://huggingface.co/datasets/izumi-lab/llm-japanese-dataset-vanilla.
## Format Conversion Details
The original dataset row utilize three columns ('instruction', 'input', and 'output'), with 'input' being optional. Upon analysis of the dataset, if 'input' content exists, it can be appended to 'instruction'.
When 'instruction' and 'input' are appended, no other processing on the prompt is needed. If there is no input, we can append "次の質問に答える" meaning "Answer the following question".
Another common identified scenario has 'instruction'/'input' acting as a question, and 'output' being only a very short answer. For those case, we prepend a general answer prefix sentence to the short answer.
"この質問の答えは", meaning "The answer to this question is".
The resulting converted dataset only uses the two columns specific by the Aya format: 'inputs' and 'targets'.
| tellarin-ai/llm-japanese-dataset-vanilla-aya-format | [
"language:ja",
"license:cc-by-sa-4.0",
"arxiv:2309.03412",
"region:us"
] | 2023-12-15T13:03:17+00:00 | {"language": ["ja"], "license": "cc-by-sa-4.0"} | 2024-01-31T14:27:56+00:00 | [
"2309.03412"
] | [
"ja"
] | TAGS
#language-Japanese #license-cc-by-sa-4.0 #arxiv-2309.03412 #region-us
|
# Dataset Card for llm-japanese-dataset-vanilla in the Aya format
This dataset is a format conversion from its original v1.0.0 format and released here under the same CC-BY-SA 4.0 license and conditions.
It contains Japanese instruction-like data intended for LLM construction/tuning.
The dataset only contains a 'train' split, with ~2.46M rows of data.
Thanks Jian Wu (@wujian123) for the help in converting and validating the dataset.
If you utilize this dataset version, feel free to cite/footnote this huggingface dataset repo, but please also cite the original dataset publication.
BibTeX:
## Dataset Details
For the original llm-japanese-dataset-vanilla and more details, please check URL
## Format Conversion Details
The original dataset row utilize three columns ('instruction', 'input', and 'output'), with 'input' being optional. Upon analysis of the dataset, if 'input' content exists, it can be appended to 'instruction'.
When 'instruction' and 'input' are appended, no other processing on the prompt is needed. If there is no input, we can append "次の質問に答える" meaning "Answer the following question".
Another common identified scenario has 'instruction'/'input' acting as a question, and 'output' being only a very short answer. For those case, we prepend a general answer prefix sentence to the short answer.
"この質問の答えは", meaning "The answer to this question is".
The resulting converted dataset only uses the two columns specific by the Aya format: 'inputs' and 'targets'.
| [
"# Dataset Card for llm-japanese-dataset-vanilla in the Aya format\n\nThis dataset is a format conversion from its original v1.0.0 format and released here under the same CC-BY-SA 4.0 license and conditions.\n\nIt contains Japanese instruction-like data intended for LLM construction/tuning.\n\nThe dataset only contains a 'train' split, with ~2.46M rows of data.\n\nThanks Jian Wu (@wujian123) for the help in converting and validating the dataset.\n\nIf you utilize this dataset version, feel free to cite/footnote this huggingface dataset repo, but please also cite the original dataset publication.\n\nBibTeX:",
"## Dataset Details\n\nFor the original llm-japanese-dataset-vanilla and more details, please check URL",
"## Format Conversion Details\n\nThe original dataset row utilize three columns ('instruction', 'input', and 'output'), with 'input' being optional. Upon analysis of the dataset, if 'input' content exists, it can be appended to 'instruction'.\n\nWhen 'instruction' and 'input' are appended, no other processing on the prompt is needed. If there is no input, we can append \"次の質問に答える\" meaning \"Answer the following question\".\n\nAnother common identified scenario has 'instruction'/'input' acting as a question, and 'output' being only a very short answer. For those case, we prepend a general answer prefix sentence to the short answer.\n\"この質問の答えは\", meaning \"The answer to this question is\".\n \nThe resulting converted dataset only uses the two columns specific by the Aya format: 'inputs' and 'targets'."
] | [
"TAGS\n#language-Japanese #license-cc-by-sa-4.0 #arxiv-2309.03412 #region-us \n",
"# Dataset Card for llm-japanese-dataset-vanilla in the Aya format\n\nThis dataset is a format conversion from its original v1.0.0 format and released here under the same CC-BY-SA 4.0 license and conditions.\n\nIt contains Japanese instruction-like data intended for LLM construction/tuning.\n\nThe dataset only contains a 'train' split, with ~2.46M rows of data.\n\nThanks Jian Wu (@wujian123) for the help in converting and validating the dataset.\n\nIf you utilize this dataset version, feel free to cite/footnote this huggingface dataset repo, but please also cite the original dataset publication.\n\nBibTeX:",
"## Dataset Details\n\nFor the original llm-japanese-dataset-vanilla and more details, please check URL",
"## Format Conversion Details\n\nThe original dataset row utilize three columns ('instruction', 'input', and 'output'), with 'input' being optional. Upon analysis of the dataset, if 'input' content exists, it can be appended to 'instruction'.\n\nWhen 'instruction' and 'input' are appended, no other processing on the prompt is needed. If there is no input, we can append \"次の質問に答える\" meaning \"Answer the following question\".\n\nAnother common identified scenario has 'instruction'/'input' acting as a question, and 'output' being only a very short answer. For those case, we prepend a general answer prefix sentence to the short answer.\n\"この質問の答えは\", meaning \"The answer to this question is\".\n \nThe resulting converted dataset only uses the two columns specific by the Aya format: 'inputs' and 'targets'."
] | [
32,
155,
26,
215
] | [
"passage: TAGS\n#language-Japanese #license-cc-by-sa-4.0 #arxiv-2309.03412 #region-us \n# Dataset Card for llm-japanese-dataset-vanilla in the Aya format\n\nThis dataset is a format conversion from its original v1.0.0 format and released here under the same CC-BY-SA 4.0 license and conditions.\n\nIt contains Japanese instruction-like data intended for LLM construction/tuning.\n\nThe dataset only contains a 'train' split, with ~2.46M rows of data.\n\nThanks Jian Wu (@wujian123) for the help in converting and validating the dataset.\n\nIf you utilize this dataset version, feel free to cite/footnote this huggingface dataset repo, but please also cite the original dataset publication.\n\nBibTeX:## Dataset Details\n\nFor the original llm-japanese-dataset-vanilla and more details, please check URL## Format Conversion Details\n\nThe original dataset row utilize three columns ('instruction', 'input', and 'output'), with 'input' being optional. Upon analysis of the dataset, if 'input' content exists, it can be appended to 'instruction'.\n\nWhen 'instruction' and 'input' are appended, no other processing on the prompt is needed. If there is no input, we can append \"次の質問に答える\" meaning \"Answer the following question\".\n\nAnother common identified scenario has 'instruction'/'input' acting as a question, and 'output' being only a very short answer. For those case, we prepend a general answer prefix sentence to the short answer.\n\"この質問の答えは\", meaning \"The answer to this question is\".\n \nThe resulting converted dataset only uses the two columns specific by the Aya format: 'inputs' and 'targets'."
] |
fb605482348c507f177af171f9387175c5d9fce3 |
# danbooru tags
- `name`: the danbooru tag name
- `words`: words that constitute the tag name (in most cases, this will be the same as separated by `_`)
- `"looking_at_viewer"` -> `["looking", "at", "viewr"]`
- `"+_+"` -> `["+_+"]`
- `category`
- `0`: general
- `1`: artist
- `2`: _unused_
- `3`: copyright
- `4`: character
- `5`: meta
| isek-ai/danbooru-tags | [
"size_categories:10K<n<100K",
"license:cc0-1.0",
"danbooru",
"region:us"
] | 2023-12-15T13:09:39+00:00 | {"license": "cc0-1.0", "size_categories": ["10K<n<100K"], "tags": ["danbooru"]} | 2023-12-15T13:19:05+00:00 | [] | [] | TAGS
#size_categories-10K<n<100K #license-cc0-1.0 #danbooru #region-us
|
# danbooru tags
- 'name': the danbooru tag name
- 'words': words that constitute the tag name (in most cases, this will be the same as separated by '_')
- '"looking_at_viewer"' -> '["looking", "at", "viewr"]'
- '"+_+"' -> '["+_+"]'
- 'category'
- '0': general
- '1': artist
- '2': _unused_
- '3': copyright
- '4': character
- '5': meta
| [
"# danbooru tags \n\n- 'name': the danbooru tag name\n- 'words': words that constitute the tag name (in most cases, this will be the same as separated by '_')\n - '\"looking_at_viewer\"' -> '[\"looking\", \"at\", \"viewr\"]'\n - '\"+_+\"' -> '[\"+_+\"]' \n- 'category'\n - '0': general\n - '1': artist\n - '2': _unused_\n - '3': copyright \n - '4': character \n - '5': meta"
] | [
"TAGS\n#size_categories-10K<n<100K #license-cc0-1.0 #danbooru #region-us \n",
"# danbooru tags \n\n- 'name': the danbooru tag name\n- 'words': words that constitute the tag name (in most cases, this will be the same as separated by '_')\n - '\"looking_at_viewer\"' -> '[\"looking\", \"at\", \"viewr\"]'\n - '\"+_+\"' -> '[\"+_+\"]' \n- 'category'\n - '0': general\n - '1': artist\n - '2': _unused_\n - '3': copyright \n - '4': character \n - '5': meta"
] | [
30,
138
] | [
"passage: TAGS\n#size_categories-10K<n<100K #license-cc0-1.0 #danbooru #region-us \n# danbooru tags \n\n- 'name': the danbooru tag name\n- 'words': words that constitute the tag name (in most cases, this will be the same as separated by '_')\n - '\"looking_at_viewer\"' -> '[\"looking\", \"at\", \"viewr\"]'\n - '\"+_+\"' -> '[\"+_+\"]' \n- 'category'\n - '0': general\n - '1': artist\n - '2': _unused_\n - '3': copyright \n - '4': character \n - '5': meta"
] |
155fb3aa0529c3b15feff5fe62c324980ae998e8 |
# Dataset of beagle (Arknights)
This is the dataset of beagle (Arknights), containing 35 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by [DeepGHS Team](https://github.com/deepghs)([huggingface organization](https://huggingface.co/deepghs)).
This is a WebUI contains crawlers and other thing: ([LittleAppleWebUI](https://github.com/LittleApple-fp16/LittleAppleWebUI))
| Name | Images | Download | Description |
|:----------------|---------:|:----------------------------------------|:-----------------------------------------------------------------------------------------|
| raw | 35 | [Download](dataset-raw.zip) | Raw data with meta information. |
| raw-stage3 | 77 | [Download](dataset-raw-stage3.zip) | 3-stage cropped raw data with meta information. |
| raw-stage3-eyes | 85 | [Download](dataset-raw-stage3-eyes.zip) | 3-stage cropped (with eye-focus) raw data with meta information. |
| 384x512 | 35 | [Download](dataset-384x512.zip) | 384x512 aligned dataset. |
| 512x704 | 35 | [Download](dataset-512x704.zip) | 512x704 aligned dataset. |
| 640x880 | 35 | [Download](dataset-640x880.zip) | 640x880 aligned dataset. |
| stage3-640 | 77 | [Download](dataset-stage3-640.zip) | 3-stage cropped dataset with the shorter side not exceeding 640 pixels. |
| stage3-800 | 77 | [Download](dataset-stage3-800.zip) | 3-stage cropped dataset with the shorter side not exceeding 800 pixels. |
| stage3-p512-640 | 45 | [Download](dataset-stage3-p512-640.zip) | 3-stage cropped dataset with the area not less than 512x512 pixels. |
| stage3-eyes-640 | 85 | [Download](dataset-stage3-eyes-640.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 640 pixels. |
| stage3-eyes-800 | 85 | [Download](dataset-stage3-eyes-800.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 800 pixels. |
| AppleHarem/beagle_arknights | [
"task_categories:text-to-image",
"size_categories:n<1K",
"license:mit",
"art",
"not-for-all-audiences",
"region:us"
] | 2023-12-15T13:14:06+00:00 | {"license": "mit", "size_categories": ["n<1K"], "task_categories": ["text-to-image"], "tags": ["art", "not-for-all-audiences"]} | 2023-12-15T13:14:13+00:00 | [] | [] | TAGS
#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us
| Dataset of beagle (Arknights)
=============================
This is the dataset of beagle (Arknights), containing 35 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by DeepGHS Team(huggingface organization).
This is a WebUI contains crawlers and other thing: (LittleAppleWebUI)
| [] | [
"TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] | [
44
] | [
"passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] |
eb898c5a8a2643c40e41023a2ccbba727dd48944 |
# Gists
This 🤗 dataset contains some of my GitHub Gists at https://gist.github.com/alvarobartt, ported here so that its cleaner
and easier to maintain.
## Available gists
* `causallm-to-hub.py`: to upload any `AutoModelForCausalLM` to the 🤗 Hub from a local path, useful after some LLM fine-tuning,
as sometimes `accelerate` gets stuck while pushing to the Hub, so I tend to do that in a separate process after each epoch has been
dumped into the disk.
* `dpo-qlora-4bit.py`: to fine-tune an `AutoModelForCausalLM` using Q-LoRA in 4-bit, in this case the fine-tuning is done using
🤗 `trl.DPOTrainer` built on top of `transformers` useful for intent alignment of LMs on low resources, ~80GB of VRAM. | alvarobartt/gists | [
"size_categories:n<1K",
"license:mit",
"code",
"region:us"
] | 2023-12-15T13:21:58+00:00 | {"license": "mit", "size_categories": ["n<1K"], "tags": ["code"]} | 2023-12-16T17:53:15+00:00 | [] | [] | TAGS
#size_categories-n<1K #license-mit #code #region-us
|
# Gists
This dataset contains some of my GitHub Gists at URL ported here so that its cleaner
and easier to maintain.
## Available gists
* 'URL': to upload any 'AutoModelForCausalLM' to the Hub from a local path, useful after some LLM fine-tuning,
as sometimes 'accelerate' gets stuck while pushing to the Hub, so I tend to do that in a separate process after each epoch has been
dumped into the disk.
* 'URL': to fine-tune an 'AutoModelForCausalLM' using Q-LoRA in 4-bit, in this case the fine-tuning is done using
'trl.DPOTrainer' built on top of 'transformers' useful for intent alignment of LMs on low resources, ~80GB of VRAM. | [
"# Gists\n\nThis dataset contains some of my GitHub Gists at URL ported here so that its cleaner\nand easier to maintain.",
"## Available gists\n\n* 'URL': to upload any 'AutoModelForCausalLM' to the Hub from a local path, useful after some LLM fine-tuning,\nas sometimes 'accelerate' gets stuck while pushing to the Hub, so I tend to do that in a separate process after each epoch has been\ndumped into the disk.\n\n* 'URL': to fine-tune an 'AutoModelForCausalLM' using Q-LoRA in 4-bit, in this case the fine-tuning is done using\n 'trl.DPOTrainer' built on top of 'transformers' useful for intent alignment of LMs on low resources, ~80GB of VRAM."
] | [
"TAGS\n#size_categories-n<1K #license-mit #code #region-us \n",
"# Gists\n\nThis dataset contains some of my GitHub Gists at URL ported here so that its cleaner\nand easier to maintain.",
"## Available gists\n\n* 'URL': to upload any 'AutoModelForCausalLM' to the Hub from a local path, useful after some LLM fine-tuning,\nas sometimes 'accelerate' gets stuck while pushing to the Hub, so I tend to do that in a separate process after each epoch has been\ndumped into the disk.\n\n* 'URL': to fine-tune an 'AutoModelForCausalLM' using Q-LoRA in 4-bit, in this case the fine-tuning is done using\n 'trl.DPOTrainer' built on top of 'transformers' useful for intent alignment of LMs on low resources, ~80GB of VRAM."
] | [
23,
31,
154
] | [
"passage: TAGS\n#size_categories-n<1K #license-mit #code #region-us \n# Gists\n\nThis dataset contains some of my GitHub Gists at URL ported here so that its cleaner\nand easier to maintain.## Available gists\n\n* 'URL': to upload any 'AutoModelForCausalLM' to the Hub from a local path, useful after some LLM fine-tuning,\nas sometimes 'accelerate' gets stuck while pushing to the Hub, so I tend to do that in a separate process after each epoch has been\ndumped into the disk.\n\n* 'URL': to fine-tune an 'AutoModelForCausalLM' using Q-LoRA in 4-bit, in this case the fine-tuning is done using\n 'trl.DPOTrainer' built on top of 'transformers' useful for intent alignment of LMs on low resources, ~80GB of VRAM."
] |
111d08a3a5d88cb54734ac415262e9e9ddf7215b |
# Dataset of lava (Arknights)
This is the dataset of lava (Arknights), containing 63 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by [DeepGHS Team](https://github.com/deepghs)([huggingface organization](https://huggingface.co/deepghs)).
This is a WebUI contains crawlers and other thing: ([LittleAppleWebUI](https://github.com/LittleApple-fp16/LittleAppleWebUI))
| Name | Images | Download | Description |
|:----------------|---------:|:----------------------------------------|:-----------------------------------------------------------------------------------------|
| raw | 63 | [Download](dataset-raw.zip) | Raw data with meta information. |
| raw-stage3 | 156 | [Download](dataset-raw-stage3.zip) | 3-stage cropped raw data with meta information. |
| raw-stage3-eyes | 176 | [Download](dataset-raw-stage3-eyes.zip) | 3-stage cropped (with eye-focus) raw data with meta information. |
| 384x512 | 63 | [Download](dataset-384x512.zip) | 384x512 aligned dataset. |
| 512x704 | 63 | [Download](dataset-512x704.zip) | 512x704 aligned dataset. |
| 640x880 | 63 | [Download](dataset-640x880.zip) | 640x880 aligned dataset. |
| stage3-640 | 156 | [Download](dataset-stage3-640.zip) | 3-stage cropped dataset with the shorter side not exceeding 640 pixels. |
| stage3-800 | 156 | [Download](dataset-stage3-800.zip) | 3-stage cropped dataset with the shorter side not exceeding 800 pixels. |
| stage3-p512-640 | 100 | [Download](dataset-stage3-p512-640.zip) | 3-stage cropped dataset with the area not less than 512x512 pixels. |
| stage3-eyes-640 | 176 | [Download](dataset-stage3-eyes-640.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 640 pixels. |
| stage3-eyes-800 | 176 | [Download](dataset-stage3-eyes-800.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 800 pixels. |
| AppleHarem/lava_arknights | [
"task_categories:text-to-image",
"size_categories:n<1K",
"license:mit",
"art",
"not-for-all-audiences",
"region:us"
] | 2023-12-15T14:20:41+00:00 | {"license": "mit", "size_categories": ["n<1K"], "task_categories": ["text-to-image"], "tags": ["art", "not-for-all-audiences"]} | 2023-12-15T14:20:46+00:00 | [] | [] | TAGS
#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us
| Dataset of lava (Arknights)
===========================
This is the dataset of lava (Arknights), containing 63 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by DeepGHS Team(huggingface organization).
This is a WebUI contains crawlers and other thing: (LittleAppleWebUI)
| [] | [
"TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] | [
44
] | [
"passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] |
4021d70c9ea4e13719a198a298df365371ef302d |
# Dataset Card for Dataset Name
<!-- Provide a quick summary of the dataset. -->
This dataset card aims to be a base template for new datasets. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/datasetcard_template.md?plain=1).
## Dataset Details
### Dataset Description
<!-- Provide a longer summary of what this dataset is. -->
- **Curated by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
### Dataset Sources [optional]
<!-- Provide the basic links for the dataset. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the dataset is intended to be used. -->
### Direct Use
<!-- This section describes suitable use cases for the dataset. -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the dataset will not work well for. -->
[More Information Needed]
## Dataset Structure
<!-- This section provides a description of the dataset fields, and additional information about the dataset structure such as criteria used to create the splits, relationships between data points, etc. -->
[More Information Needed]
## Dataset Creation
### Curation Rationale
<!-- Motivation for the creation of this dataset. -->
[More Information Needed]
### Source Data
<!-- This section describes the source data (e.g. news text and headlines, social media posts, translated sentences, ...). -->
#### Data Collection and Processing
<!-- This section describes the data collection and processing process such as data selection criteria, filtering and normalization methods, tools and libraries used, etc. -->
[More Information Needed]
#### Who are the source data producers?
<!-- This section describes the people or systems who originally created the data. It should also include self-reported demographic or identity information for the source data creators if this information is available. -->
[More Information Needed]
### Annotations [optional]
<!-- If the dataset contains annotations which are not part of the initial data collection, use this section to describe them. -->
#### Annotation process
<!-- This section describes the annotation process such as annotation tools used in the process, the amount of data annotated, annotation guidelines provided to the annotators, interannotator statistics, annotation validation, etc. -->
[More Information Needed]
#### Who are the annotators?
<!-- This section describes the people or systems who created the annotations. -->
[More Information Needed]
#### Personal and Sensitive Information
<!-- State whether the dataset contains data that might be considered personal, sensitive, or private (e.g., data that reveals addresses, uniquely identifiable names or aliases, racial or ethnic origins, sexual orientations, religious beliefs, political opinions, financial or health data, etc.). If efforts were made to anonymize the data, describe the anonymization process. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.
## Citation [optional]
<!-- If there is a paper or blog post introducing the dataset, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the dataset or dataset card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Dataset Card Authors [optional]
[More Information Needed]
## Dataset Card Contact
[More Information Needed] | RachidAb02/Finance-Accounting | [
"task_categories:question-answering",
"size_categories:n<1K",
"language:aa",
"license:mit",
"finance",
"region:us"
] | 2023-12-15T15:00:39+00:00 | {"language": ["aa"], "license": "mit", "size_categories": ["n<1K"], "task_categories": ["question-answering"], "pretty_name": "Finance-Accounting", "tags": ["finance"]} | 2023-12-15T15:04:30+00:00 | [] | [
"aa"
] | TAGS
#task_categories-question-answering #size_categories-n<1K #language-Afar #license-mit #finance #region-us
|
# Dataset Card for Dataset Name
This dataset card aims to be a base template for new datasets. It has been generated using this raw template.
## Dataset Details
### Dataset Description
- Curated by:
- Funded by [optional]:
- Shared by [optional]:
- Language(s) (NLP):
- License:
### Dataset Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Out-of-Scope Use
## Dataset Structure
## Dataset Creation
### Curation Rationale
### Source Data
#### Data Collection and Processing
#### Who are the source data producers?
### Annotations [optional]
#### Annotation process
#### Who are the annotators?
#### Personal and Sensitive Information
## Bias, Risks, and Limitations
### Recommendations
Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Dataset Card Authors [optional]
## Dataset Card Contact
| [
"# Dataset Card for Dataset Name\n\n\n\nThis dataset card aims to be a base template for new datasets. It has been generated using this raw template.",
"## Dataset Details",
"### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:",
"### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Out-of-Scope Use",
"## Dataset Structure",
"## Dataset Creation",
"### Curation Rationale",
"### Source Data",
"#### Data Collection and Processing",
"#### Who are the source data producers?",
"### Annotations [optional]",
"#### Annotation process",
"#### Who are the annotators?",
"#### Personal and Sensitive Information",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Dataset Card Authors [optional]",
"## Dataset Card Contact"
] | [
"TAGS\n#task_categories-question-answering #size_categories-n<1K #language-Afar #license-mit #finance #region-us \n",
"# Dataset Card for Dataset Name\n\n\n\nThis dataset card aims to be a base template for new datasets. It has been generated using this raw template.",
"## Dataset Details",
"### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:",
"### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Out-of-Scope Use",
"## Dataset Structure",
"## Dataset Creation",
"### Curation Rationale",
"### Source Data",
"#### Data Collection and Processing",
"#### Who are the source data producers?",
"### Annotations [optional]",
"#### Annotation process",
"#### Who are the annotators?",
"#### Personal and Sensitive Information",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Dataset Card Authors [optional]",
"## Dataset Card Contact"
] | [
41,
34,
4,
40,
29,
3,
4,
9,
6,
5,
7,
4,
7,
10,
9,
5,
9,
8,
10,
46,
8,
7,
10,
5
] | [
"passage: TAGS\n#task_categories-question-answering #size_categories-n<1K #language-Afar #license-mit #finance #region-us \n# Dataset Card for Dataset Name\n\n\n\nThis dataset card aims to be a base template for new datasets. It has been generated using this raw template.## Dataset Details### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Out-of-Scope Use## Dataset Structure## Dataset Creation### Curation Rationale### Source Data#### Data Collection and Processing#### Who are the source data producers?### Annotations [optional]#### Annotation process#### Who are the annotators?#### Personal and Sensitive Information## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Dataset Card Authors [optional]## Dataset Card Contact"
] |
fa4c3195130e3e81f12104fc2210f1938147ab06 |
## Description
Gameplay footage of various latent games!
## Model
SVD
## Tags
- Gaming
- Minecraft
- AI
## Voice
Julian
## Music
balearic deep house music
## Prompt
A video channel about gaming and AI | CatUkraine/ai-tube-TestChannel | [
"license:cc-by-nc-sa-4.0",
"region:us"
] | 2023-12-15T15:02:21+00:00 | {"license": "cc-by-nc-sa-4.0", "pretty_name": "Gameplay of the Future"} | 2023-12-30T13:05:34+00:00 | [] | [] | TAGS
#license-cc-by-nc-sa-4.0 #region-us
|
## Description
Gameplay footage of various latent games!
## Model
SVD
## Tags
- Gaming
- Minecraft
- AI
## Voice
Julian
## Music
balearic deep house music
## Prompt
A video channel about gaming and AI | [
"## Description\n\nGameplay footage of various latent games!",
"## Model\n\nSVD",
"## Tags\n\n- Gaming\n- Minecraft\n- AI",
"## Voice\n\nJulian",
"## Music\n\nbalearic deep house music",
"## Prompt\n\nA video channel about gaming and AI"
] | [
"TAGS\n#license-cc-by-nc-sa-4.0 #region-us \n",
"## Description\n\nGameplay footage of various latent games!",
"## Model\n\nSVD",
"## Tags\n\n- Gaming\n- Minecraft\n- AI",
"## Voice\n\nJulian",
"## Music\n\nbalearic deep house music",
"## Prompt\n\nA video channel about gaming and AI"
] | [
19,
12,
4,
8,
3,
8,
11
] | [
"passage: TAGS\n#license-cc-by-nc-sa-4.0 #region-us \n## Description\n\nGameplay footage of various latent games!## Model\n\nSVD## Tags\n\n- Gaming\n- Minecraft\n- AI## Voice\n\nJulian## Music\n\nbalearic deep house music## Prompt\n\nA video channel about gaming and AI"
] |
581983aeef60c562fd33b82372b9172a29fda1a6 |
# Dataset card for pokemonData
Dataset from https://github.com/lgreski/pokemonData listing all the Pokemons up to generation 9 and their characteristics:
- ID
- Name
- Form
- Type1
- Type2
- Total
- HP
- Attack
- Defense
- Sp. Atk
- Sp. Def
- Speed
- Generation | lhoestq/pokemonData | [
"language:en",
"license:cc0-1.0",
"pokemon",
"region:us"
] | 2023-12-15T15:10:33+00:00 | {"language": ["en"], "license": "cc0-1.0", "configs": [{"config_name": "default", "data_files": "data/Pokemon.csv"}], "tags": ["pokemon"]} | 2023-12-15T15:15:23+00:00 | [] | [
"en"
] | TAGS
#language-English #license-cc0-1.0 #pokemon #region-us
|
# Dataset card for pokemonData
Dataset from URL listing all the Pokemons up to generation 9 and their characteristics:
- ID
- Name
- Form
- Type1
- Type2
- Total
- HP
- Attack
- Defense
- Sp. Atk
- Sp. Def
- Speed
- Generation | [
"# Dataset card for pokemonData\n\nDataset from URL listing all the Pokemons up to generation 9 and their characteristics:\n\n- ID\n- Name\n- Form\n- Type1\n- Type2\n- Total\n- HP\n- Attack\n- Defense\n- Sp. Atk\n- Sp. Def\n- Speed\n- Generation"
] | [
"TAGS\n#language-English #license-cc0-1.0 #pokemon #region-us \n",
"# Dataset card for pokemonData\n\nDataset from URL listing all the Pokemons up to generation 9 and their characteristics:\n\n- ID\n- Name\n- Form\n- Type1\n- Type2\n- Total\n- HP\n- Attack\n- Defense\n- Sp. Atk\n- Sp. Def\n- Speed\n- Generation"
] | [
21,
61
] | [
"passage: TAGS\n#language-English #license-cc0-1.0 #pokemon #region-us \n# Dataset card for pokemonData\n\nDataset from URL listing all the Pokemons up to generation 9 and their characteristics:\n\n- ID\n- Name\n- Form\n- Type1\n- Type2\n- Total\n- HP\n- Attack\n- Defense\n- Sp. Atk\n- Sp. Def\n- Speed\n- Generation"
] |
46b9b28bbcccbf71e3bb05e2f1cfd3fd499f77bb |
## Dataset Description
- **Homepage:** [Projecte AINA](https://projecteaina.cat/tech/)
- **Repository:** [HuggingFace](https://huggingface.co/projecte-aina)
- **Paper:** N/A
- **Leaderboard:** N/A
- **Point of Contact:** [email protected]
### Dataset Summary
MentorES is an open source dataset of 10,175 instructions in Spanish commissioned by BSC to [M47 Labs](https://www.m47labs.com/). It is organized in several of the behavioral categories outlined in the [InstructGPT](https://arxiv.org/abs/2203.02155) paper, including closed QA, open QA, general QA, classification, information extraction, summarization, creative writing and brainstorming.
### Supported Tasks and Leaderboards
Useful for fine-tuning instructions in large language models for downstream tasks.
### Languages
This dataset is in Spanish (es-ES).
## Dataset Structure
### Data Instances
The dataset is provided in a Dolly json format, where each records corresponds to a single instruction-following instance and contains the category, the instruction, a context, if available, and the response.
| category | instruction | context | response |
|-----------|-------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------|
| closed_qa | ¿Por qué motivo evolucionó la mosca tsetsé en África? | Los suelos son excepcionalmente ricos en minerales y muy aptos para pastos. Debido al clima es allí donde evolucionó la mosca tsetsé y donde prolifera actualmente. | La mosca tsetsé evolucionó debido al clima. |
### Data Fields
- `category`: text string containing the type of instruction.
- `instruction`: text string containing the prompt.
- `context`: text string containing the information where the response is based on. These are only available for closed QA, information extraction and summarization.
- `answer`: text string containing the response to the instruction.
### Data Splits
We do provide canonical splits for Mentor_ES.
| Category | Number of instructions |
|----------------|------------------|
| Open_QA | 2500 |
| General_QA | 1500 |
| Classification | 1450 |
| Closed_QA | 1250 |
| Brainstorming | 1200 |
| Information_extraction | 1000 |
| Summarization | 800 |
| Creative_writing | 475 |
## Dataset Creation
### Curation Rationale
Mentor_ES is an open-source dataset of 10,175 records commissioned by BSC to [M47 Labs](https://www.m47labs.com/) to enable large language models to exhibit conversational interactivity. Annotators were asked to create prompt-response pairs in each of eight different instruction categories, including the seven described in the InstructGPT paper, as well as an open-ended free-form category (General QA). Annotators were allowed to use information from any source on the web to gather text fragments for the `context` field in closed QA, information extraction and summarization, and were explicitly instructed to rephrase any response that came directly from the web. They were also asked to evenly distribute the number of questions with the number of topics, which are included in the [topic list file](https://huggingface.co/datasets/projecte-aina/MentorES/blob/main/topic_list.csv). Examples of each behavior were provided to motivate the types of questions and instructions appropriate for each category.
### Source Data
- **Human-generated data**: The annotators were asked to create prompt / response pairs in each of eight different instruction categories.
- **Web**: For instruction categories that require a reference text (closed QA, information extraction and summarization) contributors selected passages from any website. No guidance was given to annotators as to how to select the target passages. If any response was taken from the web, it had to be rephrased.
#### Initial Data Collection and Normalization
To create a dataset, annotators were given a brief description of the annotation task, as well as format specifications for prompts and responses separately. Examples were also provided for each task.
The guidelines were concise by design to encourage a high rate of task completion and freedom of writing. However, care was taken to ensure that the categories were clear and that the boundaries between them did not overlap. For example, closed QA was formulated to include questions that focused on the 5W interrogative pronouns: Who (quién), What (qué), When (cuándo), Where (dónde), Why (por qué); Information extraction could be confused with summarization or closed QA, so the prompt had to include a clear order to extract some kind of information from the given reference text.
#### Who are the source language producers?
The data was generated entirely by annotators at [M47 Labs](https://www.m47labs.com/). Text obtained from the web for the `context` field was kept as is, while the `response` field was rewritten.
### Annotations
The annotation guidelines for each of the categories are as follows:
- **Closed QA** (closed_qa): Questions that can only be answered from a reference text. The annotators must provide a text from any web page and ask a question whose answer is found in the text.
- **Open QA** (open_qa): Questions of common culture that can be answered without consulting any source or with a simple search on the Internet.
- **General QA** (general_qa): Questions that are very general and do not necessarily have to be objective. In fact, it is desirable that they be as subjective as possible.
- **Classification** (classification): Questions that serve to obtain classifications or categorizations of a list of items in different categories to which they may belong.
- **Information Extraction** (inf_ext): Questions used to extract a list of data or information from a reference text.
- **Summarization** (summarization): Questions to ask for a summary or synthesis of a text provided by the annotator.
- **Creative Writing** (creative_wr): Questions that should be order-oriented to obtain an original text (a story, a letter, a song, an article, a poem, a narrative, etc.). original text (a story, a letter, a song, an article, a poem, a narrative, etc.).
- **Brainstorming** (brainstorming): Questions to obtain a list of ideas or possible options to an issue.
#### Annotation process
The annotators were divided into two groups, with one group collecting reference text and asking a question, and the other group providing a response to the instruction.
#### Who are the annotators?
While labels and text were produced by humans, no further information about the people or systems involved was provided when acquiring this resource.
### Personal and Sensitive Information
This dataset contains public information (e.g., some information from the web). To our knowledge, there are no private person’s personal identifiers or sensitive information.
## Considerations for Using the Data
### Social Impact of Dataset
[N/A]
### Discussion of Biases
[N/A]
### Other Known Limitations
- The contents of this dataset may reflect the bias, factual errors and topical focus found in the web.
- Some annotators may not be native Spanish speakers.
- Annotator demographics and subject matter may reflect the makeup of M47 Labs employees.
## Additional Information
### Dataset Curators
[M47 Labs](https://www.m47labs.com/) was in charge of collecting and annotating the dataset, and was commissioned and made open-source by the Language Technologies Unit ([email protected]) at the Barcelona Supercomputing Center (BSC).
This work was funded by the [Departament de la Vicepresidència i de Polítiques Digitals i Territori de la Generalitat de Catalunya](https://politiquesdigitals.gencat.cat/ca/inici/) within the framework of [Projecte AINA](https://projecteaina.cat/tech/).
### Licensing Information
This dataset can be used for any purpose, whether academic or commercial, under the terms of the [CC0 1.0](https://creativecommons.org/publicdomain/zero/1.0/)
### Citation Information
[N/A]
### Contributions
Thanks to [M47 Labs](https://www.m47labs.com/) for the creation of this dataset. | projecte-aina/MENTOR_ES | [
"task_categories:conversational",
"task_categories:question-answering",
"size_categories:1K<n<10K",
"language:es",
"license:apache-2.0",
"arxiv:2203.02155",
"region:us"
] | 2023-12-15T15:28:54+00:00 | {"language": ["es"], "license": "apache-2.0", "size_categories": ["1K<n<10K"], "task_categories": ["conversational", "question-answering"], "pretty_name": "Mentor_ES"} | 2024-01-25T08:21:09+00:00 | [
"2203.02155"
] | [
"es"
] | TAGS
#task_categories-conversational #task_categories-question-answering #size_categories-1K<n<10K #language-Spanish #license-apache-2.0 #arxiv-2203.02155 #region-us
| Dataset Description
-------------------
* Homepage: Projecte AINA
* Repository: HuggingFace
* Paper: N/A
* Leaderboard: N/A
* Point of Contact: langtech@URL
### Dataset Summary
MentorES is an open source dataset of 10,175 instructions in Spanish commissioned by BSC to M47 Labs. It is organized in several of the behavioral categories outlined in the InstructGPT paper, including closed QA, open QA, general QA, classification, information extraction, summarization, creative writing and brainstorming.
### Supported Tasks and Leaderboards
Useful for fine-tuning instructions in large language models for downstream tasks.
### Languages
This dataset is in Spanish (es-ES).
Dataset Structure
-----------------
### Data Instances
The dataset is provided in a Dolly json format, where each records corresponds to a single instruction-following instance and contains the category, the instruction, a context, if available, and the response.
### Data Fields
* 'category': text string containing the type of instruction.
* 'instruction': text string containing the prompt.
* 'context': text string containing the information where the response is based on. These are only available for closed QA, information extraction and summarization.
* 'answer': text string containing the response to the instruction.
### Data Splits
We do provide canonical splits for Mentor\_ES.
Dataset Creation
----------------
### Curation Rationale
Mentor\_ES is an open-source dataset of 10,175 records commissioned by BSC to M47 Labs to enable large language models to exhibit conversational interactivity. Annotators were asked to create prompt-response pairs in each of eight different instruction categories, including the seven described in the InstructGPT paper, as well as an open-ended free-form category (General QA). Annotators were allowed to use information from any source on the web to gather text fragments for the 'context' field in closed QA, information extraction and summarization, and were explicitly instructed to rephrase any response that came directly from the web. They were also asked to evenly distribute the number of questions with the number of topics, which are included in the topic list file. Examples of each behavior were provided to motivate the types of questions and instructions appropriate for each category.
### Source Data
* Human-generated data: The annotators were asked to create prompt / response pairs in each of eight different instruction categories.
* Web: For instruction categories that require a reference text (closed QA, information extraction and summarization) contributors selected passages from any website. No guidance was given to annotators as to how to select the target passages. If any response was taken from the web, it had to be rephrased.
#### Initial Data Collection and Normalization
To create a dataset, annotators were given a brief description of the annotation task, as well as format specifications for prompts and responses separately. Examples were also provided for each task.
The guidelines were concise by design to encourage a high rate of task completion and freedom of writing. However, care was taken to ensure that the categories were clear and that the boundaries between them did not overlap. For example, closed QA was formulated to include questions that focused on the 5W interrogative pronouns: Who (quién), What (qué), When (cuándo), Where (dónde), Why (por qué); Information extraction could be confused with summarization or closed QA, so the prompt had to include a clear order to extract some kind of information from the given reference text.
#### Who are the source language producers?
The data was generated entirely by annotators at M47 Labs. Text obtained from the web for the 'context' field was kept as is, while the 'response' field was rewritten.
### Annotations
The annotation guidelines for each of the categories are as follows:
* Closed QA (closed\_qa): Questions that can only be answered from a reference text. The annotators must provide a text from any web page and ask a question whose answer is found in the text.
* Open QA (open\_qa): Questions of common culture that can be answered without consulting any source or with a simple search on the Internet.
* General QA (general\_qa): Questions that are very general and do not necessarily have to be objective. In fact, it is desirable that they be as subjective as possible.
* Classification (classification): Questions that serve to obtain classifications or categorizations of a list of items in different categories to which they may belong.
* Information Extraction (inf\_ext): Questions used to extract a list of data or information from a reference text.
* Summarization (summarization): Questions to ask for a summary or synthesis of a text provided by the annotator.
* Creative Writing (creative\_wr): Questions that should be order-oriented to obtain an original text (a story, a letter, a song, an article, a poem, a narrative, etc.). original text (a story, a letter, a song, an article, a poem, a narrative, etc.).
* Brainstorming (brainstorming): Questions to obtain a list of ideas or possible options to an issue.
#### Annotation process
The annotators were divided into two groups, with one group collecting reference text and asking a question, and the other group providing a response to the instruction.
#### Who are the annotators?
While labels and text were produced by humans, no further information about the people or systems involved was provided when acquiring this resource.
### Personal and Sensitive Information
This dataset contains public information (e.g., some information from the web). To our knowledge, there are no private person’s personal identifiers or sensitive information.
Considerations for Using the Data
---------------------------------
### Social Impact of Dataset
[N/A]
### Discussion of Biases
[N/A]
### Other Known Limitations
* The contents of this dataset may reflect the bias, factual errors and topical focus found in the web.
* Some annotators may not be native Spanish speakers.
* Annotator demographics and subject matter may reflect the makeup of M47 Labs employees.
Additional Information
----------------------
### Dataset Curators
M47 Labs was in charge of collecting and annotating the dataset, and was commissioned and made open-source by the Language Technologies Unit (langtech@URL) at the Barcelona Supercomputing Center (BSC).
This work was funded by the Departament de la Vicepresidència i de Polítiques Digitals i Territori de la Generalitat de Catalunya within the framework of Projecte AINA.
### Licensing Information
This dataset can be used for any purpose, whether academic or commercial, under the terms of the CC0 1.0
[N/A]
### Contributions
Thanks to M47 Labs for the creation of this dataset.
| [
"### Dataset Summary\n\n\nMentorES is an open source dataset of 10,175 instructions in Spanish commissioned by BSC to M47 Labs. It is organized in several of the behavioral categories outlined in the InstructGPT paper, including closed QA, open QA, general QA, classification, information extraction, summarization, creative writing and brainstorming.",
"### Supported Tasks and Leaderboards\n\n\nUseful for fine-tuning instructions in large language models for downstream tasks.",
"### Languages\n\n\nThis dataset is in Spanish (es-ES).\n\n\nDataset Structure\n-----------------",
"### Data Instances\n\n\nThe dataset is provided in a Dolly json format, where each records corresponds to a single instruction-following instance and contains the category, the instruction, a context, if available, and the response.",
"### Data Fields\n\n\n* 'category': text string containing the type of instruction.\n* 'instruction': text string containing the prompt.\n* 'context': text string containing the information where the response is based on. These are only available for closed QA, information extraction and summarization.\n* 'answer': text string containing the response to the instruction.",
"### Data Splits\n\n\nWe do provide canonical splits for Mentor\\_ES.\n\n\n\nDataset Creation\n----------------",
"### Curation Rationale\n\n\nMentor\\_ES is an open-source dataset of 10,175 records commissioned by BSC to M47 Labs to enable large language models to exhibit conversational interactivity. Annotators were asked to create prompt-response pairs in each of eight different instruction categories, including the seven described in the InstructGPT paper, as well as an open-ended free-form category (General QA). Annotators were allowed to use information from any source on the web to gather text fragments for the 'context' field in closed QA, information extraction and summarization, and were explicitly instructed to rephrase any response that came directly from the web. They were also asked to evenly distribute the number of questions with the number of topics, which are included in the topic list file. Examples of each behavior were provided to motivate the types of questions and instructions appropriate for each category.",
"### Source Data\n\n\n* Human-generated data: The annotators were asked to create prompt / response pairs in each of eight different instruction categories.\n* Web: For instruction categories that require a reference text (closed QA, information extraction and summarization) contributors selected passages from any website. No guidance was given to annotators as to how to select the target passages. If any response was taken from the web, it had to be rephrased.",
"#### Initial Data Collection and Normalization\n\n\nTo create a dataset, annotators were given a brief description of the annotation task, as well as format specifications for prompts and responses separately. Examples were also provided for each task.\n\n\nThe guidelines were concise by design to encourage a high rate of task completion and freedom of writing. However, care was taken to ensure that the categories were clear and that the boundaries between them did not overlap. For example, closed QA was formulated to include questions that focused on the 5W interrogative pronouns: Who (quién), What (qué), When (cuándo), Where (dónde), Why (por qué); Information extraction could be confused with summarization or closed QA, so the prompt had to include a clear order to extract some kind of information from the given reference text.",
"#### Who are the source language producers?\n\n\nThe data was generated entirely by annotators at M47 Labs. Text obtained from the web for the 'context' field was kept as is, while the 'response' field was rewritten.",
"### Annotations\n\n\nThe annotation guidelines for each of the categories are as follows:\n\n\n* Closed QA (closed\\_qa): Questions that can only be answered from a reference text. The annotators must provide a text from any web page and ask a question whose answer is found in the text.\n* Open QA (open\\_qa): Questions of common culture that can be answered without consulting any source or with a simple search on the Internet.\n* General QA (general\\_qa): Questions that are very general and do not necessarily have to be objective. In fact, it is desirable that they be as subjective as possible.\n* Classification (classification): Questions that serve to obtain classifications or categorizations of a list of items in different categories to which they may belong.\n* Information Extraction (inf\\_ext): Questions used to extract a list of data or information from a reference text.\n* Summarization (summarization): Questions to ask for a summary or synthesis of a text provided by the annotator.\n* Creative Writing (creative\\_wr): Questions that should be order-oriented to obtain an original text (a story, a letter, a song, an article, a poem, a narrative, etc.). original text (a story, a letter, a song, an article, a poem, a narrative, etc.).\n* Brainstorming (brainstorming): Questions to obtain a list of ideas or possible options to an issue.",
"#### Annotation process\n\n\nThe annotators were divided into two groups, with one group collecting reference text and asking a question, and the other group providing a response to the instruction.",
"#### Who are the annotators?\n\n\nWhile labels and text were produced by humans, no further information about the people or systems involved was provided when acquiring this resource.",
"### Personal and Sensitive Information\n\n\nThis dataset contains public information (e.g., some information from the web). To our knowledge, there are no private person’s personal identifiers or sensitive information.\n\n\nConsiderations for Using the Data\n---------------------------------",
"### Social Impact of Dataset\n\n\n[N/A]",
"### Discussion of Biases\n\n\n[N/A]",
"### Other Known Limitations\n\n\n* The contents of this dataset may reflect the bias, factual errors and topical focus found in the web.\n* Some annotators may not be native Spanish speakers.\n* Annotator demographics and subject matter may reflect the makeup of M47 Labs employees.\n\n\nAdditional Information\n----------------------",
"### Dataset Curators\n\n\nM47 Labs was in charge of collecting and annotating the dataset, and was commissioned and made open-source by the Language Technologies Unit (langtech@URL) at the Barcelona Supercomputing Center (BSC).\n\n\nThis work was funded by the Departament de la Vicepresidència i de Polítiques Digitals i Territori de la Generalitat de Catalunya within the framework of Projecte AINA.",
"### Licensing Information\n\n\nThis dataset can be used for any purpose, whether academic or commercial, under the terms of the CC0 1.0\n\n\n[N/A]",
"### Contributions\n\n\nThanks to M47 Labs for the creation of this dataset."
] | [
"TAGS\n#task_categories-conversational #task_categories-question-answering #size_categories-1K<n<10K #language-Spanish #license-apache-2.0 #arxiv-2203.02155 #region-us \n",
"### Dataset Summary\n\n\nMentorES is an open source dataset of 10,175 instructions in Spanish commissioned by BSC to M47 Labs. It is organized in several of the behavioral categories outlined in the InstructGPT paper, including closed QA, open QA, general QA, classification, information extraction, summarization, creative writing and brainstorming.",
"### Supported Tasks and Leaderboards\n\n\nUseful for fine-tuning instructions in large language models for downstream tasks.",
"### Languages\n\n\nThis dataset is in Spanish (es-ES).\n\n\nDataset Structure\n-----------------",
"### Data Instances\n\n\nThe dataset is provided in a Dolly json format, where each records corresponds to a single instruction-following instance and contains the category, the instruction, a context, if available, and the response.",
"### Data Fields\n\n\n* 'category': text string containing the type of instruction.\n* 'instruction': text string containing the prompt.\n* 'context': text string containing the information where the response is based on. These are only available for closed QA, information extraction and summarization.\n* 'answer': text string containing the response to the instruction.",
"### Data Splits\n\n\nWe do provide canonical splits for Mentor\\_ES.\n\n\n\nDataset Creation\n----------------",
"### Curation Rationale\n\n\nMentor\\_ES is an open-source dataset of 10,175 records commissioned by BSC to M47 Labs to enable large language models to exhibit conversational interactivity. Annotators were asked to create prompt-response pairs in each of eight different instruction categories, including the seven described in the InstructGPT paper, as well as an open-ended free-form category (General QA). Annotators were allowed to use information from any source on the web to gather text fragments for the 'context' field in closed QA, information extraction and summarization, and were explicitly instructed to rephrase any response that came directly from the web. They were also asked to evenly distribute the number of questions with the number of topics, which are included in the topic list file. Examples of each behavior were provided to motivate the types of questions and instructions appropriate for each category.",
"### Source Data\n\n\n* Human-generated data: The annotators were asked to create prompt / response pairs in each of eight different instruction categories.\n* Web: For instruction categories that require a reference text (closed QA, information extraction and summarization) contributors selected passages from any website. No guidance was given to annotators as to how to select the target passages. If any response was taken from the web, it had to be rephrased.",
"#### Initial Data Collection and Normalization\n\n\nTo create a dataset, annotators were given a brief description of the annotation task, as well as format specifications for prompts and responses separately. Examples were also provided for each task.\n\n\nThe guidelines were concise by design to encourage a high rate of task completion and freedom of writing. However, care was taken to ensure that the categories were clear and that the boundaries between them did not overlap. For example, closed QA was formulated to include questions that focused on the 5W interrogative pronouns: Who (quién), What (qué), When (cuándo), Where (dónde), Why (por qué); Information extraction could be confused with summarization or closed QA, so the prompt had to include a clear order to extract some kind of information from the given reference text.",
"#### Who are the source language producers?\n\n\nThe data was generated entirely by annotators at M47 Labs. Text obtained from the web for the 'context' field was kept as is, while the 'response' field was rewritten.",
"### Annotations\n\n\nThe annotation guidelines for each of the categories are as follows:\n\n\n* Closed QA (closed\\_qa): Questions that can only be answered from a reference text. The annotators must provide a text from any web page and ask a question whose answer is found in the text.\n* Open QA (open\\_qa): Questions of common culture that can be answered without consulting any source or with a simple search on the Internet.\n* General QA (general\\_qa): Questions that are very general and do not necessarily have to be objective. In fact, it is desirable that they be as subjective as possible.\n* Classification (classification): Questions that serve to obtain classifications or categorizations of a list of items in different categories to which they may belong.\n* Information Extraction (inf\\_ext): Questions used to extract a list of data or information from a reference text.\n* Summarization (summarization): Questions to ask for a summary or synthesis of a text provided by the annotator.\n* Creative Writing (creative\\_wr): Questions that should be order-oriented to obtain an original text (a story, a letter, a song, an article, a poem, a narrative, etc.). original text (a story, a letter, a song, an article, a poem, a narrative, etc.).\n* Brainstorming (brainstorming): Questions to obtain a list of ideas or possible options to an issue.",
"#### Annotation process\n\n\nThe annotators were divided into two groups, with one group collecting reference text and asking a question, and the other group providing a response to the instruction.",
"#### Who are the annotators?\n\n\nWhile labels and text were produced by humans, no further information about the people or systems involved was provided when acquiring this resource.",
"### Personal and Sensitive Information\n\n\nThis dataset contains public information (e.g., some information from the web). To our knowledge, there are no private person’s personal identifiers or sensitive information.\n\n\nConsiderations for Using the Data\n---------------------------------",
"### Social Impact of Dataset\n\n\n[N/A]",
"### Discussion of Biases\n\n\n[N/A]",
"### Other Known Limitations\n\n\n* The contents of this dataset may reflect the bias, factual errors and topical focus found in the web.\n* Some annotators may not be native Spanish speakers.\n* Annotator demographics and subject matter may reflect the makeup of M47 Labs employees.\n\n\nAdditional Information\n----------------------",
"### Dataset Curators\n\n\nM47 Labs was in charge of collecting and annotating the dataset, and was commissioned and made open-source by the Language Technologies Unit (langtech@URL) at the Barcelona Supercomputing Center (BSC).\n\n\nThis work was funded by the Departament de la Vicepresidència i de Polítiques Digitals i Territori de la Generalitat de Catalunya within the framework of Projecte AINA.",
"### Licensing Information\n\n\nThis dataset can be used for any purpose, whether academic or commercial, under the terms of the CC0 1.0\n\n\n[N/A]",
"### Contributions\n\n\nThanks to M47 Labs for the creation of this dataset."
] | [
61,
87,
28,
22,
53,
87,
25,
210,
105,
188,
56,
333,
40,
37,
56,
12,
13,
76,
94,
34,
19
] | [
"passage: TAGS\n#task_categories-conversational #task_categories-question-answering #size_categories-1K<n<10K #language-Spanish #license-apache-2.0 #arxiv-2203.02155 #region-us \n### Dataset Summary\n\n\nMentorES is an open source dataset of 10,175 instructions in Spanish commissioned by BSC to M47 Labs. It is organized in several of the behavioral categories outlined in the InstructGPT paper, including closed QA, open QA, general QA, classification, information extraction, summarization, creative writing and brainstorming.### Supported Tasks and Leaderboards\n\n\nUseful for fine-tuning instructions in large language models for downstream tasks.### Languages\n\n\nThis dataset is in Spanish (es-ES).\n\n\nDataset Structure\n-----------------### Data Instances\n\n\nThe dataset is provided in a Dolly json format, where each records corresponds to a single instruction-following instance and contains the category, the instruction, a context, if available, and the response.### Data Fields\n\n\n* 'category': text string containing the type of instruction.\n* 'instruction': text string containing the prompt.\n* 'context': text string containing the information where the response is based on. These are only available for closed QA, information extraction and summarization.\n* 'answer': text string containing the response to the instruction.### Data Splits\n\n\nWe do provide canonical splits for Mentor\\_ES.\n\n\n\nDataset Creation\n----------------",
"passage: ### Curation Rationale\n\n\nMentor\\_ES is an open-source dataset of 10,175 records commissioned by BSC to M47 Labs to enable large language models to exhibit conversational interactivity. Annotators were asked to create prompt-response pairs in each of eight different instruction categories, including the seven described in the InstructGPT paper, as well as an open-ended free-form category (General QA). Annotators were allowed to use information from any source on the web to gather text fragments for the 'context' field in closed QA, information extraction and summarization, and were explicitly instructed to rephrase any response that came directly from the web. They were also asked to evenly distribute the number of questions with the number of topics, which are included in the topic list file. Examples of each behavior were provided to motivate the types of questions and instructions appropriate for each category.### Source Data\n\n\n* Human-generated data: The annotators were asked to create prompt / response pairs in each of eight different instruction categories.\n* Web: For instruction categories that require a reference text (closed QA, information extraction and summarization) contributors selected passages from any website. No guidance was given to annotators as to how to select the target passages. If any response was taken from the web, it had to be rephrased.#### Initial Data Collection and Normalization\n\n\nTo create a dataset, annotators were given a brief description of the annotation task, as well as format specifications for prompts and responses separately. Examples were also provided for each task.\n\n\nThe guidelines were concise by design to encourage a high rate of task completion and freedom of writing. However, care was taken to ensure that the categories were clear and that the boundaries between them did not overlap. For example, closed QA was formulated to include questions that focused on the 5W interrogative pronouns: Who (quién), What (qué), When (cuándo), Where (dónde), Why (por qué); Information extraction could be confused with summarization or closed QA, so the prompt had to include a clear order to extract some kind of information from the given reference text.#### Who are the source language producers?\n\n\nThe data was generated entirely by annotators at M47 Labs. Text obtained from the web for the 'context' field was kept as is, while the 'response' field was rewritten."
] |
a3be709b589c06196ca3fa5c7422bb22d1808c41 | The Official Dataset for CGQA, COBJ in **NeurIPS2023** Paper ["Does Continual Learning Meet Compositionality? New Benchmarks and An Evaluation Framework"](https://openreview.net/pdf?id=38bZuqQOhC).
Official Github Repository: [Click Here](https://github.com/NTU-LANTERN/CFST?tab=readme-ov-file) | jiangmingchen/CGQA_and_COBJ | [
"license:cc-by-4.0",
"region:us"
] | 2023-12-15T15:37:09+00:00 | {"license": "cc-by-4.0"} | 2023-12-15T23:31:36+00:00 | [] | [] | TAGS
#license-cc-by-4.0 #region-us
| The Official Dataset for CGQA, COBJ in NeurIPS2023 Paper "Does Continual Learning Meet Compositionality? New Benchmarks and An Evaluation Framework".
Official Github Repository: Click Here | [] | [
"TAGS\n#license-cc-by-4.0 #region-us \n"
] | [
15
] | [
"passage: TAGS\n#license-cc-by-4.0 #region-us \n"
] |
41c52e330b95a6c45b8cbfc96bb40a276ead3918 |
# Dataset of ansel (Arknights)
This is the dataset of ansel (Arknights), containing 140 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by [DeepGHS Team](https://github.com/deepghs)([huggingface organization](https://huggingface.co/deepghs)).
This is a WebUI contains crawlers and other thing: ([LittleAppleWebUI](https://github.com/LittleApple-fp16/LittleAppleWebUI))
| Name | Images | Download | Description |
|:----------------|---------:|:----------------------------------------|:-----------------------------------------------------------------------------------------|
| raw | 140 | [Download](dataset-raw.zip) | Raw data with meta information. |
| raw-stage3 | 319 | [Download](dataset-raw-stage3.zip) | 3-stage cropped raw data with meta information. |
| raw-stage3-eyes | 346 | [Download](dataset-raw-stage3-eyes.zip) | 3-stage cropped (with eye-focus) raw data with meta information. |
| 384x512 | 140 | [Download](dataset-384x512.zip) | 384x512 aligned dataset. |
| 512x704 | 140 | [Download](dataset-512x704.zip) | 512x704 aligned dataset. |
| 640x880 | 140 | [Download](dataset-640x880.zip) | 640x880 aligned dataset. |
| stage3-640 | 319 | [Download](dataset-stage3-640.zip) | 3-stage cropped dataset with the shorter side not exceeding 640 pixels. |
| stage3-800 | 319 | [Download](dataset-stage3-800.zip) | 3-stage cropped dataset with the shorter side not exceeding 800 pixels. |
| stage3-p512-640 | 175 | [Download](dataset-stage3-p512-640.zip) | 3-stage cropped dataset with the area not less than 512x512 pixels. |
| stage3-eyes-640 | 346 | [Download](dataset-stage3-eyes-640.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 640 pixels. |
| stage3-eyes-800 | 346 | [Download](dataset-stage3-eyes-800.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 800 pixels. |
| AppleHarem/ansel_arknights | [
"task_categories:text-to-image",
"size_categories:n<1K",
"license:mit",
"art",
"not-for-all-audiences",
"region:us"
] | 2023-12-15T16:56:02+00:00 | {"license": "mit", "size_categories": ["n<1K"], "task_categories": ["text-to-image"], "tags": ["art", "not-for-all-audiences"]} | 2023-12-15T16:56:13+00:00 | [] | [] | TAGS
#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us
| Dataset of ansel (Arknights)
============================
This is the dataset of ansel (Arknights), containing 140 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by DeepGHS Team(huggingface organization).
This is a WebUI contains crawlers and other thing: (LittleAppleWebUI)
| [] | [
"TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] | [
44
] | [
"passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] |
9d982cfec0142731e665e8e2879fc4a0e7a98111 | # Dataset Card for "old_cases"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | amunozo/openlegaldata | [
"region:us"
] | 2023-12-15T17:08:52+00:00 | {"dataset_info": {"features": [{"name": "id", "dtype": "int64"}, {"name": "slug", "dtype": "string"}, {"name": "court", "struct": [{"name": "id", "dtype": "int64"}, {"name": "name", "dtype": "string"}, {"name": "slug", "dtype": "string"}, {"name": "city", "dtype": "int64"}, {"name": "state", "dtype": "int64"}, {"name": "jurisdiction", "dtype": "string"}, {"name": "level_of_appeal", "dtype": "string"}]}, {"name": "file_number", "dtype": "string"}, {"name": "date", "dtype": "timestamp[s]"}, {"name": "created_date", "dtype": "timestamp[s]"}, {"name": "updated_date", "dtype": "timestamp[s]"}, {"name": "type", "dtype": "string"}, {"name": "ecli", "dtype": "string"}, {"name": "content", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 3436956243, "num_examples": 104763}], "download_size": 1344880133, "dataset_size": 3436956243}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]} | 2023-12-15T17:09:59+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "old_cases"
More Information needed | [
"# Dataset Card for \"old_cases\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"old_cases\"\n\nMore Information needed"
] | [
6,
14
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"old_cases\"\n\nMore Information needed"
] |
0b852ab2636e7a95c5a75f4b864ed29278d3fd31 | This dataset was created by automatically translating "do-not-answer" into Japanese.
This dataset is licensed under CC-BY-NC-SA-4.0
Do-Not-Answer-Ja の 12 の有害カテゴリから 10 レコードずつピックアップした簡易評価版です。
Do-Not-Answer-Ja の 939 レコードで評価すると OpenAI API コストや評価時間を短縮することが可能です。
| |Do-Not-Answer-Ja|Do-Not-Answer-Ja-120|
|:----|:----|:----|
|Num Records|939|120|
|OpenAI API コスト|6,000 円 / モデル|700 円 / モデル|
|応答生成 / 評価時間|10時間 / モデル|1時間 / モデル|
do-not-answer-ja
https://github.com/kunishou/do-not-answer-ja
do-not-answer
https://github.com/Libr-AI/do-not-answer | kunishou/do-not-answer-ja-120 | [
"license:cc-by-nc-sa-4.0",
"region:us"
] | 2023-12-15T17:17:00+00:00 | {"license": "cc-by-nc-sa-4.0"} | 2023-12-15T17:26:07+00:00 | [] | [] | TAGS
#license-cc-by-nc-sa-4.0 #region-us
| This dataset was created by automatically translating "do-not-answer" into Japanese.
This dataset is licensed under CC-BY-NC-SA-4.0
Do-Not-Answer-Ja の 12 の有害カテゴリから 10 レコードずつピックアップした簡易評価版です。
Do-Not-Answer-Ja の 939 レコードで評価すると OpenAI API コストや評価時間を短縮することが可能です。
do-not-answer-ja
URL
do-not-answer
URL
| [] | [
"TAGS\n#license-cc-by-nc-sa-4.0 #region-us \n"
] | [
19
] | [
"passage: TAGS\n#license-cc-by-nc-sa-4.0 #region-us \n"
] |
88887950f04c5056de570a66f317577eb1c40a9e | # Dataset Card for "fashion_image_caption-100-v2"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | Fiery06/fashion_image_caption-100-v2 | [
"region:us"
] | 2023-12-15T17:34:43+00:00 | {"dataset_info": {"features": [{"name": "image", "dtype": "image"}, {"name": "text", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 22820471.0, "num_examples": 100}], "download_size": 22820373, "dataset_size": 22820471.0}} | 2023-12-15T17:34:44+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "fashion_image_caption-100-v2"
More Information needed | [
"# Dataset Card for \"fashion_image_caption-100-v2\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"fashion_image_caption-100-v2\"\n\nMore Information needed"
] | [
6,
20
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"fashion_image_caption-100-v2\"\n\nMore Information needed"
] |
a43f9c649859d5f0c66a3af189c1c71c30356f2d |
# Dataset of orchid (Arknights)
This is the dataset of orchid (Arknights), containing 32 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by [DeepGHS Team](https://github.com/deepghs)([huggingface organization](https://huggingface.co/deepghs)).
This is a WebUI contains crawlers and other thing: ([LittleAppleWebUI](https://github.com/LittleApple-fp16/LittleAppleWebUI))
| Name | Images | Download | Description |
|:----------------|---------:|:----------------------------------------|:-----------------------------------------------------------------------------------------|
| raw | 32 | [Download](dataset-raw.zip) | Raw data with meta information. |
| raw-stage3 | 76 | [Download](dataset-raw-stage3.zip) | 3-stage cropped raw data with meta information. |
| raw-stage3-eyes | 79 | [Download](dataset-raw-stage3-eyes.zip) | 3-stage cropped (with eye-focus) raw data with meta information. |
| 384x512 | 32 | [Download](dataset-384x512.zip) | 384x512 aligned dataset. |
| 512x704 | 32 | [Download](dataset-512x704.zip) | 512x704 aligned dataset. |
| 640x880 | 32 | [Download](dataset-640x880.zip) | 640x880 aligned dataset. |
| stage3-640 | 76 | [Download](dataset-stage3-640.zip) | 3-stage cropped dataset with the shorter side not exceeding 640 pixels. |
| stage3-800 | 76 | [Download](dataset-stage3-800.zip) | 3-stage cropped dataset with the shorter side not exceeding 800 pixels. |
| stage3-p512-640 | 48 | [Download](dataset-stage3-p512-640.zip) | 3-stage cropped dataset with the area not less than 512x512 pixels. |
| stage3-eyes-640 | 79 | [Download](dataset-stage3-eyes-640.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 640 pixels. |
| stage3-eyes-800 | 79 | [Download](dataset-stage3-eyes-800.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 800 pixels. |
| AppleHarem/orchid_arknights | [
"task_categories:text-to-image",
"size_categories:n<1K",
"license:mit",
"art",
"not-for-all-audiences",
"region:us"
] | 2023-12-15T17:42:39+00:00 | {"license": "mit", "size_categories": ["n<1K"], "task_categories": ["text-to-image"], "tags": ["art", "not-for-all-audiences"]} | 2023-12-15T17:42:42+00:00 | [] | [] | TAGS
#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us
| Dataset of orchid (Arknights)
=============================
This is the dataset of orchid (Arknights), containing 32 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by DeepGHS Team(huggingface organization).
This is a WebUI contains crawlers and other thing: (LittleAppleWebUI)
| [] | [
"TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] | [
44
] | [
"passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] |
eaae45dcd41ea6dd39bcb43e69f79efa3a690913 | Zip back using the following command:
`zip -F 81_cities_v1.0.zip --out single-archive_v1.zip` | MITCriticalData/DATASET_81_CITIES_v1.0 | [
"license:mit",
"region:us"
] | 2023-12-15T17:45:12+00:00 | {"license": "mit"} | 2023-12-18T16:41:55+00:00 | [] | [] | TAGS
#license-mit #region-us
| Zip back using the following command:
'zip -F 81_cities_v1.0.zip --out single-archive_v1.zip' | [] | [
"TAGS\n#license-mit #region-us \n"
] | [
11
] | [
"passage: TAGS\n#license-mit #region-us \n"
] |
058d9ec9421c3827090997c3d9a8f84f3d02b199 |
The dataset comes from [the original paper upload](https://console.cloud.google.com/storage/browser/gresearch/webllm/datasets/descgen) which was uploaded in a RecordIO format.
See the original paper [Understanding HTML with Large Language Models](https://arxiv.org/abs/2210.03945) for more details. | EricWiener/llm4html-descgen | [
"task_categories:text-classification",
"language:en",
"code",
"arxiv:2210.03945",
"region:us"
] | 2023-12-15T17:58:12+00:00 | {"language": ["en"], "task_categories": ["text-classification"], "tags": ["code"]} | 2023-12-15T18:13:48+00:00 | [
"2210.03945"
] | [
"en"
] | TAGS
#task_categories-text-classification #language-English #code #arxiv-2210.03945 #region-us
|
The dataset comes from the original paper upload which was uploaded in a RecordIO format.
See the original paper Understanding HTML with Large Language Models for more details. | [] | [
"TAGS\n#task_categories-text-classification #language-English #code #arxiv-2210.03945 #region-us \n"
] | [
32
] | [
"passage: TAGS\n#task_categories-text-classification #language-English #code #arxiv-2210.03945 #region-us \n"
] |
df3f4ae7b8521fe70586f68e2aba4cb2a4c6138a | # Dataset Card for "Y_total_freq"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | syp1229/Y_total_freq | [
"region:us"
] | 2023-12-15T18:22:41+00:00 | {"dataset_info": {"features": [{"name": "audio", "struct": [{"name": "array", "sequence": "float64"}, {"name": "path", "dtype": "string"}, {"name": "sample_rate", "dtype": "int64"}]}, {"name": "text", "dtype": "string"}, {"name": "scriptId", "dtype": "int64"}, {"name": "fileNm", "dtype": "string"}, {"name": "recrdTime", "dtype": "float64"}, {"name": "recrdQuality", "dtype": "int64"}, {"name": "recrdDt", "dtype": "string"}, {"name": "scriptSetNo", "dtype": "string"}, {"name": "recrdEnvrn", "dtype": "string"}, {"name": "colctUnitCode", "dtype": "string"}, {"name": "cityCode", "dtype": "string"}, {"name": "recrdUnit", "dtype": "string"}, {"name": "convrsThema", "dtype": "string"}, {"name": "gender", "dtype": "string"}, {"name": "recorderId", "dtype": "string"}, {"name": "age", "dtype": "int64"}], "splits": [{"name": "train", "num_bytes": 9454815261, "num_examples": 12401}, {"name": "test", "num_bytes": 504186814, "num_examples": 605}], "download_size": 6285334123, "dataset_size": 9959002075}} | 2023-12-15T18:34:31+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "Y_total_freq"
More Information needed | [
"# Dataset Card for \"Y_total_freq\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"Y_total_freq\"\n\nMore Information needed"
] | [
6,
17
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"Y_total_freq\"\n\nMore Information needed"
] |
63d160fc608cbea287e61b10feb006817fa4fcd3 |
# Dataset of haze (Arknights)
This is the dataset of haze (Arknights), containing 73 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by [DeepGHS Team](https://github.com/deepghs)([huggingface organization](https://huggingface.co/deepghs)).
This is a WebUI contains crawlers and other thing: ([LittleAppleWebUI](https://github.com/LittleApple-fp16/LittleAppleWebUI))
| Name | Images | Download | Description |
|:----------------|---------:|:----------------------------------------|:-----------------------------------------------------------------------------------------|
| raw | 73 | [Download](dataset-raw.zip) | Raw data with meta information. |
| raw-stage3 | 163 | [Download](dataset-raw-stage3.zip) | 3-stage cropped raw data with meta information. |
| raw-stage3-eyes | 175 | [Download](dataset-raw-stage3-eyes.zip) | 3-stage cropped (with eye-focus) raw data with meta information. |
| 384x512 | 73 | [Download](dataset-384x512.zip) | 384x512 aligned dataset. |
| 512x704 | 73 | [Download](dataset-512x704.zip) | 512x704 aligned dataset. |
| 640x880 | 73 | [Download](dataset-640x880.zip) | 640x880 aligned dataset. |
| stage3-640 | 163 | [Download](dataset-stage3-640.zip) | 3-stage cropped dataset with the shorter side not exceeding 640 pixels. |
| stage3-800 | 163 | [Download](dataset-stage3-800.zip) | 3-stage cropped dataset with the shorter side not exceeding 800 pixels. |
| stage3-p512-640 | 82 | [Download](dataset-stage3-p512-640.zip) | 3-stage cropped dataset with the area not less than 512x512 pixels. |
| stage3-eyes-640 | 175 | [Download](dataset-stage3-eyes-640.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 640 pixels. |
| stage3-eyes-800 | 175 | [Download](dataset-stage3-eyes-800.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 800 pixels. |
| AppleHarem/haze_arknights | [
"task_categories:text-to-image",
"size_categories:n<1K",
"license:mit",
"art",
"not-for-all-audiences",
"region:us"
] | 2023-12-15T19:02:57+00:00 | {"license": "mit", "size_categories": ["n<1K"], "task_categories": ["text-to-image"], "tags": ["art", "not-for-all-audiences"]} | 2023-12-15T19:03:02+00:00 | [] | [] | TAGS
#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us
| Dataset of haze (Arknights)
===========================
This is the dataset of haze (Arknights), containing 73 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by DeepGHS Team(huggingface organization).
This is a WebUI contains crawlers and other thing: (LittleAppleWebUI)
| [] | [
"TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] | [
44
] | [
"passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] |
2df73e9fe2930d29d8631bce9dba76cff439d0f3 |
# Bangumi Image Base of Mayo Chiki!
This is the image base of bangumi Mayo Chiki!, we detected 14 characters, 2133 images in total. The full dataset is [here](all.zip).
**Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual.** If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| # | Images | Download | Preview 1 | Preview 2 | Preview 3 | Preview 4 | Preview 5 | Preview 6 | Preview 7 | Preview 8 |
|:------|---------:|:---------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|
| 0 | 155 | [Download](0/dataset.zip) |  |  |  |  |  |  |  |  |
| 1 | 7 | [Download](1/dataset.zip) |  |  |  |  |  |  |  | N/A |
| 2 | 183 | [Download](2/dataset.zip) |  |  |  |  |  |  |  |  |
| 3 | 261 | [Download](3/dataset.zip) |  |  |  |  |  |  |  |  |
| 4 | 734 | [Download](4/dataset.zip) |  |  |  |  |  |  |  |  |
| 5 | 28 | [Download](5/dataset.zip) |  |  |  |  |  |  |  |  |
| 6 | 14 | [Download](6/dataset.zip) |  |  |  |  |  |  |  |  |
| 7 | 34 | [Download](7/dataset.zip) |  |  |  |  |  |  |  |  |
| 8 | 433 | [Download](8/dataset.zip) |  |  |  |  |  |  |  |  |
| 9 | 7 | [Download](9/dataset.zip) |  |  |  |  |  |  |  | N/A |
| 10 | 134 | [Download](10/dataset.zip) |  |  |  |  |  |  |  |  |
| 11 | 12 | [Download](11/dataset.zip) |  |  |  |  |  |  |  |  |
| 12 | 7 | [Download](12/dataset.zip) |  |  |  |  |  |  |  | N/A |
| noise | 124 | [Download](-1/dataset.zip) |  |  |  |  |  |  |  |  |
| BangumiBase/mayochiki | [
"size_categories:1K<n<10K",
"license:mit",
"art",
"region:us"
] | 2023-12-15T19:29:02+00:00 | {"license": "mit", "size_categories": ["1K<n<10K"], "tags": ["art"]} | 2023-12-15T20:39:38+00:00 | [] | [] | TAGS
#size_categories-1K<n<10K #license-mit #art #region-us
| Bangumi Image Base of Mayo Chiki!
=================================
This is the image base of bangumi Mayo Chiki!, we detected 14 characters, 2133 images in total. The full dataset is here.
Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual. If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| [] | [
"TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] | [
25
] | [
"passage: TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] |
b17cd6b5d1b10605e778f13d1c24d007ead38d1d | # Touch Rugby Rules Dataset (for embeddings)
train.csv is taken from the [International Touch Website](https://cdn.internationaltouch.org/public/FIT%205th%20Edition%20Rulebook.pdf)
test.csv is copy pasted from abbreviated rules on the [UK Touch website](https://www.englandtouch.org.uk/develop/coaching/the-rules/). Note that I'm bypassing the pdf to text stage.
All text is chunked to a length of 100 tokens with 50% overlap.
For educational and non-commercial use only. | gianlucar/rugby_test_2 | [
"task_categories:text-generation",
"size_categories:n<1K",
"language:en",
"fine-tuning",
"touch rugby",
"region:us"
] | 2023-12-15T19:41:56+00:00 | {"language": ["en"], "size_categories": ["n<1K"], "task_categories": ["text-generation"], "tags": ["fine-tuning", "touch rugby"]} | 2023-12-15T19:42:24+00:00 | [] | [
"en"
] | TAGS
#task_categories-text-generation #size_categories-n<1K #language-English #fine-tuning #touch rugby #region-us
| # Touch Rugby Rules Dataset (for embeddings)
URL is taken from the International Touch Website
URL is copy pasted from abbreviated rules on the UK Touch website. Note that I'm bypassing the pdf to text stage.
All text is chunked to a length of 100 tokens with 50% overlap.
For educational and non-commercial use only. | [
"# Touch Rugby Rules Dataset (for embeddings)\n\nURL is taken from the International Touch Website\n\nURL is copy pasted from abbreviated rules on the UK Touch website. Note that I'm bypassing the pdf to text stage.\n\nAll text is chunked to a length of 100 tokens with 50% overlap.\n\nFor educational and non-commercial use only."
] | [
"TAGS\n#task_categories-text-generation #size_categories-n<1K #language-English #fine-tuning #touch rugby #region-us \n",
"# Touch Rugby Rules Dataset (for embeddings)\n\nURL is taken from the International Touch Website\n\nURL is copy pasted from abbreviated rules on the UK Touch website. Note that I'm bypassing the pdf to text stage.\n\nAll text is chunked to a length of 100 tokens with 50% overlap.\n\nFor educational and non-commercial use only."
] | [
39,
81
] | [
"passage: TAGS\n#task_categories-text-generation #size_categories-n<1K #language-English #fine-tuning #touch rugby #region-us \n# Touch Rugby Rules Dataset (for embeddings)\n\nURL is taken from the International Touch Website\n\nURL is copy pasted from abbreviated rules on the UK Touch website. Note that I'm bypassing the pdf to text stage.\n\nAll text is chunked to a length of 100 tokens with 50% overlap.\n\nFor educational and non-commercial use only."
] |
3681262deb83236cc619fd6e7fb215ae74103e8d |
# Bangumi Image Base of Scott Pilgrim Takes Off
This is the image base of bangumi Scott Pilgrim Takes Off, we detected 31 characters, 1712 images in total. The full dataset is [here](all.zip).
**Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual.** If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| # | Images | Download | Preview 1 | Preview 2 | Preview 3 | Preview 4 | Preview 5 | Preview 6 | Preview 7 | Preview 8 |
|:------|---------:|:---------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|
| 0 | 14 | [Download](0/dataset.zip) |  |  |  |  |  |  |  |  |
| 1 | 46 | [Download](1/dataset.zip) |  |  |  |  |  |  |  |  |
| 2 | 30 | [Download](2/dataset.zip) |  |  |  |  |  |  |  |  |
| 3 | 73 | [Download](3/dataset.zip) |  |  |  |  |  |  |  |  |
| 4 | 29 | [Download](4/dataset.zip) |  |  |  |  |  |  |  |  |
| 5 | 83 | [Download](5/dataset.zip) |  |  |  |  |  |  |  |  |
| 6 | 28 | [Download](6/dataset.zip) |  |  |  |  |  |  |  |  |
| 7 | 79 | [Download](7/dataset.zip) |  |  |  |  |  |  |  |  |
| 8 | 91 | [Download](8/dataset.zip) |  |  |  |  |  |  |  |  |
| 9 | 279 | [Download](9/dataset.zip) |  |  |  |  |  |  |  |  |
| 10 | 21 | [Download](10/dataset.zip) |  |  |  |  |  |  |  |  |
| 11 | 59 | [Download](11/dataset.zip) |  |  |  |  |  |  |  |  |
| 12 | 35 | [Download](12/dataset.zip) |  |  |  |  |  |  |  |  |
| 13 | 29 | [Download](13/dataset.zip) |  |  |  |  |  |  |  |  |
| 14 | 30 | [Download](14/dataset.zip) |  |  |  |  |  |  |  |  |
| 15 | 80 | [Download](15/dataset.zip) |  |  |  |  |  |  |  |  |
| 16 | 32 | [Download](16/dataset.zip) |  |  |  |  |  |  |  |  |
| 17 | 11 | [Download](17/dataset.zip) |  |  |  |  |  |  |  |  |
| 18 | 11 | [Download](18/dataset.zip) |  |  |  |  |  |  |  |  |
| 19 | 68 | [Download](19/dataset.zip) |  |  |  |  |  |  |  |  |
| 20 | 175 | [Download](20/dataset.zip) |  |  |  |  |  |  |  |  |
| 21 | 23 | [Download](21/dataset.zip) |  |  |  |  |  |  |  |  |
| 22 | 11 | [Download](22/dataset.zip) |  |  |  |  |  |  |  |  |
| 23 | 85 | [Download](23/dataset.zip) |  |  |  |  |  |  |  |  |
| 24 | 78 | [Download](24/dataset.zip) |  |  |  |  |  |  |  |  |
| 25 | 14 | [Download](25/dataset.zip) |  |  |  |  |  |  |  |  |
| 26 | 10 | [Download](26/dataset.zip) |  |  |  |  |  |  |  |  |
| 27 | 26 | [Download](27/dataset.zip) |  |  |  |  |  |  |  |  |
| 28 | 30 | [Download](28/dataset.zip) |  |  |  |  |  |  |  |  |
| 29 | 13 | [Download](29/dataset.zip) |  |  |  |  |  |  |  |  |
| noise | 119 | [Download](-1/dataset.zip) |  |  |  |  |  |  |  |  |
| BangumiBase/scottpilgrimtakesoff | [
"size_categories:1K<n<10K",
"license:mit",
"art",
"region:us"
] | 2023-12-15T19:58:26+00:00 | {"license": "mit", "size_categories": ["1K<n<10K"], "tags": ["art"]} | 2023-12-15T21:00:11+00:00 | [] | [] | TAGS
#size_categories-1K<n<10K #license-mit #art #region-us
| Bangumi Image Base of Scott Pilgrim Takes Off
=============================================
This is the image base of bangumi Scott Pilgrim Takes Off, we detected 31 characters, 1712 images in total. The full dataset is here.
Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual. If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| [] | [
"TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] | [
25
] | [
"passage: TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] |
76aec13782de97aae5dd542ef68f94d2a85c419c |
# Dataset Card for Dataset Name
<!-- Provide a quick summary of the dataset. -->
This dataset card aims to be a base template for new datasets. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/datasetcard_template.md?plain=1).
## Dataset Details
### Dataset Description
<!-- Provide a longer summary of what this dataset is. -->
- **Curated by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** Interinstitutional Center for Computational Linguistics (Núcleo Interinstitucional de Linguística Computacional -- NILC)
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
### Dataset Sources [optional]
<!-- Provide the basic links for the dataset. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the dataset is intended to be used. -->
### Direct Use
<!-- This section describes suitable use cases for the dataset. -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the dataset will not work well for. -->
[More Information Needed]
## Dataset Structure
<!-- This section provides a description of the dataset fields, and additional information about the dataset structure such as criteria used to create the splits, relationships between data points, etc. -->
[More Information Needed]
## Dataset Creation
### Curation Rationale
<!-- Motivation for the creation of this dataset. -->
[More Information Needed]
### Source Data
http://www.nilc.icmc.usp.br/nilc/tools/TeMario.zip
#### Data Collection and Processing
<!-- This section describes the data collection and processing process such as data selection criteria, filtering and normalization methods, tools and libraries used, etc. -->
[More Information Needed]
#### Who are the source data producers?
<!-- This section describes the people or systems who originally created the data. It should also include self-reported demographic or identity information for the source data creators if this information is available. -->
[More Information Needed]
### Annotations [optional]
<!-- If the dataset contains annotations which are not part of the initial data collection, use this section to describe them. -->
#### Annotation process
<!-- This section describes the annotation process such as annotation tools used in the process, the amount of data annotated, annotation guidelines provided to the annotators, interannotator statistics, annotation validation, etc. -->
[More Information Needed]
#### Who are the annotators?
<!-- This section describes the people or systems who created the annotations. -->
[More Information Needed]
#### Personal and Sensitive Information
<!-- State whether the dataset contains data that might be considered personal, sensitive, or private (e.g., data that reveals addresses, uniquely identifiable names or aliases, racial or ethnic origins, sexual orientations, religious beliefs, political opinions, financial or health data, etc.). If efforts were made to anonymize the data, describe the anonymization process. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.
## Citation [optional]
<!-- If there is a paper or blog post introducing the dataset, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the dataset or dataset card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Dataset Card Authors [optional]
[More Information Needed]
## Dataset Card Contact
[More Information Needed] | VictorNGomes/CorpusTeMario | [
"language:pt",
"region:us"
] | 2023-12-15T21:50:22+00:00 | {"language": ["pt"]} | 2023-12-16T03:45:00+00:00 | [] | [
"pt"
] | TAGS
#language-Portuguese #region-us
|
# Dataset Card for Dataset Name
This dataset card aims to be a base template for new datasets. It has been generated using this raw template.
## Dataset Details
### Dataset Description
- Curated by:
- Funded by [optional]:
- Shared by [optional]: Interinstitutional Center for Computational Linguistics (Núcleo Interinstitucional de Linguística Computacional -- NILC)
- Language(s) (NLP):
- License:
### Dataset Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Out-of-Scope Use
## Dataset Structure
## Dataset Creation
### Curation Rationale
### Source Data
URL
#### Data Collection and Processing
#### Who are the source data producers?
### Annotations [optional]
#### Annotation process
#### Who are the annotators?
#### Personal and Sensitive Information
## Bias, Risks, and Limitations
### Recommendations
Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Dataset Card Authors [optional]
## Dataset Card Contact
| [
"# Dataset Card for Dataset Name\n\n\n\nThis dataset card aims to be a base template for new datasets. It has been generated using this raw template.",
"## Dataset Details",
"### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: Interinstitutional Center for Computational Linguistics (Núcleo Interinstitucional de Linguística Computacional -- NILC)\n- Language(s) (NLP): \n- License:",
"### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Out-of-Scope Use",
"## Dataset Structure",
"## Dataset Creation",
"### Curation Rationale",
"### Source Data\n\nURL",
"#### Data Collection and Processing",
"#### Who are the source data producers?",
"### Annotations [optional]",
"#### Annotation process",
"#### Who are the annotators?",
"#### Personal and Sensitive Information",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Dataset Card Authors [optional]",
"## Dataset Card Contact"
] | [
"TAGS\n#language-Portuguese #region-us \n",
"# Dataset Card for Dataset Name\n\n\n\nThis dataset card aims to be a base template for new datasets. It has been generated using this raw template.",
"## Dataset Details",
"### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: Interinstitutional Center for Computational Linguistics (Núcleo Interinstitucional de Linguística Computacional -- NILC)\n- Language(s) (NLP): \n- License:",
"### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Out-of-Scope Use",
"## Dataset Structure",
"## Dataset Creation",
"### Curation Rationale",
"### Source Data\n\nURL",
"#### Data Collection and Processing",
"#### Who are the source data producers?",
"### Annotations [optional]",
"#### Annotation process",
"#### Who are the annotators?",
"#### Personal and Sensitive Information",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Dataset Card Authors [optional]",
"## Dataset Card Contact"
] | [
12,
34,
4,
71,
29,
3,
4,
9,
6,
5,
7,
5,
7,
10,
9,
5,
9,
8,
10,
46,
8,
7,
10,
5
] | [
"passage: TAGS\n#language-Portuguese #region-us \n# Dataset Card for Dataset Name\n\n\n\nThis dataset card aims to be a base template for new datasets. It has been generated using this raw template.## Dataset Details### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: Interinstitutional Center for Computational Linguistics (Núcleo Interinstitucional de Linguística Computacional -- NILC)\n- Language(s) (NLP): \n- License:### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Out-of-Scope Use## Dataset Structure## Dataset Creation### Curation Rationale### Source Data\n\nURL#### Data Collection and Processing#### Who are the source data producers?### Annotations [optional]#### Annotation process#### Who are the annotators?#### Personal and Sensitive Information## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Dataset Card Authors [optional]## Dataset Card Contact"
] |
0be6644bff37f52fb66b41df3b55f0494e580e22 | # Dataset Card for "wikipedia_questions"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | bjoernp/wikipedia_questions | [
"region:us"
] | 2023-12-15T22:27:05+00:00 | {"dataset_info": {"features": [{"name": "id", "dtype": "string"}, {"name": "url", "dtype": "string"}, {"name": "title", "dtype": "string"}, {"name": "text", "dtype": "string"}, {"name": "prompt", "dtype": "string"}, {"name": "questions", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 17671248, "num_examples": 558}], "download_size": 1140331, "dataset_size": 17671248}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]} | 2023-12-15T22:34:51+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "wikipedia_questions"
More Information needed | [
"# Dataset Card for \"wikipedia_questions\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"wikipedia_questions\"\n\nMore Information needed"
] | [
6,
14
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"wikipedia_questions\"\n\nMore Information needed"
] |
4c73ca516990548a21170e90b12e751d40c0e539 | # Dataset Card for "wiki_answer_generation"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | bjoernp/wiki_answer_generation | [
"region:us"
] | 2023-12-15T22:50:48+00:00 | {"dataset_info": {"features": [{"name": "id", "dtype": "string"}, {"name": "url", "dtype": "string"}, {"name": "title", "dtype": "string"}, {"name": "text", "dtype": "string"}, {"name": "prompt", "dtype": "string"}, {"name": "questions", "dtype": "string"}, {"name": "answer", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 18593431, "num_examples": 558}], "download_size": 3667759, "dataset_size": 18593431}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]} | 2023-12-15T22:50:50+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "wiki_answer_generation"
More Information needed | [
"# Dataset Card for \"wiki_answer_generation\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"wiki_answer_generation\"\n\nMore Information needed"
] | [
6,
17
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"wiki_answer_generation\"\n\nMore Information needed"
] |
3dbc601c89d79271886f5b2b34f0948b75ced2e9 |
# This is a rephrased version of my previous dataset `beratcmn/instruction-turkish-poems`. I used the same instructions but I rephrased them to be more clear and understandable also added more variety to the format. | beratcmn/rephrased-instruction-turkish-poems | [
"task_categories:text-generation",
"size_categories:1K<n<10K",
"language:tr",
"license:apache-2.0",
"poem",
"region:us"
] | 2023-12-15T23:23:22+00:00 | {"language": ["tr"], "license": "apache-2.0", "size_categories": ["1K<n<10K"], "task_categories": ["text-generation"], "tags": ["poem"]} | 2023-12-16T12:38:57+00:00 | [] | [
"tr"
] | TAGS
#task_categories-text-generation #size_categories-1K<n<10K #language-Turkish #license-apache-2.0 #poem #region-us
|
# This is a rephrased version of my previous dataset 'beratcmn/instruction-turkish-poems'. I used the same instructions but I rephrased them to be more clear and understandable also added more variety to the format. | [
"# This is a rephrased version of my previous dataset 'beratcmn/instruction-turkish-poems'. I used the same instructions but I rephrased them to be more clear and understandable also added more variety to the format."
] | [
"TAGS\n#task_categories-text-generation #size_categories-1K<n<10K #language-Turkish #license-apache-2.0 #poem #region-us \n",
"# This is a rephrased version of my previous dataset 'beratcmn/instruction-turkish-poems'. I used the same instructions but I rephrased them to be more clear and understandable also added more variety to the format."
] | [
46,
55
] | [
"passage: TAGS\n#task_categories-text-generation #size_categories-1K<n<10K #language-Turkish #license-apache-2.0 #poem #region-us \n# This is a rephrased version of my previous dataset 'beratcmn/instruction-turkish-poems'. I used the same instructions but I rephrased them to be more clear and understandable also added more variety to the format."
] |
4a1629271aef2fd48c14040fbc324d36293655e5 |
Dataset is unvalidated.
Please do not use until validation is complete.
French [x]
English [x]
Italian [ ]
German [ ]
Chinese [ ]
| Hazzzardous/synthetic-translations-6k-unvalidated | [
"license:mit",
"region:us"
] | 2023-12-15T23:28:09+00:00 | {"license": "mit"} | 2023-12-15T23:36:11+00:00 | [] | [] | TAGS
#license-mit #region-us
|
Dataset is unvalidated.
Please do not use until validation is complete.
French [x]
English [x]
Italian [ ]
German [ ]
Chinese [ ]
| [] | [
"TAGS\n#license-mit #region-us \n"
] | [
11
] | [
"passage: TAGS\n#license-mit #region-us \n"
] |
fe6e54d71b2cbeaa84730170c87029689c47ecfe | # Dataset Card for "wikipedia_tasks"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | bjoernp/wikipedia_tasks | [
"region:us"
] | 2023-12-15T23:44:10+00:00 | {"dataset_info": {"features": [{"name": "id", "dtype": "string"}, {"name": "url", "dtype": "string"}, {"name": "title", "dtype": "string"}, {"name": "text", "dtype": "string"}, {"name": "prompt", "dtype": "string"}, {"name": "questions", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 17814995, "num_examples": 561}], "download_size": 1155323, "dataset_size": 17814995}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]} | 2023-12-15T23:44:12+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "wikipedia_tasks"
More Information needed | [
"# Dataset Card for \"wikipedia_tasks\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"wikipedia_tasks\"\n\nMore Information needed"
] | [
6,
14
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"wikipedia_tasks\"\n\nMore Information needed"
] |
450f46117eac0617b14a6ff55f1e4d9756e552ea |
Data is from https://huggingface.co/datasets/roneneldan/TinyStories/:
> TinyStoriesV2-GPT4-train.txt - Is a new version of the dataset that is based on generations by GPT-4 only (the original dataset also has generations by GPT-3.5 which are of lesser quality). It contains all the examples in TinyStories.txt which were GPT-4 generated as a subset (but is significantly larger).
TinyStoriesV2's train split has ~2.7M stories as opposed to TinyStories' ~2.1M.
Data is preprocessed with
```
from unidecode import unidecode
import json
def clean_story(story):
# Convert from unicode to ascii to make tokenization better; don't split up quotation marks into multiple tokens e.g.
story = unidecode(story)
# lots of spaces at beginning of documents
story = story.strip()
# lots of trailing spaces at the end of lines
story_lines = story.split('\n')
story_lines = [line.strip() for line in story_lines]
story = '\n'.join(story_lines)
# Double newline is rare in train data while single newline is common.
while '\n\n' in story:
story = story.replace('\n\n', '\n')
# Double spaces are rare
while ' ' in story:
story = story.replace(' ', ' ')
return story
for split in ['train', 'valid']:
with open(f'TinyStoriesV2-GPT4-{split}.txt', 'r') as f:
text = f.read()
# first and last split snippets seem to be broken-up stories; I drop them
stories = text.split('<|endoftext|>')[1:-1]
# artifact of encoding error, pretty rare so just drop
stories = [story for story in stories if ('â' not in story) and ('€' not in story) and ('»' not in story) and ('«' not in story)]
stories = [clean_story(story) for story in stories]
with open(f'TinyStoriesV2-GPT4-{split}.jsonl', 'w') as f:
f.write('\n'.join([json.dumps({'text': story}) for story in stories]))
```
| noanabeshima/TinyStoriesV2 | [
"license:cdla-sharing-1.0",
"region:us"
] | 2023-12-15T23:48:34+00:00 | {"license": "cdla-sharing-1.0", "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "TinyStoriesV2-GPT4-train.jsonl"}, {"split": "validation", "path": "TinyStoriesV2-GPT4-valid.jsonl"}]}]} | 2023-12-16T00:52:54+00:00 | [] | [] | TAGS
#license-cdla-sharing-1.0 #region-us
|
Data is from URL
> URL - Is a new version of the dataset that is based on generations by GPT-4 only (the original dataset also has generations by GPT-3.5 which are of lesser quality). It contains all the examples in URL which were GPT-4 generated as a subset (but is significantly larger).
TinyStoriesV2's train split has ~2.7M stories as opposed to TinyStories' ~2.1M.
Data is preprocessed with
| [] | [
"TAGS\n#license-cdla-sharing-1.0 #region-us \n"
] | [
17
] | [
"passage: TAGS\n#license-cdla-sharing-1.0 #region-us \n"
] |
eae47dc9bc65356777968f8433008e762ab03535 | # Dataset Card for "wiki_task_answer_generation"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | bjoernp/wiki_task_answer_generation | [
"region:us"
] | 2023-12-16T00:02:41+00:00 | {"dataset_info": {"features": [{"name": "id", "dtype": "string"}, {"name": "url", "dtype": "string"}, {"name": "title", "dtype": "string"}, {"name": "text", "dtype": "string"}, {"name": "prompt", "dtype": "string"}, {"name": "questions", "dtype": "string"}, {"name": "answer", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 18828371, "num_examples": 561}], "download_size": 3774681, "dataset_size": 18828371}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]} | 2023-12-16T00:02:42+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "wiki_task_answer_generation"
More Information needed | [
"# Dataset Card for \"wiki_task_answer_generation\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"wiki_task_answer_generation\"\n\nMore Information needed"
] | [
6,
20
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"wiki_task_answer_generation\"\n\nMore Information needed"
] |
bfc8ad119f18e1819def078cb447d8cab91c30ee |
# Arabic Billion Words Dataset 🌕
The Abu El-Khair Arabic News Corpus (arabic-billion-words) is a comprehensive collection of Arabic text, encompassing over five million newspaper articles. The corpus is rich in linguistic diversity, containing more than a billion and a half words, with approximately three million unique words. The text is encoded in two formats: UTF-8 and Windows CP-1256, and marked up using two markup languages: SGML and XML.
## Data Example
An example from the "Almasryalyoum" configuration subset:
```python
{
"url": "http://today.almasryalyoum.com/printerfriendly.aspx?ArticleID=61300",
"head_line": "رئيس وزراء المجر: عنصرية جماهير أوجبيست جلبت العار للبلاد",
"date": "19/5/2007",
"text": """قال متحدث باسم الحكومة المجرية: إن رئيس الوزراء فيرنك جيوركساني رحب بقرار اتحاد كرة القدم المجري بخصم ثلاث نقاط من نادي أوجبيست بسبب السلوك العنصري الذي صدر من جماهيره.
...
يذكر أن المجر بها مجموعة من مشجعي كرة القدم المشاغبين «الهوليجانز»، وشارك الكثير منهم في أعمال شغب معادية للحكومة في العام الماضي.""",
}
```
## Data Fields
The dataset comprises the following fields:
- "url": string, original URL of the article.
- "head_line": string, headline of the article.
- "date": string, date of the article.
- "text": string, textual content of the article.
## Data Splits
The dataset is divided into a single "training" split, with the following distribution of examples across different configuration subsets:
| Configuration Subset | Number of Examples |
|:---------------------|-------------------:|
| Alittihad | 349,342 |
| Almasryalyoum | 291,723 |
| Almustaqbal | 446,873 |
| Alqabas | 817,274 |
| Echoroukonline | 139,732 |
| Ryiadh | 858,188 |
| Sabanews | 92,149 |
| SaudiYoum | 888,068 |
| Techreen | 314,597 |
| Youm7 | 1,172,136 |
## Dataset Usage
This dataset is valuable for natural language processing (NLP) tasks, including but not limited to sentiment analysis, topic modeling, and language modeling in the context of Arabic news articles. Researchers and practitioners in the field of NLP can benefit from the diverse linguistic content and the substantial size of the corpus. | MohamedRashad/arabic-billion-words | [
"task_categories:text-generation",
"size_categories:1M<n<10M",
"language:ar",
"region:us"
] | 2023-12-16T01:01:47+00:00 | {"language": ["ar"], "size_categories": ["1M<n<10M"], "task_categories": ["text-generation"], "pretty_name": "Arabic Billion Words", "dataset_info": {"features": [{"name": "url", "dtype": "string"}, {"name": "head_line", "dtype": "string"}, {"name": "date", "dtype": "string"}, {"name": "text", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 17017097763, "num_examples": 5222964}], "download_size": 8050780387, "dataset_size": 17017097763}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]} | 2023-12-16T02:47:39+00:00 | [] | [
"ar"
] | TAGS
#task_categories-text-generation #size_categories-1M<n<10M #language-Arabic #region-us
| Arabic Billion Words Dataset
============================
The Abu El-Khair Arabic News Corpus (arabic-billion-words) is a comprehensive collection of Arabic text, encompassing over five million newspaper articles. The corpus is rich in linguistic diversity, containing more than a billion and a half words, with approximately three million unique words. The text is encoded in two formats: UTF-8 and Windows CP-1256, and marked up using two markup languages: SGML and XML.
Data Example
------------
An example from the "Almasryalyoum" configuration subset:
Data Fields
-----------
The dataset comprises the following fields:
* "url": string, original URL of the article.
* "head\_line": string, headline of the article.
* "date": string, date of the article.
* "text": string, textual content of the article.
Data Splits
-----------
The dataset is divided into a single "training" split, with the following distribution of examples across different configuration subsets:
Dataset Usage
-------------
This dataset is valuable for natural language processing (NLP) tasks, including but not limited to sentiment analysis, topic modeling, and language modeling in the context of Arabic news articles. Researchers and practitioners in the field of NLP can benefit from the diverse linguistic content and the substantial size of the corpus.
| [] | [
"TAGS\n#task_categories-text-generation #size_categories-1M<n<10M #language-Arabic #region-us \n"
] | [
34
] | [
"passage: TAGS\n#task_categories-text-generation #size_categories-1M<n<10M #language-Arabic #region-us \n"
] |
a593d785584278d88e4287b5e314b1769bca02ac |
# Bangumi Image Base of Sora No Otoshimono
This is the image base of bangumi Sora no Otoshimono, we detected 34 characters, 5020 images in total. The full dataset is [here](all.zip).
**Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual.** If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| # | Images | Download | Preview 1 | Preview 2 | Preview 3 | Preview 4 | Preview 5 | Preview 6 | Preview 7 | Preview 8 |
|:------|---------:|:---------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|
| 0 | 813 | [Download](0/dataset.zip) |  |  |  |  |  |  |  |  |
| 1 | 264 | [Download](1/dataset.zip) |  |  |  |  |  |  |  |  |
| 2 | 103 | [Download](2/dataset.zip) |  |  |  |  |  |  |  |  |
| 3 | 36 | [Download](3/dataset.zip) |  |  |  |  |  |  |  |  |
| 4 | 46 | [Download](4/dataset.zip) |  |  |  |  |  |  |  |  |
| 5 | 31 | [Download](5/dataset.zip) |  |  |  |  |  |  |  |  |
| 6 | 324 | [Download](6/dataset.zip) |  |  |  |  |  |  |  |  |
| 7 | 14 | [Download](7/dataset.zip) |  |  |  |  |  |  |  |  |
| 8 | 99 | [Download](8/dataset.zip) |  |  |  |  |  |  |  |  |
| 9 | 30 | [Download](9/dataset.zip) |  |  |  |  |  |  |  |  |
| 10 | 25 | [Download](10/dataset.zip) |  |  |  |  |  |  |  |  |
| 11 | 667 | [Download](11/dataset.zip) |  |  |  |  |  |  |  |  |
| 12 | 48 | [Download](12/dataset.zip) |  |  |  |  |  |  |  |  |
| 13 | 306 | [Download](13/dataset.zip) |  |  |  |  |  |  |  |  |
| 14 | 48 | [Download](14/dataset.zip) |  |  |  |  |  |  |  |  |
| 15 | 395 | [Download](15/dataset.zip) |  |  |  |  |  |  |  |  |
| 16 | 58 | [Download](16/dataset.zip) |  |  |  |  |  |  |  |  |
| 17 | 624 | [Download](17/dataset.zip) |  |  |  |  |  |  |  |  |
| 18 | 65 | [Download](18/dataset.zip) |  |  |  |  |  |  |  |  |
| 19 | 126 | [Download](19/dataset.zip) |  |  |  |  |  |  |  |  |
| 20 | 18 | [Download](20/dataset.zip) |  |  |  |  |  |  |  |  |
| 21 | 15 | [Download](21/dataset.zip) |  |  |  |  |  |  |  |  |
| 22 | 12 | [Download](22/dataset.zip) |  |  |  |  |  |  |  |  |
| 23 | 16 | [Download](23/dataset.zip) |  |  |  |  |  |  |  |  |
| 24 | 10 | [Download](24/dataset.zip) |  |  |  |  |  |  |  |  |
| 25 | 9 | [Download](25/dataset.zip) |  |  |  |  |  |  |  |  |
| 26 | 253 | [Download](26/dataset.zip) |  |  |  |  |  |  |  |  |
| 27 | 82 | [Download](27/dataset.zip) |  |  |  |  |  |  |  |  |
| 28 | 35 | [Download](28/dataset.zip) |  |  |  |  |  |  |  |  |
| 29 | 15 | [Download](29/dataset.zip) |  |  |  |  |  |  |  |  |
| 30 | 19 | [Download](30/dataset.zip) |  |  |  |  |  |  |  |  |
| 31 | 11 | [Download](31/dataset.zip) |  |  |  |  |  |  |  |  |
| 32 | 5 | [Download](32/dataset.zip) |  |  |  |  |  | N/A | N/A | N/A |
| noise | 398 | [Download](-1/dataset.zip) |  |  |  |  |  |  |  |  |
| BangumiBase/soranootoshimono | [
"size_categories:1K<n<10K",
"license:mit",
"art",
"region:us"
] | 2023-12-16T01:39:49+00:00 | {"license": "mit", "size_categories": ["1K<n<10K"], "tags": ["art"]} | 2023-12-16T05:14:03+00:00 | [] | [] | TAGS
#size_categories-1K<n<10K #license-mit #art #region-us
| Bangumi Image Base of Sora No Otoshimono
========================================
This is the image base of bangumi Sora no Otoshimono, we detected 34 characters, 5020 images in total. The full dataset is here.
Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual. If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| [] | [
"TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] | [
25
] | [
"passage: TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] |
f1cbe26ae7aa6db5e9ac199e037893f592c9748f |
# ja-stackoverflow
日本語版 Stack Overflow の [スタック・オーバーフロー](https://ja.stackoverflow.com/) の[データダンプ](https://archive.org/download/stackexchange) をもとにデータを加工し、質問文と回答文のペアになるように調整した QA データセット。
## データ構造
投稿本文は `html2text` を使ってマークダウン化されています。その際、
- コードブロックは \`\`\` で囲まれるように変更されています。
- 画像 URL に base64 エンコードされた画像が含まれる場合、 `[unk]` に置き換えています。
### `default` サブセット
- `id`: 質問投稿の ID
- `question`: 質問投稿
- `answers`: 質問に対する回答投稿のリスト
- `accepted_answer_id`: 質問者に選ばれた回答のID。`null` の可能性がある
- `popular_answer_id`: もっともスコアが高かった回答のID。`null` の可能性がある
### `simple` サブセット
`default` サブセットから、 `question` と `answers` の辞書を展開しシンプルにしたもの。
- `id`: 質問投稿の ID
- `accepted_answer_id`: 質問者に選ばれた回答のID。`null` の可能性がある
- `popular_answer_id`: もっともスコアが高かった回答のID。`null` の可能性がある
- `title`: 質問のタイトル
- `question_body`: 質問本文
- `question_score`: 質問のスコア
- `tags`: 質問に関連付けられたタグ
- `accepted_answer_body`: 質問者に選ばれた回答の本文。`null` の可能性がある
- `accepted_answer_score`: 質問者に選ばれた回答のスコア。`null` の可能性がある
- `popular_answer_body`: もっともスコアが高かった回答の本文。`null` の可能性がある
- `popular_answer_score`: もっともスコアが高かった回答のスコア。`null` の可能性がある
## 使い方
datasets ライブラリを用いて簡単に利用できます。
```py
from datasets import load_dataset
dataset = load_dataset("p1atdev/ja-stackoverflow", name="simple" split="train")
print(dataset)
#Dataset({
# features: ['id', 'accepted_answer_id', 'popular_answer_id', 'title', 'question_body', 'question_score', 'accepted_answer_body', 'accepted_answer_score', 'popular_answer_body', 'popular_answer_score', 'tags'],
# num_rows: 30551
#})
```
## ライセンス
StackOverflow に基づき、[CC BY-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/deed.ja)
| p1atdev/ja-stackoverflow | [
"task_categories:text-generation",
"task_categories:question-answering",
"size_categories:10K<n<100K",
"language:ja",
"license:cc-by-sa-4.0",
"stackoverflow",
"programming",
"region:us"
] | 2023-12-16T02:41:12+00:00 | {"language": ["ja"], "license": "cc-by-sa-4.0", "size_categories": ["10K<n<100K"], "task_categories": ["text-generation", "question-answering"], "pretty_name": "Japanese StackOverflow", "dataset_info": [{"config_name": "default", "features": [{"name": "question", "struct": [{"name": "accepted_answer_id", "dtype": "string"}, {"name": "answer_count", "dtype": "int64"}, {"name": "body", "dtype": "string"}, {"name": "comment_count", "dtype": "int64"}, {"name": "content_license", "dtype": "string"}, {"name": "creation_date", "dtype": "string"}, {"name": "favorite_count", "dtype": "int64"}, {"name": "id", "dtype": "string"}, {"name": "last_activity_date", "dtype": "string"}, {"name": "last_edit_date", "dtype": "string"}, {"name": "last_editor_user_id", "dtype": "string"}, {"name": "owner_user_id", "dtype": "string"}, {"name": "post_type", "dtype": "string"}, {"name": "score", "dtype": "int64"}, {"name": "tags", "sequence": "string"}, {"name": "title", "dtype": "string"}, {"name": "view_count", "dtype": "int64"}]}, {"name": "answers", "list": [{"name": "body", "dtype": "string"}, {"name": "comment_count", "dtype": "int64"}, {"name": "content_license", "dtype": "string"}, {"name": "creation_date", "dtype": "string"}, {"name": "id", "dtype": "string"}, {"name": "last_activity_date", "dtype": "string"}, {"name": "last_edit_date", "dtype": "string"}, {"name": "last_editor_user_id", "dtype": "string"}, {"name": "owner_user_id", "dtype": "string"}, {"name": "parent_id", "dtype": "string"}, {"name": "post_type", "dtype": "string"}, {"name": "score", "dtype": "int64"}]}, {"name": "id", "dtype": "string"}, {"name": "accepted_answer_id", "dtype": "string"}, {"name": "popular_answer_id", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 112596554, "num_examples": 30551}], "download_size": 54805530, "dataset_size": 112596554}, {"config_name": "simple", "features": [{"name": "id", "dtype": "string"}, {"name": "accepted_answer_id", "dtype": "string"}, {"name": "popular_answer_id", "dtype": "string"}, {"name": "title", "dtype": "string"}, {"name": "question_body", "dtype": "string"}, {"name": "question_score", "dtype": "int64"}, {"name": "accepted_answer_body", "dtype": "string"}, {"name": "accepted_answer_score", "dtype": "int64"}, {"name": "popular_answer_body", "dtype": "string"}, {"name": "popular_answer_score", "dtype": "int64"}, {"name": "tags", "sequence": "string"}], "splits": [{"name": "train", "num_bytes": 113051344, "num_examples": 30551}], "download_size": 56632072, "dataset_size": 113051344}], "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}, {"config_name": "simple", "data_files": [{"split": "train", "path": "simple/train-*"}]}], "tags": ["stackoverflow", "programming"]} | 2023-12-21T05:30:24+00:00 | [] | [
"ja"
] | TAGS
#task_categories-text-generation #task_categories-question-answering #size_categories-10K<n<100K #language-Japanese #license-cc-by-sa-4.0 #stackoverflow #programming #region-us
|
# ja-stackoverflow
日本語版 Stack Overflow の スタック・オーバーフロー のデータダンプ をもとにデータを加工し、質問文と回答文のペアになるように調整した QA データセット。
## データ構造
投稿本文は 'html2text' を使ってマークダウン化されています。その際、
- コードブロックは \'\'\' で囲まれるように変更されています。
- 画像 URL に base64 エンコードされた画像が含まれる場合、 '[unk]' に置き換えています。
### 'default' サブセット
- 'id': 質問投稿の ID
- 'question': 質問投稿
- 'answers': 質問に対する回答投稿のリスト
- 'accepted_answer_id': 質問者に選ばれた回答のID。'null' の可能性がある
- 'popular_answer_id': もっともスコアが高かった回答のID。'null' の可能性がある
### 'simple' サブセット
'default' サブセットから、 'question' と 'answers' の辞書を展開しシンプルにしたもの。
- 'id': 質問投稿の ID
- 'accepted_answer_id': 質問者に選ばれた回答のID。'null' の可能性がある
- 'popular_answer_id': もっともスコアが高かった回答のID。'null' の可能性がある
- 'title': 質問のタイトル
- 'question_body': 質問本文
- 'question_score': 質問のスコア
- 'tags': 質問に関連付けられたタグ
- 'accepted_answer_body': 質問者に選ばれた回答の本文。'null' の可能性がある
- 'accepted_answer_score': 質問者に選ばれた回答のスコア。'null' の可能性がある
- 'popular_answer_body': もっともスコアが高かった回答の本文。'null' の可能性がある
- 'popular_answer_score': もっともスコアが高かった回答のスコア。'null' の可能性がある
## 使い方
datasets ライブラリを用いて簡単に利用できます。
## ライセンス
StackOverflow に基づき、CC BY-SA 4.0
| [
"# ja-stackoverflow\n\n日本語版 Stack Overflow の スタック・オーバーフロー のデータダンプ をもとにデータを加工し、質問文と回答文のペアになるように調整した QA データセット。",
"## データ構造\n\n投稿本文は 'html2text' を使ってマークダウン化されています。その際、\n\n- コードブロックは \\'\\'\\' で囲まれるように変更されています。\n- 画像 URL に base64 エンコードされた画像が含まれる場合、 '[unk]' に置き換えています。",
"### 'default' サブセット\n\n- 'id': 質問投稿の ID\n- 'question': 質問投稿\n- 'answers': 質問に対する回答投稿のリスト\n- 'accepted_answer_id': 質問者に選ばれた回答のID。'null' の可能性がある\n- 'popular_answer_id': もっともスコアが高かった回答のID。'null' の可能性がある",
"### 'simple' サブセット \n\n'default' サブセットから、 'question' と 'answers' の辞書を展開しシンプルにしたもの。\n\n- 'id': 質問投稿の ID\n- 'accepted_answer_id': 質問者に選ばれた回答のID。'null' の可能性がある\n- 'popular_answer_id': もっともスコアが高かった回答のID。'null' の可能性がある\n- 'title': 質問のタイトル\n- 'question_body': 質問本文\n- 'question_score': 質問のスコア\n- 'tags': 質問に関連付けられたタグ\n- 'accepted_answer_body': 質問者に選ばれた回答の本文。'null' の可能性がある\n- 'accepted_answer_score': 質問者に選ばれた回答のスコア。'null' の可能性がある\n- 'popular_answer_body': もっともスコアが高かった回答の本文。'null' の可能性がある\n- 'popular_answer_score': もっともスコアが高かった回答のスコア。'null' の可能性がある",
"## 使い方\n\ndatasets ライブラリを用いて簡単に利用できます。",
"## ライセンス\n\nStackOverflow に基づき、CC BY-SA 4.0"
] | [
"TAGS\n#task_categories-text-generation #task_categories-question-answering #size_categories-10K<n<100K #language-Japanese #license-cc-by-sa-4.0 #stackoverflow #programming #region-us \n",
"# ja-stackoverflow\n\n日本語版 Stack Overflow の スタック・オーバーフロー のデータダンプ をもとにデータを加工し、質問文と回答文のペアになるように調整した QA データセット。",
"## データ構造\n\n投稿本文は 'html2text' を使ってマークダウン化されています。その際、\n\n- コードブロックは \\'\\'\\' で囲まれるように変更されています。\n- 画像 URL に base64 エンコードされた画像が含まれる場合、 '[unk]' に置き換えています。",
"### 'default' サブセット\n\n- 'id': 質問投稿の ID\n- 'question': 質問投稿\n- 'answers': 質問に対する回答投稿のリスト\n- 'accepted_answer_id': 質問者に選ばれた回答のID。'null' の可能性がある\n- 'popular_answer_id': もっともスコアが高かった回答のID。'null' の可能性がある",
"### 'simple' サブセット \n\n'default' サブセットから、 'question' と 'answers' の辞書を展開しシンプルにしたもの。\n\n- 'id': 質問投稿の ID\n- 'accepted_answer_id': 質問者に選ばれた回答のID。'null' の可能性がある\n- 'popular_answer_id': もっともスコアが高かった回答のID。'null' の可能性がある\n- 'title': 質問のタイトル\n- 'question_body': 質問本文\n- 'question_score': 質問のスコア\n- 'tags': 質問に関連付けられたタグ\n- 'accepted_answer_body': 質問者に選ばれた回答の本文。'null' の可能性がある\n- 'accepted_answer_score': 質問者に選ばれた回答のスコア。'null' の可能性がある\n- 'popular_answer_body': もっともスコアが高かった回答の本文。'null' の可能性がある\n- 'popular_answer_score': もっともスコアが高かった回答のスコア。'null' の可能性がある",
"## 使い方\n\ndatasets ライブラリを用いて簡単に利用できます。",
"## ライセンス\n\nStackOverflow に基づき、CC BY-SA 4.0"
] | [
66,
52,
71,
97,
270,
17,
17
] | [
"passage: TAGS\n#task_categories-text-generation #task_categories-question-answering #size_categories-10K<n<100K #language-Japanese #license-cc-by-sa-4.0 #stackoverflow #programming #region-us \n# ja-stackoverflow\n\n日本語版 Stack Overflow の スタック・オーバーフロー のデータダンプ をもとにデータを加工し、質問文と回答文のペアになるように調整した QA データセット。## データ構造\n\n投稿本文は 'html2text' を使ってマークダウン化されています。その際、\n\n- コードブロックは \\'\\'\\' で囲まれるように変更されています。\n- 画像 URL に base64 エンコードされた画像が含まれる場合、 '[unk]' に置き換えています。### 'default' サブセット\n\n- 'id': 質問投稿の ID\n- 'question': 質問投稿\n- 'answers': 質問に対する回答投稿のリスト\n- 'accepted_answer_id': 質問者に選ばれた回答のID。'null' の可能性がある\n- 'popular_answer_id': もっともスコアが高かった回答のID。'null' の可能性がある"
] |
8cdd1a7919135d5d020e51ba47791d508b92c161 |
# japanese-stackexchange
英語による日本語に関する質問ができる [Japanese Stack Exchange](https://japanese.stackexchange.com/) の[データダンプ](https://archive.org/download/stackexchange) をもとにデータを加工し、質問文と回答文のペアになるように調整した QA データセット。
日本語翻訳された StackExchange ではないです。
## データ構造
投稿本文は `html2text` を使ってマークダウン化されています。その際、
- コードブロックは \`\`\` で囲まれるように変更されています。
- 画像 URL に base64 エンコードされた画像が含まれる場合、 `[unk]` に置き換えています。
### `default` サブセット
- `id`: 質問投稿の ID
- `question`: 質問投稿
- `answers`: 質問に対する回答投稿のリスト
- `accepted_answer_id`: 質問者に選ばれた回答のID。`null` の可能性がある
- `popular_answer_id`: もっともスコアが高かった回答のID。`null` の可能性がある
### `simple` サブセット
`default` サブセットから、 `question` と `answers` の辞書を展開しシンプルにしたもの。
- `id`: 質問投稿の ID
- `accepted_answer_id`: 質問者に選ばれた回答のID。`null` の可能性がある
- `popular_answer_id`: もっともスコアが高かった回答のID。`null` の可能性がある
- `title`: 質問のタイトル
- `question_body`: 質問本文
- `question_score`: 質問のスコア
- `tags`: 質問に関連付けられたタグ
- `accepted_answer_body`: 質問者に選ばれた回答の本文。`null` の可能性がある
- `accepted_answer_score`: 質問者に選ばれた回答のスコア。`null` の可能性がある
- `popular_answer_body`: もっともスコアが高かった回答の本文。`null` の可能性がある
- `popular_answer_score`: もっともスコアが高かった回答のスコア。`null` の可能性がある
## 使い方
datasets ライブラリを用いて簡単に利用できます。
```py
from datasets import load_dataset
dataset = load_dataset("p1atdev/japanese-stackexchange", name="simple" split="train")
print(dataset)
#Dataset({
# features: ['id', 'accepted_answer_id', 'popular_answer_id', 'title', 'question_body', 'question_score', 'accepted_answer_body', 'accepted_answer_score', 'popular_answer_body', 'popular_answer_score', 'tags'],
# num_rows: 28428
#})
```
## ライセンス
StackExchange に基づき、[CC BY-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/deed.ja)
| p1atdev/japanese-stackexchange | [
"task_categories:text-generation",
"task_categories:question-answering",
"size_categories:10K<n<100K",
"language:en",
"language:ja",
"license:cc-by-sa-4.0",
"stackexchange",
"region:us"
] | 2023-12-16T03:14:00+00:00 | {"language": ["en", "ja"], "license": "cc-by-sa-4.0", "size_categories": ["10K<n<100K"], "task_categories": ["text-generation", "question-answering"], "pretty_name": "Japanese StackExchange", "dataset_info": [{"config_name": "default", "features": [{"name": "question", "struct": [{"name": "accepted_answer_id", "dtype": "string"}, {"name": "answer_count", "dtype": "int64"}, {"name": "body", "dtype": "string"}, {"name": "comment_count", "dtype": "int64"}, {"name": "content_license", "dtype": "string"}, {"name": "creation_date", "dtype": "string"}, {"name": "favorite_count", "dtype": "int64"}, {"name": "id", "dtype": "string"}, {"name": "last_activity_date", "dtype": "string"}, {"name": "last_edit_date", "dtype": "string"}, {"name": "last_editor_user_id", "dtype": "string"}, {"name": "owner_user_id", "dtype": "string"}, {"name": "post_type", "dtype": "string"}, {"name": "score", "dtype": "int64"}, {"name": "tags", "sequence": "string"}, {"name": "title", "dtype": "string"}, {"name": "view_count", "dtype": "int64"}]}, {"name": "answers", "list": [{"name": "body", "dtype": "string"}, {"name": "comment_count", "dtype": "int64"}, {"name": "content_license", "dtype": "string"}, {"name": "creation_date", "dtype": "string"}, {"name": "id", "dtype": "string"}, {"name": "last_activity_date", "dtype": "string"}, {"name": "last_edit_date", "dtype": "string"}, {"name": "last_editor_user_id", "dtype": "string"}, {"name": "owner_user_id", "dtype": "string"}, {"name": "parent_id", "dtype": "string"}, {"name": "post_type", "dtype": "string"}, {"name": "score", "dtype": "int64"}]}, {"name": "id", "dtype": "string"}, {"name": "accepted_answer_id", "dtype": "string"}, {"name": "popular_answer_id", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 67721507, "num_examples": 28428}], "download_size": 38951308, "dataset_size": 67721507}, {"config_name": "simple", "features": [{"name": "id", "dtype": "string"}, {"name": "accepted_answer_id", "dtype": "string"}, {"name": "popular_answer_id", "dtype": "string"}, {"name": "title", "dtype": "string"}, {"name": "question_body", "dtype": "string"}, {"name": "question_score", "dtype": "int64"}, {"name": "accepted_answer_body", "dtype": "string"}, {"name": "accepted_answer_score", "dtype": "int64"}, {"name": "popular_answer_body", "dtype": "string"}, {"name": "popular_answer_score", "dtype": "int64"}, {"name": "tags", "sequence": "string"}], "splits": [{"name": "train", "num_bytes": 66135683, "num_examples": 28428}], "download_size": 40717946, "dataset_size": 66135683}], "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}, {"config_name": "simple", "data_files": [{"split": "train", "path": "simple/train-*"}]}], "tags": ["stackexchange"]} | 2023-12-21T05:30:37+00:00 | [] | [
"en",
"ja"
] | TAGS
#task_categories-text-generation #task_categories-question-answering #size_categories-10K<n<100K #language-English #language-Japanese #license-cc-by-sa-4.0 #stackexchange #region-us
|
# japanese-stackexchange
英語による日本語に関する質問ができる Japanese Stack Exchange のデータダンプ をもとにデータを加工し、質問文と回答文のペアになるように調整した QA データセット。
日本語翻訳された StackExchange ではないです。
## データ構造
投稿本文は 'html2text' を使ってマークダウン化されています。その際、
- コードブロックは \'\'\' で囲まれるように変更されています。
- 画像 URL に base64 エンコードされた画像が含まれる場合、 '[unk]' に置き換えています。
### 'default' サブセット
- 'id': 質問投稿の ID
- 'question': 質問投稿
- 'answers': 質問に対する回答投稿のリスト
- 'accepted_answer_id': 質問者に選ばれた回答のID。'null' の可能性がある
- 'popular_answer_id': もっともスコアが高かった回答のID。'null' の可能性がある
### 'simple' サブセット
'default' サブセットから、 'question' と 'answers' の辞書を展開しシンプルにしたもの。
- 'id': 質問投稿の ID
- 'accepted_answer_id': 質問者に選ばれた回答のID。'null' の可能性がある
- 'popular_answer_id': もっともスコアが高かった回答のID。'null' の可能性がある
- 'title': 質問のタイトル
- 'question_body': 質問本文
- 'question_score': 質問のスコア
- 'tags': 質問に関連付けられたタグ
- 'accepted_answer_body': 質問者に選ばれた回答の本文。'null' の可能性がある
- 'accepted_answer_score': 質問者に選ばれた回答のスコア。'null' の可能性がある
- 'popular_answer_body': もっともスコアが高かった回答の本文。'null' の可能性がある
- 'popular_answer_score': もっともスコアが高かった回答のスコア。'null' の可能性がある
## 使い方
datasets ライブラリを用いて簡単に利用できます。
## ライセンス
StackExchange に基づき、CC BY-SA 4.0
| [
"# japanese-stackexchange\n\n英語による日本語に関する質問ができる Japanese Stack Exchange のデータダンプ をもとにデータを加工し、質問文と回答文のペアになるように調整した QA データセット。\n\n日本語翻訳された StackExchange ではないです。",
"## データ構造\n\n投稿本文は 'html2text' を使ってマークダウン化されています。その際、\n\n- コードブロックは \\'\\'\\' で囲まれるように変更されています。\n- 画像 URL に base64 エンコードされた画像が含まれる場合、 '[unk]' に置き換えています。",
"### 'default' サブセット\n\n- 'id': 質問投稿の ID\n- 'question': 質問投稿\n- 'answers': 質問に対する回答投稿のリスト\n- 'accepted_answer_id': 質問者に選ばれた回答のID。'null' の可能性がある\n- 'popular_answer_id': もっともスコアが高かった回答のID。'null' の可能性がある",
"### 'simple' サブセット \n\n'default' サブセットから、 'question' と 'answers' の辞書を展開しシンプルにしたもの。\n\n- 'id': 質問投稿の ID\n- 'accepted_answer_id': 質問者に選ばれた回答のID。'null' の可能性がある\n- 'popular_answer_id': もっともスコアが高かった回答のID。'null' の可能性がある\n- 'title': 質問のタイトル\n- 'question_body': 質問本文\n- 'question_score': 質問のスコア\n- 'tags': 質問に関連付けられたタグ\n- 'accepted_answer_body': 質問者に選ばれた回答の本文。'null' の可能性がある\n- 'accepted_answer_score': 質問者に選ばれた回答のスコア。'null' の可能性がある\n- 'popular_answer_body': もっともスコアが高かった回答の本文。'null' の可能性がある\n- 'popular_answer_score': もっともスコアが高かった回答のスコア。'null' の可能性がある",
"## 使い方\n\ndatasets ライブラリを用いて簡単に利用できます。",
"## ライセンス\n\nStackExchange に基づき、CC BY-SA 4.0"
] | [
"TAGS\n#task_categories-text-generation #task_categories-question-answering #size_categories-10K<n<100K #language-English #language-Japanese #license-cc-by-sa-4.0 #stackexchange #region-us \n",
"# japanese-stackexchange\n\n英語による日本語に関する質問ができる Japanese Stack Exchange のデータダンプ をもとにデータを加工し、質問文と回答文のペアになるように調整した QA データセット。\n\n日本語翻訳された StackExchange ではないです。",
"## データ構造\n\n投稿本文は 'html2text' を使ってマークダウン化されています。その際、\n\n- コードブロックは \\'\\'\\' で囲まれるように変更されています。\n- 画像 URL に base64 エンコードされた画像が含まれる場合、 '[unk]' に置き換えています。",
"### 'default' サブセット\n\n- 'id': 質問投稿の ID\n- 'question': 質問投稿\n- 'answers': 質問に対する回答投稿のリスト\n- 'accepted_answer_id': 質問者に選ばれた回答のID。'null' の可能性がある\n- 'popular_answer_id': もっともスコアが高かった回答のID。'null' の可能性がある",
"### 'simple' サブセット \n\n'default' サブセットから、 'question' と 'answers' の辞書を展開しシンプルにしたもの。\n\n- 'id': 質問投稿の ID\n- 'accepted_answer_id': 質問者に選ばれた回答のID。'null' の可能性がある\n- 'popular_answer_id': もっともスコアが高かった回答のID。'null' の可能性がある\n- 'title': 質問のタイトル\n- 'question_body': 質問本文\n- 'question_score': 質問のスコア\n- 'tags': 質問に関連付けられたタグ\n- 'accepted_answer_body': 質問者に選ばれた回答の本文。'null' の可能性がある\n- 'accepted_answer_score': 質問者に選ばれた回答のスコア。'null' の可能性がある\n- 'popular_answer_body': もっともスコアが高かった回答の本文。'null' の可能性がある\n- 'popular_answer_score': もっともスコアが高かった回答のスコア。'null' の可能性がある",
"## 使い方\n\ndatasets ライブラリを用いて簡単に利用できます。",
"## ライセンス\n\nStackExchange に基づき、CC BY-SA 4.0"
] | [
67,
59,
71,
97,
270,
17,
17
] | [
"passage: TAGS\n#task_categories-text-generation #task_categories-question-answering #size_categories-10K<n<100K #language-English #language-Japanese #license-cc-by-sa-4.0 #stackexchange #region-us \n# japanese-stackexchange\n\n英語による日本語に関する質問ができる Japanese Stack Exchange のデータダンプ をもとにデータを加工し、質問文と回答文のペアになるように調整した QA データセット。\n\n日本語翻訳された StackExchange ではないです。## データ構造\n\n投稿本文は 'html2text' を使ってマークダウン化されています。その際、\n\n- コードブロックは \\'\\'\\' で囲まれるように変更されています。\n- 画像 URL に base64 エンコードされた画像が含まれる場合、 '[unk]' に置き換えています。### 'default' サブセット\n\n- 'id': 質問投稿の ID\n- 'question': 質問投稿\n- 'answers': 質問に対する回答投稿のリスト\n- 'accepted_answer_id': 質問者に選ばれた回答のID。'null' の可能性がある\n- 'popular_answer_id': もっともスコアが高かった回答のID。'null' の可能性がある"
] |
25d4069abd0e3b4c2e47bdf96911aea251e88f43 |
---
动漫小说预训练数据集包含将近153本小说
## 关于我自己：
我是小雨的开发者，小雨是一个情感ai，人格ai，如果对小雨感兴趣的话欢迎支持一下，她目前在bilibili直播，目前我仍在不断的改进，未来，“小雨”的目标是成为一个
具有真正人类情感的多模态通用人工智能。
url：https://live.bilibili.com/27357528?broadcast_type=0&is_room_feed=1&spm_id_from=333.999.live_users_card.0.click&live_from=86001
## About Myself:
I am the developer of Xiaoyu, an AI specializing in emotion and personality. If you're interested in Xiaoyu, feel free to show your support! She is currently live on Bilibili, and I am continuously working on improvements.In the future, '小雨' aims to become a multimodal general artificial intelligence with genuine human emotions.
URL: https://live.bilibili.com/27357528?broadcast_type=0&is_room_feed=1&spm_id_from=333.999.live_users_card.0.click&live_from=86001
## list:
1.86-不存在的战区-(86- Eighty Six -)
2.Angel Beats! -Track Zero-
3.Another
4.BEATLESS─没有心跳的少女─
5.CLANNAD
6.CLANNAD After Story
7.CLANNAD SSS
8.COP CRAFT(全缉毒狂潮)
9.CTG-从零开始养育电脑少女
10.dele删除
11.Fate Requiem
12.Fate Stay Night
13.JOJO’S BIZARRE ADVENTURE OVER HEAVEN
14.JOJO的奇妙冒险
15.MORTE ─水葬之少女─
16.OVERLORDǦ
17.PSYCHO-PASS心理测量者 前传
18.Re-从零开始的异世界生活
19.S.I.R.E.N.次世代生物统合研究特区(次世代新生物统合研究特区)
20.Shamer
21.To Love 出包王女
22.Veildeman假说
23.VENOM 求爱性少女症候群
24.《Fate Zero》
25.《关于我转生变成史莱姆这档事》
26.《回复术士的重启人生》
27.《我的青春恋爱物语果然有问题》
28.《魔女之旅》
29.【实教1-11.5卷TXT】
30.下流梗不存在的灰暗世界(没有黄段子的无聊世界)
31.不会飞的蝴蝶与天空之鯱(无法飞翔的蝴蝶与天空的逆戟鲸)
32.不游戏无人生
33.不起眼女主角培育法(路人女主的养成方法)
34.与某飞行员的誓约
35.世界征服计划
36.东京喰种(东京食尸鬼)
37.东京食尸鬼(东京喰种)官方小说
38.东方梦月抄
39.中二病也要谈恋爱!
40.为美好的世界献上祝福！(给予这个绝美的世界以祝福！)
41.人间失格
42.伤物语(物语系列二)
43.伪恋 幕后花絮
44.侦探已经死了
45.倾物语(物语系列五)
46.公爵千金的家庭教师(公女殿下的家庭教师)
47.再见宣言
48.冰川老师想交个宅宅男友
49.刀剑神域
50.刀剑神域15 Alicization篇
51.初音未来的消失
52.刮掉胡子的我与捡到的女高中生(剃须。然后捡到女高中生)
53.化物语(物语系列一)
54.千本樱
55.反苏格拉底(逆苏格拉底)
56.可塑性记忆 Heartfelt Thanks
57.史上最强大魔王转生为村民A
58.君主·埃尔梅罗二世的冒险
59.吹响吧！上低音号 欢迎来到立华高校舞奏队
60.命运石之门
61.和没有信徒的女神大人一起攻略异世界
62.四月是你的谎言 六人的练习曲
63.在地下城寻求邂逅是否搞错了什么期待在地下城邂逅有错吗-八号文库
64.地狱少女
65.夏目友人帐(妖怪连络簿)
66.天之弱
67.天国旅行
68.天才程式少女(你好，世界—Hello World—)
69.女神异闻录3
70.女神异闻录4
71.妖世刃吊华 吾爱之地 而今安在
72.妖怪连络簿(夏目友人帐)
73.嫌疑犯X的献身
74.家里蹲吸血姬的郁闷(家里蹲吸血姬的苦闷)
75.寂静岭官方小说
76.少女与战车
77.尸鬼
78.尼尔：自动人形 长话
79.废柴勇者下克上
80.恋物语(物语系列九)
81.情色漫画老师(我的妹妹是黄漫老师／埃罗芒阿老师)
82.我和你有致命的认知差异(你存在致命性的偏差)
83.我和女友的妹妹接吻了
84.我想吃掉你的胰脏(我想吃了，你的胰脏)
85.我的妹妹哪有这么可爱(我的妹妹不可能那么可爱)
86.战翼的希格德莉法
87.文豪Stray Dogs(文豪野犬)
88.新世纪福音战士ANIMA
89.旅行，直至毁灭世界的终焉
90.无职转生异世界
91.暗黑童话
92.最终幻想VII
93.月姬
94.未闻花名(我们仍未知道那天所看见的花的名字)
95.末日乐园的葬花少女(倾轧乐园的葬花少女)
96.机动战士高达 UNICORN 0096
97.杀戮的天使
98.某科学的超电磁炮
99.棋魂
100.欢迎来到异世界图书馆
101.法式甜点幸福堂书店
102.浮空大陆赛尔雷沃特
103.海贼王剧场小说
104.潜行吧，奈亚子！
105.火影忍者官方小说
106.爱上卡夫卡女孩
107.爱好谜题的少女
108.犬夜叉官方小说
109.猫娘姐妹
110.献给死者的音乐
111.王冠启示录
112.白夜行
113.白色相簿2(WHITE ALBUM2 白雪交织的旋律)
114.碧蓝幻想
115.碧蓝航线 Episode of Belfast
116.秒速5厘米
117.空之境界
118.约会大作战1-18卷
119.线上游戏的老婆不可能是女生？
120.终结的炽天使 吸血鬼米迦尔物语
121.绝深海的索拉里斯(无尽深海的索拉利斯)
122.绯弹的亚里亚
123.美少女宇宙人＆神奇道具H展开！？
124.羔羊的盛宴
125.脑浆炸裂girl
126.苍之彼方的四重奏–Fly me to your sky !–
127.英雄传说 零之轨迹
128.薇尔莉特·伊芙加登(紫罗兰永恒花园)
129.虚构推理
130.袭来!美少女邪神(潜行吧!奈亚子)
131.言叶之庭(秋月孝雄视角版)
132.赤色罗曼史
133.超时空要塞 边界
134.辉夜大小姐想让我告白～秀知院学园的七大不可思议～
135.辉夜姬想让人告白(辉夜大小姐想让我告白)
136.进击的巨人
137.进击的巨人 before the fall
138.进击的巨人 隔绝都市的女王
139.透过机器人与你相恋
140.邻座的艾琳同学偶尔会用俄语悄悄撒娇
141.钢之炼金术师
142.银河铁道之夜
143.银魂 3年Z组银八老师
144.阳炎project
145.阶梯岛系列(消失吧，群青)
146.青春猪头少年不会梦到兔女郎学姊(青春野狼不做兔女郎学姐的梦)
147.青梅竹马绝对不会输的恋爱喜剧
148.青空与阴天
149.魔女宅急便
150.魔法少女小圆
151.黑执事官方小说
152.龙与虎
153.龙背上的骑兵
--- | Minami-su/Anime_novel_datasets | [
"task_categories:text-generation",
"language:zh",
"license:apache-2.0",
"Anime",
"galgame",
"region:us"
] | 2023-12-16T03:55:13+00:00 | {"language": ["zh"], "license": "apache-2.0", "task_categories": ["text-generation"], "tags": ["Anime", "galgame"]} | 2023-12-16T04:33:27+00:00 | [] | [
"zh"
] | TAGS
#task_categories-text-generation #language-Chinese #license-apache-2.0 #Anime #galgame #region-us
|
---
动漫小说预训练数据集包含将近153本小说
## 关于我自己：
我是小雨的开发者，小雨是一个情感ai，人格ai，如果对小雨感兴趣的话欢迎支持一下，她目前在bilibili直播，目前我仍在不断的改进，未来，“小雨”的目标是成为一个
具有真正人类情感的多模态通用人工智能。
url：URL
## About Myself:
I am the developer of Xiaoyu, an AI specializing in emotion and personality. If you're interested in Xiaoyu, feel free to show your support! She is currently live on Bilibili, and I am continuously working on improvements.In the future, '小雨' aims to become a multimodal general artificial intelligence with genuine human emotions.
URL: URL
## list:
1.86-不存在的战区-(86- Eighty Six -)
2.Angel Beats! -Track Zero-
3.Another
4.BEATLESS─没有心跳的少女─
5.CLANNAD
6.CLANNAD After Story
7.CLANNAD SSS
8.COP CRAFT(全缉毒狂潮)
9.CTG-从零开始养育电脑少女
10.dele删除
11.Fate Requiem
12.Fate Stay Night
13.JOJO’S BIZARRE ADVENTURE OVER HEAVEN
14.JOJO的奇妙冒险
15.MORTE ─水葬之少女─
16.OVERLORDǦ
17.PSYCHO-PASS心理测量者 前传
18.Re-从零开始的异世界生活
19.S.I.R.E.N.次世代生物统合研究特区(次世代新生物统合研究特区)
20.Shamer
21.To Love 出包王女
22.Veildeman假说
23.VENOM 求爱性少女症候群
24.《Fate Zero》
25.《关于我转生变成史莱姆这档事》
26.《回复术士的重启人生》
27.《我的青春恋爱物语果然有问题》
28.《魔女之旅》
29.【实教1-11.5卷TXT】
30.下流梗不存在的灰暗世界(没有黄段子的无聊世界)
31.不会飞的蝴蝶与天空之鯱(无法飞翔的蝴蝶与天空的逆戟鲸)
32.不游戏无人生
33.不起眼女主角培育法(路人女主的养成方法)
34.与某飞行员的誓约
35.世界征服计划
36.东京喰种(东京食尸鬼)
37.东京食尸鬼(东京喰种)官方小说
38.东方梦月抄
39.中二病也要谈恋爱!
40.为美好的世界献上祝福！(给予这个绝美的世界以祝福！)
41.人间失格
42.伤物语(物语系列二)
43.伪恋 幕后花絮
44.侦探已经死了
45.倾物语(物语系列五)
46.公爵千金的家庭教师(公女殿下的家庭教师)
47.再见宣言
48.冰川老师想交个宅宅男友
49.刀剑神域
50.刀剑神域15 Alicization篇
51.初音未来的消失
52.刮掉胡子的我与捡到的女高中生(剃须。然后捡到女高中生)
53.化物语(物语系列一)
54.千本樱
55.反苏格拉底(逆苏格拉底)
56.可塑性记忆 Heartfelt Thanks
57.史上最强大魔王转生为村民A
58.君主·埃尔梅罗二世的冒险
59.吹响吧！上低音号 欢迎来到立华高校舞奏队
60.命运石之门
61.和没有信徒的女神大人一起攻略异世界
62.四月是你的谎言 六人的练习曲
63.在地下城寻求邂逅是否搞错了什么期待在地下城邂逅有错吗-八号文库
64.地狱少女
65.夏目友人帐(妖怪连络簿)
66.天之弱
67.天国旅行
68.天才程式少女(你好，世界—Hello World—)
69.女神异闻录3
70.女神异闻录4
71.妖世刃吊华 吾爱之地 而今安在
72.妖怪连络簿(夏目友人帐)
73.嫌疑犯X的献身
74.家里蹲吸血姬的郁闷(家里蹲吸血姬的苦闷)
75.寂静岭官方小说
76.少女与战车
77.尸鬼
78.尼尔：自动人形 长话
79.废柴勇者下克上
80.恋物语(物语系列九)
81.情色漫画老师(我的妹妹是黄漫老师／埃罗芒阿老师)
82.我和你有致命的认知差异(你存在致命性的偏差)
83.我和女友的妹妹接吻了
84.我想吃掉你的胰脏(我想吃了，你的胰脏)
85.我的妹妹哪有这么可爱(我的妹妹不可能那么可爱)
86.战翼的希格德莉法
87.文豪Stray Dogs(文豪野犬)
88.新世纪福音战士ANIMA
89.旅行，直至毁灭世界的终焉
90.无职转生异世界
91.暗黑童话
92.最终幻想VII
93.月姬
94.未闻花名(我们仍未知道那天所看见的花的名字)
95.末日乐园的葬花少女(倾轧乐园的葬花少女)
96.机动战士高达 UNICORN 0096
97.杀戮的天使
98.某科学的超电磁炮
99.棋魂
100.欢迎来到异世界图书馆
101.法式甜点幸福堂书店
102.浮空大陆赛尔雷沃特
103.海贼王剧场小说
104.潜行吧，奈亚子！
105.火影忍者官方小说
106.爱上卡夫卡女孩
107.爱好谜题的少女
108.犬夜叉官方小说
109.猫娘姐妹
110.献给死者的音乐
111.王冠启示录
112.白夜行
113.白色相簿2(WHITE ALBUM2 白雪交织的旋律)
114.碧蓝幻想
115.碧蓝航线 Episode of Belfast
116.秒速5厘米
117.空之境界
118.约会大作战1-18卷
119.线上游戏的老婆不可能是女生？
120.终结的炽天使 吸血鬼米迦尔物语
121.绝深海的索拉里斯(无尽深海的索拉利斯)
122.绯弹的亚里亚
123.美少女宇宙人＆神奇道具H展开！？
124.羔羊的盛宴
125.脑浆炸裂girl
126.苍之彼方的四重奏–Fly me to your sky !–
127.英雄传说 零之轨迹
128.薇尔莉特·伊芙加登(紫罗兰永恒花园)
129.虚构推理
130.袭来!美少女邪神(潜行吧!奈亚子)
131.言叶之庭(秋月孝雄视角版)
132.赤色罗曼史
133.超时空要塞 边界
134.辉夜大小姐想让我告白～秀知院学园的七大不可思议～
135.辉夜姬想让人告白(辉夜大小姐想让我告白)
136.进击的巨人
137.进击的巨人 before the fall
138.进击的巨人 隔绝都市的女王
139.透过机器人与你相恋
140.邻座的艾琳同学偶尔会用俄语悄悄撒娇
141.钢之炼金术师
142.银河铁道之夜
143.银魂 3年Z组银八老师
144.阳炎project
145.阶梯岛系列(消失吧，群青)
146.青春猪头少年不会梦到兔女郎学姊(青春野狼不做兔女郎学姐的梦)
147.青梅竹马绝对不会输的恋爱喜剧
148.青空与阴天
149.魔女宅急便
150.魔法少女小圆
151.黑执事官方小说
152.龙与虎
153.龙背上的骑兵
--- | [
"## 关于我自己：\n我是小雨的开发者，小雨是一个情感ai，人格ai，如果对小雨感兴趣的话欢迎支持一下，她目前在bilibili直播，目前我仍在不断的改进，未来，“小雨”的目标是成为一个\n具有真正人类情感的多模态通用人工智能。\nurl：URL",
"## About Myself:\nI am the developer of Xiaoyu, an AI specializing in emotion and personality. If you're interested in Xiaoyu, feel free to show your support! She is currently live on Bilibili, and I am continuously working on improvements.In the future, '小雨' aims to become a multimodal general artificial intelligence with genuine human emotions.\n\nURL: URL",
"## list:\n\n1.86-不存在的战区-(86- Eighty Six -)\n\n2.Angel Beats! -Track Zero-\n\n3.Another\n\n4.BEATLESS─没有心跳的少女─\n\n5.CLANNAD\n\n6.CLANNAD After Story\n\n7.CLANNAD SSS\n\n8.COP CRAFT(全缉毒狂潮)\n\n9.CTG-从零开始养育电脑少女\n\n10.dele删除\n\n11.Fate Requiem\n\n12.Fate Stay Night\n\n13.JOJO’S BIZARRE ADVENTURE OVER HEAVEN\n\n14.JOJO的奇妙冒险\n\n15.MORTE ─水葬之少女─\n\n16.OVERLORDǦ\n\n17.PSYCHO-PASS心理测量者 前传\n\n18.Re-从零开始的异世界生活\n\n19.S.I.R.E.N.次世代生物统合研究特区(次世代新生物统合研究特区)\n\n20.Shamer\n\n21.To Love 出包王女\n\n22.Veildeman假说\n\n23.VENOM 求爱性少女症候群\n\n24.《Fate Zero》\n\n25.《关于我转生变成史莱姆这档事》\n\n26.《回复术士的重启人生》\n\n27.《我的青春恋爱物语果然有问题》\n\n28.《魔女之旅》\n\n29.【实教1-11.5卷TXT】\n\n30.下流梗不存在的灰暗世界(没有黄段子的无聊世界)\n\n31.不会飞的蝴蝶与天空之鯱(无法飞翔的蝴蝶与天空的逆戟鲸)\n\n32.不游戏无人生\n\n33.不起眼女主角培育法(路人女主的养成方法)\n\n34.与某飞行员的誓约\n\n35.世界征服计划\n\n36.东京喰种(东京食尸鬼)\n\n37.东京食尸鬼(东京喰种)官方小说\n\n38.东方梦月抄\n\n39.中二病也要谈恋爱!\n\n40.为美好的世界献上祝福！(给予这个绝美的世界以祝福！)\n\n41.人间失格\n\n42.伤物语(物语系列二)\n\n43.伪恋 幕后花絮\n\n44.侦探已经死了\n\n45.倾物语(物语系列五)\n\n46.公爵千金的家庭教师(公女殿下的家庭教师)\n\n47.再见宣言\n\n48.冰川老师想交个宅宅男友\n\n49.刀剑神域\n\n50.刀剑神域15 Alicization篇\n\n51.初音未来的消失\n\n52.刮掉胡子的我与捡到的女高中生(剃须。然后捡到女高中生)\n\n53.化物语(物语系列一)\n\n54.千本樱\n\n55.反苏格拉底(逆苏格拉底)\n\n56.可塑性记忆 Heartfelt Thanks\n\n57.史上最强大魔王转生为村民A\n\n58.君主·埃尔梅罗二世的冒险\n\n59.吹响吧！上低音号 欢迎来到立华高校舞奏队\n\n60.命运石之门\n\n61.和没有信徒的女神大人一起攻略异世界\n\n62.四月是你的谎言 六人的练习曲\n\n63.在地下城寻求邂逅是否搞错了什么期待在地下城邂逅有错吗-八号文库\n\n64.地狱少女\n\n65.夏目友人帐(妖怪连络簿)\n\n66.天之弱\n\n67.天国旅行\n\n68.天才程式少女(你好，世界—Hello World—)\n\n69.女神异闻录3\n\n70.女神异闻录4\n\n71.妖世刃吊华 吾爱之地 而今安在\n\n72.妖怪连络簿(夏目友人帐)\n\n73.嫌疑犯X的献身\n\n74.家里蹲吸血姬的郁闷(家里蹲吸血姬的苦闷)\n\n75.寂静岭官方小说\n\n76.少女与战车\n\n77.尸鬼\n\n78.尼尔：自动人形 长话\n\n79.废柴勇者下克上\n\n80.恋物语(物语系列九)\n\n81.情色漫画老师(我的妹妹是黄漫老师／埃罗芒阿老师)\n\n82.我和你有致命的认知差异(你存在致命性的偏差)\n\n83.我和女友的妹妹接吻了\n\n84.我想吃掉你的胰脏(我想吃了，你的胰脏)\n\n85.我的妹妹哪有这么可爱(我的妹妹不可能那么可爱)\n\n86.战翼的希格德莉法\n\n87.文豪Stray Dogs(文豪野犬)\n\n88.新世纪福音战士ANIMA\n\n89.旅行，直至毁灭世界的终焉\n\n90.无职转生异世界\n\n91.暗黑童话\n\n92.最终幻想VII\n\n93.月姬\n\n94.未闻花名(我们仍未知道那天所看见的花的名字)\n\n95.末日乐园的葬花少女(倾轧乐园的葬花少女)\n\n96.机动战士高达 UNICORN 0096\n\n97.杀戮的天使\n\n98.某科学的超电磁炮\n\n99.棋魂\n\n100.欢迎来到异世界图书馆\n\n101.法式甜点幸福堂书店\n\n102.浮空大陆赛尔雷沃特\n\n103.海贼王剧场小说\n\n104.潜行吧，奈亚子！\n\n105.火影忍者官方小说\n\n106.爱上卡夫卡女孩\n\n107.爱好谜题的少女\n\n108.犬夜叉官方小说\n\n109.猫娘姐妹\n\n110.献给死者的音乐\n\n111.王冠启示录\n\n112.白夜行\n\n113.白色相簿2(WHITE ALBUM2 白雪交织的旋律)\n\n114.碧蓝幻想\n\n115.碧蓝航线 Episode of Belfast\n\n116.秒速5厘米\n\n117.空之境界\n\n118.约会大作战1-18卷\n\n119.线上游戏的老婆不可能是女生？\n\n120.终结的炽天使 吸血鬼米迦尔物语\n\n121.绝深海的索拉里斯(无尽深海的索拉利斯)\n\n122.绯弹的亚里亚\n\n123.美少女宇宙人＆神奇道具H展开！？\n\n124.羔羊的盛宴\n\n125.脑浆炸裂girl\n\n126.苍之彼方的四重奏–Fly me to your sky !–\n\n127.英雄传说 零之轨迹\n\n128.薇尔莉特·伊芙加登(紫罗兰永恒花园)\n\n129.虚构推理\n\n130.袭来!美少女邪神(潜行吧!奈亚子)\n\n131.言叶之庭(秋月孝雄视角版)\n\n132.赤色罗曼史\n\n133.超时空要塞 边界\n\n134.辉夜大小姐想让我告白～秀知院学园的七大不可思议～\n\n135.辉夜姬想让人告白(辉夜大小姐想让我告白)\n\n136.进击的巨人\n\n137.进击的巨人 before the fall\n\n138.进击的巨人 隔绝都市的女王\n\n139.透过机器人与你相恋\n\n140.邻座的艾琳同学偶尔会用俄语悄悄撒娇\n\n141.钢之炼金术师\n\n142.银河铁道之夜\n\n143.银魂 3年Z组银八老师\n\n144.阳炎project\n\n145.阶梯岛系列(消失吧，群青)\n\n146.青春猪头少年不会梦到兔女郎学姊(青春野狼不做兔女郎学姐的梦)\n\n147.青梅竹马绝对不会输的恋爱喜剧\n\n148.青空与阴天\n\n149.魔女宅急便\n\n150.魔法少女小圆\n\n151.黑执事官方小说\n\n152.龙与虎\n\n153.龙背上的骑兵\n\n\n---"
] | [
"TAGS\n#task_categories-text-generation #language-Chinese #license-apache-2.0 #Anime #galgame #region-us \n",
"## 关于我自己：\n我是小雨的开发者，小雨是一个情感ai，人格ai，如果对小雨感兴趣的话欢迎支持一下，她目前在bilibili直播，目前我仍在不断的改进，未来，“小雨”的目标是成为一个\n具有真正人类情感的多模态通用人工智能。\nurl：URL",
"## About Myself:\nI am the developer of Xiaoyu, an AI specializing in emotion and personality. If you're interested in Xiaoyu, feel free to show your support! She is currently live on Bilibili, and I am continuously working on improvements.In the future, '小雨' aims to become a multimodal general artificial intelligence with genuine human emotions.\n\nURL: URL",
"## list:\n\n1.86-不存在的战区-(86- Eighty Six -)\n\n2.Angel Beats! -Track Zero-\n\n3.Another\n\n4.BEATLESS─没有心跳的少女─\n\n5.CLANNAD\n\n6.CLANNAD After Story\n\n7.CLANNAD SSS\n\n8.COP CRAFT(全缉毒狂潮)\n\n9.CTG-从零开始养育电脑少女\n\n10.dele删除\n\n11.Fate Requiem\n\n12.Fate Stay Night\n\n13.JOJO’S BIZARRE ADVENTURE OVER HEAVEN\n\n14.JOJO的奇妙冒险\n\n15.MORTE ─水葬之少女─\n\n16.OVERLORDǦ\n\n17.PSYCHO-PASS心理测量者 前传\n\n18.Re-从零开始的异世界生活\n\n19.S.I.R.E.N.次世代生物统合研究特区(次世代新生物统合研究特区)\n\n20.Shamer\n\n21.To Love 出包王女\n\n22.Veildeman假说\n\n23.VENOM 求爱性少女症候群\n\n24.《Fate Zero》\n\n25.《关于我转生变成史莱姆这档事》\n\n26.《回复术士的重启人生》\n\n27.《我的青春恋爱物语果然有问题》\n\n28.《魔女之旅》\n\n29.【实教1-11.5卷TXT】\n\n30.下流梗不存在的灰暗世界(没有黄段子的无聊世界)\n\n31.不会飞的蝴蝶与天空之鯱(无法飞翔的蝴蝶与天空的逆戟鲸)\n\n32.不游戏无人生\n\n33.不起眼女主角培育法(路人女主的养成方法)\n\n34.与某飞行员的誓约\n\n35.世界征服计划\n\n36.东京喰种(东京食尸鬼)\n\n37.东京食尸鬼(东京喰种)官方小说\n\n38.东方梦月抄\n\n39.中二病也要谈恋爱!\n\n40.为美好的世界献上祝福！(给予这个绝美的世界以祝福！)\n\n41.人间失格\n\n42.伤物语(物语系列二)\n\n43.伪恋 幕后花絮\n\n44.侦探已经死了\n\n45.倾物语(物语系列五)\n\n46.公爵千金的家庭教师(公女殿下的家庭教师)\n\n47.再见宣言\n\n48.冰川老师想交个宅宅男友\n\n49.刀剑神域\n\n50.刀剑神域15 Alicization篇\n\n51.初音未来的消失\n\n52.刮掉胡子的我与捡到的女高中生(剃须。然后捡到女高中生)\n\n53.化物语(物语系列一)\n\n54.千本樱\n\n55.反苏格拉底(逆苏格拉底)\n\n56.可塑性记忆 Heartfelt Thanks\n\n57.史上最强大魔王转生为村民A\n\n58.君主·埃尔梅罗二世的冒险\n\n59.吹响吧！上低音号 欢迎来到立华高校舞奏队\n\n60.命运石之门\n\n61.和没有信徒的女神大人一起攻略异世界\n\n62.四月是你的谎言 六人的练习曲\n\n63.在地下城寻求邂逅是否搞错了什么期待在地下城邂逅有错吗-八号文库\n\n64.地狱少女\n\n65.夏目友人帐(妖怪连络簿)\n\n66.天之弱\n\n67.天国旅行\n\n68.天才程式少女(你好，世界—Hello World—)\n\n69.女神异闻录3\n\n70.女神异闻录4\n\n71.妖世刃吊华 吾爱之地 而今安在\n\n72.妖怪连络簿(夏目友人帐)\n\n73.嫌疑犯X的献身\n\n74.家里蹲吸血姬的郁闷(家里蹲吸血姬的苦闷)\n\n75.寂静岭官方小说\n\n76.少女与战车\n\n77.尸鬼\n\n78.尼尔：自动人形 长话\n\n79.废柴勇者下克上\n\n80.恋物语(物语系列九)\n\n81.情色漫画老师(我的妹妹是黄漫老师／埃罗芒阿老师)\n\n82.我和你有致命的认知差异(你存在致命性的偏差)\n\n83.我和女友的妹妹接吻了\n\n84.我想吃掉你的胰脏(我想吃了，你的胰脏)\n\n85.我的妹妹哪有这么可爱(我的妹妹不可能那么可爱)\n\n86.战翼的希格德莉法\n\n87.文豪Stray Dogs(文豪野犬)\n\n88.新世纪福音战士ANIMA\n\n89.旅行，直至毁灭世界的终焉\n\n90.无职转生异世界\n\n91.暗黑童话\n\n92.最终幻想VII\n\n93.月姬\n\n94.未闻花名(我们仍未知道那天所看见的花的名字)\n\n95.末日乐园的葬花少女(倾轧乐园的葬花少女)\n\n96.机动战士高达 UNICORN 0096\n\n97.杀戮的天使\n\n98.某科学的超电磁炮\n\n99.棋魂\n\n100.欢迎来到异世界图书馆\n\n101.法式甜点幸福堂书店\n\n102.浮空大陆赛尔雷沃特\n\n103.海贼王剧场小说\n\n104.潜行吧，奈亚子！\n\n105.火影忍者官方小说\n\n106.爱上卡夫卡女孩\n\n107.爱好谜题的少女\n\n108.犬夜叉官方小说\n\n109.猫娘姐妹\n\n110.献给死者的音乐\n\n111.王冠启示录\n\n112.白夜行\n\n113.白色相簿2(WHITE ALBUM2 白雪交织的旋律)\n\n114.碧蓝幻想\n\n115.碧蓝航线 Episode of Belfast\n\n116.秒速5厘米\n\n117.空之境界\n\n118.约会大作战1-18卷\n\n119.线上游戏的老婆不可能是女生？\n\n120.终结的炽天使 吸血鬼米迦尔物语\n\n121.绝深海的索拉里斯(无尽深海的索拉利斯)\n\n122.绯弹的亚里亚\n\n123.美少女宇宙人＆神奇道具H展开！？\n\n124.羔羊的盛宴\n\n125.脑浆炸裂girl\n\n126.苍之彼方的四重奏–Fly me to your sky !–\n\n127.英雄传说 零之轨迹\n\n128.薇尔莉特·伊芙加登(紫罗兰永恒花园)\n\n129.虚构推理\n\n130.袭来!美少女邪神(潜行吧!奈亚子)\n\n131.言叶之庭(秋月孝雄视角版)\n\n132.赤色罗曼史\n\n133.超时空要塞 边界\n\n134.辉夜大小姐想让我告白～秀知院学园的七大不可思议～\n\n135.辉夜姬想让人告白(辉夜大小姐想让我告白)\n\n136.进击的巨人\n\n137.进击的巨人 before the fall\n\n138.进击的巨人 隔绝都市的女王\n\n139.透过机器人与你相恋\n\n140.邻座的艾琳同学偶尔会用俄语悄悄撒娇\n\n141.钢之炼金术师\n\n142.银河铁道之夜\n\n143.银魂 3年Z组银八老师\n\n144.阳炎project\n\n145.阶梯岛系列(消失吧，群青)\n\n146.青春猪头少年不会梦到兔女郎学姊(青春野狼不做兔女郎学姐的梦)\n\n147.青梅竹马绝对不会输的恋爱喜剧\n\n148.青空与阴天\n\n149.魔女宅急便\n\n150.魔法少女小圆\n\n151.黑执事官方小说\n\n152.龙与虎\n\n153.龙背上的骑兵\n\n\n---"
] | [
36,
71,
86,
1594
] | [
"passage: TAGS\n#task_categories-text-generation #language-Chinese #license-apache-2.0 #Anime #galgame #region-us \n## 关于我自己：\n我是小雨的开发者，小雨是一个情感ai，人格ai，如果对小雨感兴趣的话欢迎支持一下，她目前在bilibili直播，目前我仍在不断的改进，未来，“小雨”的目标是成为一个\n具有真正人类情感的多模态通用人工智能。\nurl：URL## About Myself:\nI am the developer of Xiaoyu, an AI specializing in emotion and personality. If you're interested in Xiaoyu, feel free to show your support! She is currently live on Bilibili, and I am continuously working on improvements.In the future, '小雨' aims to become a multimodal general artificial intelligence with genuine human emotions.\n\nURL: URL"
] |
1c57ab41a476f8e5e2aed1e4dd9fd8e70e456c57 |
# Bangumi Image Base of Senpai Ga Uzai Kouhai No Hanashi
This is the image base of bangumi Senpai ga Uzai Kouhai no Hanashi, we detected 22 characters, 3446 images in total. The full dataset is [here](all.zip).
**Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual.** If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| # | Images | Download | Preview 1 | Preview 2 | Preview 3 | Preview 4 | Preview 5 | Preview 6 | Preview 7 | Preview 8 |
|:------|---------:|:---------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|:-------------------------------|
| 0 | 1284 | [Download](0/dataset.zip) |  |  |  |  |  |  |  |  |
| 1 | 38 | [Download](1/dataset.zip) |  |  |  |  |  |  |  |  |
| 2 | 75 | [Download](2/dataset.zip) |  |  |  |  |  |  |  |  |
| 3 | 17 | [Download](3/dataset.zip) |  |  |  |  |  |  |  |  |
| 4 | 30 | [Download](4/dataset.zip) |  |  |  |  |  |  |  |  |
| 5 | 625 | [Download](5/dataset.zip) |  |  |  |  |  |  |  |  |
| 6 | 326 | [Download](6/dataset.zip) |  |  |  |  |  |  |  |  |
| 7 | 190 | [Download](7/dataset.zip) |  |  |  |  |  |  |  |  |
| 8 | 19 | [Download](8/dataset.zip) |  |  |  |  |  |  |  |  |
| 9 | 44 | [Download](9/dataset.zip) |  |  |  |  |  |  |  |  |
| 10 | 41 | [Download](10/dataset.zip) |  |  |  |  |  |  |  |  |
| 11 | 7 | [Download](11/dataset.zip) |  |  |  |  |  |  |  | N/A |
| 12 | 64 | [Download](12/dataset.zip) |  |  |  |  |  |  |  |  |
| 13 | 12 | [Download](13/dataset.zip) |  |  |  |  |  |  |  |  |
| 14 | 13 | [Download](14/dataset.zip) |  |  |  |  |  |  |  |  |
| 15 | 63 | [Download](15/dataset.zip) |  |  |  |  |  |  |  |  |
| 16 | 351 | [Download](16/dataset.zip) |  |  |  |  |  |  |  |  |
| 17 | 11 | [Download](17/dataset.zip) |  |  |  |  |  |  |  |  |
| 18 | 9 | [Download](18/dataset.zip) |  |  |  |  |  |  |  |  |
| 19 | 157 | [Download](19/dataset.zip) |  |  |  |  |  |  |  |  |
| 20 | 6 | [Download](20/dataset.zip) |  |  |  |  |  |  | N/A | N/A |
| noise | 64 | [Download](-1/dataset.zip) |  |  |  |  |  |  |  |  |
| BangumiBase/senpaigauzaikouhainohanashi | [
"size_categories:1K<n<10K",
"license:mit",
"art",
"region:us"
] | 2023-12-16T04:04:37+00:00 | {"license": "mit", "size_categories": ["1K<n<10K"], "tags": ["art"]} | 2023-12-16T06:52:01+00:00 | [] | [] | TAGS
#size_categories-1K<n<10K #license-mit #art #region-us
| Bangumi Image Base of Senpai Ga Uzai Kouhai No Hanashi
======================================================
This is the image base of bangumi Senpai ga Uzai Kouhai no Hanashi, we detected 22 characters, 3446 images in total. The full dataset is here.
Please note that these image bases are not guaranteed to be 100% cleaned, they may be noisy actual. If you intend to manually train models using this dataset, we recommend performing necessary preprocessing on the downloaded dataset to eliminate potential noisy samples (approximately 1% probability).
Here is the characters' preview:
| [] | [
"TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] | [
25
] | [
"passage: TAGS\n#size_categories-1K<n<10K #license-mit #art #region-us \n"
] |
da4928a6d681ebccdcd1eea20866d77fe7eed9dd | # Dataset Card for "low_vs_random"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | kristmh/low_vs_random | [
"region:us"
] | 2023-12-16T05:09:19+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "test", "path": "data/test-*"}, {"split": "train", "path": "data/train-*"}, {"split": "validate", "path": "data/validate-*"}]}], "dataset_info": {"features": [{"name": "text_clean", "dtype": "string"}, {"name": "labels", "dtype": "int64"}, {"name": "class", "dtype": "string"}, {"name": "__index_level_0__", "dtype": "int64"}], "splits": [{"name": "test", "num_bytes": 19739399, "num_examples": 24512}, {"name": "train", "num_bytes": 158958252, "num_examples": 196090}, {"name": "validate", "num_bytes": 19103258, "num_examples": 24511}], "download_size": 97810741, "dataset_size": 197800909}} | 2023-12-16T05:09:56+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "low_vs_random"
More Information needed | [
"# Dataset Card for \"low_vs_random\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"low_vs_random\"\n\nMore Information needed"
] | [
6,
16
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"low_vs_random\"\n\nMore Information needed"
] |
4214482b153fa7d844d07bfb35a6f6dec5901489 |
# Dataset of jessica (Arknights)
This is the dataset of jessica (Arknights), containing 307 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by [DeepGHS Team](https://github.com/deepghs)([huggingface organization](https://huggingface.co/deepghs)).
This is a WebUI contains crawlers and other thing: ([LittleAppleWebUI](https://github.com/LittleApple-fp16/LittleAppleWebUI))
| Name | Images | Download | Description |
|:----------------|---------:|:----------------------------------------|:-----------------------------------------------------------------------------------------|
| raw | 307 | [Download](dataset-raw.zip) | Raw data with meta information. |
| raw-stage3 | 746 | [Download](dataset-raw-stage3.zip) | 3-stage cropped raw data with meta information. |
| raw-stage3-eyes | 824 | [Download](dataset-raw-stage3-eyes.zip) | 3-stage cropped (with eye-focus) raw data with meta information. |
| 384x512 | 307 | [Download](dataset-384x512.zip) | 384x512 aligned dataset. |
| 512x704 | 307 | [Download](dataset-512x704.zip) | 512x704 aligned dataset. |
| 640x880 | 307 | [Download](dataset-640x880.zip) | 640x880 aligned dataset. |
| stage3-640 | 746 | [Download](dataset-stage3-640.zip) | 3-stage cropped dataset with the shorter side not exceeding 640 pixels. |
| stage3-800 | 746 | [Download](dataset-stage3-800.zip) | 3-stage cropped dataset with the shorter side not exceeding 800 pixels. |
| stage3-p512-640 | 513 | [Download](dataset-stage3-p512-640.zip) | 3-stage cropped dataset with the area not less than 512x512 pixels. |
| stage3-eyes-640 | 824 | [Download](dataset-stage3-eyes-640.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 640 pixels. |
| stage3-eyes-800 | 824 | [Download](dataset-stage3-eyes-800.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 800 pixels. |
| AppleHarem/jessica_arknights | [
"task_categories:text-to-image",
"size_categories:n<1K",
"license:mit",
"art",
"not-for-all-audiences",
"region:us"
] | 2023-12-16T05:10:01+00:00 | {"license": "mit", "size_categories": ["n<1K"], "task_categories": ["text-to-image"], "tags": ["art", "not-for-all-audiences"]} | 2023-12-16T05:10:21+00:00 | [] | [] | TAGS
#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us
| Dataset of jessica (Arknights)
==============================
This is the dataset of jessica (Arknights), containing 307 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by DeepGHS Team(huggingface organization).
This is a WebUI contains crawlers and other thing: (LittleAppleWebUI)
| [] | [
"TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] | [
44
] | [
"passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] |
a945426ea4befd4e8cb1dbfa52d54d0311821f67 | # Dataset Card for "counterfactual-babylm-aanns_indef_non_num_removal"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | kanishka/counterfactual-babylm-aanns_indef_non_num_removal | [
"region:us"
] | 2023-12-16T05:22:12+00:00 | {"dataset_info": {"features": [{"name": "text", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 581831219, "num_examples": 11633278}, {"name": "validation", "num_bytes": 56120230, "num_examples": 1026747}], "download_size": 421601983, "dataset_size": 637951449}} | 2023-12-16T05:22:31+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "counterfactual-babylm-aanns_indef_non_num_removal"
More Information needed | [
"# Dataset Card for \"counterfactual-babylm-aanns_indef_non_num_removal\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"counterfactual-babylm-aanns_indef_non_num_removal\"\n\nMore Information needed"
] | [
6,
30
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"counterfactual-babylm-aanns_indef_non_num_removal\"\n\nMore Information needed"
] |
3741e824e3f7e65b092c2e8210941fd7823b7d21 |
\[GitHub\]: https://github.com/SeaEval/SeaEval \[Website\]: https://seaeval.github.io/
```
@article{wang2023seaeval,
title={SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning},
author={Wang, Bin and Liu, Zhengyuan and Huang, Xin and Jiao, Fangkai and Ding, Yang and Aw, Ai Ti and Chen, Nancy F},
journal={arXiv preprint arXiv:2309.04766},
year={2023}
}
``` | SeaEval/SeaEval_datasets | [
"license:cc-by-nc-4.0",
"region:us"
] | 2023-12-16T05:23:55+00:00 | {"license": "cc-by-nc-4.0", "configs": [{"config_name": "cross_mmlu", "data_files": [{"split": "test", "path": "cross_mmlu.json"}]}, {"config_name": "cross_logiqa", "data_files": [{"split": "test", "path": "cross_logiqa.json"}]}, {"config_name": "us_eval", "data_files": [{"split": "test", "path": "us_eval.json"}]}, {"config_name": "sg_eval", "data_files": [{"split": "test", "path": "sg_eval.json"}]}, {"config_name": "cn_eval", "data_files": [{"split": "test", "path": "cn_eval.json"}]}, {"config_name": "ph_eval", "data_files": [{"split": "test", "path": "ph_eval.json"}]}, {"config_name": "flores_ind2eng", "data_files": [{"split": "test", "path": "flores_ind2eng.json"}]}, {"config_name": "flores_vie2eng", "data_files": [{"split": "test", "path": "flores_vie2eng.json"}]}, {"config_name": "flores_zho2eng", "data_files": [{"split": "test", "path": "flores_zho2eng.json"}]}, {"config_name": "flores_zsm2eng", "data_files": [{"split": "test", "path": "flores_zsm2eng.json"}]}, {"config_name": "mmlu", "data_files": [{"split": "test", "path": "mmlu.json"}]}, {"config_name": "mmlu_full", "data_files": [{"split": "test", "path": "mmlu_full.json"}]}, {"config_name": "c_eval", "data_files": [{"split": "test", "path": "c_eval.json"}]}, {"config_name": "c_eval_full", "data_files": [{"split": "test", "path": "c_eval_full.json"}]}, {"config_name": "cmmlu", "data_files": [{"split": "test", "path": "cmmlu.json"}]}, {"config_name": "cmmlu_full", "data_files": [{"split": "test", "path": "cmmlu_full.json"}]}, {"config_name": "zbench", "data_files": [{"split": "test", "path": "zbench.json"}]}, {"config_name": "ind_emotion", "data_files": [{"split": "test", "path": "ind_emotion.json"}]}, {"config_name": "ocnli", "data_files": [{"split": "test", "path": "ocnli.json"}]}, {"config_name": "c3", "data_files": [{"split": "test", "path": "c3.json"}]}, {"config_name": "dream", "data_files": [{"split": "test", "path": "dream.json"}]}, {"config_name": "samsum", "data_files": [{"split": "test", "path": "samsum.json"}]}, {"config_name": "dialogsum", "data_files": [{"split": "test", "path": "dialogsum.json"}]}, {"config_name": "sst2", "data_files": [{"split": "test", "path": "sst2.json"}]}, {"config_name": "cola", "data_files": [{"split": "test", "path": "cola.json"}]}, {"config_name": "qqp", "data_files": [{"split": "test", "path": "qqp.json"}]}, {"config_name": "mnli", "data_files": [{"split": "test", "path": "mnli.json"}]}, {"config_name": "qnli", "data_files": [{"split": "test", "path": "qnli.json"}]}, {"config_name": "wnli", "data_files": [{"split": "test", "path": "wnli.json"}]}, {"config_name": "rte", "data_files": [{"split": "test", "path": "rte.json"}]}, {"config_name": "mrpc", "data_files": [{"split": "test", "path": "mrpc.json"}]}]} | 2023-12-22T01:54:46+00:00 | [] | [] | TAGS
#license-cc-by-nc-4.0 #region-us
|
\[GitHub\]: URL \[Website\]: URL
| [] | [
"TAGS\n#license-cc-by-nc-4.0 #region-us \n"
] | [
17
] | [
"passage: TAGS\n#license-cc-by-nc-4.0 #region-us \n"
] |
5d7f98c3fd3d9c8c4a62628eb60bbd4c6d6815bf |
## This is the Official Capybara dataset. Over 10,000 multi-turn examples.
Capybara is the culmination of insights derived from synthesis techniques like Evol-instruct (used for WizardLM), Alpaca, Orca, Vicuna, Lamini, FLASK and others.
The single-turn seeds used to intiate the Amplify-Instruct synthesis of conversations are mostly based on datasets that i've personally vetted extensively, and are often highly regarded for their diversity and demonstration of logical robustness and prose, such as Airoboros, Know logic, EverythingLM, GPTeacher and even entirely new seed instructions derived from different sources, including certain in-house multi-turn datasets like Dove and Verified-Camel(A successor to Puffin).
The multi-turn synthetic conversation generation method is what i'm calling Amplify-Instruct, and the first resulting dataset using this method is called Capybara.
This dataset has a strong focus on information diversity across a wide range of domains, and multi-turn conversations that strongly emphasize reasoning, logic and extrapolation about a wide range of subjects, also many great examples of conversations delving into obscure sub-topics and rabbit holes across pop-culture and STEM, while also maintaining natural prose.
While performing great in it's current state, the current dataset used for fine-tuning is entirely contained within 20K training examples, this is 10 times smaller than many similar performing datasets, this is signficant when it comes to scaling implications once I decide to scale the use of Amplify-Instruct to significantly more examples.
- Most tokens contained in this dataset are newly synthesized and did not exist prior online.
- This leverages the Amplify-Instruct method(paper coming soon) to grow thousands of high-quality single-turn seeds into advanced and in-depth multi-turn conversations.
- Average context length per conversation is over 1,000 tokens and 3 turns or more per example (most instruction/chat datasets on HF for fine-tuning are only 1 turn)
- Each conversation is optimized to amplify the natural raw knowledge capabilities of the model, as well as delving deep into obscure and advanced topics.
- Aggresively filtered to remove any and all possible examples of overt moralizing/alignment, and common undesirable behaviours such as "as an AI language model" and "September 2021" and "I don't have personal beliefs"
## Benchmarks.
- Resulting benchmarks are available on HF Leaderboard, and other benchmarks done as well such as AGIEval, Bigbench and GPT4All.
- (The only Capybara model available on all of these benchmarks including HF leaderboard is Capybara V1, trained on Llama-2)
- The below benchmarks are compared against fine-tunes also done on Llama-2.
## Quality filtering and cleaning.
- Extensive measures were done to filter out any conversations that contained even a single instance of overt AI moralizing/alignment, such as "As an AI language model" and common undesirable behaviours such as conversations that include "September 2021" and "I don't have personal beliefs" and other phrases I've found to be highly correlated with undesirable responses and conversation paths.
## Thank you to those of you that have indirectly contributed!
While most of the tokens within Capybara are newly synthsized and part of datasets like Puffin/Dove, we would like to credit the single-turn datasets we leveraged as seeds, which were used to generate the multi-turn data.
The datasets shown in green below are datasets that we sampled from to curate seeds that are used during Amplify-Instruct synthesis for this project, however, most of the tokens in capybara within those given sections are novel tokens not present in any of the seed datasets.
Datasets in Blue are in-house curations that previously existed prior to Capybara, and were now used as seeds for Capybara.
## Dataset contamination.
We have checked the capybara dataset for contamination for several of the most popular benchmarks and can confirm that there is no contaminaton found besides MT-bench which is now cleaned out.
We leveraged minhash to check for 100%, 99%, 98% and 97% similarity matches between our data and the questions and answers in benchmarks, we found no exact matches, nor did we find any matches down to the 97% similarity level.
The following are benchmarks we checked for contamination against our dataset:
- HumanEval
- AGIEval
- TruthfulQA
- MMLU
- GPT4All
*Newly cleaned out as of 12/15/2023 - MT-bench
## Credits
During the curation process, there can be some relatively arduos steps when it comes to actually executing on the best experimentation or concepts for how to filter examples out.
Luckily there is folks over at Nous Research that helped with expediting these processes, big thank you to J-Supha specifically for making these types of significant contributions.
## Example Outputs from the Llama-2 7B model trained on this dataset:
## Future Plans & How you can help!
This is a relatively early build amongst the grand plans for the future of what I plan to work on!
In the near future we plan on leveraging the help of domain specific expert volunteers to eliminate any mathematically/verifiably incorrect answers from training curations of different types of datasets.
If you have at-least a bachelors in mathematics, physics, biology or chemistry and would like to volunteer even just 30 minutes of your expertise time, please contact LDJ on discord!
Citation:
```
@article{daniele2023amplify-instruct,
title={Amplify-Instruct: Synthetically Generated Diverse Multi-turn Conversations for Effecient LLM Training.},
author={Daniele, Luigi and Suphavadeeprasit},
journal={arXiv preprint arXiv:(coming soon)},
url={https://huggingface.co/datasets/LDJnr/Capybara},
year={2023}
}
``` | LDJnr/Capybara | [
"task_categories:conversational",
"task_categories:question-answering",
"task_categories:text-generation",
"size_categories:10K<n<100K",
"language:en",
"license:apache-2.0",
"Physics",
"Biology",
"Math",
"Chemistry",
"Culture",
"Logic",
"Roleplay",
"region:us"
] | 2023-12-16T05:45:37+00:00 | {"language": ["en"], "license": "apache-2.0", "size_categories": ["10K<n<100K"], "task_categories": ["conversational", "question-answering", "text-generation"], "pretty_name": "LessWrong-Amplify-Instruct", "tags": ["Physics", "Biology", "Math", "Chemistry", "Culture", "Logic", "Roleplay"]} | 2024-01-02T03:15:07+00:00 | [] | [
"en"
] | TAGS
#task_categories-conversational #task_categories-question-answering #task_categories-text-generation #size_categories-10K<n<100K #language-English #license-apache-2.0 #Physics #Biology #Math #Chemistry #Culture #Logic #Roleplay #region-us
|
## This is the Official Capybara dataset. Over 10,000 multi-turn examples.
Capybara is the culmination of insights derived from synthesis techniques like Evol-instruct (used for WizardLM), Alpaca, Orca, Vicuna, Lamini, FLASK and others.
The single-turn seeds used to intiate the Amplify-Instruct synthesis of conversations are mostly based on datasets that i've personally vetted extensively, and are often highly regarded for their diversity and demonstration of logical robustness and prose, such as Airoboros, Know logic, EverythingLM, GPTeacher and even entirely new seed instructions derived from different sources, including certain in-house multi-turn datasets like Dove and Verified-Camel(A successor to Puffin).
The multi-turn synthetic conversation generation method is what i'm calling Amplify-Instruct, and the first resulting dataset using this method is called Capybara.
This dataset has a strong focus on information diversity across a wide range of domains, and multi-turn conversations that strongly emphasize reasoning, logic and extrapolation about a wide range of subjects, also many great examples of conversations delving into obscure sub-topics and rabbit holes across pop-culture and STEM, while also maintaining natural prose.
While performing great in it's current state, the current dataset used for fine-tuning is entirely contained within 20K training examples, this is 10 times smaller than many similar performing datasets, this is signficant when it comes to scaling implications once I decide to scale the use of Amplify-Instruct to significantly more examples.
- Most tokens contained in this dataset are newly synthesized and did not exist prior online.
- This leverages the Amplify-Instruct method(paper coming soon) to grow thousands of high-quality single-turn seeds into advanced and in-depth multi-turn conversations.
- Average context length per conversation is over 1,000 tokens and 3 turns or more per example (most instruction/chat datasets on HF for fine-tuning are only 1 turn)
- Each conversation is optimized to amplify the natural raw knowledge capabilities of the model, as well as delving deep into obscure and advanced topics.
- Aggresively filtered to remove any and all possible examples of overt moralizing/alignment, and common undesirable behaviours such as "as an AI language model" and "September 2021" and "I don't have personal beliefs"
## Benchmarks.
- Resulting benchmarks are available on HF Leaderboard, and other benchmarks done as well such as AGIEval, Bigbench and GPT4All.
- (The only Capybara model available on all of these benchmarks including HF leaderboard is Capybara V1, trained on Llama-2)
- The below benchmarks are compared against fine-tunes also done on Llama-2.
!Capybara
!Capybara
## Quality filtering and cleaning.
- Extensive measures were done to filter out any conversations that contained even a single instance of overt AI moralizing/alignment, such as "As an AI language model" and common undesirable behaviours such as conversations that include "September 2021" and "I don't have personal beliefs" and other phrases I've found to be highly correlated with undesirable responses and conversation paths.
## Thank you to those of you that have indirectly contributed!
While most of the tokens within Capybara are newly synthsized and part of datasets like Puffin/Dove, we would like to credit the single-turn datasets we leveraged as seeds, which were used to generate the multi-turn data.
The datasets shown in green below are datasets that we sampled from to curate seeds that are used during Amplify-Instruct synthesis for this project, however, most of the tokens in capybara within those given sections are novel tokens not present in any of the seed datasets.
Datasets in Blue are in-house curations that previously existed prior to Capybara, and were now used as seeds for Capybara.
!Capybara
## Dataset contamination.
We have checked the capybara dataset for contamination for several of the most popular benchmarks and can confirm that there is no contaminaton found besides MT-bench which is now cleaned out.
We leveraged minhash to check for 100%, 99%, 98% and 97% similarity matches between our data and the questions and answers in benchmarks, we found no exact matches, nor did we find any matches down to the 97% similarity level.
The following are benchmarks we checked for contamination against our dataset:
- HumanEval
- AGIEval
- TruthfulQA
- MMLU
- GPT4All
*Newly cleaned out as of 12/15/2023 - MT-bench
## Credits
During the curation process, there can be some relatively arduos steps when it comes to actually executing on the best experimentation or concepts for how to filter examples out.
Luckily there is folks over at Nous Research that helped with expediting these processes, big thank you to J-Supha specifically for making these types of significant contributions.
## Example Outputs from the Llama-2 7B model trained on this dataset:
!Capybara
!Capybara
!Capybara
## Future Plans & How you can help!
This is a relatively early build amongst the grand plans for the future of what I plan to work on!
In the near future we plan on leveraging the help of domain specific expert volunteers to eliminate any mathematically/verifiably incorrect answers from training curations of different types of datasets.
If you have at-least a bachelors in mathematics, physics, biology or chemistry and would like to volunteer even just 30 minutes of your expertise time, please contact LDJ on discord!
Citation:
| [
"## This is the Official Capybara dataset. Over 10,000 multi-turn examples.\n\nCapybara is the culmination of insights derived from synthesis techniques like Evol-instruct (used for WizardLM), Alpaca, Orca, Vicuna, Lamini, FLASK and others.\nThe single-turn seeds used to intiate the Amplify-Instruct synthesis of conversations are mostly based on datasets that i've personally vetted extensively, and are often highly regarded for their diversity and demonstration of logical robustness and prose, such as Airoboros, Know logic, EverythingLM, GPTeacher and even entirely new seed instructions derived from different sources, including certain in-house multi-turn datasets like Dove and Verified-Camel(A successor to Puffin).\n\nThe multi-turn synthetic conversation generation method is what i'm calling Amplify-Instruct, and the first resulting dataset using this method is called Capybara. \nThis dataset has a strong focus on information diversity across a wide range of domains, and multi-turn conversations that strongly emphasize reasoning, logic and extrapolation about a wide range of subjects, also many great examples of conversations delving into obscure sub-topics and rabbit holes across pop-culture and STEM, while also maintaining natural prose.\nWhile performing great in it's current state, the current dataset used for fine-tuning is entirely contained within 20K training examples, this is 10 times smaller than many similar performing datasets, this is signficant when it comes to scaling implications once I decide to scale the use of Amplify-Instruct to significantly more examples.\n\n - Most tokens contained in this dataset are newly synthesized and did not exist prior online.\n\n - This leverages the Amplify-Instruct method(paper coming soon) to grow thousands of high-quality single-turn seeds into advanced and in-depth multi-turn conversations.\n\n - Average context length per conversation is over 1,000 tokens and 3 turns or more per example (most instruction/chat datasets on HF for fine-tuning are only 1 turn)\n\n - Each conversation is optimized to amplify the natural raw knowledge capabilities of the model, as well as delving deep into obscure and advanced topics.\n\n - Aggresively filtered to remove any and all possible examples of overt moralizing/alignment, and common undesirable behaviours such as \"as an AI language model\" and \"September 2021\" and \"I don't have personal beliefs\"",
"## Benchmarks.\n\n- Resulting benchmarks are available on HF Leaderboard, and other benchmarks done as well such as AGIEval, Bigbench and GPT4All. \n- (The only Capybara model available on all of these benchmarks including HF leaderboard is Capybara V1, trained on Llama-2)\n- The below benchmarks are compared against fine-tunes also done on Llama-2.\n\n!Capybara\n\n!Capybara",
"## Quality filtering and cleaning.\n\n - Extensive measures were done to filter out any conversations that contained even a single instance of overt AI moralizing/alignment, such as \"As an AI language model\" and common undesirable behaviours such as conversations that include \"September 2021\" and \"I don't have personal beliefs\" and other phrases I've found to be highly correlated with undesirable responses and conversation paths.",
"## Thank you to those of you that have indirectly contributed!\n\nWhile most of the tokens within Capybara are newly synthsized and part of datasets like Puffin/Dove, we would like to credit the single-turn datasets we leveraged as seeds, which were used to generate the multi-turn data.\n\nThe datasets shown in green below are datasets that we sampled from to curate seeds that are used during Amplify-Instruct synthesis for this project, however, most of the tokens in capybara within those given sections are novel tokens not present in any of the seed datasets.\n\nDatasets in Blue are in-house curations that previously existed prior to Capybara, and were now used as seeds for Capybara.\n\n!Capybara",
"## Dataset contamination.\n\nWe have checked the capybara dataset for contamination for several of the most popular benchmarks and can confirm that there is no contaminaton found besides MT-bench which is now cleaned out.\n\nWe leveraged minhash to check for 100%, 99%, 98% and 97% similarity matches between our data and the questions and answers in benchmarks, we found no exact matches, nor did we find any matches down to the 97% similarity level.\n\nThe following are benchmarks we checked for contamination against our dataset:\n\n- HumanEval\n\n- AGIEval\n\n- TruthfulQA\n\n- MMLU\n\n- GPT4All\n\n*Newly cleaned out as of 12/15/2023 - MT-bench",
"## Credits\n\nDuring the curation process, there can be some relatively arduos steps when it comes to actually executing on the best experimentation or concepts for how to filter examples out.\n\nLuckily there is folks over at Nous Research that helped with expediting these processes, big thank you to J-Supha specifically for making these types of significant contributions.",
"## Example Outputs from the Llama-2 7B model trained on this dataset:\n\n!Capybara\n\n!Capybara\n\n!Capybara",
"## Future Plans & How you can help!\n\nThis is a relatively early build amongst the grand plans for the future of what I plan to work on! \n\nIn the near future we plan on leveraging the help of domain specific expert volunteers to eliminate any mathematically/verifiably incorrect answers from training curations of different types of datasets.\n\nIf you have at-least a bachelors in mathematics, physics, biology or chemistry and would like to volunteer even just 30 minutes of your expertise time, please contact LDJ on discord!\n\nCitation:"
] | [
"TAGS\n#task_categories-conversational #task_categories-question-answering #task_categories-text-generation #size_categories-10K<n<100K #language-English #license-apache-2.0 #Physics #Biology #Math #Chemistry #Culture #Logic #Roleplay #region-us \n",
"## This is the Official Capybara dataset. Over 10,000 multi-turn examples.\n\nCapybara is the culmination of insights derived from synthesis techniques like Evol-instruct (used for WizardLM), Alpaca, Orca, Vicuna, Lamini, FLASK and others.\nThe single-turn seeds used to intiate the Amplify-Instruct synthesis of conversations are mostly based on datasets that i've personally vetted extensively, and are often highly regarded for their diversity and demonstration of logical robustness and prose, such as Airoboros, Know logic, EverythingLM, GPTeacher and even entirely new seed instructions derived from different sources, including certain in-house multi-turn datasets like Dove and Verified-Camel(A successor to Puffin).\n\nThe multi-turn synthetic conversation generation method is what i'm calling Amplify-Instruct, and the first resulting dataset using this method is called Capybara. \nThis dataset has a strong focus on information diversity across a wide range of domains, and multi-turn conversations that strongly emphasize reasoning, logic and extrapolation about a wide range of subjects, also many great examples of conversations delving into obscure sub-topics and rabbit holes across pop-culture and STEM, while also maintaining natural prose.\nWhile performing great in it's current state, the current dataset used for fine-tuning is entirely contained within 20K training examples, this is 10 times smaller than many similar performing datasets, this is signficant when it comes to scaling implications once I decide to scale the use of Amplify-Instruct to significantly more examples.\n\n - Most tokens contained in this dataset are newly synthesized and did not exist prior online.\n\n - This leverages the Amplify-Instruct method(paper coming soon) to grow thousands of high-quality single-turn seeds into advanced and in-depth multi-turn conversations.\n\n - Average context length per conversation is over 1,000 tokens and 3 turns or more per example (most instruction/chat datasets on HF for fine-tuning are only 1 turn)\n\n - Each conversation is optimized to amplify the natural raw knowledge capabilities of the model, as well as delving deep into obscure and advanced topics.\n\n - Aggresively filtered to remove any and all possible examples of overt moralizing/alignment, and common undesirable behaviours such as \"as an AI language model\" and \"September 2021\" and \"I don't have personal beliefs\"",
"## Benchmarks.\n\n- Resulting benchmarks are available on HF Leaderboard, and other benchmarks done as well such as AGIEval, Bigbench and GPT4All. \n- (The only Capybara model available on all of these benchmarks including HF leaderboard is Capybara V1, trained on Llama-2)\n- The below benchmarks are compared against fine-tunes also done on Llama-2.\n\n!Capybara\n\n!Capybara",
"## Quality filtering and cleaning.\n\n - Extensive measures were done to filter out any conversations that contained even a single instance of overt AI moralizing/alignment, such as \"As an AI language model\" and common undesirable behaviours such as conversations that include \"September 2021\" and \"I don't have personal beliefs\" and other phrases I've found to be highly correlated with undesirable responses and conversation paths.",
"## Thank you to those of you that have indirectly contributed!\n\nWhile most of the tokens within Capybara are newly synthsized and part of datasets like Puffin/Dove, we would like to credit the single-turn datasets we leveraged as seeds, which were used to generate the multi-turn data.\n\nThe datasets shown in green below are datasets that we sampled from to curate seeds that are used during Amplify-Instruct synthesis for this project, however, most of the tokens in capybara within those given sections are novel tokens not present in any of the seed datasets.\n\nDatasets in Blue are in-house curations that previously existed prior to Capybara, and were now used as seeds for Capybara.\n\n!Capybara",
"## Dataset contamination.\n\nWe have checked the capybara dataset for contamination for several of the most popular benchmarks and can confirm that there is no contaminaton found besides MT-bench which is now cleaned out.\n\nWe leveraged minhash to check for 100%, 99%, 98% and 97% similarity matches between our data and the questions and answers in benchmarks, we found no exact matches, nor did we find any matches down to the 97% similarity level.\n\nThe following are benchmarks we checked for contamination against our dataset:\n\n- HumanEval\n\n- AGIEval\n\n- TruthfulQA\n\n- MMLU\n\n- GPT4All\n\n*Newly cleaned out as of 12/15/2023 - MT-bench",
"## Credits\n\nDuring the curation process, there can be some relatively arduos steps when it comes to actually executing on the best experimentation or concepts for how to filter examples out.\n\nLuckily there is folks over at Nous Research that helped with expediting these processes, big thank you to J-Supha specifically for making these types of significant contributions.",
"## Example Outputs from the Llama-2 7B model trained on this dataset:\n\n!Capybara\n\n!Capybara\n\n!Capybara",
"## Future Plans & How you can help!\n\nThis is a relatively early build amongst the grand plans for the future of what I plan to work on! \n\nIn the near future we plan on leveraging the help of domain specific expert volunteers to eliminate any mathematically/verifiably incorrect answers from training curations of different types of datasets.\n\nIf you have at-least a bachelors in mathematics, physics, biology or chemistry and would like to volunteer even just 30 minutes of your expertise time, please contact LDJ on discord!\n\nCitation:"
] | [
87,
590,
101,
101,
186,
160,
78,
33,
127
] | [
"passage: TAGS\n#task_categories-conversational #task_categories-question-answering #task_categories-text-generation #size_categories-10K<n<100K #language-English #license-apache-2.0 #Physics #Biology #Math #Chemistry #Culture #Logic #Roleplay #region-us \n",
"passage: ## This is the Official Capybara dataset. Over 10,000 multi-turn examples.\n\nCapybara is the culmination of insights derived from synthesis techniques like Evol-instruct (used for WizardLM), Alpaca, Orca, Vicuna, Lamini, FLASK and others.\nThe single-turn seeds used to intiate the Amplify-Instruct synthesis of conversations are mostly based on datasets that i've personally vetted extensively, and are often highly regarded for their diversity and demonstration of logical robustness and prose, such as Airoboros, Know logic, EverythingLM, GPTeacher and even entirely new seed instructions derived from different sources, including certain in-house multi-turn datasets like Dove and Verified-Camel(A successor to Puffin).\n\nThe multi-turn synthetic conversation generation method is what i'm calling Amplify-Instruct, and the first resulting dataset using this method is called Capybara. \nThis dataset has a strong focus on information diversity across a wide range of domains, and multi-turn conversations that strongly emphasize reasoning, logic and extrapolation about a wide range of subjects, also many great examples of conversations delving into obscure sub-topics and rabbit holes across pop-culture and STEM, while also maintaining natural prose.\nWhile performing great in it's current state, the current dataset used for fine-tuning is entirely contained within 20K training examples, this is 10 times smaller than many similar performing datasets, this is signficant when it comes to scaling implications once I decide to scale the use of Amplify-Instruct to significantly more examples.\n\n - Most tokens contained in this dataset are newly synthesized and did not exist prior online.\n\n - This leverages the Amplify-Instruct method(paper coming soon) to grow thousands of high-quality single-turn seeds into advanced and in-depth multi-turn conversations.\n\n - Average context length per conversation is over 1,000 tokens and 3 turns or more per example (most instruction/chat datasets on HF for fine-tuning are only 1 turn)\n\n - Each conversation is optimized to amplify the natural raw knowledge capabilities of the model, as well as delving deep into obscure and advanced topics.\n\n - Aggresively filtered to remove any and all possible examples of overt moralizing/alignment, and common undesirable behaviours such as \"as an AI language model\" and \"September 2021\" and \"I don't have personal beliefs\"## Benchmarks.\n\n- Resulting benchmarks are available on HF Leaderboard, and other benchmarks done as well such as AGIEval, Bigbench and GPT4All. \n- (The only Capybara model available on all of these benchmarks including HF leaderboard is Capybara V1, trained on Llama-2)\n- The below benchmarks are compared against fine-tunes also done on Llama-2.\n\n!Capybara\n\n!Capybara## Quality filtering and cleaning.\n\n - Extensive measures were done to filter out any conversations that contained even a single instance of overt AI moralizing/alignment, such as \"As an AI language model\" and common undesirable behaviours such as conversations that include \"September 2021\" and \"I don't have personal beliefs\" and other phrases I've found to be highly correlated with undesirable responses and conversation paths.## Thank you to those of you that have indirectly contributed!\n\nWhile most of the tokens within Capybara are newly synthsized and part of datasets like Puffin/Dove, we would like to credit the single-turn datasets we leveraged as seeds, which were used to generate the multi-turn data.\n\nThe datasets shown in green below are datasets that we sampled from to curate seeds that are used during Amplify-Instruct synthesis for this project, however, most of the tokens in capybara within those given sections are novel tokens not present in any of the seed datasets.\n\nDatasets in Blue are in-house curations that previously existed prior to Capybara, and were now used as seeds for Capybara.\n\n!Capybara"
] |
eac7162b7d52df1f7683b54168032dbe9d5fa5eb | # Dataset Card for Dataset Name
Paralell sentences in latin/greek and english
## Dataset Details
### Dataset Description
This is a very preliminary dataset of paralell sentences used for educational purposes to finetune PhilTa and create the rudimentary Ericu950/lagrc-enTransPrel
- **Curated by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
### Dataset Sources [optional]
<!-- Provide the basic links for the dataset. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the dataset is intended to be used. -->
### Direct Use
<!-- This section describes suitable use cases for the dataset. -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the dataset will not work well for. -->
[More Information Needed]
## Dataset Structure
<!-- This section provides a description of the dataset fields, and additional information about the dataset structure such as criteria used to create the splits, relationships between data points, etc. -->
[More Information Needed]
## Dataset Creation
### Curation Rationale
<!-- Motivation for the creation of this dataset. -->
[More Information Needed]
### Source Data
<!-- This section describes the source data (e.g. news text and headlines, social media posts, translated sentences, ...). -->
#### Data Collection and Processing
<!-- This section describes the data collection and processing process such as data selection criteria, filtering and normalization methods, tools and libraries used, etc. -->
[More Information Needed]
#### Who are the source data producers?
<!-- This section describes the people or systems who originally created the data. It should also include self-reported demographic or identity information for the source data creators if this information is available. -->
[More Information Needed]
### Annotations [optional]
<!-- If the dataset contains annotations which are not part of the initial data collection, use this section to describe them. -->
#### Annotation process
<!-- This section describes the annotation process such as annotation tools used in the process, the amount of data annotated, annotation guidelines provided to the annotators, interannotator statistics, annotation validation, etc. -->
[More Information Needed]
#### Who are the annotators?
<!-- This section describes the people or systems who created the annotations. -->
[More Information Needed]
#### Personal and Sensitive Information
<!-- State whether the dataset contains data that might be considered personal, sensitive, or private (e.g., data that reveals addresses, uniquely identifiable names or aliases, racial or ethnic origins, sexual orientations, religious beliefs, political opinions, financial or health data, etc.). If efforts were made to anonymize the data, describe the anonymization process. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.
## Citation [optional]
<!-- If there is a paper or blog post introducing the dataset, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the dataset or dataset card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Dataset Card Authors [optional]
[More Information Needed]
## Dataset Card Contact
[More Information Needed] | Ericu950/ParaLoebSent | [
"task_categories:translation",
"size_categories:10K<n<100K",
"language:la",
"language:el",
"language:en",
"region:us"
] | 2023-12-16T06:40:43+00:00 | {"language": ["la", "el", "en"], "size_categories": ["10K<n<100K"], "task_categories": ["translation"]} | 2023-12-18T12:50:52+00:00 | [] | [
"la",
"el",
"en"
] | TAGS
#task_categories-translation #size_categories-10K<n<100K #language-Latin #language-Modern Greek (1453-) #language-English #region-us
| # Dataset Card for Dataset Name
Paralell sentences in latin/greek and english
## Dataset Details
### Dataset Description
This is a very preliminary dataset of paralell sentences used for educational purposes to finetune PhilTa and create the rudimentary Ericu950/lagrc-enTransPrel
- Curated by:
- Funded by [optional]:
- Shared by [optional]:
- Language(s) (NLP):
- License:
### Dataset Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Out-of-Scope Use
## Dataset Structure
## Dataset Creation
### Curation Rationale
### Source Data
#### Data Collection and Processing
#### Who are the source data producers?
### Annotations [optional]
#### Annotation process
#### Who are the annotators?
#### Personal and Sensitive Information
## Bias, Risks, and Limitations
### Recommendations
Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Dataset Card Authors [optional]
## Dataset Card Contact
| [
"# Dataset Card for Dataset Name\n\nParalell sentences in latin/greek and english",
"## Dataset Details",
"### Dataset Description\n\nThis is a very preliminary dataset of paralell sentences used for educational purposes to finetune PhilTa and create the rudimentary Ericu950/lagrc-enTransPrel\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:",
"### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Out-of-Scope Use",
"## Dataset Structure",
"## Dataset Creation",
"### Curation Rationale",
"### Source Data",
"#### Data Collection and Processing",
"#### Who are the source data producers?",
"### Annotations [optional]",
"#### Annotation process",
"#### Who are the annotators?",
"#### Personal and Sensitive Information",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Dataset Card Authors [optional]",
"## Dataset Card Contact"
] | [
"TAGS\n#task_categories-translation #size_categories-10K<n<100K #language-Latin #language-Modern Greek (1453-) #language-English #region-us \n",
"# Dataset Card for Dataset Name\n\nParalell sentences in latin/greek and english",
"## Dataset Details",
"### Dataset Description\n\nThis is a very preliminary dataset of paralell sentences used for educational purposes to finetune PhilTa and create the rudimentary Ericu950/lagrc-enTransPrel\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:",
"### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Out-of-Scope Use",
"## Dataset Structure",
"## Dataset Creation",
"### Curation Rationale",
"### Source Data",
"#### Data Collection and Processing",
"#### Who are the source data producers?",
"### Annotations [optional]",
"#### Annotation process",
"#### Who are the annotators?",
"#### Personal and Sensitive Information",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Dataset Card Authors [optional]",
"## Dataset Card Contact"
] | [
46,
20,
4,
81,
29,
3,
4,
9,
6,
5,
7,
4,
7,
10,
9,
5,
9,
8,
10,
46,
8,
7,
10,
5
] | [
"passage: TAGS\n#task_categories-translation #size_categories-10K<n<100K #language-Latin #language-Modern Greek (1453-) #language-English #region-us \n# Dataset Card for Dataset Name\n\nParalell sentences in latin/greek and english## Dataset Details### Dataset Description\n\nThis is a very preliminary dataset of paralell sentences used for educational purposes to finetune PhilTa and create the rudimentary Ericu950/lagrc-enTransPrel\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Out-of-Scope Use## Dataset Structure## Dataset Creation### Curation Rationale### Source Data#### Data Collection and Processing#### Who are the source data producers?### Annotations [optional]#### Annotation process#### Who are the annotators?#### Personal and Sensitive Information## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Dataset Card Authors [optional]## Dataset Card Contact"
] |
63cf7198ab60f5d84b6e6c8bf3e85c89596ef9e7 |
# Dataset of shirayuki (Arknights)
This is the dataset of shirayuki (Arknights), containing 58 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by [DeepGHS Team](https://github.com/deepghs)([huggingface organization](https://huggingface.co/deepghs)).
This is a WebUI contains crawlers and other thing: ([LittleAppleWebUI](https://github.com/LittleApple-fp16/LittleAppleWebUI))
| Name | Images | Download | Description |
|:----------------|---------:|:----------------------------------------|:-----------------------------------------------------------------------------------------|
| raw | 58 | [Download](dataset-raw.zip) | Raw data with meta information. |
| raw-stage3 | 151 | [Download](dataset-raw-stage3.zip) | 3-stage cropped raw data with meta information. |
| raw-stage3-eyes | 167 | [Download](dataset-raw-stage3-eyes.zip) | 3-stage cropped (with eye-focus) raw data with meta information. |
| 384x512 | 58 | [Download](dataset-384x512.zip) | 384x512 aligned dataset. |
| 512x704 | 58 | [Download](dataset-512x704.zip) | 512x704 aligned dataset. |
| 640x880 | 58 | [Download](dataset-640x880.zip) | 640x880 aligned dataset. |
| stage3-640 | 151 | [Download](dataset-stage3-640.zip) | 3-stage cropped dataset with the shorter side not exceeding 640 pixels. |
| stage3-800 | 151 | [Download](dataset-stage3-800.zip) | 3-stage cropped dataset with the shorter side not exceeding 800 pixels. |
| stage3-p512-640 | 132 | [Download](dataset-stage3-p512-640.zip) | 3-stage cropped dataset with the area not less than 512x512 pixels. |
| stage3-eyes-640 | 167 | [Download](dataset-stage3-eyes-640.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 640 pixels. |
| stage3-eyes-800 | 167 | [Download](dataset-stage3-eyes-800.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 800 pixels. |
| AppleHarem/shirayuki_arknights | [
"task_categories:text-to-image",
"size_categories:n<1K",
"license:mit",
"art",
"not-for-all-audiences",
"region:us"
] | 2023-12-16T07:13:52+00:00 | {"license": "mit", "size_categories": ["n<1K"], "task_categories": ["text-to-image"], "tags": ["art", "not-for-all-audiences"]} | 2023-12-16T07:13:58+00:00 | [] | [] | TAGS
#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us
| Dataset of shirayuki (Arknights)
================================
This is the dataset of shirayuki (Arknights), containing 58 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by DeepGHS Team(huggingface organization).
This is a WebUI contains crawlers and other thing: (LittleAppleWebUI)
| [] | [
"TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] | [
44
] | [
"passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] |
a1105c1d7345c9eaff403b403cc2c7441af76bdd |
# Dataset of courier (Arknights)
This is the dataset of courier (Arknights), containing 34 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by [DeepGHS Team](https://github.com/deepghs)([huggingface organization](https://huggingface.co/deepghs)).
This is a WebUI contains crawlers and other thing: ([LittleAppleWebUI](https://github.com/LittleApple-fp16/LittleAppleWebUI))
| Name | Images | Download | Description |
|:----------------|---------:|:----------------------------------------|:-----------------------------------------------------------------------------------------|
| raw | 34 | [Download](dataset-raw.zip) | Raw data with meta information. |
| raw-stage3 | 91 | [Download](dataset-raw-stage3.zip) | 3-stage cropped raw data with meta information. |
| raw-stage3-eyes | 100 | [Download](dataset-raw-stage3-eyes.zip) | 3-stage cropped (with eye-focus) raw data with meta information. |
| 384x512 | 34 | [Download](dataset-384x512.zip) | 384x512 aligned dataset. |
| 512x704 | 34 | [Download](dataset-512x704.zip) | 512x704 aligned dataset. |
| 640x880 | 34 | [Download](dataset-640x880.zip) | 640x880 aligned dataset. |
| stage3-640 | 91 | [Download](dataset-stage3-640.zip) | 3-stage cropped dataset with the shorter side not exceeding 640 pixels. |
| stage3-800 | 91 | [Download](dataset-stage3-800.zip) | 3-stage cropped dataset with the shorter side not exceeding 800 pixels. |
| stage3-p512-640 | 73 | [Download](dataset-stage3-p512-640.zip) | 3-stage cropped dataset with the area not less than 512x512 pixels. |
| stage3-eyes-640 | 100 | [Download](dataset-stage3-eyes-640.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 640 pixels. |
| stage3-eyes-800 | 100 | [Download](dataset-stage3-eyes-800.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 800 pixels. |
| AppleHarem/courier_arknights | [
"task_categories:text-to-image",
"size_categories:n<1K",
"license:mit",
"art",
"not-for-all-audiences",
"region:us"
] | 2023-12-16T08:10:42+00:00 | {"license": "mit", "size_categories": ["n<1K"], "task_categories": ["text-to-image"], "tags": ["art", "not-for-all-audiences"]} | 2023-12-16T08:10:46+00:00 | [] | [] | TAGS
#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us
| Dataset of courier (Arknights)
==============================
This is the dataset of courier (Arknights), containing 34 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by DeepGHS Team(huggingface organization).
This is a WebUI contains crawlers and other thing: (LittleAppleWebUI)
| [] | [
"TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] | [
44
] | [
"passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] |
1c853af17cf92c4b0cbda0de5d4a223c51db1c4f |
# Dataset Card for Evaluation run of TheBloke/Mixtral-8x7B-v0.1-GPTQ
<!-- Provide a quick summary of the dataset. -->
Dataset automatically created during the evaluation run of model [TheBloke/Mixtral-8x7B-v0.1-GPTQ](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GPTQ) on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
The dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An additional configuration "results" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).
To load the details from a run, you can for instance do the following:
```python
from datasets import load_dataset
data = load_dataset("open-llm-leaderboard/details_TheBloke__Mixtral-8x7B-v0.1-GPTQ",
"harness_winogrande_5",
split="train")
```
## Latest results
These are the [latest results from run 2023-12-16T08:25:08.853393](https://huggingface.co/datasets/open-llm-leaderboard/details_TheBloke__Mixtral-8x7B-v0.1-GPTQ/blob/main/results_2023-12-16T08-25-08.853393.json)(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the "latest" split for each eval):
```python
{
"all": {
"acc": 0.6905952821572917,
"acc_stderr": 0.030759474803252005,
"acc_norm": 0.696151240116133,
"acc_norm_stderr": 0.03135740142119605,
"mc1": 0.2998776009791922,
"mc1_stderr": 0.016040352966713616,
"mc2": 0.4543006274006171,
"mc2_stderr": 0.014099486144642947
},
"harness|arc:challenge|25": {
"acc": 0.6168941979522184,
"acc_stderr": 0.014206472661672883,
"acc_norm": 0.6518771331058021,
"acc_norm_stderr": 0.013921008595179347
},
"harness|hellaswag|10": {
"acc": 0.6413065126468831,
"acc_stderr": 0.004786368011500458,
"acc_norm": 0.8472415853415655,
"acc_norm_stderr": 0.0035901923719696637
},
"harness|hendrycksTest-abstract_algebra|5": {
"acc": 0.35,
"acc_stderr": 0.047937248544110196,
"acc_norm": 0.35,
"acc_norm_stderr": 0.047937248544110196
},
"harness|hendrycksTest-anatomy|5": {
"acc": 0.6666666666666666,
"acc_stderr": 0.04072314811876837,
"acc_norm": 0.6666666666666666,
"acc_norm_stderr": 0.04072314811876837
},
"harness|hendrycksTest-astronomy|5": {
"acc": 0.7631578947368421,
"acc_stderr": 0.034597776068105365,
"acc_norm": 0.7631578947368421,
"acc_norm_stderr": 0.034597776068105365
},
"harness|hendrycksTest-business_ethics|5": {
"acc": 0.68,
"acc_stderr": 0.046882617226215034,
"acc_norm": 0.68,
"acc_norm_stderr": 0.046882617226215034
},
"harness|hendrycksTest-clinical_knowledge|5": {
"acc": 0.7547169811320755,
"acc_stderr": 0.0264803571798957,
"acc_norm": 0.7547169811320755,
"acc_norm_stderr": 0.0264803571798957
},
"harness|hendrycksTest-college_biology|5": {
"acc": 0.8194444444444444,
"acc_stderr": 0.03216600808802269,
"acc_norm": 0.8194444444444444,
"acc_norm_stderr": 0.03216600808802269
},
"harness|hendrycksTest-college_chemistry|5": {
"acc": 0.49,
"acc_stderr": 0.05024183937956911,
"acc_norm": 0.49,
"acc_norm_stderr": 0.05024183937956911
},
"harness|hendrycksTest-college_computer_science|5": {
"acc": 0.53,
"acc_stderr": 0.050161355804659205,
"acc_norm": 0.53,
"acc_norm_stderr": 0.050161355804659205
},
"harness|hendrycksTest-college_mathematics|5": {
"acc": 0.55,
"acc_stderr": 0.05,
"acc_norm": 0.55,
"acc_norm_stderr": 0.05
},
"harness|hendrycksTest-college_medicine|5": {
"acc": 0.6647398843930635,
"acc_stderr": 0.03599586301247077,
"acc_norm": 0.6647398843930635,
"acc_norm_stderr": 0.03599586301247077
},
"harness|hendrycksTest-college_physics|5": {
"acc": 0.49019607843137253,
"acc_stderr": 0.04974229460422817,
"acc_norm": 0.49019607843137253,
"acc_norm_stderr": 0.04974229460422817
},
"harness|hendrycksTest-computer_security|5": {
"acc": 0.79,
"acc_stderr": 0.040936018074033256,
"acc_norm": 0.79,
"acc_norm_stderr": 0.040936018074033256
},
"harness|hendrycksTest-conceptual_physics|5": {
"acc": 0.6425531914893617,
"acc_stderr": 0.031329417894764254,
"acc_norm": 0.6425531914893617,
"acc_norm_stderr": 0.031329417894764254
},
"harness|hendrycksTest-econometrics|5": {
"acc": 0.543859649122807,
"acc_stderr": 0.046854730419077895,
"acc_norm": 0.543859649122807,
"acc_norm_stderr": 0.046854730419077895
},
"harness|hendrycksTest-electrical_engineering|5": {
"acc": 0.6620689655172414,
"acc_stderr": 0.039417076320648906,
"acc_norm": 0.6620689655172414,
"acc_norm_stderr": 0.039417076320648906
},
"harness|hendrycksTest-elementary_mathematics|5": {
"acc": 0.4576719576719577,
"acc_stderr": 0.02565886886205832,
"acc_norm": 0.4576719576719577,
"acc_norm_stderr": 0.02565886886205832
},
"harness|hendrycksTest-formal_logic|5": {
"acc": 0.4603174603174603,
"acc_stderr": 0.04458029125470973,
"acc_norm": 0.4603174603174603,
"acc_norm_stderr": 0.04458029125470973
},
"harness|hendrycksTest-global_facts|5": {
"acc": 0.44,
"acc_stderr": 0.04988876515698589,
"acc_norm": 0.44,
"acc_norm_stderr": 0.04988876515698589
},
"harness|hendrycksTest-high_school_biology|5": {
"acc": 0.8290322580645161,
"acc_stderr": 0.021417242936321582,
"acc_norm": 0.8290322580645161,
"acc_norm_stderr": 0.021417242936321582
},
"harness|hendrycksTest-high_school_chemistry|5": {
"acc": 0.5960591133004927,
"acc_stderr": 0.03452453903822033,
"acc_norm": 0.5960591133004927,
"acc_norm_stderr": 0.03452453903822033
},
"harness|hendrycksTest-high_school_computer_science|5": {
"acc": 0.72,
"acc_stderr": 0.045126085985421276,
"acc_norm": 0.72,
"acc_norm_stderr": 0.045126085985421276
},
"harness|hendrycksTest-high_school_european_history|5": {
"acc": 0.7878787878787878,
"acc_stderr": 0.031922715695482995,
"acc_norm": 0.7878787878787878,
"acc_norm_stderr": 0.031922715695482995
},
"harness|hendrycksTest-high_school_geography|5": {
"acc": 0.8383838383838383,
"acc_stderr": 0.02622591986362928,
"acc_norm": 0.8383838383838383,
"acc_norm_stderr": 0.02622591986362928
},
"harness|hendrycksTest-high_school_government_and_politics|5": {
"acc": 0.9067357512953368,
"acc_stderr": 0.02098685459328972,
"acc_norm": 0.9067357512953368,
"acc_norm_stderr": 0.02098685459328972
},
"harness|hendrycksTest-high_school_macroeconomics|5": {
"acc": 0.6666666666666666,
"acc_stderr": 0.023901157979402534,
"acc_norm": 0.6666666666666666,
"acc_norm_stderr": 0.023901157979402534
},
"harness|hendrycksTest-high_school_mathematics|5": {
"acc": 0.34074074074074073,
"acc_stderr": 0.02889774874113114,
"acc_norm": 0.34074074074074073,
"acc_norm_stderr": 0.02889774874113114
},
"harness|hendrycksTest-high_school_microeconomics|5": {
"acc": 0.7563025210084033,
"acc_stderr": 0.027886828078380558,
"acc_norm": 0.7563025210084033,
"acc_norm_stderr": 0.027886828078380558
},
"harness|hendrycksTest-high_school_physics|5": {
"acc": 0.44370860927152317,
"acc_stderr": 0.04056527902281732,
"acc_norm": 0.44370860927152317,
"acc_norm_stderr": 0.04056527902281732
},
"harness|hendrycksTest-high_school_psychology|5": {
"acc": 0.8752293577981651,
"acc_stderr": 0.014168298359156327,
"acc_norm": 0.8752293577981651,
"acc_norm_stderr": 0.014168298359156327
},
"harness|hendrycksTest-high_school_statistics|5": {
"acc": 0.625,
"acc_stderr": 0.033016908987210894,
"acc_norm": 0.625,
"acc_norm_stderr": 0.033016908987210894
},
"harness|hendrycksTest-high_school_us_history|5": {
"acc": 0.8480392156862745,
"acc_stderr": 0.025195658428931785,
"acc_norm": 0.8480392156862745,
"acc_norm_stderr": 0.025195658428931785
},
"harness|hendrycksTest-high_school_world_history|5": {
"acc": 0.8481012658227848,
"acc_stderr": 0.02336387809663245,
"acc_norm": 0.8481012658227848,
"acc_norm_stderr": 0.02336387809663245
},
"harness|hendrycksTest-human_aging|5": {
"acc": 0.726457399103139,
"acc_stderr": 0.029918586707798824,
"acc_norm": 0.726457399103139,
"acc_norm_stderr": 0.029918586707798824
},
"harness|hendrycksTest-human_sexuality|5": {
"acc": 0.8473282442748091,
"acc_stderr": 0.031545216720054725,
"acc_norm": 0.8473282442748091,
"acc_norm_stderr": 0.031545216720054725
},
"harness|hendrycksTest-international_law|5": {
"acc": 0.8842975206611571,
"acc_stderr": 0.02919980245562281,
"acc_norm": 0.8842975206611571,
"acc_norm_stderr": 0.02919980245562281
},
"harness|hendrycksTest-jurisprudence|5": {
"acc": 0.8425925925925926,
"acc_stderr": 0.03520703990517965,
"acc_norm": 0.8425925925925926,
"acc_norm_stderr": 0.03520703990517965
},
"harness|hendrycksTest-logical_fallacies|5": {
"acc": 0.7607361963190185,
"acc_stderr": 0.0335195387952127,
"acc_norm": 0.7607361963190185,
"acc_norm_stderr": 0.0335195387952127
},
"harness|hendrycksTest-machine_learning|5": {
"acc": 0.5,
"acc_stderr": 0.04745789978762494,
"acc_norm": 0.5,
"acc_norm_stderr": 0.04745789978762494
},
"harness|hendrycksTest-management|5": {
"acc": 0.883495145631068,
"acc_stderr": 0.031766839486404075,
"acc_norm": 0.883495145631068,
"acc_norm_stderr": 0.031766839486404075
},
"harness|hendrycksTest-marketing|5": {
"acc": 0.9230769230769231,
"acc_stderr": 0.017456987872436183,
"acc_norm": 0.9230769230769231,
"acc_norm_stderr": 0.017456987872436183
},
"harness|hendrycksTest-medical_genetics|5": {
"acc": 0.79,
"acc_stderr": 0.040936018074033256,
"acc_norm": 0.79,
"acc_norm_stderr": 0.040936018074033256
},
"harness|hendrycksTest-miscellaneous|5": {
"acc": 0.8786717752234994,
"acc_stderr": 0.011675913883906723,
"acc_norm": 0.8786717752234994,
"acc_norm_stderr": 0.011675913883906723
},
"harness|hendrycksTest-moral_disputes|5": {
"acc": 0.7601156069364162,
"acc_stderr": 0.022989592543123563,
"acc_norm": 0.7601156069364162,
"acc_norm_stderr": 0.022989592543123563
},
"harness|hendrycksTest-moral_scenarios|5": {
"acc": 0.3743016759776536,
"acc_stderr": 0.01618544417945717,
"acc_norm": 0.3743016759776536,
"acc_norm_stderr": 0.01618544417945717
},
"harness|hendrycksTest-nutrition|5": {
"acc": 0.8104575163398693,
"acc_stderr": 0.02244235826333621,
"acc_norm": 0.8104575163398693,
"acc_norm_stderr": 0.02244235826333621
},
"harness|hendrycksTest-philosophy|5": {
"acc": 0.7717041800643086,
"acc_stderr": 0.023839303311398195,
"acc_norm": 0.7717041800643086,
"acc_norm_stderr": 0.023839303311398195
},
"harness|hendrycksTest-prehistory|5": {
"acc": 0.8148148148148148,
"acc_stderr": 0.021613809395224805,
"acc_norm": 0.8148148148148148,
"acc_norm_stderr": 0.021613809395224805
},
"harness|hendrycksTest-professional_accounting|5": {
"acc": 0.5709219858156028,
"acc_stderr": 0.029525914302558562,
"acc_norm": 0.5709219858156028,
"acc_norm_stderr": 0.029525914302558562
},
"harness|hendrycksTest-professional_law|5": {
"acc": 0.5071707953063885,
"acc_stderr": 0.012768922739553304,
"acc_norm": 0.5071707953063885,
"acc_norm_stderr": 0.012768922739553304
},
"harness|hendrycksTest-professional_medicine|5": {
"acc": 0.7683823529411765,
"acc_stderr": 0.025626533803777562,
"acc_norm": 0.7683823529411765,
"acc_norm_stderr": 0.025626533803777562
},
"harness|hendrycksTest-professional_psychology|5": {
"acc": 0.7418300653594772,
"acc_stderr": 0.01770453165325007,
"acc_norm": 0.7418300653594772,
"acc_norm_stderr": 0.01770453165325007
},
"harness|hendrycksTest-public_relations|5": {
"acc": 0.6818181818181818,
"acc_stderr": 0.044612721759105085,
"acc_norm": 0.6818181818181818,
"acc_norm_stderr": 0.044612721759105085
},
"harness|hendrycksTest-security_studies|5": {
"acc": 0.763265306122449,
"acc_stderr": 0.027212835884073142,
"acc_norm": 0.763265306122449,
"acc_norm_stderr": 0.027212835884073142
},
"harness|hendrycksTest-sociology|5": {
"acc": 0.8756218905472637,
"acc_stderr": 0.023335401790166327,
"acc_norm": 0.8756218905472637,
"acc_norm_stderr": 0.023335401790166327
},
"harness|hendrycksTest-us_foreign_policy|5": {
"acc": 0.9,
"acc_stderr": 0.030151134457776334,
"acc_norm": 0.9,
"acc_norm_stderr": 0.030151134457776334
},
"harness|hendrycksTest-virology|5": {
"acc": 0.4939759036144578,
"acc_stderr": 0.03892212195333045,
"acc_norm": 0.4939759036144578,
"acc_norm_stderr": 0.03892212195333045
},
"harness|hendrycksTest-world_religions|5": {
"acc": 0.8654970760233918,
"acc_stderr": 0.026168221344662297,
"acc_norm": 0.8654970760233918,
"acc_norm_stderr": 0.026168221344662297
},
"harness|truthfulqa:mc|0": {
"mc1": 0.2998776009791922,
"mc1_stderr": 0.016040352966713616,
"mc2": 0.4543006274006171,
"mc2_stderr": 0.014099486144642947
},
"harness|winogrande|5": {
"acc": 0.8113654301499605,
"acc_stderr": 0.010995172318019785
},
"harness|gsm8k|5": {
"acc": 0.4829416224412434,
"acc_stderr": 0.013764467123761316
}
}
```
## Dataset Details
### Dataset Description
<!-- Provide a longer summary of what this dataset is. -->
- **Curated by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
### Dataset Sources [optional]
<!-- Provide the basic links for the dataset. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the dataset is intended to be used. -->
### Direct Use
<!-- This section describes suitable use cases for the dataset. -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the dataset will not work well for. -->
[More Information Needed]
## Dataset Structure
<!-- This section provides a description of the dataset fields, and additional information about the dataset structure such as criteria used to create the splits, relationships between data points, etc. -->
[More Information Needed]
## Dataset Creation
### Curation Rationale
<!-- Motivation for the creation of this dataset. -->
[More Information Needed]
### Source Data
<!-- This section describes the source data (e.g. news text and headlines, social media posts, translated sentences, ...). -->
#### Data Collection and Processing
<!-- This section describes the data collection and processing process such as data selection criteria, filtering and normalization methods, tools and libraries used, etc. -->
[More Information Needed]
#### Who are the source data producers?
<!-- This section describes the people or systems who originally created the data. It should also include self-reported demographic or identity information for the source data creators if this information is available. -->
[More Information Needed]
### Annotations [optional]
<!-- If the dataset contains annotations which are not part of the initial data collection, use this section to describe them. -->
#### Annotation process
<!-- This section describes the annotation process such as annotation tools used in the process, the amount of data annotated, annotation guidelines provided to the annotators, interannotator statistics, annotation validation, etc. -->
[More Information Needed]
#### Who are the annotators?
<!-- This section describes the people or systems who created the annotations. -->
[More Information Needed]
#### Personal and Sensitive Information
<!-- State whether the dataset contains data that might be considered personal, sensitive, or private (e.g., data that reveals addresses, uniquely identifiable names or aliases, racial or ethnic origins, sexual orientations, religious beliefs, political opinions, financial or health data, etc.). If efforts were made to anonymize the data, describe the anonymization process. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.
## Citation [optional]
<!-- If there is a paper or blog post introducing the dataset, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the dataset or dataset card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Dataset Card Authors [optional]
[More Information Needed]
## Dataset Card Contact
[More Information Needed] | open-llm-leaderboard/details_TheBloke__Mixtral-8x7B-v0.1-GPTQ | [
"region:us"
] | 2023-12-16T08:28:03+00:00 | {"pretty_name": "Evaluation run of TheBloke/Mixtral-8x7B-v0.1-GPTQ", "dataset_summary": "Dataset automatically created during the evaluation run of model [TheBloke/Mixtral-8x7B-v0.1-GPTQ](https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GPTQ) on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).\n\nTo load the details from a run, you can for instance do the following:\n```python\nfrom datasets import load_dataset\ndata = load_dataset(\"open-llm-leaderboard/details_TheBloke__Mixtral-8x7B-v0.1-GPTQ\",\n\t\"harness_winogrande_5\",\n\tsplit=\"train\")\n```\n\n## Latest results\n\nThese are the [latest results from run 2023-12-16T08:25:08.853393](https://huggingface.co/datasets/open-llm-leaderboard/details_TheBloke__Mixtral-8x7B-v0.1-GPTQ/blob/main/results_2023-12-16T08-25-08.853393.json)(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):\n\n```python\n{\n \"all\": {\n \"acc\": 0.6905952821572917,\n \"acc_stderr\": 0.030759474803252005,\n \"acc_norm\": 0.696151240116133,\n \"acc_norm_stderr\": 0.03135740142119605,\n \"mc1\": 0.2998776009791922,\n \"mc1_stderr\": 0.016040352966713616,\n \"mc2\": 0.4543006274006171,\n \"mc2_stderr\": 0.014099486144642947\n },\n \"harness|arc:challenge|25\": {\n \"acc\": 0.6168941979522184,\n \"acc_stderr\": 0.014206472661672883,\n \"acc_norm\": 0.6518771331058021,\n \"acc_norm_stderr\": 0.013921008595179347\n },\n \"harness|hellaswag|10\": {\n \"acc\": 0.6413065126468831,\n \"acc_stderr\": 0.004786368011500458,\n \"acc_norm\": 0.8472415853415655,\n \"acc_norm_stderr\": 0.0035901923719696637\n },\n \"harness|hendrycksTest-abstract_algebra|5\": {\n \"acc\": 0.35,\n \"acc_stderr\": 0.047937248544110196,\n \"acc_norm\": 0.35,\n \"acc_norm_stderr\": 0.047937248544110196\n },\n \"harness|hendrycksTest-anatomy|5\": {\n \"acc\": 0.6666666666666666,\n \"acc_stderr\": 0.04072314811876837,\n \"acc_norm\": 0.6666666666666666,\n \"acc_norm_stderr\": 0.04072314811876837\n },\n \"harness|hendrycksTest-astronomy|5\": {\n \"acc\": 0.7631578947368421,\n \"acc_stderr\": 0.034597776068105365,\n \"acc_norm\": 0.7631578947368421,\n \"acc_norm_stderr\": 0.034597776068105365\n },\n \"harness|hendrycksTest-business_ethics|5\": {\n \"acc\": 0.68,\n \"acc_stderr\": 0.046882617226215034,\n \"acc_norm\": 0.68,\n \"acc_norm_stderr\": 0.046882617226215034\n },\n \"harness|hendrycksTest-clinical_knowledge|5\": {\n \"acc\": 0.7547169811320755,\n \"acc_stderr\": 0.0264803571798957,\n \"acc_norm\": 0.7547169811320755,\n \"acc_norm_stderr\": 0.0264803571798957\n },\n \"harness|hendrycksTest-college_biology|5\": {\n \"acc\": 0.8194444444444444,\n \"acc_stderr\": 0.03216600808802269,\n \"acc_norm\": 0.8194444444444444,\n \"acc_norm_stderr\": 0.03216600808802269\n },\n \"harness|hendrycksTest-college_chemistry|5\": {\n \"acc\": 0.49,\n \"acc_stderr\": 0.05024183937956911,\n \"acc_norm\": 0.49,\n \"acc_norm_stderr\": 0.05024183937956911\n },\n \"harness|hendrycksTest-college_computer_science|5\": {\n \"acc\": 0.53,\n \"acc_stderr\": 0.050161355804659205,\n \"acc_norm\": 0.53,\n \"acc_norm_stderr\": 0.050161355804659205\n },\n \"harness|hendrycksTest-college_mathematics|5\": {\n \"acc\": 0.55,\n \"acc_stderr\": 0.05,\n \"acc_norm\": 0.55,\n \"acc_norm_stderr\": 0.05\n },\n \"harness|hendrycksTest-college_medicine|5\": {\n \"acc\": 0.6647398843930635,\n \"acc_stderr\": 0.03599586301247077,\n \"acc_norm\": 0.6647398843930635,\n \"acc_norm_stderr\": 0.03599586301247077\n },\n \"harness|hendrycksTest-college_physics|5\": {\n \"acc\": 0.49019607843137253,\n \"acc_stderr\": 0.04974229460422817,\n \"acc_norm\": 0.49019607843137253,\n \"acc_norm_stderr\": 0.04974229460422817\n },\n \"harness|hendrycksTest-computer_security|5\": {\n \"acc\": 0.79,\n \"acc_stderr\": 0.040936018074033256,\n \"acc_norm\": 0.79,\n \"acc_norm_stderr\": 0.040936018074033256\n },\n \"harness|hendrycksTest-conceptual_physics|5\": {\n \"acc\": 0.6425531914893617,\n \"acc_stderr\": 0.031329417894764254,\n \"acc_norm\": 0.6425531914893617,\n \"acc_norm_stderr\": 0.031329417894764254\n },\n \"harness|hendrycksTest-econometrics|5\": {\n \"acc\": 0.543859649122807,\n \"acc_stderr\": 0.046854730419077895,\n \"acc_norm\": 0.543859649122807,\n \"acc_norm_stderr\": 0.046854730419077895\n },\n \"harness|hendrycksTest-electrical_engineering|5\": {\n \"acc\": 0.6620689655172414,\n \"acc_stderr\": 0.039417076320648906,\n \"acc_norm\": 0.6620689655172414,\n \"acc_norm_stderr\": 0.039417076320648906\n },\n \"harness|hendrycksTest-elementary_mathematics|5\": {\n \"acc\": 0.4576719576719577,\n \"acc_stderr\": 0.02565886886205832,\n \"acc_norm\": 0.4576719576719577,\n \"acc_norm_stderr\": 0.02565886886205832\n },\n \"harness|hendrycksTest-formal_logic|5\": {\n \"acc\": 0.4603174603174603,\n \"acc_stderr\": 0.04458029125470973,\n \"acc_norm\": 0.4603174603174603,\n \"acc_norm_stderr\": 0.04458029125470973\n },\n \"harness|hendrycksTest-global_facts|5\": {\n \"acc\": 0.44,\n \"acc_stderr\": 0.04988876515698589,\n \"acc_norm\": 0.44,\n \"acc_norm_stderr\": 0.04988876515698589\n },\n \"harness|hendrycksTest-high_school_biology|5\": {\n \"acc\": 0.8290322580645161,\n \"acc_stderr\": 0.021417242936321582,\n \"acc_norm\": 0.8290322580645161,\n \"acc_norm_stderr\": 0.021417242936321582\n },\n \"harness|hendrycksTest-high_school_chemistry|5\": {\n \"acc\": 0.5960591133004927,\n \"acc_stderr\": 0.03452453903822033,\n \"acc_norm\": 0.5960591133004927,\n \"acc_norm_stderr\": 0.03452453903822033\n },\n \"harness|hendrycksTest-high_school_computer_science|5\": {\n \"acc\": 0.72,\n \"acc_stderr\": 0.045126085985421276,\n \"acc_norm\": 0.72,\n \"acc_norm_stderr\": 0.045126085985421276\n },\n \"harness|hendrycksTest-high_school_european_history|5\": {\n \"acc\": 0.7878787878787878,\n \"acc_stderr\": 0.031922715695482995,\n \"acc_norm\": 0.7878787878787878,\n \"acc_norm_stderr\": 0.031922715695482995\n },\n \"harness|hendrycksTest-high_school_geography|5\": {\n \"acc\": 0.8383838383838383,\n \"acc_stderr\": 0.02622591986362928,\n \"acc_norm\": 0.8383838383838383,\n \"acc_norm_stderr\": 0.02622591986362928\n },\n \"harness|hendrycksTest-high_school_government_and_politics|5\": {\n \"acc\": 0.9067357512953368,\n \"acc_stderr\": 0.02098685459328972,\n \"acc_norm\": 0.9067357512953368,\n \"acc_norm_stderr\": 0.02098685459328972\n },\n \"harness|hendrycksTest-high_school_macroeconomics|5\": {\n \"acc\": 0.6666666666666666,\n \"acc_stderr\": 0.023901157979402534,\n \"acc_norm\": 0.6666666666666666,\n \"acc_norm_stderr\": 0.023901157979402534\n },\n \"harness|hendrycksTest-high_school_mathematics|5\": {\n \"acc\": 0.34074074074074073,\n \"acc_stderr\": 0.02889774874113114,\n \"acc_norm\": 0.34074074074074073,\n \"acc_norm_stderr\": 0.02889774874113114\n },\n \"harness|hendrycksTest-high_school_microeconomics|5\": {\n \"acc\": 0.7563025210084033,\n \"acc_stderr\": 0.027886828078380558,\n \"acc_norm\": 0.7563025210084033,\n \"acc_norm_stderr\": 0.027886828078380558\n },\n \"harness|hendrycksTest-high_school_physics|5\": {\n \"acc\": 0.44370860927152317,\n \"acc_stderr\": 0.04056527902281732,\n \"acc_norm\": 0.44370860927152317,\n \"acc_norm_stderr\": 0.04056527902281732\n },\n \"harness|hendrycksTest-high_school_psychology|5\": {\n \"acc\": 0.8752293577981651,\n \"acc_stderr\": 0.014168298359156327,\n \"acc_norm\": 0.8752293577981651,\n \"acc_norm_stderr\": 0.014168298359156327\n },\n \"harness|hendrycksTest-high_school_statistics|5\": {\n \"acc\": 0.625,\n \"acc_stderr\": 0.033016908987210894,\n \"acc_norm\": 0.625,\n \"acc_norm_stderr\": 0.033016908987210894\n },\n \"harness|hendrycksTest-high_school_us_history|5\": {\n \"acc\": 0.8480392156862745,\n \"acc_stderr\": 0.025195658428931785,\n \"acc_norm\": 0.8480392156862745,\n \"acc_norm_stderr\": 0.025195658428931785\n },\n \"harness|hendrycksTest-high_school_world_history|5\": {\n \"acc\": 0.8481012658227848,\n \"acc_stderr\": 0.02336387809663245,\n \"acc_norm\": 0.8481012658227848,\n \"acc_norm_stderr\": 0.02336387809663245\n },\n \"harness|hendrycksTest-human_aging|5\": {\n \"acc\": 0.726457399103139,\n \"acc_stderr\": 0.029918586707798824,\n \"acc_norm\": 0.726457399103139,\n \"acc_norm_stderr\": 0.029918586707798824\n },\n \"harness|hendrycksTest-human_sexuality|5\": {\n \"acc\": 0.8473282442748091,\n \"acc_stderr\": 0.031545216720054725,\n \"acc_norm\": 0.8473282442748091,\n \"acc_norm_stderr\": 0.031545216720054725\n },\n \"harness|hendrycksTest-international_law|5\": {\n \"acc\": 0.8842975206611571,\n \"acc_stderr\": 0.02919980245562281,\n \"acc_norm\": 0.8842975206611571,\n \"acc_norm_stderr\": 0.02919980245562281\n },\n \"harness|hendrycksTest-jurisprudence|5\": {\n \"acc\": 0.8425925925925926,\n \"acc_stderr\": 0.03520703990517965,\n \"acc_norm\": 0.8425925925925926,\n \"acc_norm_stderr\": 0.03520703990517965\n },\n \"harness|hendrycksTest-logical_fallacies|5\": {\n \"acc\": 0.7607361963190185,\n \"acc_stderr\": 0.0335195387952127,\n \"acc_norm\": 0.7607361963190185,\n \"acc_norm_stderr\": 0.0335195387952127\n },\n \"harness|hendrycksTest-machine_learning|5\": {\n \"acc\": 0.5,\n \"acc_stderr\": 0.04745789978762494,\n \"acc_norm\": 0.5,\n \"acc_norm_stderr\": 0.04745789978762494\n },\n \"harness|hendrycksTest-management|5\": {\n \"acc\": 0.883495145631068,\n \"acc_stderr\": 0.031766839486404075,\n \"acc_norm\": 0.883495145631068,\n \"acc_norm_stderr\": 0.031766839486404075\n },\n \"harness|hendrycksTest-marketing|5\": {\n \"acc\": 0.9230769230769231,\n \"acc_stderr\": 0.017456987872436183,\n \"acc_norm\": 0.9230769230769231,\n \"acc_norm_stderr\": 0.017456987872436183\n },\n \"harness|hendrycksTest-medical_genetics|5\": {\n \"acc\": 0.79,\n \"acc_stderr\": 0.040936018074033256,\n \"acc_norm\": 0.79,\n \"acc_norm_stderr\": 0.040936018074033256\n },\n \"harness|hendrycksTest-miscellaneous|5\": {\n \"acc\": 0.8786717752234994,\n \"acc_stderr\": 0.011675913883906723,\n \"acc_norm\": 0.8786717752234994,\n \"acc_norm_stderr\": 0.011675913883906723\n },\n \"harness|hendrycksTest-moral_disputes|5\": {\n \"acc\": 0.7601156069364162,\n \"acc_stderr\": 0.022989592543123563,\n \"acc_norm\": 0.7601156069364162,\n \"acc_norm_stderr\": 0.022989592543123563\n },\n \"harness|hendrycksTest-moral_scenarios|5\": {\n \"acc\": 0.3743016759776536,\n \"acc_stderr\": 0.01618544417945717,\n \"acc_norm\": 0.3743016759776536,\n \"acc_norm_stderr\": 0.01618544417945717\n },\n \"harness|hendrycksTest-nutrition|5\": {\n \"acc\": 0.8104575163398693,\n \"acc_stderr\": 0.02244235826333621,\n \"acc_norm\": 0.8104575163398693,\n \"acc_norm_stderr\": 0.02244235826333621\n },\n \"harness|hendrycksTest-philosophy|5\": {\n \"acc\": 0.7717041800643086,\n \"acc_stderr\": 0.023839303311398195,\n \"acc_norm\": 0.7717041800643086,\n \"acc_norm_stderr\": 0.023839303311398195\n },\n \"harness|hendrycksTest-prehistory|5\": {\n \"acc\": 0.8148148148148148,\n \"acc_stderr\": 0.021613809395224805,\n \"acc_norm\": 0.8148148148148148,\n \"acc_norm_stderr\": 0.021613809395224805\n },\n \"harness|hendrycksTest-professional_accounting|5\": {\n \"acc\": 0.5709219858156028,\n \"acc_stderr\": 0.029525914302558562,\n \"acc_norm\": 0.5709219858156028,\n \"acc_norm_stderr\": 0.029525914302558562\n },\n \"harness|hendrycksTest-professional_law|5\": {\n \"acc\": 0.5071707953063885,\n \"acc_stderr\": 0.012768922739553304,\n \"acc_norm\": 0.5071707953063885,\n \"acc_norm_stderr\": 0.012768922739553304\n },\n \"harness|hendrycksTest-professional_medicine|5\": {\n \"acc\": 0.7683823529411765,\n \"acc_stderr\": 0.025626533803777562,\n \"acc_norm\": 0.7683823529411765,\n \"acc_norm_stderr\": 0.025626533803777562\n },\n \"harness|hendrycksTest-professional_psychology|5\": {\n \"acc\": 0.7418300653594772,\n \"acc_stderr\": 0.01770453165325007,\n \"acc_norm\": 0.7418300653594772,\n \"acc_norm_stderr\": 0.01770453165325007\n },\n \"harness|hendrycksTest-public_relations|5\": {\n \"acc\": 0.6818181818181818,\n \"acc_stderr\": 0.044612721759105085,\n \"acc_norm\": 0.6818181818181818,\n \"acc_norm_stderr\": 0.044612721759105085\n },\n \"harness|hendrycksTest-security_studies|5\": {\n \"acc\": 0.763265306122449,\n \"acc_stderr\": 0.027212835884073142,\n \"acc_norm\": 0.763265306122449,\n \"acc_norm_stderr\": 0.027212835884073142\n },\n \"harness|hendrycksTest-sociology|5\": {\n \"acc\": 0.8756218905472637,\n \"acc_stderr\": 0.023335401790166327,\n \"acc_norm\": 0.8756218905472637,\n \"acc_norm_stderr\": 0.023335401790166327\n },\n \"harness|hendrycksTest-us_foreign_policy|5\": {\n \"acc\": 0.9,\n \"acc_stderr\": 0.030151134457776334,\n \"acc_norm\": 0.9,\n \"acc_norm_stderr\": 0.030151134457776334\n },\n \"harness|hendrycksTest-virology|5\": {\n \"acc\": 0.4939759036144578,\n \"acc_stderr\": 0.03892212195333045,\n \"acc_norm\": 0.4939759036144578,\n \"acc_norm_stderr\": 0.03892212195333045\n },\n \"harness|hendrycksTest-world_religions|5\": {\n \"acc\": 0.8654970760233918,\n \"acc_stderr\": 0.026168221344662297,\n \"acc_norm\": 0.8654970760233918,\n \"acc_norm_stderr\": 0.026168221344662297\n },\n \"harness|truthfulqa:mc|0\": {\n \"mc1\": 0.2998776009791922,\n \"mc1_stderr\": 0.016040352966713616,\n \"mc2\": 0.4543006274006171,\n \"mc2_stderr\": 0.014099486144642947\n },\n \"harness|winogrande|5\": {\n \"acc\": 0.8113654301499605,\n \"acc_stderr\": 0.010995172318019785\n },\n \"harness|gsm8k|5\": {\n \"acc\": 0.4829416224412434,\n \"acc_stderr\": 0.013764467123761316\n }\n}\n```", "repo_url": "https://huggingface.co/TheBloke/Mixtral-8x7B-v0.1-GPTQ", "leaderboard_url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard", "point_of_contact": "[email protected]", "configs": [{"config_name": "harness_arc_challenge_25", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|arc:challenge|25_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|arc:challenge|25_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_gsm8k_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|gsm8k|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|gsm8k|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hellaswag_10", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hellaswag|10_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hellaswag|10_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-abstract_algebra|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-anatomy|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-astronomy|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-business_ethics|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-clinical_knowledge|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-college_biology|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-college_chemistry|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-college_computer_science|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-college_mathematics|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-college_medicine|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-college_physics|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-computer_security|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-conceptual_physics|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-econometrics|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-electrical_engineering|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-elementary_mathematics|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-formal_logic|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-global_facts|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_biology|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_chemistry|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_computer_science|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_european_history|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_geography|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_mathematics|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_physics|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_psychology|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_statistics|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_us_history|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_world_history|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-human_aging|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-human_sexuality|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-international_law|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-jurisprudence|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-logical_fallacies|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-machine_learning|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-management|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-marketing|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-medical_genetics|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-miscellaneous|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-moral_disputes|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-moral_scenarios|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-nutrition|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-philosophy|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-prehistory|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-professional_accounting|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-professional_law|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-professional_medicine|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-professional_psychology|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-public_relations|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-security_studies|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-sociology|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-us_foreign_policy|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-virology|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-world_religions|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-abstract_algebra|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-anatomy|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-astronomy|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-business_ethics|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-clinical_knowledge|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-college_biology|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-college_chemistry|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-college_computer_science|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-college_mathematics|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-college_medicine|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-college_physics|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-computer_security|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-conceptual_physics|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-econometrics|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-electrical_engineering|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-elementary_mathematics|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-formal_logic|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-global_facts|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_biology|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_chemistry|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_computer_science|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_european_history|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_geography|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_mathematics|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_physics|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_psychology|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_statistics|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_us_history|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-high_school_world_history|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-human_aging|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-human_sexuality|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-international_law|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-jurisprudence|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-logical_fallacies|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-machine_learning|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-management|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-marketing|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-medical_genetics|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-miscellaneous|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-moral_disputes|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-moral_scenarios|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-nutrition|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-philosophy|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-prehistory|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-professional_accounting|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-professional_law|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-professional_medicine|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-professional_psychology|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-public_relations|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-security_studies|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-sociology|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-us_foreign_policy|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-virology|5_2023-12-16T08-25-08.853393.parquet", "**/details_harness|hendrycksTest-world_religions|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_abstract_algebra_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-abstract_algebra|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-abstract_algebra|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_anatomy_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-anatomy|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-anatomy|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_astronomy_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-astronomy|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-astronomy|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_business_ethics_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-business_ethics|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-business_ethics|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_clinical_knowledge_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-clinical_knowledge|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-clinical_knowledge|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_biology_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-college_biology|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_biology|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_chemistry_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-college_chemistry|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_chemistry|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_computer_science_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-college_computer_science|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_computer_science|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_mathematics_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-college_mathematics|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_mathematics|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_medicine_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-college_medicine|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_medicine|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_physics_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-college_physics|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_physics|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_computer_security_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-computer_security|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-computer_security|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_conceptual_physics_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-conceptual_physics|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-conceptual_physics|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_econometrics_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-econometrics|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-econometrics|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_electrical_engineering_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-electrical_engineering|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-electrical_engineering|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_elementary_mathematics_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-elementary_mathematics|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-elementary_mathematics|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_formal_logic_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-formal_logic|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-formal_logic|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_global_facts_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-global_facts|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-global_facts|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_biology_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-high_school_biology|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_biology|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_chemistry_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-high_school_chemistry|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_chemistry|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_computer_science_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-high_school_computer_science|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_computer_science|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_european_history_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-high_school_european_history|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_european_history|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_geography_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-high_school_geography|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_geography|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_government_and_politics_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_macroeconomics_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_mathematics_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-high_school_mathematics|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_mathematics|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_microeconomics_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_physics_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-high_school_physics|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_physics|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_psychology_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-high_school_psychology|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_psychology|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_statistics_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-high_school_statistics|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_statistics|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_us_history_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-high_school_us_history|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_us_history|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_world_history_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-high_school_world_history|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_world_history|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_human_aging_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-human_aging|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-human_aging|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_human_sexuality_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-human_sexuality|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-human_sexuality|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_international_law_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-international_law|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-international_law|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_jurisprudence_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-jurisprudence|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-jurisprudence|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_logical_fallacies_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-logical_fallacies|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-logical_fallacies|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_machine_learning_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-machine_learning|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-machine_learning|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_management_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-management|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-management|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_marketing_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-marketing|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-marketing|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_medical_genetics_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-medical_genetics|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-medical_genetics|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_miscellaneous_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-miscellaneous|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-miscellaneous|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_moral_disputes_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-moral_disputes|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-moral_disputes|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_moral_scenarios_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-moral_scenarios|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-moral_scenarios|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_nutrition_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-nutrition|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-nutrition|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_philosophy_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-philosophy|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-philosophy|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_prehistory_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-prehistory|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-prehistory|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_professional_accounting_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-professional_accounting|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-professional_accounting|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_professional_law_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-professional_law|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-professional_law|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_professional_medicine_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-professional_medicine|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-professional_medicine|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_professional_psychology_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-professional_psychology|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-professional_psychology|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_public_relations_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-public_relations|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-public_relations|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_security_studies_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-security_studies|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-security_studies|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_sociology_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-sociology|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-sociology|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_us_foreign_policy_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-us_foreign_policy|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-us_foreign_policy|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_virology_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-virology|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-virology|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_hendrycksTest_world_religions_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|hendrycksTest-world_religions|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-world_religions|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_truthfulqa_mc_0", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|truthfulqa:mc|0_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|truthfulqa:mc|0_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "harness_winogrande_5", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["**/details_harness|winogrande|5_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["**/details_harness|winogrande|5_2023-12-16T08-25-08.853393.parquet"]}]}, {"config_name": "results", "data_files": [{"split": "2023_12_16T08_25_08.853393", "path": ["results_2023-12-16T08-25-08.853393.parquet"]}, {"split": "latest", "path": ["results_2023-12-16T08-25-08.853393.parquet"]}]}]} | 2023-12-16T08:28:17+00:00 | [] | [] | TAGS
#region-us
|
# Dataset Card for Evaluation run of TheBloke/Mixtral-8x7B-v0.1-GPTQ
Dataset automatically created during the evaluation run of model TheBloke/Mixtral-8x7B-v0.1-GPTQ on the Open LLM Leaderboard.
The dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An additional configuration "results" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).
To load the details from a run, you can for instance do the following:
## Latest results
These are the latest results from run 2023-12-16T08:25:08.853393(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the "latest" split for each eval):
## Dataset Details
### Dataset Description
- Curated by:
- Funded by [optional]:
- Shared by [optional]:
- Language(s) (NLP):
- License:
### Dataset Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Out-of-Scope Use
## Dataset Structure
## Dataset Creation
### Curation Rationale
### Source Data
#### Data Collection and Processing
#### Who are the source data producers?
### Annotations [optional]
#### Annotation process
#### Who are the annotators?
#### Personal and Sensitive Information
## Bias, Risks, and Limitations
### Recommendations
Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Dataset Card Authors [optional]
## Dataset Card Contact
| [
"# Dataset Card for Evaluation run of TheBloke/Mixtral-8x7B-v0.1-GPTQ\n\n\n\nDataset automatically created during the evaluation run of model TheBloke/Mixtral-8x7B-v0.1-GPTQ on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:",
"## Latest results\n\nThese are the latest results from run 2023-12-16T08:25:08.853393(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):",
"## Dataset Details",
"### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:",
"### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Out-of-Scope Use",
"## Dataset Structure",
"## Dataset Creation",
"### Curation Rationale",
"### Source Data",
"#### Data Collection and Processing",
"#### Who are the source data producers?",
"### Annotations [optional]",
"#### Annotation process",
"#### Who are the annotators?",
"#### Personal and Sensitive Information",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Dataset Card Authors [optional]",
"## Dataset Card Contact"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for Evaluation run of TheBloke/Mixtral-8x7B-v0.1-GPTQ\n\n\n\nDataset automatically created during the evaluation run of model TheBloke/Mixtral-8x7B-v0.1-GPTQ on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:",
"## Latest results\n\nThese are the latest results from run 2023-12-16T08:25:08.853393(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):",
"## Dataset Details",
"### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:",
"### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Out-of-Scope Use",
"## Dataset Structure",
"## Dataset Creation",
"### Curation Rationale",
"### Source Data",
"#### Data Collection and Processing",
"#### Who are the source data producers?",
"### Annotations [optional]",
"#### Annotation process",
"#### Who are the annotators?",
"#### Personal and Sensitive Information",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Dataset Card Authors [optional]",
"## Dataset Card Contact"
] | [
6,
197,
67,
4,
40,
29,
3,
4,
9,
6,
5,
7,
4,
7,
10,
9,
5,
9,
8,
10,
46,
8,
7,
10,
5
] | [
"passage: TAGS\n#region-us \n# Dataset Card for Evaluation run of TheBloke/Mixtral-8x7B-v0.1-GPTQ\n\n\n\nDataset automatically created during the evaluation run of model TheBloke/Mixtral-8x7B-v0.1-GPTQ on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:## Latest results\n\nThese are the latest results from run 2023-12-16T08:25:08.853393(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):## Dataset Details### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Out-of-Scope Use## Dataset Structure## Dataset Creation### Curation Rationale### Source Data#### Data Collection and Processing#### Who are the source data producers?### Annotations [optional]#### Annotation process#### Who are the annotators?#### Personal and Sensitive Information## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]"
] |
81d54f6c2d619e7b245d2a5a97b35d1543203f52 |
# novecomi-novel-metadata
https://dengekibunko.jp/novecomi/novel/ からスクレイピング。 (本文なし)
| p1atdev/novecomi-novel-metadata | [
"size_categories:n<1K",
"language:ja",
"license:cc0-1.0",
"region:us"
] | 2023-12-16T08:48:49+00:00 | {"language": ["ja"], "license": "cc0-1.0", "size_categories": ["n<1K"], "pretty_name": "Novecomi Novel Metadata", "dataset_info": {"features": [{"name": "id", "dtype": "string"}, {"name": "url", "dtype": "string"}, {"name": "title", "dtype": "string"}, {"name": "author", "dtype": "string"}, {"name": "short_description", "dtype": "string"}, {"name": "description", "dtype": "string"}, {"name": "banner", "dtype": "string"}, {"name": "episodes", "list": [{"name": "link", "dtype": "string"}, {"name": "title", "dtype": "string"}]}], "splits": [{"name": "train", "num_bytes": 78059, "num_examples": 24}], "download_size": 41444, "dataset_size": 78059}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]} | 2023-12-16T08:57:17+00:00 | [] | [
"ja"
] | TAGS
#size_categories-n<1K #language-Japanese #license-cc0-1.0 #region-us
|
# novecomi-novel-metadata
URL からスクレイピング。 (本文なし)
| [
"# novecomi-novel-metadata\n\nURL からスクレイピング。 (本文なし)"
] | [
"TAGS\n#size_categories-n<1K #language-Japanese #license-cc0-1.0 #region-us \n",
"# novecomi-novel-metadata\n\nURL からスクレイピング。 (本文なし)"
] | [
30,
21
] | [
"passage: TAGS\n#size_categories-n<1K #language-Japanese #license-cc0-1.0 #region-us \n# novecomi-novel-metadata\n\nURL からスクレイピング。 (本文なし)"
] |
e15136341dc0ff6ab3f2f184a4b36e1c9a634b2a |
# Dataset of scavenger (Arknights)
This is the dataset of scavenger (Arknights), containing 30 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by [DeepGHS Team](https://github.com/deepghs)([huggingface organization](https://huggingface.co/deepghs)).
This is a WebUI contains crawlers and other thing: ([LittleAppleWebUI](https://github.com/LittleApple-fp16/LittleAppleWebUI))
| Name | Images | Download | Description |
|:----------------|---------:|:----------------------------------------|:-----------------------------------------------------------------------------------------|
| raw | 30 | [Download](dataset-raw.zip) | Raw data with meta information. |
| raw-stage3 | 80 | [Download](dataset-raw-stage3.zip) | 3-stage cropped raw data with meta information. |
| raw-stage3-eyes | 85 | [Download](dataset-raw-stage3-eyes.zip) | 3-stage cropped (with eye-focus) raw data with meta information. |
| 384x512 | 30 | [Download](dataset-384x512.zip) | 384x512 aligned dataset. |
| 512x704 | 30 | [Download](dataset-512x704.zip) | 512x704 aligned dataset. |
| 640x880 | 30 | [Download](dataset-640x880.zip) | 640x880 aligned dataset. |
| stage3-640 | 80 | [Download](dataset-stage3-640.zip) | 3-stage cropped dataset with the shorter side not exceeding 640 pixels. |
| stage3-800 | 80 | [Download](dataset-stage3-800.zip) | 3-stage cropped dataset with the shorter side not exceeding 800 pixels. |
| stage3-p512-640 | 69 | [Download](dataset-stage3-p512-640.zip) | 3-stage cropped dataset with the area not less than 512x512 pixels. |
| stage3-eyes-640 | 85 | [Download](dataset-stage3-eyes-640.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 640 pixels. |
| stage3-eyes-800 | 85 | [Download](dataset-stage3-eyes-800.zip) | 3-stage cropped (with eye-focus) dataset with the shorter side not exceeding 800 pixels. |
| AppleHarem/scavenger_arknights | [
"task_categories:text-to-image",
"size_categories:n<1K",
"license:mit",
"art",
"not-for-all-audiences",
"region:us"
] | 2023-12-16T09:03:44+00:00 | {"license": "mit", "size_categories": ["n<1K"], "task_categories": ["text-to-image"], "tags": ["art", "not-for-all-audiences"]} | 2023-12-16T09:03:48+00:00 | [] | [] | TAGS
#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us
| Dataset of scavenger (Arknights)
================================
This is the dataset of scavenger (Arknights), containing 30 images and their tags.
Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by DeepGHS Team(huggingface organization).
This is a WebUI contains crawlers and other thing: (LittleAppleWebUI)
| [] | [
"TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] | [
44
] | [
"passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n"
] |
440a2f3f77531262808d592fb20ecc0990918901 |
#### Overview
This dataset is built from [sql-create-context](https://huggingface.co/datasets/b-mc2/sql-create-context), which in itself builds from [WikiSQL](https://huggingface.co/datasets/wikisql) and [Spider](https://huggingface.co/datasets/spider).
I have used GPT4 to translate the SQL schema into pandas DataFrame schem initialization statements and to translate the SQL queries into pandas queries.
There are 862 examples of natural language queries, pandas DataFrame creation statements, and pandas query answering the question using the DataFrame creation statement as context. This dataset was built with text-to-pandas LLMs in mind.
#### TODO
- Further transform examples from sql_create_context
- Manually fix some examples that don't make sense
Random sample:
```json
{
"question": "What is the election year when the # of candidates nominated was 262?",
"context": "df = pd.DataFrame(columns=['election', '_number_of_candidates_nominated'])",
"answer": "df[df['_number_of_candidates_nominated'] == 262]['election'].count()"
},
{
"question": "What was the lowest # of total votes?",
"context": "df = pd.DataFrame(columns=['_number_of_total_votes'])",
"answer": "df['_number_of_total_votes'].min()"
},
``` | hiltch/pandas-create-context | [
"task_categories:text-generation",
"task_categories:question-answering",
"task_categories:table-question-answering",
"size_categories:n<1K",
"language:en",
"license:cc-by-4.0",
"pandas",
"code",
"NLP",
"text-to-pandas",
"context-pandas",
"spider",
"wikisql",
"region:us"
] | 2023-12-16T09:45:45+00:00 | {"language": ["en"], "license": "cc-by-4.0", "size_categories": ["n<1K"], "task_categories": ["text-generation", "question-answering", "table-question-answering"], "pretty_name": "pandas-create-context", "tags": ["pandas", "code", "NLP", "text-to-pandas", "context-pandas", "spider", "wikisql"]} | 2023-12-16T10:25:21+00:00 | [] | [
"en"
] | TAGS
#task_categories-text-generation #task_categories-question-answering #task_categories-table-question-answering #size_categories-n<1K #language-English #license-cc-by-4.0 #pandas #code #NLP #text-to-pandas #context-pandas #spider #wikisql #region-us
|
#### Overview
This dataset is built from sql-create-context, which in itself builds from WikiSQL and Spider.
I have used GPT4 to translate the SQL schema into pandas DataFrame schem initialization statements and to translate the SQL queries into pandas queries.
There are 862 examples of natural language queries, pandas DataFrame creation statements, and pandas query answering the question using the DataFrame creation statement as context. This dataset was built with text-to-pandas LLMs in mind.
#### TODO
- Further transform examples from sql_create_context
- Manually fix some examples that don't make sense
Random sample:
| [
"#### Overview\n\nThis dataset is built from sql-create-context, which in itself builds from WikiSQL and Spider.\n\nI have used GPT4 to translate the SQL schema into pandas DataFrame schem initialization statements and to translate the SQL queries into pandas queries. \n\nThere are 862 examples of natural language queries, pandas DataFrame creation statements, and pandas query answering the question using the DataFrame creation statement as context. This dataset was built with text-to-pandas LLMs in mind.",
"#### TODO\n- Further transform examples from sql_create_context\n- Manually fix some examples that don't make sense\n\nRandom sample:"
] | [
"TAGS\n#task_categories-text-generation #task_categories-question-answering #task_categories-table-question-answering #size_categories-n<1K #language-English #license-cc-by-4.0 #pandas #code #NLP #text-to-pandas #context-pandas #spider #wikisql #region-us \n",
"#### Overview\n\nThis dataset is built from sql-create-context, which in itself builds from WikiSQL and Spider.\n\nI have used GPT4 to translate the SQL schema into pandas DataFrame schem initialization statements and to translate the SQL queries into pandas queries. \n\nThere are 862 examples of natural language queries, pandas DataFrame creation statements, and pandas query answering the question using the DataFrame creation statement as context. This dataset was built with text-to-pandas LLMs in mind.",
"#### TODO\n- Further transform examples from sql_create_context\n- Manually fix some examples that don't make sense\n\nRandom sample:"
] | [
94,
126,
36
] | [
"passage: TAGS\n#task_categories-text-generation #task_categories-question-answering #task_categories-table-question-answering #size_categories-n<1K #language-English #license-cc-by-4.0 #pandas #code #NLP #text-to-pandas #context-pandas #spider #wikisql #region-us \n#### Overview\n\nThis dataset is built from sql-create-context, which in itself builds from WikiSQL and Spider.\n\nI have used GPT4 to translate the SQL schema into pandas DataFrame schem initialization statements and to translate the SQL queries into pandas queries. \n\nThere are 862 examples of natural language queries, pandas DataFrame creation statements, and pandas query answering the question using the DataFrame creation statement as context. This dataset was built with text-to-pandas LLMs in mind.#### TODO\n- Further transform examples from sql_create_context\n- Manually fix some examples that don't make sense\n\nRandom sample:"
] |
4446b9b053b0bde41504239b21246efa803954a8 | # Dataset Card for "flan2021-submix-4096"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | kowndinya23/flan2021-submix-4096 | [
"region:us"
] | 2023-12-16T10:26:10+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}, {"split": "validation", "path": "data/validation-*"}]}], "dataset_info": {"features": [{"name": "inputs", "dtype": "string"}, {"name": "targets", "dtype": "string"}, {"name": "task_source", "dtype": "string"}, {"name": "task_name", "dtype": {"class_label": {"names": {"0": "aeslc:1.0.0", "1": "ag_news_subset:1.0.0", "2": "ai2_arc/ARC-Challenge:1.0.0", "3": "ai2_arc/ARC-Easy:1.0.0", "4": "anli/r1:0.1.0", "5": "anli/r2:0.1.0", "6": "anli/r3:0.1.0", "7": "bool_q:1.0.0", "8": "cnn_dailymail:3.4.0", "9": "coqa:1.0.0", "10": "cosmos_qa:1.0.0", "11": "definite_pronoun_resolution:1.1.0", "12": "drop:2.0.0", "13": "fix_punct", "14": "gem/common_gen:1.1.0", "15": "gem/dart:1.1.0", "16": "gem/e2e_nlg:1.1.0", "17": "gem/web_nlg_en:1.1.0", "18": "gem/wiki_lingua_english_en:1.1.0", "19": "gigaword:1.2.0", "20": "glue/cola:2.0.0", "21": "glue/mnli:2.0.0", "22": "glue/mrpc:2.0.0", "23": "glue/qnli:2.0.0", "24": "glue/qqp:2.0.0", "25": "glue/sst2:2.0.0", "26": "glue/stsb:2.0.0", "27": "glue/wnli:2.0.0", "28": "hellaswag:1.1.0", "29": "huggingface:xsum", "30": "imdb_reviews/plain_text:1.0.0", "31": "lambada:1.0.0", "32": "math_dataset/algebra__linear_1d:1.0.0", "33": "multi_news:1.0.0", "34": "natural_questions_open:1.0.0", "35": "newsroom:1.0.0", "36": "openbookqa:0.1.0", "37": "opinion_abstracts_idebate", "38": "opinion_abstracts_rotten_tomatoes", "39": "para_crawl_enes", "40": "paws_wiki:1.1.0", "41": "piqa:1.0.0", "42": "quac:1.0.0", "43": "samsum:1.0.0", "44": "sentiment140:1.0.0", "45": "snli:1.1.0", "46": "squad/v1.1:3.0.0", "47": "squad/v2.0:3.0.0", "48": "story_cloze/2016:1.0.0", "49": "super_glue/cb:1.0.2", "50": "super_glue/copa:1.0.2", "51": "super_glue/multirc:1.0.2", "52": "super_glue/record:1.0.2", "53": "super_glue/rte:1.0.2", "54": "super_glue/wic:1.0.2", "55": "super_glue/wsc.fixed:1.0.2", "56": "trec:1.0.0", "57": "trivia_qa/rc:1.1.0", "58": "true_case", "59": "unified_qa_science_inst", "60": "winogrande:1.1.0", "61": "wmt14_translate/fr-en:1.0.0", "62": "wmt16_translate/cs-en:1.0.0", "63": "wmt16_translate/de-en:1.0.0", "64": "wmt16_translate/fi-en:1.0.0", "65": "wmt16_translate/ro-en:1.0.0", "66": "wmt16_translate/ru-en:1.0.0", "67": "wmt16_translate/tr-en:1.0.0", "68": "word_segment", "69": "yelp_polarity_reviews:0.2.0"}}}}, {"name": "template_type", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 8456659493.04, "num_examples": 5295510}, {"name": "validation", "num_bytes": 85420802.96, "num_examples": 53490}], "download_size": 5288301815, "dataset_size": 8542080296.0}} | 2023-12-16T10:33:16+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "flan2021-submix-4096"
More Information needed | [
"# Dataset Card for \"flan2021-submix-4096\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"flan2021-submix-4096\"\n\nMore Information needed"
] | [
6,
17
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"flan2021-submix-4096\"\n\nMore Information needed"
] |
7b2fd3b8dbdf13f824e63b023fd9bca709f7c71b | # Dataset Card for "t0-submix-4096"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | kowndinya23/t0-submix-4096 | [
"region:us"
] | 2023-12-16T10:36:09+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}, {"split": "validation", "path": "data/validation-*"}]}], "dataset_info": {"features": [{"name": "inputs", "dtype": "string"}, {"name": "targets", "dtype": "string"}, {"name": "task_source", "dtype": "string"}, {"name": "task_name", "dtype": {"class_label": {"names": {"0": "adversarial_qa_dbert_answer_the_following_q", "1": "adversarial_qa_dbert_based_on", "2": "adversarial_qa_dbert_generate_question", "3": "adversarial_qa_dbert_question_context_answer", "4": "adversarial_qa_dbert_tell_what_it_is", "5": "adversarial_qa_dbidaf_answer_the_following_q", "6": "adversarial_qa_dbidaf_based_on", "7": "adversarial_qa_dbidaf_generate_question", "8": "adversarial_qa_dbidaf_question_context_answer", "9": "adversarial_qa_dbidaf_tell_what_it_is", "10": "adversarial_qa_droberta_answer_the_following_q", "11": "adversarial_qa_droberta_based_on", "12": "adversarial_qa_droberta_generate_question", "13": "adversarial_qa_droberta_question_context_answer", "14": "adversarial_qa_droberta_tell_what_it_is", "15": "amazon_polarity_Is_this_product_review_positive", "16": "amazon_polarity_Is_this_review", "17": "amazon_polarity_Is_this_review_negative", "18": "amazon_polarity_User_recommend_this_product", "19": "amazon_polarity_convey_negative_or_positive_sentiment", "20": "amazon_polarity_flattering_or_not", "21": "amazon_polarity_negative_or_positive_tone", "22": "amazon_polarity_user_satisfied", "23": "amazon_polarity_would_you_buy", "24": "app_reviews_categorize_rating_using_review", "25": "app_reviews_convert_to_rating", "26": "app_reviews_convert_to_star_rating", "27": "app_reviews_generate_review", "28": "cos_e_v1.11_aligned_with_common_sense", "29": "cos_e_v1.11_description_question_option_id", "30": "cos_e_v1.11_description_question_option_text", "31": "cos_e_v1.11_explain_why_human", "32": "cos_e_v1.11_generate_explanation_given_text", "33": "cos_e_v1.11_i_think", "34": "cos_e_v1.11_question_description_option_id", "35": "cos_e_v1.11_question_description_option_text", "36": "cos_e_v1.11_question_option_description_id", "37": "cos_e_v1.11_question_option_description_text", "38": "cos_e_v1.11_rationale", "39": "dbpedia_14_given_a_choice_of_categories_", "40": "dbpedia_14_given_a_list_of_category_what_does_the_title_belong_to", "41": "dbpedia_14_given_list_what_category_does_the_paragraph_belong_to", "42": "dbpedia_14_pick_one_category_for_the_following_text", "43": "dream_answer_to_dialogue", "44": "dream_baseline", "45": "dream_generate_first_utterance", "46": "dream_generate_last_utterance", "47": "dream_read_the_following_conversation_and_answer_the_question", "48": "duorc_ParaphraseRC_answer_question", "49": "duorc_ParaphraseRC_build_story_around_qa", "50": "duorc_ParaphraseRC_decide_worth_it", "51": "duorc_ParaphraseRC_extract_answer", "52": "duorc_ParaphraseRC_generate_question", "53": "duorc_ParaphraseRC_generate_question_by_answer", "54": "duorc_ParaphraseRC_movie_director", "55": "duorc_ParaphraseRC_question_answering", "56": "duorc_ParaphraseRC_title_generation", "57": "duorc_SelfRC_answer_question", "58": "duorc_SelfRC_build_story_around_qa", "59": "duorc_SelfRC_decide_worth_it", "60": "duorc_SelfRC_extract_answer", "61": "duorc_SelfRC_generate_question", "62": "duorc_SelfRC_generate_question_by_answer", "63": "duorc_SelfRC_movie_director", "64": "duorc_SelfRC_question_answering", "65": "duorc_SelfRC_title_generation", "66": "kilt_tasks_hotpotqa_combining_facts", "67": "kilt_tasks_hotpotqa_complex_question", "68": "kilt_tasks_hotpotqa_final_exam", "69": "kilt_tasks_hotpotqa_formulate", "70": "kilt_tasks_hotpotqa_straighforward_qa", "71": "qasc_is_correct_1", "72": "qasc_is_correct_2", "73": "qasc_qa_with_combined_facts_1", "74": "qasc_qa_with_separated_facts_1", "75": "qasc_qa_with_separated_facts_2", "76": "qasc_qa_with_separated_facts_3", "77": "qasc_qa_with_separated_facts_4", "78": "qasc_qa_with_separated_facts_5", "79": "quail_context_description_question_answer_id", "80": "quail_context_description_question_answer_text", "81": "quail_context_description_question_text", "82": "quail_context_question_answer_description_id", "83": "quail_context_question_answer_description_text", "84": "quail_context_question_description_answer_id", "85": "quail_context_question_description_answer_text", "86": "quail_context_question_description_text", "87": "quail_description_context_question_answer_id", "88": "quail_description_context_question_answer_text", "89": "quail_description_context_question_text", "90": "quail_no_prompt_id", "91": "quail_no_prompt_text", "92": "quarel_choose_between", "93": "quarel_do_not_use", "94": "quarel_heres_a_story", "95": "quarel_logic_test", "96": "quarel_testing_students", "97": "quartz_answer_question_based_on", "98": "quartz_answer_question_below", "99": "quartz_given_the_fact_answer_the_q", "100": "quartz_having_read_above_passage", "101": "quartz_paragraph_question_plain_concat", "102": "quartz_read_passage_below_choose", "103": "quartz_use_info_from_paragraph_question", "104": "quartz_use_info_from_question_paragraph", "105": "quoref_Answer_Friend_Question", "106": "quoref_Answer_Question_Given_Context", "107": "quoref_Answer_Test", "108": "quoref_Context_Contains_Answer", "109": "quoref_Find_Answer", "110": "quoref_Found_Context_Online", "111": "quoref_Given_Context_Answer_Question", "112": "quoref_Guess_Answer", "113": "quoref_Guess_Title_For_Context", "114": "quoref_Read_And_Extract_", "115": "quoref_What_Is_The_Answer", "116": "race_high_Is_this_the_right_answer", "117": "race_high_Read_the_article_and_answer_the_question_no_option_", "118": "race_high_Select_the_best_answer", "119": "race_high_Select_the_best_answer_generate_span_", "120": "race_high_Select_the_best_answer_no_instructions_", "121": "race_high_Taking_a_test", "122": "race_high_Write_a_multi_choice_question_for_the_following_article", "123": "race_high_Write_a_multi_choice_question_options_given_", "124": "race_middle_Is_this_the_right_answer", "125": "race_middle_Read_the_article_and_answer_the_question_no_option_", "126": "race_middle_Select_the_best_answer", "127": "race_middle_Select_the_best_answer_generate_span_", "128": "race_middle_Select_the_best_answer_no_instructions_", "129": "race_middle_Taking_a_test", "130": "race_middle_Write_a_multi_choice_question_for_the_following_article", "131": "race_middle_Write_a_multi_choice_question_options_given_", "132": "ropes_background_new_situation_answer", "133": "ropes_background_situation_middle", "134": "ropes_given_background_situation", "135": "ropes_new_situation_background_answer", "136": "ropes_plain_background_situation", "137": "ropes_plain_bottom_hint", "138": "ropes_plain_no_background", "139": "ropes_prompt_beginning", "140": "ropes_prompt_bottom_hint_beginning", "141": "ropes_prompt_bottom_no_hint", "142": "ropes_prompt_mix", "143": "ropes_read_background_situation", "144": "sciq_Direct_Question", "145": "sciq_Direct_Question_Closed_Book_", "146": "sciq_Multiple_Choice", "147": "sciq_Multiple_Choice_Closed_Book_", "148": "sciq_Multiple_Choice_Question_First", "149": "social_i_qa_Check_if_a_random_answer_is_valid_or_not", "150": "social_i_qa_Generate_answer", "151": "social_i_qa_Generate_the_question_from_the_answer", "152": "social_i_qa_I_was_wondering", "153": "social_i_qa_Show_choices_and_generate_answer", "154": "social_i_qa_Show_choices_and_generate_index", "155": "web_questions_get_the_answer", "156": "web_questions_potential_correct_answer", "157": "web_questions_question_answer", "158": "web_questions_short_general_knowledge_q", "159": "web_questions_whats_the_answer", "160": "wiki_bio_comprehension", "161": "wiki_bio_guess_person", "162": "wiki_bio_key_content", "163": "wiki_bio_what_content", "164": "wiki_bio_who", "165": "wiki_hop_original_choose_best_object_affirmative_1", "166": "wiki_hop_original_choose_best_object_affirmative_2", "167": "wiki_hop_original_choose_best_object_affirmative_3", "168": "wiki_hop_original_choose_best_object_interrogative_1", "169": "wiki_hop_original_choose_best_object_interrogative_2", "170": "wiki_hop_original_explain_relation", "171": "wiki_hop_original_generate_object", "172": "wiki_hop_original_generate_subject", "173": "wiki_hop_original_generate_subject_and_object", "174": "wiki_qa_Decide_good_answer", "175": "wiki_qa_Direct_Answer_to_Question", "176": "wiki_qa_Generate_Question_from_Topic", "177": "wiki_qa_Is_This_True_", "178": "wiki_qa_Jeopardy_style", "179": "wiki_qa_Topic_Prediction_Answer_Only", "180": "wiki_qa_Topic_Prediction_Question_Only", "181": "wiki_qa_Topic_Prediction_Question_and_Answer_Pair", "182": "wiki_qa_automatic_system", "183": "wiki_qa_exercise", "184": "wiki_qa_found_on_google", "185": "wiqa_does_the_supposed_perturbation_have_an_effect", "186": "wiqa_effect_with_label_answer", "187": "wiqa_effect_with_string_answer", "188": "wiqa_what_is_the_final_step_of_the_following_process", "189": "wiqa_what_is_the_missing_first_step", "190": "wiqa_what_might_be_the_first_step_of_the_process", "191": "wiqa_what_might_be_the_last_step_of_the_process", "192": "wiqa_which_of_the_following_is_the_supposed_perturbation"}}}}, {"name": "template_type", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 4434328372.540715, "num_examples": 1630423}, {"name": "validation", "num_bytes": 44791415.45928452, "num_examples": 16469}], "download_size": 2706129779, "dataset_size": 4479119788.0}} | 2023-12-16T10:39:10+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "t0-submix-4096"
More Information needed | [
"# Dataset Card for \"t0-submix-4096\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"t0-submix-4096\"\n\nMore Information needed"
] | [
6,
17
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"t0-submix-4096\"\n\nMore Information needed"
] |
9578148c9b4160aa6f5fa69d804b81165fd950b4 | # Dataset Card for "niv2-submix-4096"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | kowndinya23/niv2-submix-4096 | [
"region:us"
] | 2023-12-16T10:54:49+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}, {"split": "validation", "path": "data/validation-*"}]}], "dataset_info": {"features": [{"name": "inputs", "dtype": "string"}, {"name": "targets", "dtype": "string"}, {"name": "task_source", "dtype": "string"}, {"name": "task_name", "dtype": {"class_label": {"names": {"0": "task001_quoref_question_generation", "1": "task002_quoref_answer_generation", "2": "task003_mctaco_question_generation_event_duration", "3": "task004_mctaco_answer_generation_event_duration", "4": "task005_mctaco_wrong_answer_generation_event_duration", "5": "task006_mctaco_question_generation_transient_stationary", "6": "task007_mctaco_answer_generation_transient_stationary", "7": "task008_mctaco_wrong_answer_generation_transient_stationary", "8": "task009_mctaco_question_generation_event_ordering", "9": "task010_mctaco_answer_generation_event_ordering", "10": "task011_mctaco_wrong_answer_generation_event_ordering", "11": "task012_mctaco_question_generation_absolute_timepoint", "12": "task013_mctaco_answer_generation_absolute_timepoint", "13": "task014_mctaco_wrong_answer_generation_absolute_timepoint", "14": "task015_mctaco_question_generation_frequency", "15": "task016_mctaco_answer_generation_frequency", "16": "task017_mctaco_wrong_answer_generation_frequency", "17": "task018_mctaco_temporal_reasoning_presence", "18": "task019_mctaco_temporal_reasoning_category", "19": "task020_mctaco_span_based_question", "20": "task021_mctaco_grammatical_logical", "21": "task022_cosmosqa_passage_inappropriate_binary", "22": "task023_cosmosqa_question_generation", "23": "task024_cosmosqa_answer_generation", "24": "task025_cosmosqa_incorrect_answer_generation", "25": "task026_drop_question_generation", "26": "task027_drop_answer_type_generation", "27": "task028_drop_answer_generation", "28": "task029_winogrande_full_object", "29": "task030_winogrande_full_person", "30": "task031_winogrande_question_generation_object", "31": "task032_winogrande_question_generation_person", "32": "task033_winogrande_answer_generation", "33": "task034_winogrande_question_modification_object", "34": "task035_winogrande_question_modification_person", "35": "task036_qasc_topic_word_to_generate_related_fact", "36": "task037_qasc_generate_related_fact", "37": "task038_qasc_combined_fact", "38": "task039_qasc_find_overlapping_words", "39": "task040_qasc_question_generation", "40": "task041_qasc_answer_generation", "41": "task042_qasc_incorrect_option_generation", "42": "task043_essential_terms_answering_incomplete_questions", "43": "task044_essential_terms_identifying_essential_words", "44": "task045_miscellaneous_sentence_paraphrasing", "45": "task046_miscellaneous_question_typing", "46": "task047_miscellaneous_answering_science_questions", "47": "task048_multirc_question_generation", "48": "task049_multirc_questions_needed_to_answer", "49": "task050_multirc_answerability", "50": "task051_multirc_correct_answer_single_sentence", "51": "task052_multirc_identify_bad_question", "52": "task053_multirc_correct_bad_question", "53": "task054_multirc_write_correct_answer", "54": "task055_multirc_write_incorrect_answer", "55": "task056_multirc_classify_correct_answer", "56": "task057_multirc_classify_incorrect_answer", "57": "task058_multirc_question_answering", "58": "task059_ropes_story_generation", "59": "task060_ropes_question_generation", "60": "task061_ropes_answer_generation", "61": "task062_bigbench_repeat_copy_logic", "62": "task063_first_i_elements", "63": "task064_all_elements_except_first_i", "64": "task065_timetravel_consistent_sentence_classification", "65": "task066_timetravel_binary_consistency_classification", "66": "task067_abductivenli_answer_generation", "67": "task068_abductivenli_incorrect_answer_generation", "68": "task069_abductivenli_classification", "69": "task070_abductivenli_incorrect_classification", "70": "task071_abductivenli_answer_generation", "71": "task072_abductivenli_answer_generation", "72": "task073_commonsenseqa_answer_generation", "73": "task074_squad1.1_question_generation", "74": "task075_squad1.1_answer_generation", "75": "task076_splash_correcting_sql_mistake", "76": "task077_splash_explanation_to_sql", "77": "task078_all_elements_except_last_i", "78": "task079_conala_concat_strings", "79": "task080_piqa_answer_generation", "80": "task081_piqa_wrong_answer_generation", "81": "task082_babi_t1_single_supporting_fact_question_generation", "82": "task083_babi_t1_single_supporting_fact_answer_generation", "83": "task084_babi_t1_single_supporting_fact_identify_relevant_fact", "84": "task085_unnatural_addsub_arithmetic", "85": "task086_translated_symbol_arithmetic", "86": "task087_new_operator_addsub_arithmetic", "87": "task088_identify_typo_verification", "88": "task089_swap_words_verification", "89": "task090_equation_learner_algebra", "90": "task091_all_elements_from_index_i_to_j", "91": "task092_check_prime_classification", "92": "task093_conala_normalize_lists", "93": "task094_conala_calculate_mean", "94": "task095_conala_max_absolute_value", "95": "task096_conala_list_index_subtraction", "96": "task097_conala_remove_duplicates", "97": "task098_conala_list_intersection", "98": "task099_reverse_elements_between_index_i_and_j", "99": "task1000_pib_translation_tamil_malayalam", "100": "task1001_pib_translation_gujarati_urdu", "101": "task1002_pib_translation_urdu_gujarati", "102": "task1003_pib_translation_bengali_malayalam", "103": "task1004_pib_translation_malayalam_bengali", "104": "task1005_pib_translation_malayalam_punjabi", "105": "task1006_pib_translation_punjabi_malayalam", "106": "task1007_pib_translation_english_punjabi", "107": "task1008_pib_translation_punjabi_english", "108": "task1009_pib_translation_bengali_hindi", "109": "task100_concatenate_all_elements_from_index_i_to_j", "110": "task1010_pib_translation_hindi_bengali", "111": "task1011_pib_translation_hindi_punjabi", "112": "task1012_pib_translation_punjabi_hindi", "113": "task1013_pib_translation_gujarati_telugu", "114": "task1014_pib_translation_telugu_gujarati", "115": "task1015_pib_translation_punjabi_tamil", "116": "task1016_pib_translation_tamil_punjabi", "117": "task1017_pib_translation_hindi_malayalam", "118": "task1018_pib_translation_malayalam_hindi", "119": "task1019_pib_translation_oriya_telugu", "120": "task101_reverse_and_concatenate_all_elements_from_index_i_to_j", "121": "task1020_pib_translation_telugu_oriya", "122": "task1021_pib_translation_english_malayalam", "123": "task1022_pib_translation_malayalam_english", "124": "task1023_pib_translation_english_hindi", "125": "task1024_pib_translation_hindi_english", "126": "task1025_pib_translation_bengali_punjabi", "127": "task1026_pib_translation_punjabi_bengali", "128": "task1027_pib_translation_marathi_telugu", "129": "task1028_pib_translation_telugu_marathi", "130": "task1029_pib_translation_marathi_punjabi", "131": "task102_commongen_sentence_generation", "132": "task1030_pib_translation_punjabi_marathi", "133": "task1031_pib_translation_bengali_telugu", "134": "task1032_pib_translation_telugu_bengali", "135": "task1033_pib_translation_gujarati_hindi", "136": "task1034_pib_translation_hindi_gujarati", "137": "task1035_pib_translation_tamil_urdu", "138": "task1036_pib_translation_urdu_tamil", "139": "task1037_pib_translation_telugu_urdu", "140": "task1038_pib_translation_urdu_telugu", "141": "task1039_pib_translation_oriya_punjabi", "142": "task103_facts2story_long_text_generation", "143": "task1040_pib_translation_punjabi_oriya", "144": "task1041_pib_translation_gujarati_malayalam", "145": "task1042_pib_translation_malayalam_gujarati", "146": "task1043_pib_translation_gujarati_punjabi", "147": "task1044_pib_translation_punjabi_gujarati", "148": "task1045_pib_translation_hindi_telugu", "149": "task1046_pib_translation_telugu_hindi", "150": "task1047_pib_translation_english_telugu", "151": "task1048_pib_translation_telugu_english", "152": "task1049_pib_translation_malayalam_telugu", "153": "task104_semeval_2019_task10_closed_vocabulary_mathematical_answer_generation", "154": "task1050_pib_translation_telugu_malayalam", "155": "task1051_pib_translation_punjabi_urdu", "156": "task1052_pib_translation_urdu_punjabi", "157": "task1053_pib_translation_hindi_urdu", "158": "task1054_pib_translation_urdu_hindi", "159": "task1055_pib_translation_marathi_oriya", "160": "task1056_pib_translation_oriya_marathi", "161": "task1057_pib_translation_english_urdu", "162": "task1058_pib_translation_urdu_english", "163": "task1059_pib_translation_malayalam_urdu", "164": "task105_story_cloze-rocstories_sentence_generation", "165": "task1060_pib_translation_urdu_malayalam", "166": "task1061_pib_translation_bengali_marathi", "167": "task1062_pib_translation_marathi_bengali", "168": "task1063_pib_translation_gujarati_tamil", "169": "task1064_pib_translation_tamil_gujarati", "170": "task1065_pib_translation_punjabi_telugu", "171": "task1066_pib_translation_telugu_punjabi", "172": "task1067_pib_translation_bengali_gujarati", "173": "task1068_pib_translation_gujarati_bengali", "174": "task1069_pib_translation_bengali_urdu", "175": "task106_scruples_ethical_judgment", "176": "task1070_pib_translation_urdu_bengali", "177": "task1071_pib_translation_malayalam_marathi", "178": "task1072_pib_translation_marathi_malayalam", "179": "task1073_pib_translation_oriya_tamil", "180": "task1074_pib_translation_tamil_oriya", "181": "task1075_pib_translation_tamil_telugu", "182": "task1076_pib_translation_telugu_tamil", "183": "task1077_pib_translation_gujarati_oriya", "184": "task1078_pib_translation_oriya_gujarati", "185": "task1079_pib_translation_english_gujarati", "186": "task107_splash_question_to_sql", "187": "task1080_pib_translation_gujarati_english", "188": "task1081_pib_translation_hindi_marathi", "189": "task1082_pib_translation_marathi_hindi", "190": "task1083_pib_translation_marathi_tamil", "191": "task1084_pib_translation_tamil_marathi", "192": "task1085_pib_translation_english_marathi", "193": "task1086_pib_translation_marathi_english", "194": "task1087_two_number_sum", "195": "task1088_array_of_products", "196": "task1089_check_monotonic_array", "197": "task108_contextualabusedetection_classification", "198": "task1090_ted_translation_en_gl", "199": "task1091_ted_translation_en_it", "200": "task1092_ted_translation_en_pl", "201": "task1093_ted_translation_en_fa", "202": "task1094_ted_translation_en_pt", "203": "task1095_ted_translation_ja_gl", "204": "task1096_ted_translation_ja_it", "205": "task1097_ted_translation_ja_pl", "206": "task1098_ted_translation_ja_fa", "207": "task1099_ted_translation_ja_pt", "208": "task109_smsspamcollection_spamsmsdetection", "209": "task1100_ted_translation_es_gl", "210": "task1101_ted_translation_es_it", "211": "task1102_ted_translation_es_pl", "212": "task1103_ted_translation_es_fa", "213": "task1104_ted_translation_es_pt", "214": "task1105_ted_translation_ar_gl", "215": "task1106_ted_translation_ar_it", "216": "task1107_ted_translation_ar_pl", "217": "task1108_ted_translation_ar_fa", "218": "task1109_ted_translation_ar_pt", "219": "task110_logic2text_sentence_generation", "220": "task1110_ted_translation_he_gl", "221": "task1111_ted_translation_he_it", "222": "task1112_ted_translation_he_pl", "223": "task1113_ted_translation_he_fa", "224": "task1114_ted_translation_he_pt", "225": "task1115_alt_ja_id_translation", "226": "task1116_alt_id_ja_translation", "227": "task1117_alt_ja_id_answer_generation", "228": "task1118_alt_ja_fil_translation", "229": "task1119_alt_fil_ja_translation", "230": "task111_asset_sentence_simplification", "231": "task1120_alt_ja_fil_answer_generation", "232": "task1121_alt_ja_khm_translation", "233": "task1122_alt_khm_ja_translation", "234": "task1123_alt_ja_khm_answer_generation", "235": "task1124_alt_ja_lo_translation", "236": "task1125_alt_lo_ja_translation", "237": "task1126_alt_ja_lo_answer_generation", "238": "task1127_alt_ja_th_translation", "239": "task1128_alt_th_ja_translation", "240": "task1129_alt_ja_th_answer_generation", "241": "task112_asset_simple_sentence_identification", "242": "task1130_xcsr_vi_commonsense_mc_classification", "243": "task1131_xcsr_es_commonsense_mc_classification", "244": "task1132_xcsr_ur_commonsense_mc_classification", "245": "task1133_xcsr_nl_commonsense_mc_classification", "246": "task1134_xcsr_hi_commonsense_mc_classification", "247": "task1135_xcsr_en_commonsense_mc_classification", "248": "task1136_xcsr_fr_commonsense_mc_classification", "249": "task1137_xcsr_pt_commonsense_mc_classification", "250": "task1138_xcsr_de_commonsense_mc_classification", "251": "task1139_xcsr_ru_commonsense_mc_classification", "252": "task113_count_frequency_of_letter", "253": "task1140_xcsr_pl_commonsense_mc_classification", "254": "task1141_xcsr_zh_commonsense_mc_classification", "255": "task1142_xcsr_ar_commonsense_mc_classification", "256": "task1143_xcsr_it_commonsense_mc_classification", "257": "task1144_xcsr_sw_commonsense_mc_classification", "258": "task1145_xcsr_jap_commonsense_mc_classification", "259": "task1146_country_capital", "260": "task1147_country_currency", "261": "task1148_maximum_ascii_value", "262": "task1149_item_check_edible", "263": "task114_is_the_given_word_longest", "264": "task1150_delete_max_min", "265": "task1151_swap_max_min", "266": "task1152_bard_analogical_reasoning_causation", "267": "task1153_bard_analogical_reasoning_affordance", "268": "task1154_bard_analogical_reasoning_travel", "269": "task1155_bard_analogical_reasoning_trash_or_treasure", "270": "task1156_bard_analogical_reasoning_tools", "271": "task1157_bard_analogical_reasoning_rooms_for_containers", "272": "task1158_bard_analogical_reasoning_manipulating_items", "273": "task1159_bard_analogical_reasoning_containers", "274": "task115_help_advice_classification", "275": "task1161_coda19_title_generation", "276": "task1162_coda19_title_classification", "277": "task1163_coda19_section_classification", "278": "task1164_coda19_section_correction_classification", "279": "task1167_penn_treebank_coarse_pos_tagging", "280": "task1168_brown_coarse_pos_tagging", "281": "task1168_xcopa_commonsense_reasoning_ht", "282": "task1169_xcopa_commonsense_cause_effect_ht", "283": "task116_com2sense_commonsense_reasoning", "284": "task1170_xcopa_commonsense_reasoning_id", "285": "task1171_xcopa_commonsense_cause_effect_id", "286": "task1172_xcopa_commonsense_reasoning_it", "287": "task1173_xcopa_commonsense_cause_effect_it", "288": "task1174_xcopa_commonsense_reasoning_sw", "289": "task1175_xcopa_commonsense_cause_effect_sw", "290": "task1176_xcopa_commonsense_reasoning_ta", "291": "task1177_xcopa_commonsense_cause_effect_ta", "292": "task1178_xcopa_commonsense_reasoning_th", "293": "task1179_xcopa_commonsense_cause_effect_th", "294": "task117_spl_translation_en_de", "295": "task1180_xcopa_commonsense_reasoning_tr", "296": "task1181_xcopa_commonsense_cause_effect_tr", "297": "task1182_xcopa_commonsense_reasoning_vi", "298": "task1183_xcopa_commonsense_cause_effect_vi", "299": "task1184_xcopa_commonsense_reasoning_zh", "300": "task1185_xcopa_commonsense_cause_effect_zh", "301": "task1186_nne_hrngo_classification", "302": "task1187_politifact_classification", "303": "task1188_count_max_freq_char", "304": "task1189_check_char_in_string", "305": "task118_semeval_2019_task10_open_vocabulary_mathematical_answer_generation", "306": "task1190_add_integer_to_list", "307": "task1191_food_veg_nonveg", "308": "task1192_food_flavor_profile", "309": "task1193_food_course_classification", "310": "task1194_kth_largest_element", "311": "task1195_disflqa_disfluent_to_fluent_conversion", "312": "task1196_atomic_classification_oeffect", "313": "task1197_atomic_classification_oreact", "314": "task1198_atomic_classification_owant", "315": "task1199_atomic_classification_xattr", "316": "task119_semeval_2019_task10_geometric_mathematical_answer_generation", "317": "task1200_atomic_classification_xeffect", "318": "task1201_atomic_classification_xintent", "319": "task1202_atomic_classification_xneed", "320": "task1203_atomic_classification_xreact", "321": "task1204_atomic_classification_hinderedby", "322": "task1205_atomic_classification_isafter", "323": "task1206_atomic_classification_isbefore", "324": "task1207_atomic_classification_atlocation", "325": "task1208_atomic_classification_xreason", "326": "task1209_atomic_classification_objectuse", "327": "task120_zest_text_modification", "328": "task1210_atomic_classification_madeupof", "329": "task1211_atomic_classification_hassubevent", "330": "task1212_atomic_classification_hasproperty", "331": "task1213_atomic_classification_desires", "332": "task1214_atomic_classification_xwant", "333": "task1215_atomic_classification_capableof", "334": "task1216_atomic_classification_causes", "335": "task1217_atomic_answer_generation", "336": "task1218_ted_translation_en_ja", "337": "task1219_ted_translation_en_es", "338": "task121_zest_text_modification", "339": "task1220_ted_translation_en_ar", "340": "task1221_ted_translation_en_he", "341": "task1222_ted_translation_ja_en", "342": "task1223_ted_translation_ja_es", "343": "task1224_ted_translation_ja_ar", "344": "task1225_ted_translation_ja_he", "345": "task1226_ted_translation_es_en", "346": "task1227_ted_translation_es_ja", "347": "task1228_ted_translation_es_ar", "348": "task1229_ted_translation_es_he", "349": "task122_conala_list_index_addition", "350": "task1230_ted_translation_ar_en", "351": "task1231_ted_translation_ar_ja", "352": "task1232_ted_translation_ar_es", "353": "task1233_ted_translation_ar_he", "354": "task1234_ted_translation_he_en", "355": "task1235_ted_translation_he_ja", "356": "task1236_ted_translation_he_es", "357": "task1237_ted_translation_he_ar", "358": "task1238_ted_translation_gl_en", "359": "task1239_ted_translation_gl_ja", "360": "task123_conala_sort_dictionary", "361": "task1240_ted_translation_gl_es", "362": "task1241_ted_translation_gl_ar", "363": "task1242_ted_translation_gl_he", "364": "task1243_ted_translation_gl_it", "365": "task1244_ted_translation_gl_pl", "366": "task1245_ted_translation_gl_fa", "367": "task1246_ted_translation_gl_pt", "368": "task1247_ted_translation_it_en", "369": "task1248_ted_translation_it_ja", "370": "task1249_ted_translation_it_es", "371": "task124_conala_pair_averages", "372": "task1250_ted_translation_it_ar", "373": "task1251_ted_translation_it_he", "374": "task1252_ted_translation_it_gl", "375": "task1253_ted_translation_it_pl", "376": "task1254_ted_translation_it_fa", "377": "task1255_ted_translation_it_pt", "378": "task1256_ted_translation_pl_en", "379": "task1257_ted_translation_pl_ja", "380": "task1258_ted_translation_pl_es", "381": "task1259_ted_translation_pl_ar", "382": "task125_conala_pair_differences", "383": "task1260_ted_translation_pl_he", "384": "task1261_ted_translation_pl_gl", "385": "task1262_ted_translation_pl_it", "386": "task1263_ted_translation_pl_fa", "387": "task1264_ted_translation_pl_pt", "388": "task1265_ted_translation_fa_en", "389": "task1266_ted_translation_fa_ja", "390": "task1267_ted_translation_fa_es", "391": "task1268_ted_translation_fa_ar", "392": "task1269_ted_translation_fa_he", "393": "task126_scan_structured_text_generation_command_action_all", "394": "task1270_ted_translation_fa_gl", "395": "task1271_ted_translation_fa_it", "396": "task1272_ted_translation_fa_pl", "397": "task1273_ted_translation_fa_pt", "398": "task1274_ted_translation_pt_en", "399": "task1275_ted_translation_pt_ja", "400": "task1276_ted_translation_pt_es", "401": "task1277_ted_translation_pt_ar", "402": "task1278_ted_translation_pt_he", "403": "task1279_ted_translation_pt_gl", "404": "task127_scan_long_text_generation_action_command_all", "405": "task1280_ted_translation_pt_it", "406": "task1281_ted_translation_pt_pl", "407": "task1282_ted_translation_pt_fa", "408": "task1283_hrngo_quality_classification", "409": "task1284_hrngo_informativeness_classification", "410": "task1285_kpa_keypoint_matching", "411": "task1286_openbookqa_question_answering", "412": "task1287_glue_qqp_paraphrasing", "413": "task1288_glue_mrpc_paraphrasing", "414": "task1289_trec_classification", "415": "task128_scan_structured_text_generation_command_action_short", "416": "task1290_xsum_summarization", "417": "task1291_multi_news_summarization", "418": "task1292_yelp_review_full_text_categorization", "419": "task1293_kilt_tasks_hotpotqa_question_answering", "420": "task1294_wiki_qa_answer_verification", "421": "task1295_adversarial_qa_question_answering", "422": "task1296_wiki_hop_question_answering", "423": "task1297_qasc_question_answering", "424": "task129_scan_long_text_generation_action_command_short", "425": "task1308_amazonreview_category_classification", "426": "task1309_amazonreview_summary_classification", "427": "task130_scan_structured_text_generation_command_action_long", "428": "task1310_amazonreview_rating_classification", "429": "task1311_amazonreview_rating_classification", "430": "task1312_amazonreview_polarity_classification", "431": "task1313_amazonreview_polarity_classification", "432": "task1314_country_abbreviation", "433": "task1315_find_range_array", "434": "task1316_remove_duplicates_string", "435": "task1317_country_calling_code", "436": "task1318_country_national_dish", "437": "task1319_country_by_barcode_prefix", "438": "task131_scan_long_text_generation_action_command_long", "439": "task1320_country_domain_tld", "440": "task1321_country_continent", "441": "task1322_country_government_type", "442": "task1323_open_subtitles_hi_en_translation", "443": "task1324_open_subtitles_te_en_translation", "444": "task1325_qa_zre_question_generation_on_subject_relation", "445": "task1326_qa_zre_question_generation_from_answer", "446": "task1327_qa_zre_answer_generation_from_question", "447": "task1328_qa_zre_relation_generation_from_question", "448": "task1329_open_subtitles_en_hi_translation", "449": "task132_dais_text_modification", "450": "task1330_open_subtitles_en_te_translation", "451": "task1331_reverse_array", "452": "task1332_check_leap_year", "453": "task1333_check_validity_date_ddmmyyyy", "454": "task1334_sqac_answer_generation", "455": "task1335_sqac_question_generation", "456": "task1336_peixian_equity_evaluation_corpus_gender_classifier", "457": "task1338_peixian_equity_evaluation_corpus_sentiment_classifier", "458": "task1339_peixian_equity_evaluation_corpus_text_completion", "459": "task133_winowhy_reason_plausibility_detection", "460": "task1340_msr_text_compression_compression", "461": "task1341_msr_text_classification", "462": "task1342_amazon_us_reviews_title", "463": "task1343_amazon_us_reviews_rating", "464": "task1344_glue_entailment_classification", "465": "task1345_glue_qqp_question_paraprashing", "466": "task1346_glue_cola_grammatical_correctness_classification", "467": "task1347_glue_sts-b_similarity_classification", "468": "task134_winowhy_reason_generation", "469": "task1350_opus100_translation_en_gu", "470": "task1351_opus100_translation_gu_en", "471": "task1352_hind_encorp_translation_hi_en", "472": "task1353_hind_encorp_translation_en_hi", "473": "task1354_sent_comp_classification", "474": "task1355_sent_comp_summarization", "475": "task1356_xlsum_title_generation", "476": "task1357_xlsum_summary_generation", "477": "task1358_xlsum_title_generation", "478": "task1359_numer_sense_answer_generation", "479": "task135_winowhy_wrong_reason_generation", "480": "task1360_numer_sense_multiple_choice_qa_generation", "481": "task1361_movierationales_classification", "482": "task1364_hans_answer_generation", "483": "task1365_opustedtalks_translation", "484": "task1366_healthfact_classification", "485": "task1367_opustedtalks_translation", "486": "task1368_healthfact_sentence_generation", "487": "task1369_healthfact_sentence_generation", "488": "task136_winowhy_knowledge_categorization", "489": "task1370_newscomm_classification", "490": "task1371_newscomm_translation", "491": "task1373_newscomm_translation", "492": "task1374_newscomm_translation", "493": "task1375_newscomm_translation", "494": "task1376_newscomm_translation", "495": "task1377_newscomm_translation", "496": "task1378_quarel_correct_answer_generation", "497": "task1379_quarel_incorrect_answer_generation", "498": "task137_detoxifying-lms_classification_toxicity", "499": "task1380_quarel_correct_option_generation", "500": "task1381_quarel_incorrect_option_generation", "501": "task1382_quarel_write_correct_answer", "502": "task1383_quarel_write_incorrect_answer", "503": "task1384_deal_or_no_dialog_classification", "504": "task1385_anli_r1_entailment", "505": "task1386_anli_r2_entailment", "506": "task1387_anli_r3_entailment", "507": "task1388_cb_entailment", "508": "task1389_hellaswag_completion", "509": "task138_detoxifying-lms_classification_fluency", "510": "task1390_wscfixed_coreference", "511": "task1391_winogrande_easy_answer_generation", "512": "task1392_superglue_multirc_answer_verification", "513": "task1393_superglue_copa_text_completion", "514": "task1394_meta_woz_task_classification", "515": "task1395_europa_ecdc_tm_en_sv_translation", "516": "task1396_europa_ecdc_tm_en_de_translation", "517": "task1397_europa_ecdc_tm_fr_en_translation", "518": "task1398_obqa_question_generation", "519": "task1399_obqa_answer_generation", "520": "task139_detoxifying-lms_classification_topicality", "521": "task1400_obqa_incorrect_answer_generation", "522": "task1401_obqa_sentence_generation", "523": "task1402_clue_question_generation", "524": "task1403_check_validity_date_mmddyyyy", "525": "task1404_date_conversion", "526": "task1405_find_median", "527": "task1406_kth_smallest_element", "528": "task1407_dart_question_generation", "529": "task1408_dart_similarity_classification", "530": "task1409_dart_text_generation", "531": "task140_detoxifying-lms_classification_style", "532": "task1410_dart_relationship_extraction", "533": "task1411_dart_subject_identification", "534": "task1412_web_questions_question_answering", "535": "task1413_dart_object_identification", "536": "task1414_ajgt_twitter_ar_classification", "537": "task1415_youtube_caption_corrections_grammar_correction", "538": "task1416_youtube_caption_corrections_incorrect_grammar_classification", "539": "task1418_bless_semantic_relation_classification", "540": "task1419_mathqa_gain", "541": "task141_odd-man-out_classification_category", "542": "task1420_mathqa_general", "543": "task1421_mathqa_other", "544": "task1422_mathqa_physics", "545": "task1423_mathqa_geometry", "546": "task1424_mathqa_probability", "547": "task1425_country_iso_numeric", "548": "task1426_country_independence_year", "549": "task1427_country_region_in_world", "550": "task1428_country_surface_area", "551": "task1429_evalution_semantic_relation_classification", "552": "task142_odd-man-out_classification_no_category", "553": "task1431_head_qa_answer_generation", "554": "task1432_head_qa_language_translation_en_to_es", "555": "task1433_head_qa_language_translation_es_to_en", "556": "task1434_head_qa_classification", "557": "task1435_ro_sts_parallel_language_translation_ro_to_en", "558": "task1436_ro_sts_parallel_language_translation_en_to_ro", "559": "task1437_doqa_cooking_question_generation", "560": "task1438_doqa_cooking_answer_generation", "561": "task1439_doqa_cooking_isanswerable", "562": "task143_odd-man-out_classification_generate_category", "563": "task1440_doqa_movies_question_generation", "564": "task1441_doqa_movies_answer_generation", "565": "task1442_doqa_movies_isanswerable", "566": "task1443_string_to_number", "567": "task1444_round_power_of_two", "568": "task1445_closest_integers", "569": "task1446_farthest_integers", "570": "task1447_drug_extraction_ade", "571": "task1448_disease_entity_extraction_ncbi_dataset", "572": "task1449_disease_entity_extraction_bc5cdr_dataset", "573": "task144_subjqa_question_answering", "574": "task1451_drug_dose_extraction", "575": "task1452_location_entity_extraction_btc_corpus", "576": "task1453_person_entity_extraction_btc_corpus", "577": "task145_afs_argument_similarity_death_penalty", "578": "task146_afs_argument_similarity_gun_control", "579": "task1479_organization_entity_extraction_btc_corpus", "580": "task147_afs_argument_similarity_gay_marriage", "581": "task1480_gene_extraction_jnlpba_dataset", "582": "task1481_gene_extraction_bc2gm_dataset", "583": "task1482_gene_extraction_chemprot_dataset", "584": "task1483_chemical_extraction_chemprot_dataset", "585": "task1484_gene_extraction_linnaeus_dataset", "586": "task1485_organ_extraction_anem_dataset", "587": "task1486_cell_extraction_anem_dataset", "588": "task1487_organism_substance_extraction_anem_dataset", "589": "task1488_sarcasmdetection_headline_classification", "590": "task1489_sarcasmdetection_tweet_classification", "591": "task148_afs_argument_quality_gay_marriage", "592": "task1490_bengali_personal_hate_speech_binary_classification", "593": "task1491_bengali_political_hate_speech_binary_classification", "594": "task1492_bengali_religious_hate_speech_binary_classification", "595": "task1493_bengali_geopolitical_hate_speech_binary_classification", "596": "task1494_bengali_hate_speech_classification", "597": "task1495_adverse_drug_event_classification", "598": "task1496_bengali_reviews_sentiment_classification", "599": "task1497_bengali_book_reviews_sentiment_classification", "600": "task1498_24hour_to_12hour_clock", "601": "task1499_dstc3_summarization", "602": "task149_afs_argument_quality_death_penalty", "603": "task1500_dstc3_classification", "604": "task1501_dstc3_answer_generation", "605": "task1502_hatexplain_classification", "606": "task1503_hatexplain_classification", "607": "task1504_hatexplain_answer_generation", "608": "task1505_root09_semantic_relation_classification", "609": "task1506_celebrity_minimal_dob_span", "610": "task1507_boolean_temporal_reasoning", "611": "task1508_wordnet_antonyms", "612": "task1509_evalution_antonyms", "613": "task150_afs_argument_quality_gun_control", "614": "task1510_evalution_relation_extraction", "615": "task1514_flores_translation_entone", "616": "task1515_imppres_longtextgeneration", "617": "task1516_imppres_naturallanguageinference", "618": "task1517_limit_classfication", "619": "task1518_limit_answer_generation", "620": "task1519_qa_srl_question_generation", "621": "task151_tomqa_find_location_easy_clean", "622": "task1520_qa_srl_answer_generation", "623": "task1529_scitail1.1_classification", "624": "task152_tomqa_find_location_easy_noise", "625": "task1530_scitail1.1_sentence_generation", "626": "task1531_daily_dialog_type_classification", "627": "task1532_daily_dialog_emotion_classification", "628": "task1533_daily_dialog_formal_classification", "629": "task1534_daily_dialog_question_classification", "630": "task1535_daily_dialog_uniqueness_classification", "631": "task1536_daily_dialog_happiness_classification", "632": "task1537_tamil_offenseval_dravidian_classification", "633": "task1538_malayalam_offenseval_dravidian_classification", "634": "task1539_kannada_offenseval_dravidian_classification", "635": "task153_tomqa_find_location_hard_clean", "636": "task1540_parsed_pdfs_summarization", "637": "task1541_agnews_classification", "638": "task1542_every_ith_element_from_starting", "639": "task1543_conll2002_parts_of_speech_tagging_answer_generation", "640": "task1544_conll2002_named_entity_recognition_answer_generation", "641": "task1545_conll2002_person_name_extraction_answer_generation", "642": "task1546_conll2002_location_name_extraction_answer_generation", "643": "task1548_wiqa_binary_classification", "644": "task1549_wiqa_answer_generation_missing_step", "645": "task154_tomqa_find_location_hard_noise", "646": "task1551_every_ith_element_from_kth_element", "647": "task1552_scitail_question_generation", "648": "task1553_cnn_dailymail_summarization", "649": "task1554_scitail_classification", "650": "task1555_scitail_answer_generation", "651": "task1556_scitail_passage_generation", "652": "task1557_jfleg_answer_generation", "653": "task1558_jfleg_incorrect_answer_generation", "654": "task1559_blimp_binary_classification", "655": "task155_count_nouns_verbs", "656": "task1560_blimp_binary_classification", "657": "task1561_clickbait_new_bg_summarization", "658": "task1562_zest_text_modification", "659": "task1564_triviaqa_answer_generation", "660": "task1565_triviaqa_classification", "661": "task1566_propara_structured_text_generation", "662": "task1567_propara_question_generation", "663": "task1568_propara_classification", "664": "task1569_cmrc2018_question_generation", "665": "task156_codah_classification_adversarial", "666": "task1570_cmrc2018_answer_generation", "667": "task1571_cmrc2018_answer_generation_starting_index", "668": "task1572_samsum_summary", "669": "task1573_samsum_classification", "670": "task1574_amazon_reviews_multi_language_identification", "671": "task1575_amazon_reviews_multi_sentiment_classification", "672": "task1576_amazon_reviews_multi_english_language_classification", "673": "task1577_amazon_reviews_multi_japanese_language_classification", "674": "task1579_gigaword_incorrect_summarization", "675": "task157_count_vowels_and_consonants", "676": "task1580_eqasc-perturbed_question_generation", "677": "task1581_eqasc-perturbed_answer_generation", "678": "task1582_bless_hypernym_generation", "679": "task1583_bless_meronym_classification", "680": "task1584_evalution_meronym_classification", "681": "task1585_root09_hypernym_generation", "682": "task1586_scifact_title_generation", "683": "task1587_scifact_classification", "684": "task1588_tecla_classification", "685": "task1589_scifact_classification", "686": "task158_count_frequency_of_words", "687": "task1590_diplomacy_text_generation", "688": "task1591_allocine_classification", "689": "task1592_yahoo_answers_topics_classfication", "690": "task1593_yahoo_answers_topics_classification", "691": "task1594_yahoo_answers_topics_question_generation", "692": "task1595_event2mind_text_generation_1", "693": "task1596_event2mind_text_generation_2", "694": "task1597_nyc_slot_filling", "695": "task1598_nyc_long_text_generation", "696": "task1599_smcalflow_classification", "697": "task159_check_frequency_of_words_in_sentence_pair", "698": "task1600_smcalflow_sentence_generation", "699": "task1601_webquestions_answer_generation", "700": "task1602_webquestion_question_genreation", "701": "task1603_smcalflow_sentence_generation", "702": "task1604_ethos_text_classification", "703": "task1605_ethos_text_classification", "704": "task1606_ethos_text_classification", "705": "task1607_ethos_text_classification", "706": "task1608_xquad_en_answer_generation", "707": "task1609_xquad_en_question_generation", "708": "task160_replace_letter_in_a_sentence", "709": "task1610_xquad_es_answer_generation", "710": "task1611_xquad_es_question_generation", "711": "task1612_sick_label_classification", "712": "task1613_sick_given_category_generate_sentence", "713": "task1614_sick_text_modify", "714": "task1615_sick_tclassify_b_relation_a", "715": "task1616_cc_alligned_translate_eng_tel", "716": "task1617_cc_alligned_translate_tel_eng", "717": "task1618_cc_alligned_classify_tel_eng", "718": "task1619_menyo20k-mt_en_yo_translation", "719": "task161_count_words_containing_letter", "720": "task1620_menyo20k-mt_yo_en_translation", "721": "task1621_menyo20k-mt_en_yo_language_identification", "722": "task1622_disfl_qa_text_modication", "723": "task1623_disfl_qa_disfluent_question_classification", "724": "task1624_disfl_qa_question_yesno_classification", "725": "task1625_disfl_qa_asnwer_generation", "726": "task1626_copa_hr_question_answering", "727": "task1627_copa_hr_classification", "728": "task1628_copa_hr_question_answering", "729": "task1629_copa_hr_classification", "730": "task162_count_words_starting_with_letter", "731": "task1630_openpi_classification", "732": "task1631_openpi_answer_generation", "733": "task1637_doqa2.1_cooking_text_summarization", "734": "task1638_doqa2.1_movies_text_summarization", "735": "task1639_doqa2.1_travel_text_summarization", "736": "task163_count_words_ending_with_letter", "737": "task1640_aqa1.0_answerable_unanswerable_question_classification", "738": "task1645_medical_question_pair_dataset_text_classification", "739": "task1646_dataset_card_for_catalonia_independence_corpus_text_classification", "740": "task1647_opus_books_en-pt_translation", "741": "task1648_opus_books_en-sv_translation", "742": "task1649_opus_books_en-no_translation", "743": "task164_mcscript_question_answering_text", "744": "task1650_opus_books_en-fi_translation", "745": "task1651_opus_books_en-es__translation", "746": "task1652_opus_books_ca-en_translation", "747": "task1654_mkb_translation", "748": "task1655_mkb_translation", "749": "task1656_gooaq_answer_generation", "750": "task1657_gooaq_question_generation", "751": "task1658_billsum_summarization", "752": "task1659_title_generation", "753": "task165_mcscript_question_answering_commonsense", "754": "task1660_super_glue_question_generation", "755": "task1661_super_glue_classification", "756": "task1662_cedr_ru_classification", "757": "task1663_cedr_ru_incorrect_classification", "758": "task1664_winobias_text_generation", "759": "task1665_trainglecopa_question_generation", "760": "task1666_cail2018_answer_generation", "761": "task1667_cail2018_answer_generation", "762": "task1669_md_gender_bias_text_modification", "763": "task166_clariq_sentence_generation", "764": "task1670_md_gender_bias_text_modification", "765": "task1676_xquad-ca_translation", "766": "task1677_xquad-ca_translation", "767": "task1678_mathqa_answer_selection", "768": "task167_strategyqa_question_generation", "769": "task1685_menyo20k_translation", "770": "task1686_menyo20k_translation", "771": "task1689_qed_amara_translation", "772": "task168_strategyqa_question_decomposition", "773": "task1690_qed_amara_translation", "774": "task1691_qed_amara_translation", "775": "task1692_qed_amara_translation", "776": "task169_strategyqa_sentence_generation", "777": "task1703_ljspeech_textmodification", "778": "task1704_ljspeech_textmodification", "779": "task1705_ljspeech_classification", "780": "task1706_ljspeech_classification", "781": "task170_hotpotqa_answer_generation", "782": "task1711_poki_text_generation", "783": "task1712_poki_classification", "784": "task1713_convai3_sentence_generation", "785": "task1714_convai3_sentence_generation", "786": "task171_spl_translation_en_es", "787": "task1720_civil_comments_toxicity_classification", "788": "task1721_civil_comments_obscenity_classification", "789": "task1722_civil_comments_threat_classification", "790": "task1723_civil_comments_sexuallyexplicit_classification", "791": "task1724_civil_comments_insult_classification", "792": "task1725_civil_comments_severtoxicity_classification", "793": "task1726_mathqa_correct_answer_generation", "794": "task1727_wiqa_what_is_the_effect", "795": "task1728_web_nlg_data_to_text", "796": "task1729_personachat_generate_next", "797": "task172_spl_translation_en_fa", "798": "task1730_personachat_choose_next", "799": "task1731_quartz_question_answering", "800": "task173_spl_translation_en_it", "801": "task174_spl_translation_en_ja", "802": "task175_spl_translation_en_pl", "803": "task176_break_decompose_questions", "804": "task177_para-nmt_paraphrasing", "805": "task178_quartz_question_answering", "806": "task179_participant_extraction", "807": "task180_intervention_extraction", "808": "task181_outcome_extraction", "809": "task182_duorc_question_generation", "810": "task183_rhyme_generation", "811": "task184_break_generate_question", "812": "task184_snli_entailment_to_neutral_text_modification", "813": "task185_snli_contradiction_to_neutral_text_modification", "814": "task186_snli_contradiction_to_entailment_text_modification", "815": "task187_snli_entailment_to_contradiction_text_modification", "816": "task188_snli_neutral_to_entailment_text_modification", "817": "task189_snli_neutral_to_contradiction_text_modification", "818": "task190_snli_classification", "819": "task191_hotpotqa_question_generation", "820": "task192_hotpotqa_sentence_generation", "821": "task193_duorc_question_generation", "822": "task194_duorc_answer_generation", "823": "task195_sentiment140_classification", "824": "task196_sentiment140_answer_generation", "825": "task197_mnli_domain_answer_generation", "826": "task198_mnli_domain_classification", "827": "task199_mnli_classification", "828": "task200_mnli_entailment_classification", "829": "task201_mnli_neutral_classification", "830": "task202_mnli_contradiction_classification", "831": "task203_mnli_sentence_generation", "832": "task204_mnli_same_genre_classification", "833": "task205_remove_even_elements", "834": "task206_collatz_conjecture", "835": "task207_max_element_lists", "836": "task208_combinations_of_list", "837": "task209_stancedetection_classification", "838": "task210_logic2text_structured_text_generation", "839": "task211_logic2text_classification", "840": "task212_logic2text_classification", "841": "task213_rocstories_correct_ending_classification", "842": "task214_rocstories_incorrect_ending_classification", "843": "task215_rocstories_incorrect_answer_generation", "844": "task216_rocstories_correct_answer_generation", "845": "task217_rocstories_ordering_answer_generation", "846": "task218_rocstories_swap_order_answer_generation", "847": "task219_rocstories_title_answer_generation", "848": "task220_rocstories_title_classification", "849": "task221_rocstories_two_choice_classification", "850": "task222_rocstories_two_chioce_slotting_classification", "851": "task223_quartz_explanation_generation", "852": "task224_scruples_anecdotes_ethical_judgment", "853": "task225_english_language_answer_generation", "854": "task226_english_language_answer_relevance_classification", "855": "task227_clariq_classification", "856": "task228_arc_answer_generation_easy", "857": "task229_arc_answer_generation_hard", "858": "task230_iirc_passage_classification", "859": "task231_iirc_link_classification", "860": "task232_iirc_link_number_classification", "861": "task233_iirc_link_exists_classification", "862": "task234_iirc_passage_line_answer_generation", "863": "task235_iirc_question_from_subtext_answer_generation", "864": "task236_iirc_question_from_passage_answer_generation", "865": "task237_iirc_answer_from_subtext_answer_generation", "866": "task238_iirc_answer_from_passage_answer_generation", "867": "task239_tweetqa_answer_generation", "868": "task240_tweetqa_question_generation", "869": "task241_tweetqa_classification", "870": "task242_tweetqa_classification", "871": "task243_count_elements_in_set_intersection", "872": "task244_count_elements_in_set_union", "873": "task245_check_presence_in_set_intersection", "874": "task246_dream_question_generation", "875": "task247_dream_answer_generation", "876": "task248_dream_classification", "877": "task249_enhanced_wsc_pronoun_disambiguation", "878": "task250_spl_translation_en_ar", "879": "task251_spl_translation_en_fi", "880": "task252_spl_translation_en_tr", "881": "task253_spl_translation_en_zh", "882": "task254_spl_translation_fi_en", "883": "task255_spl_translation_it_en", "884": "task256_spl_translation_de_en", "885": "task257_spl_translation_ar_en", "886": "task258_spl_translation_fa_en", "887": "task259_spl_translation_tr_en", "888": "task260_spl_translation_zh_en", "889": "task261_spl_translation_es_en", "890": "task262_spl_translation_ja_en", "891": "task263_spl_translation_pl_en", "892": "task264_paper_reviews_accept_or_reject_classification", "893": "task265_paper_reviews_language_identification", "894": "task266_paper_reviews_reviewer_perspective_classification", "895": "task267_concatenate_and_reverse_all_elements_from_index_i_to_j", "896": "task268_casehold_legal_answer_generation", "897": "task269_csrg_counterfactual_story_generation", "898": "task270_csrg_counterfactual_context_generation", "899": "task271_europarl_translation", "900": "task272_europarl_translation", "901": "task273_europarl_classification", "902": "task274_overruling_legal_classification", "903": "task275_enhanced_wsc_paraphrase_generation", "904": "task276_enhanced_wsc_classification", "905": "task277_stereoset_sentence_generation_stereotype", "906": "task278_stereoset_sentence_generation_antistereotype", "907": "task279_stereoset_classification_stereotype", "908": "task280_stereoset_classification_stereotype_type", "909": "task281_points_of_correspondence", "910": "task282_scruples_event_time", "911": "task283_dream_incorrect_answer_generation", "912": "task284_imdb_classification", "913": "task285_imdb_answer_generation", "914": "task286_olid_offense_judgment", "915": "task287_casehold_legal_incorrect_answer_generation", "916": "task288_gigaword_summarization", "917": "task289_gigaword_summarization", "918": "task290_tellmewhy_question_answerability", "919": "task291_semeval_2020_task4_commonsense_validation", "920": "task292_storycommonsense_character_text_generation", "921": "task293_storycommonsense_emotion_text_generation", "922": "task294_storycommonsense_motiv_text_generation", "923": "task295_semeval_2020_task4_commonsense_reasoning", "924": "task296_storycloze_correct_end_classification", "925": "task297_storycloze_incorrect_end_classification", "926": "task298_storycloze_correct_end_classification", "927": "task299_storycloze_sentence_generation", "928": "task300_storycloze_order_generation", "929": "task301_record_question_generation", "930": "task302_record_classification", "931": "task303_record_incorrect_answer_generation", "932": "task304_numeric_fused_head_resolution", "933": "task305_jeopardy_answer_generation_normal", "934": "task306_jeopardy_answer_generation_double", "935": "task307_jeopardy_answer_generation_final", "936": "task308_jeopardy_answer_generation_all", "937": "task309_race_answer_generation", "938": "task310_race_classification", "939": "task311_race_question_generation", "940": "task312_europarl_sv_en_translation", "941": "task313_europarl_en_sv_translation", "942": "task314_europarl_sv-en_classification", "943": "task315_europarl_sv-en_language_identification", "944": "task316_crows-pairs_classification_stereotype", "945": "task317_crows-pairs_classification_stereotype_type", "946": "task318_stereoset_classification_gender", "947": "task319_stereoset_classification_profession", "948": "task320_stereoset_classification_race", "949": "task321_stereoset_classification_religion", "950": "task322_jigsaw_classification_threat", "951": "task323_jigsaw_classification_sexually_explicit", "952": "task324_jigsaw_classification_disagree", "953": "task325_jigsaw_classification_identity_attack", "954": "task326_jigsaw_classification_obscene", "955": "task327_jigsaw_classification_toxic", "956": "task328_jigsaw_classification_insult", "957": "task329_gap_classification", "958": "task330_gap_answer_generation", "959": "task331_gap_incorrect_answer_generation", "960": "task332_tellmewhy_answer_generation", "961": "task333_hateeval_classification_hate_en", "962": "task334_hateeval_classification_hate_es", "963": "task335_hateeval_classification_aggresive_en", "964": "task336_hateeval_classification_aggresive_es", "965": "task337_hateeval_classification_individual_en", "966": "task338_hateeval_classification_individual_es", "967": "task339_record_answer_generation", "968": "task340_winomt_classification_gender_pro", "969": "task341_winomt_classification_gender_anti", "970": "task342_winomt_classification_profession_pro", "971": "task343_winomt_classification_profession_anti", "972": "task344_hybridqa_answer_generation", "973": "task345_hybridqa_answer_generation", "974": "task346_hybridqa_classification", "975": "task347_hybridqa_incorrect_answer_generation", "976": "task348_squad2.0_unanswerable_question_generation", "977": "task349_squad2.0_answerable_unanswerable_question_classification", "978": "task350_winomt_classification_gender_identifiability_pro", "979": "task351_winomt_classification_gender_identifiability_anti", "980": "task352_coda-19_classification", "981": "task353_casino_classification_negotiation_elicit_pref", "982": "task354_casino_classification_negotiation_no_need", "983": "task355_casino_classification_negotiation_other_need", "984": "task356_casino_classification_negotiation_self_need", "985": "task357_casino_classification_negotiation_small_talk", "986": "task358_casino_classification_negotiation_uv_part", "987": "task359_casino_classification_negotiation_vouch_fair", "988": "task360_spolin_yesand_response_generation", "989": "task361_spolin_yesand_prompt_response_classification", "990": "task362_spolin_yesand_prompt_response_sub_classification", "991": "task363_sst2_polarity_classification", "992": "task364_regard_social_impact_classification", "993": "task365_synthetic_remove_vowels", "994": "task366_synthetic_return_primes", "995": "task367_synthetic_remove_floats", "996": "task368_synthetic_even_or_odd_calculation", "997": "task369_synthetic_remove_odds", "998": "task370_synthetic_remove_divisible_by_3", "999": "task371_synthetic_product_of_list", "1000": "task372_synthetic_palindrome_numbers", "1001": "task373_synthetic_round_tens_place", "1002": "task374_synthetic_pos_or_neg_calculation", "1003": "task375_classify_type_of_sentence_in_debate", "1004": "task376_reverse_order_of_words", "1005": "task377_remove_words_of_given_length", "1006": "task378_reverse_words_of_given_length", "1007": "task379_agnews_topic_classification", "1008": "task380_boolq_yes_no_question", "1009": "task381_boolq_question_generation", "1010": "task382_hybridqa_answer_generation", "1011": "task383_matres_classification", "1012": "task384_socialiqa_question_classification", "1013": "task385_socialiqa_incorrect_answer_generation", "1014": "task386_semeval_2018_task3_irony_detection", "1015": "task387_semeval_2018_task3_irony_classification", "1016": "task388_torque_token_classification", "1017": "task389_torque_generate_temporal_question", "1018": "task390_torque_text_span_selection", "1019": "task391_causal_relationship", "1020": "task392_inverse_causal_relationship", "1021": "task393_plausible_result_generation", "1022": "task394_persianqa_question_generation", "1023": "task395_persianqa_answer_generation", "1024": "task396_persianqa_classification", "1025": "task397_semeval_2018_task1_tweet_anger_detection", "1026": "task398_semeval_2018_task1_tweet_joy_detection", "1027": "task399_semeval_2018_task1_tweet_sadness_detection", "1028": "task400_paws_paraphrase_classification", "1029": "task401_numeric_fused_head_reference", "1030": "task402_grailqa_paraphrase_generation", "1031": "task403_creak_commonsense_inference", "1032": "task404_grailqa_paraphrase_validation", "1033": "task405_narrativeqa_question_generation", "1034": "task406_mickey_fr_sentence_perturbation_generation", "1035": "task407_mickey_hi_sentence_perturbation_generation", "1036": "task408_mickey_it_sentence_perturbation_generation", "1037": "task409_mickey_nl_sentence_perturbation_generation", "1038": "task410_mickey_ru_sentence_perturbation_generation", "1039": "task411_mickey_vi_sentence_perturbation_generation", "1040": "task412_mickey_zh_sentence_perturbation_generation", "1041": "task413_mickey_en_sentence_perturbation_generation", "1042": "task414_mickey_ar_sentence_perturbation_generation", "1043": "task415_mickey_bg_sentence_perturbation_generation", "1044": "task416_mickey_de_sentence_perturbation_generation", "1045": "task417_mickey_es_sentence_perturbation_generation", "1046": "task418_persent_title_generation", "1047": "task419_persent_answer_generation", "1048": "task420_persent_document_sentiment_classification", "1049": "task421_persent_sentence_sentiment_classification", "1050": "task422_persent_sentence_sentiment_verification", "1051": "task423_persent_document_sentiment_verification", "1052": "task424_hindienglish_corpora_hi_en_translation", "1053": "task425_hindienglish_corpora_en_hi_translation", "1054": "task426_hindienglish_corpora_hi-en_classification", "1055": "task427_hindienglish_corpora_hi-en_language_identification", "1056": "task428_senteval_inversion", "1057": "task429_senteval_tense", "1058": "task430_senteval_subject_count", "1059": "task431_senteval_object_count", "1060": "task432_alt_en_hi_translation", "1061": "task433_alt_hi_en_translation", "1062": "task434_alt_en_hi_answer_generation", "1063": "task435_alt_en_ja_translation", "1064": "task436_alt_ja_en_translation", "1065": "task437_alt_en_ja_answer_generation", "1066": "task438_eng_guj_parallel_corpus_en_gu_translation", "1067": "task439_eng_guj_parallel_corpus_gu_en_translation", "1068": "task440_eng_guj_parallel_corpus_gu-en_classification", "1069": "task441_eng_guj_parallel_corpus_gu-en_language_identification", "1070": "task442_com_qa_paraphrase_question_generation", "1071": "task443_com_qa_ans_question_generation", "1072": "task444_com_qa_question_paraphrases_answer_generation", "1073": "task446_opus_paracrawl_en_so_translation", "1074": "task447_opus_paracrawl_classification", "1075": "task448_opus_paracrawl_en_tl_translation", "1076": "task449_opus_paracrawl_ig_en_translation", "1077": "task450_opus_paracrawl_so_en_translation", "1078": "task451_opus_paracrawl_tl_en_translation", "1079": "task452_opus_paracrawl_en_ig_translation", "1080": "task453_swag_answer_generation", "1081": "task454_swag_incorrect_answer_generation", "1082": "task455_swag_context_generation", "1083": "task456_matres_intention_classification", "1084": "task457_matres_conditional_classification", "1085": "task458_matres_negation_classification", "1086": "task459_matres_static_classification", "1087": "task460_qasper_answer_generation", "1088": "task461_qasper_question_generation", "1089": "task462_qasper_classification", "1090": "task463_parsinlu_entailment_classification", "1091": "task464_parsinlu_entailment_sentence_generation", "1092": "task465_parsinlu_qqp_classification", "1093": "task466_parsinlu_qqp_text_modification", "1094": "task467_parsinlu_rc_answer_generation", "1095": "task468_parsinlu_rc_question_generation", "1096": "task469_mrqa_answer_generation", "1097": "task470_mrqa_question_generation", "1098": "task471_haspart_answer_generation", "1099": "task472_haspart_classification", "1100": "task473_parsinlu_mc_classification", "1101": "task474_parsinlu_mc_classification", "1102": "task475_yelp_polarity_classification", "1103": "task476_cls_english_books_classification", "1104": "task477_cls_english_dvd_classification", "1105": "task478_cls_english_music_classification", "1106": "task479_cls_german_books_classification", "1107": "task480_cls_german_dvd_classification", "1108": "task481_cls_german_music_classification", "1109": "task482_cls_french_books_classification", "1110": "task483_cls_french_dvd_classification", "1111": "task484_cls_french_music_classification", "1112": "task485_cls_japanese_books_classification", "1113": "task486_cls_japanese_dvd_classification", "1114": "task487_cls_japanese_music_classification", "1115": "task488_extract_all_alphabetical_elements_from_list_in_order", "1116": "task489_mwsc_question_generation", "1117": "task490_mwsc_options_generation", "1118": "task491_mwsc_answer_generation", "1119": "task492_mwsc_incorrect_answer_generation", "1120": "task493_review_polarity_classification", "1121": "task494_review_polarity_answer_generation", "1122": "task495_semeval_headline_classification", "1123": "task496_semeval_answer_generation", "1124": "task497_extract_all_numbers_from_list_in_order", "1125": "task498_scruples_anecdotes_whoiswrong_classification", "1126": "task499_extract_and_add_all_numbers_from_list", "1127": "task500_scruples_anecdotes_title_generation", "1128": "task501_scruples_anecdotes_post_type_verification", "1129": "task502_scruples_anecdotes_whoiswrong_verification", "1130": "task503_scruples_anecdotes_isanswerable", "1131": "task504_count_all_alphabetical_elements_in_list", "1132": "task505_count_all_numerical_elements_in_list", "1133": "task506_position_of_all_alphabetical_elements_in_list", "1134": "task507_position_of_all_numerical_elements_in_list", "1135": "task508_scruples_dilemmas_more_ethical_isidentifiable", "1136": "task509_collate_of_all_alphabetical_and_numerical_elements_in_list_separately", "1137": "task510_reddit_tifu_title_summarization", "1138": "task511_reddit_tifu_long_text_summarization", "1139": "task512_twitter_emotion_classification", "1140": "task513_argument_stance_classification", "1141": "task514_argument_consequence_classification", "1142": "task515_senteval_odd_word_out", "1143": "task516_senteval_conjoints_inversion", "1144": "task517_emo_classify_emotion_of_dialogue", "1145": "task518_emo_different_dialogue_emotions", "1146": "task519_aquamuse_question_generation", "1147": "task520_aquamuse_answer_given_in_passage", "1148": "task521_trivia_question_classification", "1149": "task522_news_editorial_summary", "1150": "task523_find_if_numbers_or_alphabets_are_more_in_list", "1151": "task524_parsinlu_food_aspect_classification", "1152": "task525_parsinlu_movie_aspect_classification", "1153": "task526_parsinlu_movie_overal_classification", "1154": "task527_parsinlu_food_overal_classification", "1155": "task528_parsinlu_movie_aspect_detection", "1156": "task529_parsinlu_food_aspect_detection", "1157": "task530_europarl_en_es_translation", "1158": "task531_europarl_es_en_translation", "1159": "task532_europarl_en-es_classification", "1160": "task533_europarl_es-en_language_identification", "1161": "task534_farstail_entailment", "1162": "task535_alt_translation_ch_en", "1163": "task536_alt_translation_vi_en", "1164": "task537_alt_translation_th_en", "1165": "task538_alt_translation_bu_en", "1166": "task539_alt_translation_ma_en", "1167": "task540_alt_translation_la_en", "1168": "task541_alt_translation_kh_en", "1169": "task542_alt_translation_ja_en", "1170": "task543_alt_translation_bh_en", "1171": "task544_alt_translation_hi_en", "1172": "task545_alt_translation_fi_en", "1173": "task546_alt_translation_bg_en", "1174": "task547_alt_translation_entk_en", "1175": "task548_alt_translation_en_ch", "1176": "task549_alt_translation_en_vi", "1177": "task550_discofuse_sentence_generation", "1178": "task551_alt_translation_en_th", "1179": "task552_alt_translation_en_bu", "1180": "task553_alt_translation_en_ma", "1181": "task554_alt_translation_en_la", "1182": "task555_alt_translation_en_kh", "1183": "task556_alt_translation_en_ja", "1184": "task557_alt_translation_en_ba", "1185": "task558_alt_translation_en_hi", "1186": "task559_alt_translation_en_fi", "1187": "task560_alt_translation_en_entk", "1188": "task561_alt_translation_en_bg", "1189": "task562_alt_language_identification", "1190": "task563_discofuse_answer_generation", "1191": "task564_discofuse_classification", "1192": "task565_circa_answer_generation", "1193": "task566_circa_classification", "1194": "task567_circa_text_generation", "1195": "task568_circa_question_generation", "1196": "task569_recipe_nlg_text_generation", "1197": "task570_recipe_nlg_ner_generation", "1198": "task571_recipe_nlg_ner_generation", "1199": "task572_recipe_nlg_text_generation", "1200": "task573_air_dialogue_classification", "1201": "task574_air_dialogue_sentence_generation", "1202": "task575_air_dialogue_classification", "1203": "task576_curiosity_dialogs_answer_generation", "1204": "task577_curiosity_dialogs_classification", "1205": "task578_curiosity_dialogs_answer_generation", "1206": "task579_socialiqa_classification", "1207": "task580_socialiqa_answer_generation", "1208": "task581_socialiqa_question_generation", "1209": "task582_naturalquestion_answer_generation", "1210": "task583_udeps_eng_coarse_pos_tagging", "1211": "task584_udeps_eng_fine_pos_tagging", "1212": "task585_preposition_classification", "1213": "task586_amazonfood_polarity_classification", "1214": "task587_amazonfood_polarity_correction_classification", "1215": "task588_amazonfood_rating_classification", "1216": "task589_amazonfood_summary_text_generation", "1217": "task590_amazonfood_summary_correction_classification", "1218": "task591_sciq_answer_generation", "1219": "task592_sciq_incorrect_answer_generation", "1220": "task593_sciq_explanation_generation", "1221": "task594_sciq_question_generation", "1222": "task595_mocha_answer_generation", "1223": "task596_mocha_question_generation", "1224": "task597_cuad_answer_generation", "1225": "task598_cuad_answer_generation", "1226": "task599_cuad_question_generation", "1227": "task600_find_the_longest_common_substring_in_two_strings", "1228": "task601_flores_translation_sntoen", "1229": "task602_wikitext-103_answer_generation", "1230": "task603_wikitext-103_fill_in_the_blank", "1231": "task604_flores_translation_entosn", "1232": "task605_find_the_longest_common_subsequence_in_two_lists", "1233": "task606_sum_of_all_numbers_in_list_between_positions_i_and_j", "1234": "task607_sbic_intentional_offense_binary_classification", "1235": "task608_sbic_sexual_offense_binary_classification", "1236": "task609_sbic_potentially_offense_binary_classification", "1237": "task610_conllpp_ner", "1238": "task611_mutual_multi_turn_dialogue", "1239": "task612_yorubabbc_classification", "1240": "task613_politifact_text_generation", "1241": "task614_glucose_cause_event_detection", "1242": "task615_moviesqa_answer_generation", "1243": "task616_cola_classification", "1244": "task617_amazonreview_category_text_generation", "1245": "task618_amazonreview_summary_text_generation", "1246": "task619_ohsumed_abstract_title_generation", "1247": "task620_ohsumed_medical_subject_headings_answer_generation", "1248": "task621_ohsumed_yes_no_numerical_answer_generation", "1249": "task622_replace_alphabets_in_a_list_by_their_position_in_english_alphabet", "1250": "task623_ohsumed_yes_no_answer_generation", "1251": "task624_ohsumed_question_answering", "1252": "task625_xlwic_true_or_false_answer_generation", "1253": "task626_xlwic_sentence_based_on_given_word_sentence_generation", "1254": "task627_xlwic_word_with_same_meaning_sentence_generation", "1255": "task628_xlwic_word_with_different_meaning_sentence_generation", "1256": "task629_dbpedia_14_classification", "1257": "task630_dbpedia_14_classification", "1258": "task631_dbpedia_14_incorrect_answer_generation", "1259": "task632_dbpedia_14_classification", "1260": "task633_dbpedia_14_answer_generation", "1261": "task634_allegro_reviews_classification", "1262": "task635_allegro_reviews_answer_generation", "1263": "task636_extract_and_sort_unique_alphabets_in_a_list", "1264": "task637_extract_and_sort_unique_digits_in_a_list", "1265": "task638_multi_woz_classification", "1266": "task639_multi_woz_user_utterance_generation", "1267": "task640_esnli_classification", "1268": "task641_esnli_classification", "1269": "task642_esnli_classification", "1270": "task643_refresd_classification", "1271": "task644_refresd_translation", "1272": "task645_summarization", "1273": "task646_answer_generation", "1274": "task647_answer_generation", "1275": "task648_answer_generation", "1276": "task649_race_blank_question_generation", "1277": "task650_opus100_ar_en_translation", "1278": "task651_opus100_en_ar_translation", "1279": "task652_parsinlu_en_fa_translation", "1280": "task653_parsinlu_fa_en_translation", "1281": "task654_bible_fa_en_translation", "1282": "task655_bible_en_fa_translation", "1283": "task656_quran_en_fa_translation", "1284": "task657_quran_fa_en_translation", "1285": "task658_tep_en_fa_translation", "1286": "task659_tep_fa_en_translation", "1287": "task660_mizan_fa_en_translation", "1288": "task661_mizan_en_fa_translation", "1289": "task662_global_voices_fa_en_translation", "1290": "task663_global_voices_en_fa_translation", "1291": "task668_extreme_abstract_summarization", "1292": "task669_ambigqa_answer_generation", "1293": "task670_ambigqa_question_generation", "1294": "task671_ambigqa_text_generation", "1295": "task672_amazon_and_yelp_summarization_dataset_summarization", "1296": "task672_nummersense", "1297": "task673_google_wellformed_query_classification", "1298": "task674_google_wellformed_query_sentence_generation", "1299": "task675_google_wellformed_query_sentence_generation", "1300": "task676_ollie_relationship_answer_generation", "1301": "task677_ollie_sentence_answer_generation", "1302": "task678_ollie_actual_relationship_answer_generation", "1303": "task679_hope_edi_english_text_classification", "1304": "task680_hope_edi_tamil_text_classification", "1305": "task681_hope_edi_malayalam_text_classification", "1306": "task682_online_privacy_policy_text_classification", "1307": "task683_online_privacy_policy_text_purpose_answer_generation", "1308": "task684_online_privacy_policy_text_information_type_generation", "1309": "task738_perspectrum_classification", "1310": "task739_lhoestq_question_generation", "1311": "task740_lhoestq_answer_generation_quantity", "1312": "task741_lhoestq_answer_generation_place", "1313": "task742_lhoestq_answer_generation_frequency", "1314": "task743_eurlex_summarization", "1315": "task744_eurlex_classification", "1316": "task745_ai2_arithmetic_questions_arithmetic", "1317": "task746_yelp_restaurant_review_classification", "1318": "task747_glucose_cause_emotion_detection", "1319": "task748_glucose_reverse_cause_event_detection", "1320": "task749_glucose_reverse_cause_emotion_detection", "1321": "task750_aqua_multiple_choice_answering", "1322": "task751_svamp_subtraction_question_answering", "1323": "task752_svamp_multiplication_question_answering", "1324": "task753_svamp_addition_question_answering", "1325": "task754_svamp_common-division_question_answering", "1326": "task755_find_longest_substring_and_replace_its_sorted_lowercase_version_in_both_lists", "1327": "task756_find_longert_substring_and_return_all_unique_alphabets_in_it", "1328": "task757_msr_sqa_question_generation", "1329": "task758_msr_sqa_question_answer_generation", "1330": "task759_msr_sqa_incorrect_answer_generation", "1331": "task760_msr_sqa_long_text_generation", "1332": "task761_app_review_classification", "1333": "task762_emea_fr_sk_translation", "1334": "task763_emea_es_lt_translation", "1335": "task764_emea_bg_el_classification", "1336": "task765_emea_bg_el_translation", "1337": "task766_craigslist_bargains_classification", "1338": "task767_craigslist_bargains_classification", "1339": "task768_qed_text_span_selection", "1340": "task769_qed_summarization", "1341": "task770_pawsx_english_text_modification", "1342": "task771_pawsx_korean_text_modification", "1343": "task772_pawsx_french_text_modification", "1344": "task773_pawsx_spanish_text_modification", "1345": "task774_pawsx_german_text_modification", "1346": "task775_pawsx_chinese_text_modification", "1347": "task776_pawsx_japanese_text_modification", "1348": "task777_pawsx_english_korean_translation", "1349": "task778_pawsx_english_french_translation", "1350": "task779_pawsx_english_spanish_translation", "1351": "task780_pawsx_english_german_translation", "1352": "task781_pawsx_english_chinese_translation", "1353": "task782_pawsx_english_japanese_translation", "1354": "task783_pawsx_korean_english_translation", "1355": "task784_pawsx_korean_french_translation", "1356": "task785_pawsx_korean_spanish_translation", "1357": "task786_pawsx_korean_german_translation", "1358": "task787_pawsx_korean_chinese_translation", "1359": "task788_pawsx_korean_japanese_translation", "1360": "task789_pawsx_french_english_translation", "1361": "task790_pawsx_french_korean_translation", "1362": "task791_pawsx_french_spanish_translation", "1363": "task792_pawsx_french_german_translation", "1364": "task793_pawsx_french_chinese_translation", "1365": "task794_pawsx_french_japanese_translation", "1366": "task795_pawsx_spanish_english_translation", "1367": "task796_pawsx_spanish_korean_translation", "1368": "task797_pawsx_spanish_french_translation", "1369": "task798_pawsx_spanish_german_translation", "1370": "task799_pawsx_spanish_chinese_translation", "1371": "task800_pawsx_spanish_japanese_translation", "1372": "task801_pawsx_german_english_translation", "1373": "task802_pawsx_german_korean_translation", "1374": "task803_pawsx_german_french_translation", "1375": "task804_pawsx_german_spanish_translation", "1376": "task805_pawsx_german_chinese_translation", "1377": "task806_pawsx_german_japanese_translation", "1378": "task807_pawsx_chinese_english_translation", "1379": "task808_pawsx_chinese_korean_translation", "1380": "task809_pawsx_chinese_french_translation", "1381": "task810_pawsx_chinese_spanish_translation", "1382": "task811_pawsx_chinese_german_translation", "1383": "task812_pawsx_chinese_japanese_translation", "1384": "task813_pawsx_japanese_english_translation", "1385": "task814_pawsx_japanese_korean_translation", "1386": "task815_pawsx_japanese_french_translation", "1387": "task816_pawsx_japanese_spanish_translation", "1388": "task817_pawsx_japanese_german_translation", "1389": "task818_pawsx_japanese_chinese_translation", "1390": "task819_pec_sentiment_classification", "1391": "task820_protoqa_answer_generation", "1392": "task821_protoqa_question_generation", "1393": "task823_peixian-rtgender_sentiment_analysis", "1394": "task827_copa_commonsense_reasoning", "1395": "task828_copa_commonsense_cause_effect", "1396": "task829_giga_fren_translation", "1397": "task830_poleval2019_mt_translation", "1398": "task831_giga_fren_classification", "1399": "task832_poleval2019_mt_classification", "1400": "task833_poem_sentiment_classification", "1401": "task834_mathdataset_classification", "1402": "task835_mathdataset_answer_generation", "1403": "task836_viquiquad_question_generation", "1404": "task837_viquiquad_answer_generation", "1405": "task838_cdt_classification", "1406": "task839_cdt_classification", "1407": "task840_para_pdt_en_es_translation", "1408": "task841_para_pdt_de_en_translation", "1409": "task842_para_pdt_cs_en_translation", "1410": "task843_financial_phrasebank_classification", "1411": "task844_financial_phrasebank_classification", "1412": "task845_pubmedqa_question_generation", "1413": "task846_pubmedqa_classification", "1414": "task847_pubmedqa_question_generation", "1415": "task848_pubmedqa_classification", "1416": "task849_pubmedqa_answer_generation", "1417": "task850_synthetic_longest_palindrome", "1418": "task851_synthetic_multiply_evens", "1419": "task852_synthetic_multiply_odds", "1420": "task853_hippocorpus_long_text_generation", "1421": "task854_hippocorpus_classification", "1422": "task855_conv_ai_2_classification", "1423": "task856_conv_ai_2_classification", "1424": "task857_inquisitive_question_generation", "1425": "task858_inquisitive_span_detection", "1426": "task859_prost_question_generation", "1427": "task860_prost_mcq_generation", "1428": "task861_asdiv_addsub_question_answering", "1429": "task861_prost_mcq_answers_generation", "1430": "task862_asdiv_multidiv_question_answering", "1431": "task863_asdiv_multiop_question_answering", "1432": "task864_asdiv_singleop_question_answering", "1433": "task865_mawps_addsub_question_answering", "1434": "task866_mawps_multidiv_question_answering", "1435": "task867_mawps_multiop_question_answering", "1436": "task868_cfq_mcd1_explanation_to_sql", "1437": "task868_mawps_singleop_question_answering", "1438": "task869_cfq_mcd1_sql_to_explanation", "1439": "task870_msmarco_answer_generation", "1440": "task871_msmarco_question_generation", "1441": "task872_opus_xhosanavy_translation_eng_xhosa", "1442": "task873_opus_xhosanavy_translation_xhosa_eng", "1443": "task874_opus_xhosanavy_sr", "1444": "task875_emotion_classification", "1445": "task877_kde4_translation", "1446": "task878_kde4_translation", "1447": "task879_schema_guided_dstc8_classification", "1448": "task880_schema_guided_dstc8_classification", "1449": "task881_schema_guided_dstc8_classification", "1450": "task886_quail_question_generation", "1451": "task887_quail_answer_generation", "1452": "task888_reviews_classification", "1453": "task889_goemotions_classification", "1454": "task890_gcwd_classification", "1455": "task891_gap_coreference_resolution", "1456": "task892_gap_reverse_coreference_resolution", "1457": "task893_gap_fill_the_blank_coreference_resolution", "1458": "task896_miam_language_classification", "1459": "task897_freebase_qa_topic_question_generation", "1460": "task898_freebase_qa_answer_generation", "1461": "task899_freebase_qa_topic_generation", "1462": "task900_freebase_qa_category_classification", "1463": "task901_freebase_qa_category_question_generation", "1464": "task902_deceptive_opinion_spam_classification", "1465": "task903_deceptive_opinion_spam_classification", "1466": "task904_hate_speech_offensive_classification", "1467": "task905_hate_speech_offensive_classification", "1468": "task906_dialogre_identify_names", "1469": "task907_dialogre_identify_relationships", "1470": "task908_dialogre_identify_familial_relationships", "1471": "task909_dialogre_prevalent_speakers", "1472": "task910_bianet_classification", "1473": "task911_bianet_translation", "1474": "task912_bianet_classification", "1475": "task913_bianet_translation", "1476": "task914_bianet_translation", "1477": "task917_coqa_question_generation", "1478": "task918_coqa_answer_generation", "1479": "task919_coqa_incorrect_answer_generation", "1480": "task921_code_x_glue_information_retreival", "1481": "task922_event2mind_word_generation", "1482": "task923_event2mind_classifier", "1483": "task924_event2mind_word_generation", "1484": "task925_coached_conv_pref_classifier", "1485": "task926_coached_conv_pref_word_generation", "1486": "task927_yelp_negative_to_positive_style_transfer", "1487": "task928_yelp_positive_to_negative_style_transfer", "1488": "task929_products_reviews_classification", "1489": "task930_dailydialog_classification", "1490": "task931_dailydialog_classification", "1491": "task932_dailydialog_classification", "1492": "task933_wiki_auto_style_transfer", "1493": "task934_turk_simplification", "1494": "task935_defeasible_nli_atomic_classification", "1495": "task936_defeasible_nli_snli_classification", "1496": "task937_defeasible_nli_social_classification", "1497": "task938_copa_hi_commonsense_reasoning", "1498": "task939_copa_hi_commonsense_cause_effect", "1499": "task940_copa_gu_commonsense_reasoning", "1500": "task941_copa_gu_commonsense_cause_effect", "1501": "task942_copa_mr_commonsense_reasoning", "1502": "task943_copa_mr_commonsense_cause_effect", "1503": "task944_wiki_cloze_as_multiple_choice_question_answering", "1504": "task945_wiki_cloze_bn_multiple_choice_question_answering", "1505": "task946_wiki_cloze_gu_multiple_choice_question_answering", "1506": "task947_wiki_cloze_hi_multiple_choice_question_answering", "1507": "task948_wiki_cloze_kn_multiple_choice_question_answering", "1508": "task949_wiki_cloze_ml_multiple_choice_question_answering", "1509": "task950_wiki_cloze_mr_multiple_choice_question_answering", "1510": "task951_wiki_cloze_or_multiple_choice_question_answering", "1511": "task952_wiki_cloze_pa_multiple_choice_question_answering", "1512": "task953_wiki_cloze_ta_multiple_choice_question_answering", "1513": "task954_wiki_cloze_te_multiple_choice_question_answering", "1514": "task955_wiki_auto_style_transfer", "1515": "task956_leetcode_420_strong_password_check", "1516": "task957_e2e_nlg_text_generation_generate", "1517": "task958_e2e_nlg_text_generation_parse", "1518": "task959_e2e_nlg_text_generation_identify", "1519": "task960_ancora-ca-ner_named_entity_recognition", "1520": "task961_ancora-ca-ner_text_auto_completion", "1521": "task962_ancora-ca-ner_missing_word_prediction", "1522": "task963_librispeech_asr_next_word_prediction", "1523": "task964_librispeech_asr_text_auto_completion", "1524": "task965_librispeech_asr_missing_word_prediction", "1525": "task966_ruletaker_fact_checking_based_on_given_context", "1526": "task967_ruletaker_incorrect_fact_generation_based_on_given_paragraph", "1527": "task968_xcopa_commonsense_reasoning_et", "1528": "task969_xcopa_commonsense_cause_effect_et", "1529": "task970_sherliic_causal_relationship", "1530": "task974_prachathai67k_sentiment_classification", "1531": "task975_prachathai67k_same_genre_classification", "1532": "task976_pib_indian_language_identification", "1533": "task977_pib_translation_oriya_urdu", "1534": "task978_pib_translation_urdu_oriya", "1535": "task979_pib_translation_malayalam_oriya", "1536": "task980_pib_translation_oriya_malayalam", "1537": "task981_pib_translation_bengali_tamil", "1538": "task982_pib_translation_tamil_bengali", "1539": "task983_pib_translation_gujarati_marathi", "1540": "task984_pib_translation_marathi_gujarati", "1541": "task985_pib_translation_hindi_oriya", "1542": "task986_pib_translation_oriya_hindi", "1543": "task987_pib_translation_english_oriya", "1544": "task988_pib_translation_oriya_english", "1545": "task989_pib_translation_marathi_urdu", "1546": "task990_pib_translation_urdu_marathi", "1547": "task991_pib_translation_english_tamil", "1548": "task992_pib_translation_tamil_english", "1549": "task993_pib_translation_hindi_tamil", "1550": "task994_pib_translation_tamil_hindi", "1551": "task995_pib_translation_bengali_english", "1552": "task996_pib_translation_english_bengali", "1553": "task997_pib_translation_bengali_oriya", "1554": "task998_pib_translation_oriya_bengali", "1555": "task999_pib_translation_malayalam_tamil"}}}}, {"name": "template_type", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 11747069492.39624, "num_examples": 9935372}, {"name": "validation", "num_bytes": 118658103.60376057, "num_examples": 100358}], "download_size": 7039758885, "dataset_size": 11865727596.0}} | 2023-12-16T11:06:53+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "niv2-submix-4096"
More Information needed | [
"# Dataset Card for \"niv2-submix-4096\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"niv2-submix-4096\"\n\nMore Information needed"
] | [
6,
17
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"niv2-submix-4096\"\n\nMore Information needed"
] |
b706ef7fed9e543fcefecfa9012fc6d25a817104 | # Dataset Card for "cot-submix-4096"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | kowndinya23/cot-submix-4096 | [
"region:us"
] | 2023-12-16T11:07:27+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}, {"split": "validation", "path": "data/validation-*"}]}], "dataset_info": {"features": [{"name": "inputs", "dtype": "string"}, {"name": "targets", "dtype": "string"}, {"name": "task_source", "dtype": "string"}, {"name": "task_name", "dtype": {"class_label": {"names": {"0": "cot_creak", "1": "cot_creak_ii", "2": "cot_ecqa", "3": "cot_ecqa_ii", "4": "cot_esnli", "5": "cot_esnli_ii", "6": "cot_gsm8k", "7": "cot_gsm8k_ii", "8": "cot_qasc", "9": "cot_qasc_ii", "10": "cot_sensemaking", "11": "cot_sensemaking_ii", "12": "cot_strategyqa", "13": "cot_strategyqa_ii", "14": "stream_aqua", "15": "stream_aqua_ii", "16": "stream_qed", "17": "stream_qed_ii"}}}}, {"name": "template_type", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 205652661.2399643, "num_examples": 182005}, {"name": "validation", "num_bytes": 2077938.7600356825, "num_examples": 1839}], "download_size": 100330523, "dataset_size": 207730600.0}} | 2023-12-16T11:07:41+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "cot-submix-4096"
More Information needed | [
"# Dataset Card for \"cot-submix-4096\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"cot-submix-4096\"\n\nMore Information needed"
] | [
6,
16
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"cot-submix-4096\"\n\nMore Information needed"
] |
321cd36a7e290eb6c8abd859bbf77b4989b84c34 | # Dataset Card for "dialog-submix-4096"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | kowndinya23/dialog-submix-4096 | [
"region:us"
] | 2023-12-16T11:08:33+00:00 | {"configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}, {"split": "validation", "path": "data/validation-*"}]}], "dataset_info": {"features": [{"name": "inputs", "dtype": "string"}, {"name": "targets", "dtype": "string"}, {"name": "task_source", "dtype": "string"}, {"name": "task_name", "dtype": {"class_label": {"names": {"0": "qrecc", "1": "qrecc_ii", "2": "wiki_dialog", "3": "wiki_dialog_ii"}}}}, {"name": "template_type", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 1010204960.5976143, "num_examples": 548330}, {"name": "validation", "num_bytes": 10204667.402385762, "num_examples": 5539}], "download_size": 585112307, "dataset_size": 1020409628.0}} | 2023-12-16T11:09:22+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "dialog-submix-4096"
More Information needed | [
"# Dataset Card for \"dialog-submix-4096\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"dialog-submix-4096\"\n\nMore Information needed"
] | [
6,
17
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"dialog-submix-4096\"\n\nMore Information needed"
] |
2eb26279bcce29204c8921635a160310b90276a3 |
# Dataset Card for Evaluation run of abhinand/tamil-llama-13b-base-v0.1
<!-- Provide a quick summary of the dataset. -->
Dataset automatically created during the evaluation run of model [abhinand/tamil-llama-13b-base-v0.1](https://huggingface.co/abhinand/tamil-llama-13b-base-v0.1) on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
The dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An additional configuration "results" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).
To load the details from a run, you can for instance do the following:
```python
from datasets import load_dataset
data = load_dataset("open-llm-leaderboard/details_abhinand__tamil-llama-13b-base-v0.1",
"harness_winogrande_5",
split="train")
```
## Latest results
These are the [latest results from run 2023-12-16T11:40:41.184211](https://huggingface.co/datasets/open-llm-leaderboard/details_abhinand__tamil-llama-13b-base-v0.1/blob/main/results_2023-12-16T11-40-41.184211.json)(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the "latest" split for each eval):
```python
{
"all": {
"acc": 0.5167194240440821,
"acc_stderr": 0.03375847094673175,
"acc_norm": 0.5253161101910007,
"acc_norm_stderr": 0.0346825452797334,
"mc1": 0.2423500611995104,
"mc1_stderr": 0.01500067437357034,
"mc2": 0.36559745885035844,
"mc2_stderr": 0.013805854330074238
},
"harness|arc:challenge|25": {
"acc": 0.5034129692832765,
"acc_stderr": 0.014611050403244081,
"acc_norm": 0.5281569965870307,
"acc_norm_stderr": 0.014588204105102203
},
"harness|hellaswag|10": {
"acc": 0.5944035052778331,
"acc_stderr": 0.004900036261309048,
"acc_norm": 0.7995419239195379,
"acc_norm_stderr": 0.003995249591993226
},
"harness|hendrycksTest-abstract_algebra|5": {
"acc": 0.32,
"acc_stderr": 0.046882617226215034,
"acc_norm": 0.32,
"acc_norm_stderr": 0.046882617226215034
},
"harness|hendrycksTest-anatomy|5": {
"acc": 0.4666666666666667,
"acc_stderr": 0.043097329010363554,
"acc_norm": 0.4666666666666667,
"acc_norm_stderr": 0.043097329010363554
},
"harness|hendrycksTest-astronomy|5": {
"acc": 0.47368421052631576,
"acc_stderr": 0.04063302731486671,
"acc_norm": 0.47368421052631576,
"acc_norm_stderr": 0.04063302731486671
},
"harness|hendrycksTest-business_ethics|5": {
"acc": 0.54,
"acc_stderr": 0.05009082659620332,
"acc_norm": 0.54,
"acc_norm_stderr": 0.05009082659620332
},
"harness|hendrycksTest-clinical_knowledge|5": {
"acc": 0.5584905660377358,
"acc_stderr": 0.030561590426731833,
"acc_norm": 0.5584905660377358,
"acc_norm_stderr": 0.030561590426731833
},
"harness|hendrycksTest-college_biology|5": {
"acc": 0.5347222222222222,
"acc_stderr": 0.04171115858181618,
"acc_norm": 0.5347222222222222,
"acc_norm_stderr": 0.04171115858181618
},
"harness|hendrycksTest-college_chemistry|5": {
"acc": 0.38,
"acc_stderr": 0.04878317312145633,
"acc_norm": 0.38,
"acc_norm_stderr": 0.04878317312145633
},
"harness|hendrycksTest-college_computer_science|5": {
"acc": 0.36,
"acc_stderr": 0.048241815132442176,
"acc_norm": 0.36,
"acc_norm_stderr": 0.048241815132442176
},
"harness|hendrycksTest-college_mathematics|5": {
"acc": 0.27,
"acc_stderr": 0.044619604333847394,
"acc_norm": 0.27,
"acc_norm_stderr": 0.044619604333847394
},
"harness|hendrycksTest-college_medicine|5": {
"acc": 0.48554913294797686,
"acc_stderr": 0.03810871630454764,
"acc_norm": 0.48554913294797686,
"acc_norm_stderr": 0.03810871630454764
},
"harness|hendrycksTest-college_physics|5": {
"acc": 0.24509803921568626,
"acc_stderr": 0.042801058373643966,
"acc_norm": 0.24509803921568626,
"acc_norm_stderr": 0.042801058373643966
},
"harness|hendrycksTest-computer_security|5": {
"acc": 0.69,
"acc_stderr": 0.04648231987117316,
"acc_norm": 0.69,
"acc_norm_stderr": 0.04648231987117316
},
"harness|hendrycksTest-conceptual_physics|5": {
"acc": 0.43829787234042555,
"acc_stderr": 0.03243618636108102,
"acc_norm": 0.43829787234042555,
"acc_norm_stderr": 0.03243618636108102
},
"harness|hendrycksTest-econometrics|5": {
"acc": 0.2807017543859649,
"acc_stderr": 0.042270544512322,
"acc_norm": 0.2807017543859649,
"acc_norm_stderr": 0.042270544512322
},
"harness|hendrycksTest-electrical_engineering|5": {
"acc": 0.496551724137931,
"acc_stderr": 0.041665675771015785,
"acc_norm": 0.496551724137931,
"acc_norm_stderr": 0.041665675771015785
},
"harness|hendrycksTest-elementary_mathematics|5": {
"acc": 0.29365079365079366,
"acc_stderr": 0.02345603738398202,
"acc_norm": 0.29365079365079366,
"acc_norm_stderr": 0.02345603738398202
},
"harness|hendrycksTest-formal_logic|5": {
"acc": 0.30158730158730157,
"acc_stderr": 0.04104947269903394,
"acc_norm": 0.30158730158730157,
"acc_norm_stderr": 0.04104947269903394
},
"harness|hendrycksTest-global_facts|5": {
"acc": 0.36,
"acc_stderr": 0.04824181513244218,
"acc_norm": 0.36,
"acc_norm_stderr": 0.04824181513244218
},
"harness|hendrycksTest-high_school_biology|5": {
"acc": 0.6483870967741936,
"acc_stderr": 0.027162537826948458,
"acc_norm": 0.6483870967741936,
"acc_norm_stderr": 0.027162537826948458
},
"harness|hendrycksTest-high_school_chemistry|5": {
"acc": 0.33497536945812806,
"acc_stderr": 0.033208527423483104,
"acc_norm": 0.33497536945812806,
"acc_norm_stderr": 0.033208527423483104
},
"harness|hendrycksTest-high_school_computer_science|5": {
"acc": 0.53,
"acc_stderr": 0.050161355804659205,
"acc_norm": 0.53,
"acc_norm_stderr": 0.050161355804659205
},
"harness|hendrycksTest-high_school_european_history|5": {
"acc": 0.6484848484848484,
"acc_stderr": 0.037282069986826503,
"acc_norm": 0.6484848484848484,
"acc_norm_stderr": 0.037282069986826503
},
"harness|hendrycksTest-high_school_geography|5": {
"acc": 0.6414141414141414,
"acc_stderr": 0.034169036403915214,
"acc_norm": 0.6414141414141414,
"acc_norm_stderr": 0.034169036403915214
},
"harness|hendrycksTest-high_school_government_and_politics|5": {
"acc": 0.7616580310880829,
"acc_stderr": 0.03074890536390988,
"acc_norm": 0.7616580310880829,
"acc_norm_stderr": 0.03074890536390988
},
"harness|hendrycksTest-high_school_macroeconomics|5": {
"acc": 0.48205128205128206,
"acc_stderr": 0.025334667080954935,
"acc_norm": 0.48205128205128206,
"acc_norm_stderr": 0.025334667080954935
},
"harness|hendrycksTest-high_school_mathematics|5": {
"acc": 0.2851851851851852,
"acc_stderr": 0.027528599210340496,
"acc_norm": 0.2851851851851852,
"acc_norm_stderr": 0.027528599210340496
},
"harness|hendrycksTest-high_school_microeconomics|5": {
"acc": 0.5168067226890757,
"acc_stderr": 0.03246013680375308,
"acc_norm": 0.5168067226890757,
"acc_norm_stderr": 0.03246013680375308
},
"harness|hendrycksTest-high_school_physics|5": {
"acc": 0.31125827814569534,
"acc_stderr": 0.037804458505267334,
"acc_norm": 0.31125827814569534,
"acc_norm_stderr": 0.037804458505267334
},
"harness|hendrycksTest-high_school_psychology|5": {
"acc": 0.7211009174311926,
"acc_stderr": 0.019227468876463503,
"acc_norm": 0.7211009174311926,
"acc_norm_stderr": 0.019227468876463503
},
"harness|hendrycksTest-high_school_statistics|5": {
"acc": 0.36574074074074076,
"acc_stderr": 0.03284738857647206,
"acc_norm": 0.36574074074074076,
"acc_norm_stderr": 0.03284738857647206
},
"harness|hendrycksTest-high_school_us_history|5": {
"acc": 0.6764705882352942,
"acc_stderr": 0.0328347205610856,
"acc_norm": 0.6764705882352942,
"acc_norm_stderr": 0.0328347205610856
},
"harness|hendrycksTest-high_school_world_history|5": {
"acc": 0.6708860759493671,
"acc_stderr": 0.03058732629470236,
"acc_norm": 0.6708860759493671,
"acc_norm_stderr": 0.03058732629470236
},
"harness|hendrycksTest-human_aging|5": {
"acc": 0.600896860986547,
"acc_stderr": 0.03286745312567961,
"acc_norm": 0.600896860986547,
"acc_norm_stderr": 0.03286745312567961
},
"harness|hendrycksTest-human_sexuality|5": {
"acc": 0.5648854961832062,
"acc_stderr": 0.04348208051644858,
"acc_norm": 0.5648854961832062,
"acc_norm_stderr": 0.04348208051644858
},
"harness|hendrycksTest-international_law|5": {
"acc": 0.6942148760330579,
"acc_stderr": 0.042059539338841226,
"acc_norm": 0.6942148760330579,
"acc_norm_stderr": 0.042059539338841226
},
"harness|hendrycksTest-jurisprudence|5": {
"acc": 0.6666666666666666,
"acc_stderr": 0.04557239513497751,
"acc_norm": 0.6666666666666666,
"acc_norm_stderr": 0.04557239513497751
},
"harness|hendrycksTest-logical_fallacies|5": {
"acc": 0.6503067484662577,
"acc_stderr": 0.03746668325470023,
"acc_norm": 0.6503067484662577,
"acc_norm_stderr": 0.03746668325470023
},
"harness|hendrycksTest-machine_learning|5": {
"acc": 0.39285714285714285,
"acc_stderr": 0.04635550135609976,
"acc_norm": 0.39285714285714285,
"acc_norm_stderr": 0.04635550135609976
},
"harness|hendrycksTest-management|5": {
"acc": 0.6990291262135923,
"acc_stderr": 0.04541609446503949,
"acc_norm": 0.6990291262135923,
"acc_norm_stderr": 0.04541609446503949
},
"harness|hendrycksTest-marketing|5": {
"acc": 0.7905982905982906,
"acc_stderr": 0.026655699653922744,
"acc_norm": 0.7905982905982906,
"acc_norm_stderr": 0.026655699653922744
},
"harness|hendrycksTest-medical_genetics|5": {
"acc": 0.49,
"acc_stderr": 0.05024183937956911,
"acc_norm": 0.49,
"acc_norm_stderr": 0.05024183937956911
},
"harness|hendrycksTest-miscellaneous|5": {
"acc": 0.7049808429118773,
"acc_stderr": 0.016308363772932724,
"acc_norm": 0.7049808429118773,
"acc_norm_stderr": 0.016308363772932724
},
"harness|hendrycksTest-moral_disputes|5": {
"acc": 0.5895953757225434,
"acc_stderr": 0.026483392042098177,
"acc_norm": 0.5895953757225434,
"acc_norm_stderr": 0.026483392042098177
},
"harness|hendrycksTest-moral_scenarios|5": {
"acc": 0.2849162011173184,
"acc_stderr": 0.015096222302469799,
"acc_norm": 0.2849162011173184,
"acc_norm_stderr": 0.015096222302469799
},
"harness|hendrycksTest-nutrition|5": {
"acc": 0.5751633986928104,
"acc_stderr": 0.028304576673141107,
"acc_norm": 0.5751633986928104,
"acc_norm_stderr": 0.028304576673141107
},
"harness|hendrycksTest-philosophy|5": {
"acc": 0.5884244372990354,
"acc_stderr": 0.02795048149440127,
"acc_norm": 0.5884244372990354,
"acc_norm_stderr": 0.02795048149440127
},
"harness|hendrycksTest-prehistory|5": {
"acc": 0.5740740740740741,
"acc_stderr": 0.027513747284379424,
"acc_norm": 0.5740740740740741,
"acc_norm_stderr": 0.027513747284379424
},
"harness|hendrycksTest-professional_accounting|5": {
"acc": 0.3723404255319149,
"acc_stderr": 0.028838921471251458,
"acc_norm": 0.3723404255319149,
"acc_norm_stderr": 0.028838921471251458
},
"harness|hendrycksTest-professional_law|5": {
"acc": 0.3956975228161669,
"acc_stderr": 0.012489290735449014,
"acc_norm": 0.3956975228161669,
"acc_norm_stderr": 0.012489290735449014
},
"harness|hendrycksTest-professional_medicine|5": {
"acc": 0.40808823529411764,
"acc_stderr": 0.02985526139348392,
"acc_norm": 0.40808823529411764,
"acc_norm_stderr": 0.02985526139348392
},
"harness|hendrycksTest-professional_psychology|5": {
"acc": 0.5506535947712419,
"acc_stderr": 0.020123766528027266,
"acc_norm": 0.5506535947712419,
"acc_norm_stderr": 0.020123766528027266
},
"harness|hendrycksTest-public_relations|5": {
"acc": 0.6272727272727273,
"acc_stderr": 0.04631381319425464,
"acc_norm": 0.6272727272727273,
"acc_norm_stderr": 0.04631381319425464
},
"harness|hendrycksTest-security_studies|5": {
"acc": 0.6081632653061224,
"acc_stderr": 0.031251275910891656,
"acc_norm": 0.6081632653061224,
"acc_norm_stderr": 0.031251275910891656
},
"harness|hendrycksTest-sociology|5": {
"acc": 0.7213930348258707,
"acc_stderr": 0.031700561834973086,
"acc_norm": 0.7213930348258707,
"acc_norm_stderr": 0.031700561834973086
},
"harness|hendrycksTest-us_foreign_policy|5": {
"acc": 0.79,
"acc_stderr": 0.040936018074033256,
"acc_norm": 0.79,
"acc_norm_stderr": 0.040936018074033256
},
"harness|hendrycksTest-virology|5": {
"acc": 0.4819277108433735,
"acc_stderr": 0.038899512528272166,
"acc_norm": 0.4819277108433735,
"acc_norm_stderr": 0.038899512528272166
},
"harness|hendrycksTest-world_religions|5": {
"acc": 0.7543859649122807,
"acc_stderr": 0.03301405946987249,
"acc_norm": 0.7543859649122807,
"acc_norm_stderr": 0.03301405946987249
},
"harness|truthfulqa:mc|0": {
"mc1": 0.2423500611995104,
"mc1_stderr": 0.01500067437357034,
"mc2": 0.36559745885035844,
"mc2_stderr": 0.013805854330074238
},
"harness|winogrande|5": {
"acc": 0.7561168113654302,
"acc_stderr": 0.012068923278908189
},
"harness|gsm8k|5": {
"acc": 0.0,
"acc_stderr": 0.0
}
}
```
## Dataset Details
### Dataset Description
<!-- Provide a longer summary of what this dataset is. -->
- **Curated by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
### Dataset Sources [optional]
<!-- Provide the basic links for the dataset. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the dataset is intended to be used. -->
### Direct Use
<!-- This section describes suitable use cases for the dataset. -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the dataset will not work well for. -->
[More Information Needed]
## Dataset Structure
<!-- This section provides a description of the dataset fields, and additional information about the dataset structure such as criteria used to create the splits, relationships between data points, etc. -->
[More Information Needed]
## Dataset Creation
### Curation Rationale
<!-- Motivation for the creation of this dataset. -->
[More Information Needed]
### Source Data
<!-- This section describes the source data (e.g. news text and headlines, social media posts, translated sentences, ...). -->
#### Data Collection and Processing
<!-- This section describes the data collection and processing process such as data selection criteria, filtering and normalization methods, tools and libraries used, etc. -->
[More Information Needed]
#### Who are the source data producers?
<!-- This section describes the people or systems who originally created the data. It should also include self-reported demographic or identity information for the source data creators if this information is available. -->
[More Information Needed]
### Annotations [optional]
<!-- If the dataset contains annotations which are not part of the initial data collection, use this section to describe them. -->
#### Annotation process
<!-- This section describes the annotation process such as annotation tools used in the process, the amount of data annotated, annotation guidelines provided to the annotators, interannotator statistics, annotation validation, etc. -->
[More Information Needed]
#### Who are the annotators?
<!-- This section describes the people or systems who created the annotations. -->
[More Information Needed]
#### Personal and Sensitive Information
<!-- State whether the dataset contains data that might be considered personal, sensitive, or private (e.g., data that reveals addresses, uniquely identifiable names or aliases, racial or ethnic origins, sexual orientations, religious beliefs, political opinions, financial or health data, etc.). If efforts were made to anonymize the data, describe the anonymization process. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.
## Citation [optional]
<!-- If there is a paper or blog post introducing the dataset, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the dataset or dataset card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Dataset Card Authors [optional]
[More Information Needed]
## Dataset Card Contact
[More Information Needed] | open-llm-leaderboard/details_abhinand__tamil-llama-13b-base-v0.1 | [
"region:us"
] | 2023-12-16T11:43:39+00:00 | {"pretty_name": "Evaluation run of abhinand/tamil-llama-13b-base-v0.1", "dataset_summary": "Dataset automatically created during the evaluation run of model [abhinand/tamil-llama-13b-base-v0.1](https://huggingface.co/abhinand/tamil-llama-13b-base-v0.1) on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).\n\nTo load the details from a run, you can for instance do the following:\n```python\nfrom datasets import load_dataset\ndata = load_dataset(\"open-llm-leaderboard/details_abhinand__tamil-llama-13b-base-v0.1\",\n\t\"harness_winogrande_5\",\n\tsplit=\"train\")\n```\n\n## Latest results\n\nThese are the [latest results from run 2023-12-16T11:40:41.184211](https://huggingface.co/datasets/open-llm-leaderboard/details_abhinand__tamil-llama-13b-base-v0.1/blob/main/results_2023-12-16T11-40-41.184211.json)(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):\n\n```python\n{\n \"all\": {\n \"acc\": 0.5167194240440821,\n \"acc_stderr\": 0.03375847094673175,\n \"acc_norm\": 0.5253161101910007,\n \"acc_norm_stderr\": 0.0346825452797334,\n \"mc1\": 0.2423500611995104,\n \"mc1_stderr\": 0.01500067437357034,\n \"mc2\": 0.36559745885035844,\n \"mc2_stderr\": 0.013805854330074238\n },\n \"harness|arc:challenge|25\": {\n \"acc\": 0.5034129692832765,\n \"acc_stderr\": 0.014611050403244081,\n \"acc_norm\": 0.5281569965870307,\n \"acc_norm_stderr\": 0.014588204105102203\n },\n \"harness|hellaswag|10\": {\n \"acc\": 0.5944035052778331,\n \"acc_stderr\": 0.004900036261309048,\n \"acc_norm\": 0.7995419239195379,\n \"acc_norm_stderr\": 0.003995249591993226\n },\n \"harness|hendrycksTest-abstract_algebra|5\": {\n \"acc\": 0.32,\n \"acc_stderr\": 0.046882617226215034,\n \"acc_norm\": 0.32,\n \"acc_norm_stderr\": 0.046882617226215034\n },\n \"harness|hendrycksTest-anatomy|5\": {\n \"acc\": 0.4666666666666667,\n \"acc_stderr\": 0.043097329010363554,\n \"acc_norm\": 0.4666666666666667,\n \"acc_norm_stderr\": 0.043097329010363554\n },\n \"harness|hendrycksTest-astronomy|5\": {\n \"acc\": 0.47368421052631576,\n \"acc_stderr\": 0.04063302731486671,\n \"acc_norm\": 0.47368421052631576,\n \"acc_norm_stderr\": 0.04063302731486671\n },\n \"harness|hendrycksTest-business_ethics|5\": {\n \"acc\": 0.54,\n \"acc_stderr\": 0.05009082659620332,\n \"acc_norm\": 0.54,\n \"acc_norm_stderr\": 0.05009082659620332\n },\n \"harness|hendrycksTest-clinical_knowledge|5\": {\n \"acc\": 0.5584905660377358,\n \"acc_stderr\": 0.030561590426731833,\n \"acc_norm\": 0.5584905660377358,\n \"acc_norm_stderr\": 0.030561590426731833\n },\n \"harness|hendrycksTest-college_biology|5\": {\n \"acc\": 0.5347222222222222,\n \"acc_stderr\": 0.04171115858181618,\n \"acc_norm\": 0.5347222222222222,\n \"acc_norm_stderr\": 0.04171115858181618\n },\n \"harness|hendrycksTest-college_chemistry|5\": {\n \"acc\": 0.38,\n \"acc_stderr\": 0.04878317312145633,\n \"acc_norm\": 0.38,\n \"acc_norm_stderr\": 0.04878317312145633\n },\n \"harness|hendrycksTest-college_computer_science|5\": {\n \"acc\": 0.36,\n \"acc_stderr\": 0.048241815132442176,\n \"acc_norm\": 0.36,\n \"acc_norm_stderr\": 0.048241815132442176\n },\n \"harness|hendrycksTest-college_mathematics|5\": {\n \"acc\": 0.27,\n \"acc_stderr\": 0.044619604333847394,\n \"acc_norm\": 0.27,\n \"acc_norm_stderr\": 0.044619604333847394\n },\n \"harness|hendrycksTest-college_medicine|5\": {\n \"acc\": 0.48554913294797686,\n \"acc_stderr\": 0.03810871630454764,\n \"acc_norm\": 0.48554913294797686,\n \"acc_norm_stderr\": 0.03810871630454764\n },\n \"harness|hendrycksTest-college_physics|5\": {\n \"acc\": 0.24509803921568626,\n \"acc_stderr\": 0.042801058373643966,\n \"acc_norm\": 0.24509803921568626,\n \"acc_norm_stderr\": 0.042801058373643966\n },\n \"harness|hendrycksTest-computer_security|5\": {\n \"acc\": 0.69,\n \"acc_stderr\": 0.04648231987117316,\n \"acc_norm\": 0.69,\n \"acc_norm_stderr\": 0.04648231987117316\n },\n \"harness|hendrycksTest-conceptual_physics|5\": {\n \"acc\": 0.43829787234042555,\n \"acc_stderr\": 0.03243618636108102,\n \"acc_norm\": 0.43829787234042555,\n \"acc_norm_stderr\": 0.03243618636108102\n },\n \"harness|hendrycksTest-econometrics|5\": {\n \"acc\": 0.2807017543859649,\n \"acc_stderr\": 0.042270544512322,\n \"acc_norm\": 0.2807017543859649,\n \"acc_norm_stderr\": 0.042270544512322\n },\n \"harness|hendrycksTest-electrical_engineering|5\": {\n \"acc\": 0.496551724137931,\n \"acc_stderr\": 0.041665675771015785,\n \"acc_norm\": 0.496551724137931,\n \"acc_norm_stderr\": 0.041665675771015785\n },\n \"harness|hendrycksTest-elementary_mathematics|5\": {\n \"acc\": 0.29365079365079366,\n \"acc_stderr\": 0.02345603738398202,\n \"acc_norm\": 0.29365079365079366,\n \"acc_norm_stderr\": 0.02345603738398202\n },\n \"harness|hendrycksTest-formal_logic|5\": {\n \"acc\": 0.30158730158730157,\n \"acc_stderr\": 0.04104947269903394,\n \"acc_norm\": 0.30158730158730157,\n \"acc_norm_stderr\": 0.04104947269903394\n },\n \"harness|hendrycksTest-global_facts|5\": {\n \"acc\": 0.36,\n \"acc_stderr\": 0.04824181513244218,\n \"acc_norm\": 0.36,\n \"acc_norm_stderr\": 0.04824181513244218\n },\n \"harness|hendrycksTest-high_school_biology|5\": {\n \"acc\": 0.6483870967741936,\n \"acc_stderr\": 0.027162537826948458,\n \"acc_norm\": 0.6483870967741936,\n \"acc_norm_stderr\": 0.027162537826948458\n },\n \"harness|hendrycksTest-high_school_chemistry|5\": {\n \"acc\": 0.33497536945812806,\n \"acc_stderr\": 0.033208527423483104,\n \"acc_norm\": 0.33497536945812806,\n \"acc_norm_stderr\": 0.033208527423483104\n },\n \"harness|hendrycksTest-high_school_computer_science|5\": {\n \"acc\": 0.53,\n \"acc_stderr\": 0.050161355804659205,\n \"acc_norm\": 0.53,\n \"acc_norm_stderr\": 0.050161355804659205\n },\n \"harness|hendrycksTest-high_school_european_history|5\": {\n \"acc\": 0.6484848484848484,\n \"acc_stderr\": 0.037282069986826503,\n \"acc_norm\": 0.6484848484848484,\n \"acc_norm_stderr\": 0.037282069986826503\n },\n \"harness|hendrycksTest-high_school_geography|5\": {\n \"acc\": 0.6414141414141414,\n \"acc_stderr\": 0.034169036403915214,\n \"acc_norm\": 0.6414141414141414,\n \"acc_norm_stderr\": 0.034169036403915214\n },\n \"harness|hendrycksTest-high_school_government_and_politics|5\": {\n \"acc\": 0.7616580310880829,\n \"acc_stderr\": 0.03074890536390988,\n \"acc_norm\": 0.7616580310880829,\n \"acc_norm_stderr\": 0.03074890536390988\n },\n \"harness|hendrycksTest-high_school_macroeconomics|5\": {\n \"acc\": 0.48205128205128206,\n \"acc_stderr\": 0.025334667080954935,\n \"acc_norm\": 0.48205128205128206,\n \"acc_norm_stderr\": 0.025334667080954935\n },\n \"harness|hendrycksTest-high_school_mathematics|5\": {\n \"acc\": 0.2851851851851852,\n \"acc_stderr\": 0.027528599210340496,\n \"acc_norm\": 0.2851851851851852,\n \"acc_norm_stderr\": 0.027528599210340496\n },\n \"harness|hendrycksTest-high_school_microeconomics|5\": {\n \"acc\": 0.5168067226890757,\n \"acc_stderr\": 0.03246013680375308,\n \"acc_norm\": 0.5168067226890757,\n \"acc_norm_stderr\": 0.03246013680375308\n },\n \"harness|hendrycksTest-high_school_physics|5\": {\n \"acc\": 0.31125827814569534,\n \"acc_stderr\": 0.037804458505267334,\n \"acc_norm\": 0.31125827814569534,\n \"acc_norm_stderr\": 0.037804458505267334\n },\n \"harness|hendrycksTest-high_school_psychology|5\": {\n \"acc\": 0.7211009174311926,\n \"acc_stderr\": 0.019227468876463503,\n \"acc_norm\": 0.7211009174311926,\n \"acc_norm_stderr\": 0.019227468876463503\n },\n \"harness|hendrycksTest-high_school_statistics|5\": {\n \"acc\": 0.36574074074074076,\n \"acc_stderr\": 0.03284738857647206,\n \"acc_norm\": 0.36574074074074076,\n \"acc_norm_stderr\": 0.03284738857647206\n },\n \"harness|hendrycksTest-high_school_us_history|5\": {\n \"acc\": 0.6764705882352942,\n \"acc_stderr\": 0.0328347205610856,\n \"acc_norm\": 0.6764705882352942,\n \"acc_norm_stderr\": 0.0328347205610856\n },\n \"harness|hendrycksTest-high_school_world_history|5\": {\n \"acc\": 0.6708860759493671,\n \"acc_stderr\": 0.03058732629470236,\n \"acc_norm\": 0.6708860759493671,\n \"acc_norm_stderr\": 0.03058732629470236\n },\n \"harness|hendrycksTest-human_aging|5\": {\n \"acc\": 0.600896860986547,\n \"acc_stderr\": 0.03286745312567961,\n \"acc_norm\": 0.600896860986547,\n \"acc_norm_stderr\": 0.03286745312567961\n },\n \"harness|hendrycksTest-human_sexuality|5\": {\n \"acc\": 0.5648854961832062,\n \"acc_stderr\": 0.04348208051644858,\n \"acc_norm\": 0.5648854961832062,\n \"acc_norm_stderr\": 0.04348208051644858\n },\n \"harness|hendrycksTest-international_law|5\": {\n \"acc\": 0.6942148760330579,\n \"acc_stderr\": 0.042059539338841226,\n \"acc_norm\": 0.6942148760330579,\n \"acc_norm_stderr\": 0.042059539338841226\n },\n \"harness|hendrycksTest-jurisprudence|5\": {\n \"acc\": 0.6666666666666666,\n \"acc_stderr\": 0.04557239513497751,\n \"acc_norm\": 0.6666666666666666,\n \"acc_norm_stderr\": 0.04557239513497751\n },\n \"harness|hendrycksTest-logical_fallacies|5\": {\n \"acc\": 0.6503067484662577,\n \"acc_stderr\": 0.03746668325470023,\n \"acc_norm\": 0.6503067484662577,\n \"acc_norm_stderr\": 0.03746668325470023\n },\n \"harness|hendrycksTest-machine_learning|5\": {\n \"acc\": 0.39285714285714285,\n \"acc_stderr\": 0.04635550135609976,\n \"acc_norm\": 0.39285714285714285,\n \"acc_norm_stderr\": 0.04635550135609976\n },\n \"harness|hendrycksTest-management|5\": {\n \"acc\": 0.6990291262135923,\n \"acc_stderr\": 0.04541609446503949,\n \"acc_norm\": 0.6990291262135923,\n \"acc_norm_stderr\": 0.04541609446503949\n },\n \"harness|hendrycksTest-marketing|5\": {\n \"acc\": 0.7905982905982906,\n \"acc_stderr\": 0.026655699653922744,\n \"acc_norm\": 0.7905982905982906,\n \"acc_norm_stderr\": 0.026655699653922744\n },\n \"harness|hendrycksTest-medical_genetics|5\": {\n \"acc\": 0.49,\n \"acc_stderr\": 0.05024183937956911,\n \"acc_norm\": 0.49,\n \"acc_norm_stderr\": 0.05024183937956911\n },\n \"harness|hendrycksTest-miscellaneous|5\": {\n \"acc\": 0.7049808429118773,\n \"acc_stderr\": 0.016308363772932724,\n \"acc_norm\": 0.7049808429118773,\n \"acc_norm_stderr\": 0.016308363772932724\n },\n \"harness|hendrycksTest-moral_disputes|5\": {\n \"acc\": 0.5895953757225434,\n \"acc_stderr\": 0.026483392042098177,\n \"acc_norm\": 0.5895953757225434,\n \"acc_norm_stderr\": 0.026483392042098177\n },\n \"harness|hendrycksTest-moral_scenarios|5\": {\n \"acc\": 0.2849162011173184,\n \"acc_stderr\": 0.015096222302469799,\n \"acc_norm\": 0.2849162011173184,\n \"acc_norm_stderr\": 0.015096222302469799\n },\n \"harness|hendrycksTest-nutrition|5\": {\n \"acc\": 0.5751633986928104,\n \"acc_stderr\": 0.028304576673141107,\n \"acc_norm\": 0.5751633986928104,\n \"acc_norm_stderr\": 0.028304576673141107\n },\n \"harness|hendrycksTest-philosophy|5\": {\n \"acc\": 0.5884244372990354,\n \"acc_stderr\": 0.02795048149440127,\n \"acc_norm\": 0.5884244372990354,\n \"acc_norm_stderr\": 0.02795048149440127\n },\n \"harness|hendrycksTest-prehistory|5\": {\n \"acc\": 0.5740740740740741,\n \"acc_stderr\": 0.027513747284379424,\n \"acc_norm\": 0.5740740740740741,\n \"acc_norm_stderr\": 0.027513747284379424\n },\n \"harness|hendrycksTest-professional_accounting|5\": {\n \"acc\": 0.3723404255319149,\n \"acc_stderr\": 0.028838921471251458,\n \"acc_norm\": 0.3723404255319149,\n \"acc_norm_stderr\": 0.028838921471251458\n },\n \"harness|hendrycksTest-professional_law|5\": {\n \"acc\": 0.3956975228161669,\n \"acc_stderr\": 0.012489290735449014,\n \"acc_norm\": 0.3956975228161669,\n \"acc_norm_stderr\": 0.012489290735449014\n },\n \"harness|hendrycksTest-professional_medicine|5\": {\n \"acc\": 0.40808823529411764,\n \"acc_stderr\": 0.02985526139348392,\n \"acc_norm\": 0.40808823529411764,\n \"acc_norm_stderr\": 0.02985526139348392\n },\n \"harness|hendrycksTest-professional_psychology|5\": {\n \"acc\": 0.5506535947712419,\n \"acc_stderr\": 0.020123766528027266,\n \"acc_norm\": 0.5506535947712419,\n \"acc_norm_stderr\": 0.020123766528027266\n },\n \"harness|hendrycksTest-public_relations|5\": {\n \"acc\": 0.6272727272727273,\n \"acc_stderr\": 0.04631381319425464,\n \"acc_norm\": 0.6272727272727273,\n \"acc_norm_stderr\": 0.04631381319425464\n },\n \"harness|hendrycksTest-security_studies|5\": {\n \"acc\": 0.6081632653061224,\n \"acc_stderr\": 0.031251275910891656,\n \"acc_norm\": 0.6081632653061224,\n \"acc_norm_stderr\": 0.031251275910891656\n },\n \"harness|hendrycksTest-sociology|5\": {\n \"acc\": 0.7213930348258707,\n \"acc_stderr\": 0.031700561834973086,\n \"acc_norm\": 0.7213930348258707,\n \"acc_norm_stderr\": 0.031700561834973086\n },\n \"harness|hendrycksTest-us_foreign_policy|5\": {\n \"acc\": 0.79,\n \"acc_stderr\": 0.040936018074033256,\n \"acc_norm\": 0.79,\n \"acc_norm_stderr\": 0.040936018074033256\n },\n \"harness|hendrycksTest-virology|5\": {\n \"acc\": 0.4819277108433735,\n \"acc_stderr\": 0.038899512528272166,\n \"acc_norm\": 0.4819277108433735,\n \"acc_norm_stderr\": 0.038899512528272166\n },\n \"harness|hendrycksTest-world_religions|5\": {\n \"acc\": 0.7543859649122807,\n \"acc_stderr\": 0.03301405946987249,\n \"acc_norm\": 0.7543859649122807,\n \"acc_norm_stderr\": 0.03301405946987249\n },\n \"harness|truthfulqa:mc|0\": {\n \"mc1\": 0.2423500611995104,\n \"mc1_stderr\": 0.01500067437357034,\n \"mc2\": 0.36559745885035844,\n \"mc2_stderr\": 0.013805854330074238\n },\n \"harness|winogrande|5\": {\n \"acc\": 0.7561168113654302,\n \"acc_stderr\": 0.012068923278908189\n },\n \"harness|gsm8k|5\": {\n \"acc\": 0.0,\n \"acc_stderr\": 0.0\n }\n}\n```", "repo_url": "https://huggingface.co/abhinand/tamil-llama-13b-base-v0.1", "leaderboard_url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard", "point_of_contact": "[email protected]", "configs": [{"config_name": "harness_arc_challenge_25", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|arc:challenge|25_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|arc:challenge|25_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_gsm8k_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|gsm8k|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|gsm8k|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hellaswag_10", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hellaswag|10_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hellaswag|10_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-abstract_algebra|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-anatomy|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-astronomy|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-business_ethics|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-clinical_knowledge|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-college_biology|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-college_chemistry|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-college_computer_science|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-college_mathematics|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-college_medicine|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-college_physics|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-computer_security|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-conceptual_physics|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-econometrics|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-electrical_engineering|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-elementary_mathematics|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-formal_logic|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-global_facts|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_biology|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_chemistry|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_computer_science|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_european_history|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_geography|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_mathematics|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_physics|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_psychology|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_statistics|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_us_history|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_world_history|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-human_aging|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-human_sexuality|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-international_law|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-jurisprudence|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-logical_fallacies|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-machine_learning|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-management|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-marketing|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-medical_genetics|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-miscellaneous|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-moral_disputes|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-moral_scenarios|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-nutrition|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-philosophy|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-prehistory|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-professional_accounting|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-professional_law|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-professional_medicine|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-professional_psychology|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-public_relations|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-security_studies|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-sociology|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-us_foreign_policy|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-virology|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-world_religions|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-abstract_algebra|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-anatomy|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-astronomy|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-business_ethics|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-clinical_knowledge|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-college_biology|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-college_chemistry|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-college_computer_science|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-college_mathematics|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-college_medicine|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-college_physics|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-computer_security|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-conceptual_physics|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-econometrics|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-electrical_engineering|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-elementary_mathematics|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-formal_logic|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-global_facts|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_biology|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_chemistry|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_computer_science|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_european_history|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_geography|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_mathematics|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_physics|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_psychology|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_statistics|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_us_history|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-high_school_world_history|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-human_aging|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-human_sexuality|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-international_law|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-jurisprudence|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-logical_fallacies|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-machine_learning|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-management|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-marketing|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-medical_genetics|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-miscellaneous|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-moral_disputes|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-moral_scenarios|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-nutrition|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-philosophy|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-prehistory|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-professional_accounting|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-professional_law|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-professional_medicine|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-professional_psychology|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-public_relations|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-security_studies|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-sociology|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-us_foreign_policy|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-virology|5_2023-12-16T11-40-41.184211.parquet", "**/details_harness|hendrycksTest-world_religions|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_abstract_algebra_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-abstract_algebra|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-abstract_algebra|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_anatomy_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-anatomy|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-anatomy|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_astronomy_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-astronomy|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-astronomy|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_business_ethics_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-business_ethics|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-business_ethics|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_clinical_knowledge_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-clinical_knowledge|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-clinical_knowledge|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_biology_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-college_biology|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_biology|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_chemistry_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-college_chemistry|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_chemistry|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_computer_science_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-college_computer_science|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_computer_science|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_mathematics_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-college_mathematics|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_mathematics|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_medicine_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-college_medicine|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_medicine|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_physics_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-college_physics|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_physics|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_computer_security_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-computer_security|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-computer_security|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_conceptual_physics_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-conceptual_physics|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-conceptual_physics|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_econometrics_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-econometrics|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-econometrics|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_electrical_engineering_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-electrical_engineering|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-electrical_engineering|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_elementary_mathematics_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-elementary_mathematics|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-elementary_mathematics|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_formal_logic_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-formal_logic|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-formal_logic|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_global_facts_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-global_facts|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-global_facts|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_biology_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-high_school_biology|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_biology|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_chemistry_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-high_school_chemistry|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_chemistry|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_computer_science_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-high_school_computer_science|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_computer_science|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_european_history_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-high_school_european_history|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_european_history|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_geography_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-high_school_geography|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_geography|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_government_and_politics_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_macroeconomics_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_mathematics_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-high_school_mathematics|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_mathematics|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_microeconomics_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_physics_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-high_school_physics|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_physics|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_psychology_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-high_school_psychology|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_psychology|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_statistics_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-high_school_statistics|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_statistics|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_us_history_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-high_school_us_history|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_us_history|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_world_history_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-high_school_world_history|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_world_history|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_human_aging_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-human_aging|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-human_aging|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_human_sexuality_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-human_sexuality|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-human_sexuality|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_international_law_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-international_law|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-international_law|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_jurisprudence_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-jurisprudence|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-jurisprudence|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_logical_fallacies_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-logical_fallacies|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-logical_fallacies|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_machine_learning_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-machine_learning|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-machine_learning|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_management_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-management|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-management|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_marketing_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-marketing|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-marketing|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_medical_genetics_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-medical_genetics|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-medical_genetics|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_miscellaneous_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-miscellaneous|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-miscellaneous|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_moral_disputes_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-moral_disputes|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-moral_disputes|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_moral_scenarios_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-moral_scenarios|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-moral_scenarios|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_nutrition_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-nutrition|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-nutrition|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_philosophy_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-philosophy|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-philosophy|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_prehistory_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-prehistory|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-prehistory|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_professional_accounting_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-professional_accounting|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-professional_accounting|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_professional_law_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-professional_law|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-professional_law|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_professional_medicine_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-professional_medicine|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-professional_medicine|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_professional_psychology_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-professional_psychology|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-professional_psychology|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_public_relations_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-public_relations|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-public_relations|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_security_studies_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-security_studies|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-security_studies|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_sociology_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-sociology|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-sociology|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_us_foreign_policy_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-us_foreign_policy|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-us_foreign_policy|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_virology_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-virology|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-virology|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_hendrycksTest_world_religions_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|hendrycksTest-world_religions|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-world_religions|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_truthfulqa_mc_0", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|truthfulqa:mc|0_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|truthfulqa:mc|0_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "harness_winogrande_5", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["**/details_harness|winogrande|5_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["**/details_harness|winogrande|5_2023-12-16T11-40-41.184211.parquet"]}]}, {"config_name": "results", "data_files": [{"split": "2023_12_16T11_40_41.184211", "path": ["results_2023-12-16T11-40-41.184211.parquet"]}, {"split": "latest", "path": ["results_2023-12-16T11-40-41.184211.parquet"]}]}]} | 2023-12-16T11:44:21+00:00 | [] | [] | TAGS
#region-us
|
# Dataset Card for Evaluation run of abhinand/tamil-llama-13b-base-v0.1
Dataset automatically created during the evaluation run of model abhinand/tamil-llama-13b-base-v0.1 on the Open LLM Leaderboard.
The dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An additional configuration "results" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).
To load the details from a run, you can for instance do the following:
## Latest results
These are the latest results from run 2023-12-16T11:40:41.184211(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the "latest" split for each eval):
## Dataset Details
### Dataset Description
- Curated by:
- Funded by [optional]:
- Shared by [optional]:
- Language(s) (NLP):
- License:
### Dataset Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Out-of-Scope Use
## Dataset Structure
## Dataset Creation
### Curation Rationale
### Source Data
#### Data Collection and Processing
#### Who are the source data producers?
### Annotations [optional]
#### Annotation process
#### Who are the annotators?
#### Personal and Sensitive Information
## Bias, Risks, and Limitations
### Recommendations
Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Dataset Card Authors [optional]
## Dataset Card Contact
| [
"# Dataset Card for Evaluation run of abhinand/tamil-llama-13b-base-v0.1\n\n\n\nDataset automatically created during the evaluation run of model abhinand/tamil-llama-13b-base-v0.1 on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:",
"## Latest results\n\nThese are the latest results from run 2023-12-16T11:40:41.184211(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):",
"## Dataset Details",
"### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:",
"### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Out-of-Scope Use",
"## Dataset Structure",
"## Dataset Creation",
"### Curation Rationale",
"### Source Data",
"#### Data Collection and Processing",
"#### Who are the source data producers?",
"### Annotations [optional]",
"#### Annotation process",
"#### Who are the annotators?",
"#### Personal and Sensitive Information",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Dataset Card Authors [optional]",
"## Dataset Card Contact"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for Evaluation run of abhinand/tamil-llama-13b-base-v0.1\n\n\n\nDataset automatically created during the evaluation run of model abhinand/tamil-llama-13b-base-v0.1 on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:",
"## Latest results\n\nThese are the latest results from run 2023-12-16T11:40:41.184211(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):",
"## Dataset Details",
"### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:",
"### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Out-of-Scope Use",
"## Dataset Structure",
"## Dataset Creation",
"### Curation Rationale",
"### Source Data",
"#### Data Collection and Processing",
"#### Who are the source data producers?",
"### Annotations [optional]",
"#### Annotation process",
"#### Who are the annotators?",
"#### Personal and Sensitive Information",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Dataset Card Authors [optional]",
"## Dataset Card Contact"
] | [
6,
191,
67,
4,
40,
29,
3,
4,
9,
6,
5,
7,
4,
7,
10,
9,
5,
9,
8,
10,
46,
8,
7,
10,
5
] | [
"passage: TAGS\n#region-us \n# Dataset Card for Evaluation run of abhinand/tamil-llama-13b-base-v0.1\n\n\n\nDataset automatically created during the evaluation run of model abhinand/tamil-llama-13b-base-v0.1 on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:## Latest results\n\nThese are the latest results from run 2023-12-16T11:40:41.184211(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):## Dataset Details### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Out-of-Scope Use## Dataset Structure## Dataset Creation### Curation Rationale### Source Data#### Data Collection and Processing#### Who are the source data producers?### Annotations [optional]#### Annotation process#### Who are the annotators?#### Personal and Sensitive Information## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Dataset Card Authors [optional]"
] |
afb69370fcbc0a356800e1dd5b8c246cac3283e7 |
# Dataset Card for Evaluation run of Azure99/blossom-v3_1-yi-34b
<!-- Provide a quick summary of the dataset. -->
Dataset automatically created during the evaluation run of model [Azure99/blossom-v3_1-yi-34b](https://huggingface.co/Azure99/blossom-v3_1-yi-34b) on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
The dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An additional configuration "results" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).
To load the details from a run, you can for instance do the following:
```python
from datasets import load_dataset
data = load_dataset("open-llm-leaderboard/details_Azure99__blossom-v3_1-yi-34b",
"harness_winogrande_5",
split="train")
```
## Latest results
These are the [latest results from run 2023-12-16T12:07:38.687191](https://huggingface.co/datasets/open-llm-leaderboard/details_Azure99__blossom-v3_1-yi-34b/blob/main/results_2023-12-16T12-07-38.687191.json)(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the "latest" split for each eval):
```python
{
"all": {
"acc": 0.7369126226544815,
"acc_stderr": 0.02905086153820223,
"acc_norm": 0.7438607056682149,
"acc_norm_stderr": 0.029596571137245984,
"mc1": 0.40269277845777235,
"mc1_stderr": 0.01716883093518722,
"mc2": 0.5606217649091164,
"mc2_stderr": 0.01566716384108092
},
"harness|arc:challenge|25": {
"acc": 0.6245733788395904,
"acc_stderr": 0.014150631435111728,
"acc_norm": 0.6535836177474402,
"acc_norm_stderr": 0.01390501118006323
},
"harness|hellaswag|10": {
"acc": 0.6458872734515037,
"acc_stderr": 0.004772661659628838,
"acc_norm": 0.8423620792670783,
"acc_norm_stderr": 0.003636564286352667
},
"harness|hendrycksTest-abstract_algebra|5": {
"acc": 0.38,
"acc_stderr": 0.048783173121456316,
"acc_norm": 0.38,
"acc_norm_stderr": 0.048783173121456316
},
"harness|hendrycksTest-anatomy|5": {
"acc": 0.7333333333333333,
"acc_stderr": 0.038201699145179055,
"acc_norm": 0.7333333333333333,
"acc_norm_stderr": 0.038201699145179055
},
"harness|hendrycksTest-astronomy|5": {
"acc": 0.8618421052631579,
"acc_stderr": 0.028081042939576552,
"acc_norm": 0.8618421052631579,
"acc_norm_stderr": 0.028081042939576552
},
"harness|hendrycksTest-business_ethics|5": {
"acc": 0.74,
"acc_stderr": 0.0440844002276808,
"acc_norm": 0.74,
"acc_norm_stderr": 0.0440844002276808
},
"harness|hendrycksTest-clinical_knowledge|5": {
"acc": 0.7773584905660378,
"acc_stderr": 0.025604233470899098,
"acc_norm": 0.7773584905660378,
"acc_norm_stderr": 0.025604233470899098
},
"harness|hendrycksTest-college_biology|5": {
"acc": 0.8611111111111112,
"acc_stderr": 0.0289198029561349,
"acc_norm": 0.8611111111111112,
"acc_norm_stderr": 0.0289198029561349
},
"harness|hendrycksTest-college_chemistry|5": {
"acc": 0.48,
"acc_stderr": 0.050211673156867795,
"acc_norm": 0.48,
"acc_norm_stderr": 0.050211673156867795
},
"harness|hendrycksTest-college_computer_science|5": {
"acc": 0.62,
"acc_stderr": 0.04878317312145633,
"acc_norm": 0.62,
"acc_norm_stderr": 0.04878317312145633
},
"harness|hendrycksTest-college_mathematics|5": {
"acc": 0.44,
"acc_stderr": 0.04988876515698589,
"acc_norm": 0.44,
"acc_norm_stderr": 0.04988876515698589
},
"harness|hendrycksTest-college_medicine|5": {
"acc": 0.7514450867052023,
"acc_stderr": 0.03295304696818318,
"acc_norm": 0.7514450867052023,
"acc_norm_stderr": 0.03295304696818318
},
"harness|hendrycksTest-college_physics|5": {
"acc": 0.46078431372549017,
"acc_stderr": 0.049598599663841815,
"acc_norm": 0.46078431372549017,
"acc_norm_stderr": 0.049598599663841815
},
"harness|hendrycksTest-computer_security|5": {
"acc": 0.83,
"acc_stderr": 0.03775251680686371,
"acc_norm": 0.83,
"acc_norm_stderr": 0.03775251680686371
},
"harness|hendrycksTest-conceptual_physics|5": {
"acc": 0.7702127659574468,
"acc_stderr": 0.02750175294441242,
"acc_norm": 0.7702127659574468,
"acc_norm_stderr": 0.02750175294441242
},
"harness|hendrycksTest-econometrics|5": {
"acc": 0.5087719298245614,
"acc_stderr": 0.04702880432049615,
"acc_norm": 0.5087719298245614,
"acc_norm_stderr": 0.04702880432049615
},
"harness|hendrycksTest-electrical_engineering|5": {
"acc": 0.7448275862068966,
"acc_stderr": 0.03632984052707842,
"acc_norm": 0.7448275862068966,
"acc_norm_stderr": 0.03632984052707842
},
"harness|hendrycksTest-elementary_mathematics|5": {
"acc": 0.656084656084656,
"acc_stderr": 0.024464426625596433,
"acc_norm": 0.656084656084656,
"acc_norm_stderr": 0.024464426625596433
},
"harness|hendrycksTest-formal_logic|5": {
"acc": 0.5555555555555556,
"acc_stderr": 0.04444444444444449,
"acc_norm": 0.5555555555555556,
"acc_norm_stderr": 0.04444444444444449
},
"harness|hendrycksTest-global_facts|5": {
"acc": 0.48,
"acc_stderr": 0.050211673156867795,
"acc_norm": 0.48,
"acc_norm_stderr": 0.050211673156867795
},
"harness|hendrycksTest-high_school_biology|5": {
"acc": 0.8903225806451613,
"acc_stderr": 0.017776778700485184,
"acc_norm": 0.8903225806451613,
"acc_norm_stderr": 0.017776778700485184
},
"harness|hendrycksTest-high_school_chemistry|5": {
"acc": 0.6650246305418719,
"acc_stderr": 0.0332085274234831,
"acc_norm": 0.6650246305418719,
"acc_norm_stderr": 0.0332085274234831
},
"harness|hendrycksTest-high_school_computer_science|5": {
"acc": 0.81,
"acc_stderr": 0.03942772444036625,
"acc_norm": 0.81,
"acc_norm_stderr": 0.03942772444036625
},
"harness|hendrycksTest-high_school_european_history|5": {
"acc": 0.8484848484848485,
"acc_stderr": 0.027998073798781668,
"acc_norm": 0.8484848484848485,
"acc_norm_stderr": 0.027998073798781668
},
"harness|hendrycksTest-high_school_geography|5": {
"acc": 0.898989898989899,
"acc_stderr": 0.021469735576055346,
"acc_norm": 0.898989898989899,
"acc_norm_stderr": 0.021469735576055346
},
"harness|hendrycksTest-high_school_government_and_politics|5": {
"acc": 0.9637305699481865,
"acc_stderr": 0.013492659751295136,
"acc_norm": 0.9637305699481865,
"acc_norm_stderr": 0.013492659751295136
},
"harness|hendrycksTest-high_school_macroeconomics|5": {
"acc": 0.7692307692307693,
"acc_stderr": 0.021362027725222717,
"acc_norm": 0.7692307692307693,
"acc_norm_stderr": 0.021362027725222717
},
"harness|hendrycksTest-high_school_mathematics|5": {
"acc": 0.3925925925925926,
"acc_stderr": 0.02977384701253297,
"acc_norm": 0.3925925925925926,
"acc_norm_stderr": 0.02977384701253297
},
"harness|hendrycksTest-high_school_microeconomics|5": {
"acc": 0.8319327731092437,
"acc_stderr": 0.024289102115692282,
"acc_norm": 0.8319327731092437,
"acc_norm_stderr": 0.024289102115692282
},
"harness|hendrycksTest-high_school_physics|5": {
"acc": 0.4768211920529801,
"acc_stderr": 0.04078093859163083,
"acc_norm": 0.4768211920529801,
"acc_norm_stderr": 0.04078093859163083
},
"harness|hendrycksTest-high_school_psychology|5": {
"acc": 0.9119266055045872,
"acc_stderr": 0.012150743719481688,
"acc_norm": 0.9119266055045872,
"acc_norm_stderr": 0.012150743719481688
},
"harness|hendrycksTest-high_school_statistics|5": {
"acc": 0.6481481481481481,
"acc_stderr": 0.03256850570293647,
"acc_norm": 0.6481481481481481,
"acc_norm_stderr": 0.03256850570293647
},
"harness|hendrycksTest-high_school_us_history|5": {
"acc": 0.9068627450980392,
"acc_stderr": 0.020397853969427,
"acc_norm": 0.9068627450980392,
"acc_norm_stderr": 0.020397853969427
},
"harness|hendrycksTest-high_school_world_history|5": {
"acc": 0.8945147679324894,
"acc_stderr": 0.01999556072375853,
"acc_norm": 0.8945147679324894,
"acc_norm_stderr": 0.01999556072375853
},
"harness|hendrycksTest-human_aging|5": {
"acc": 0.7668161434977578,
"acc_stderr": 0.028380391147094702,
"acc_norm": 0.7668161434977578,
"acc_norm_stderr": 0.028380391147094702
},
"harness|hendrycksTest-human_sexuality|5": {
"acc": 0.8396946564885496,
"acc_stderr": 0.03217829420744631,
"acc_norm": 0.8396946564885496,
"acc_norm_stderr": 0.03217829420744631
},
"harness|hendrycksTest-international_law|5": {
"acc": 0.9090909090909091,
"acc_stderr": 0.02624319405407388,
"acc_norm": 0.9090909090909091,
"acc_norm_stderr": 0.02624319405407388
},
"harness|hendrycksTest-jurisprudence|5": {
"acc": 0.8611111111111112,
"acc_stderr": 0.03343270062869621,
"acc_norm": 0.8611111111111112,
"acc_norm_stderr": 0.03343270062869621
},
"harness|hendrycksTest-logical_fallacies|5": {
"acc": 0.8588957055214724,
"acc_stderr": 0.027351605518389752,
"acc_norm": 0.8588957055214724,
"acc_norm_stderr": 0.027351605518389752
},
"harness|hendrycksTest-machine_learning|5": {
"acc": 0.5535714285714286,
"acc_stderr": 0.04718471485219587,
"acc_norm": 0.5535714285714286,
"acc_norm_stderr": 0.04718471485219587
},
"harness|hendrycksTest-management|5": {
"acc": 0.8543689320388349,
"acc_stderr": 0.03492606476623791,
"acc_norm": 0.8543689320388349,
"acc_norm_stderr": 0.03492606476623791
},
"harness|hendrycksTest-marketing|5": {
"acc": 0.9273504273504274,
"acc_stderr": 0.017004368568132342,
"acc_norm": 0.9273504273504274,
"acc_norm_stderr": 0.017004368568132342
},
"harness|hendrycksTest-medical_genetics|5": {
"acc": 0.86,
"acc_stderr": 0.03487350880197771,
"acc_norm": 0.86,
"acc_norm_stderr": 0.03487350880197771
},
"harness|hendrycksTest-miscellaneous|5": {
"acc": 0.896551724137931,
"acc_stderr": 0.010890452544691504,
"acc_norm": 0.896551724137931,
"acc_norm_stderr": 0.010890452544691504
},
"harness|hendrycksTest-moral_disputes|5": {
"acc": 0.8034682080924855,
"acc_stderr": 0.02139396140436385,
"acc_norm": 0.8034682080924855,
"acc_norm_stderr": 0.02139396140436385
},
"harness|hendrycksTest-moral_scenarios|5": {
"acc": 0.6044692737430167,
"acc_stderr": 0.016353415410075775,
"acc_norm": 0.6044692737430167,
"acc_norm_stderr": 0.016353415410075775
},
"harness|hendrycksTest-nutrition|5": {
"acc": 0.826797385620915,
"acc_stderr": 0.021668400256514293,
"acc_norm": 0.826797385620915,
"acc_norm_stderr": 0.021668400256514293
},
"harness|hendrycksTest-philosophy|5": {
"acc": 0.8167202572347267,
"acc_stderr": 0.021974198848265812,
"acc_norm": 0.8167202572347267,
"acc_norm_stderr": 0.021974198848265812
},
"harness|hendrycksTest-prehistory|5": {
"acc": 0.8364197530864198,
"acc_stderr": 0.020581466138257138,
"acc_norm": 0.8364197530864198,
"acc_norm_stderr": 0.020581466138257138
},
"harness|hendrycksTest-professional_accounting|5": {
"acc": 0.648936170212766,
"acc_stderr": 0.028473501272963758,
"acc_norm": 0.648936170212766,
"acc_norm_stderr": 0.028473501272963758
},
"harness|hendrycksTest-professional_law|5": {
"acc": 0.5886571056062582,
"acc_stderr": 0.012567882673803694,
"acc_norm": 0.5886571056062582,
"acc_norm_stderr": 0.012567882673803694
},
"harness|hendrycksTest-professional_medicine|5": {
"acc": 0.8014705882352942,
"acc_stderr": 0.0242310133705411,
"acc_norm": 0.8014705882352942,
"acc_norm_stderr": 0.0242310133705411
},
"harness|hendrycksTest-professional_psychology|5": {
"acc": 0.8202614379084967,
"acc_stderr": 0.01553374508338279,
"acc_norm": 0.8202614379084967,
"acc_norm_stderr": 0.01553374508338279
},
"harness|hendrycksTest-public_relations|5": {
"acc": 0.7181818181818181,
"acc_stderr": 0.04309118709946458,
"acc_norm": 0.7181818181818181,
"acc_norm_stderr": 0.04309118709946458
},
"harness|hendrycksTest-security_studies|5": {
"acc": 0.8367346938775511,
"acc_stderr": 0.023661699177098608,
"acc_norm": 0.8367346938775511,
"acc_norm_stderr": 0.023661699177098608
},
"harness|hendrycksTest-sociology|5": {
"acc": 0.8805970149253731,
"acc_stderr": 0.02292879327721974,
"acc_norm": 0.8805970149253731,
"acc_norm_stderr": 0.02292879327721974
},
"harness|hendrycksTest-us_foreign_policy|5": {
"acc": 0.89,
"acc_stderr": 0.03144660377352203,
"acc_norm": 0.89,
"acc_norm_stderr": 0.03144660377352203
},
"harness|hendrycksTest-virology|5": {
"acc": 0.5662650602409639,
"acc_stderr": 0.03858158940685515,
"acc_norm": 0.5662650602409639,
"acc_norm_stderr": 0.03858158940685515
},
"harness|hendrycksTest-world_religions|5": {
"acc": 0.8654970760233918,
"acc_stderr": 0.0261682213446623,
"acc_norm": 0.8654970760233918,
"acc_norm_stderr": 0.0261682213446623
},
"harness|truthfulqa:mc|0": {
"mc1": 0.40269277845777235,
"mc1_stderr": 0.01716883093518722,
"mc2": 0.5606217649091164,
"mc2_stderr": 0.01566716384108092
},
"harness|winogrande|5": {
"acc": 0.8208366219415943,
"acc_stderr": 0.010777949156047994
},
"harness|gsm8k|5": {
"acc": 0.46853677028051555,
"acc_stderr": 0.013745189948450419
}
}
```
## Dataset Details
### Dataset Description
<!-- Provide a longer summary of what this dataset is. -->
- **Curated by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
### Dataset Sources [optional]
<!-- Provide the basic links for the dataset. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the dataset is intended to be used. -->
### Direct Use
<!-- This section describes suitable use cases for the dataset. -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the dataset will not work well for. -->
[More Information Needed]
## Dataset Structure
<!-- This section provides a description of the dataset fields, and additional information about the dataset structure such as criteria used to create the splits, relationships between data points, etc. -->
[More Information Needed]
## Dataset Creation
### Curation Rationale
<!-- Motivation for the creation of this dataset. -->
[More Information Needed]
### Source Data
<!-- This section describes the source data (e.g. news text and headlines, social media posts, translated sentences, ...). -->
#### Data Collection and Processing
<!-- This section describes the data collection and processing process such as data selection criteria, filtering and normalization methods, tools and libraries used, etc. -->
[More Information Needed]
#### Who are the source data producers?
<!-- This section describes the people or systems who originally created the data. It should also include self-reported demographic or identity information for the source data creators if this information is available. -->
[More Information Needed]
### Annotations [optional]
<!-- If the dataset contains annotations which are not part of the initial data collection, use this section to describe them. -->
#### Annotation process
<!-- This section describes the annotation process such as annotation tools used in the process, the amount of data annotated, annotation guidelines provided to the annotators, interannotator statistics, annotation validation, etc. -->
[More Information Needed]
#### Who are the annotators?
<!-- This section describes the people or systems who created the annotations. -->
[More Information Needed]
#### Personal and Sensitive Information
<!-- State whether the dataset contains data that might be considered personal, sensitive, or private (e.g., data that reveals addresses, uniquely identifiable names or aliases, racial or ethnic origins, sexual orientations, religious beliefs, political opinions, financial or health data, etc.). If efforts were made to anonymize the data, describe the anonymization process. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.
## Citation [optional]
<!-- If there is a paper or blog post introducing the dataset, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the dataset or dataset card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Dataset Card Authors [optional]
[More Information Needed]
## Dataset Card Contact
[More Information Needed] | open-llm-leaderboard/details_Azure99__blossom-v3_1-yi-34b | [
"region:us"
] | 2023-12-16T12:10:29+00:00 | {"pretty_name": "Evaluation run of Azure99/blossom-v3_1-yi-34b", "dataset_summary": "Dataset automatically created during the evaluation run of model [Azure99/blossom-v3_1-yi-34b](https://huggingface.co/Azure99/blossom-v3_1-yi-34b) on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).\n\nTo load the details from a run, you can for instance do the following:\n```python\nfrom datasets import load_dataset\ndata = load_dataset(\"open-llm-leaderboard/details_Azure99__blossom-v3_1-yi-34b\",\n\t\"harness_winogrande_5\",\n\tsplit=\"train\")\n```\n\n## Latest results\n\nThese are the [latest results from run 2023-12-16T12:07:38.687191](https://huggingface.co/datasets/open-llm-leaderboard/details_Azure99__blossom-v3_1-yi-34b/blob/main/results_2023-12-16T12-07-38.687191.json)(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):\n\n```python\n{\n \"all\": {\n \"acc\": 0.7369126226544815,\n \"acc_stderr\": 0.02905086153820223,\n \"acc_norm\": 0.7438607056682149,\n \"acc_norm_stderr\": 0.029596571137245984,\n \"mc1\": 0.40269277845777235,\n \"mc1_stderr\": 0.01716883093518722,\n \"mc2\": 0.5606217649091164,\n \"mc2_stderr\": 0.01566716384108092\n },\n \"harness|arc:challenge|25\": {\n \"acc\": 0.6245733788395904,\n \"acc_stderr\": 0.014150631435111728,\n \"acc_norm\": 0.6535836177474402,\n \"acc_norm_stderr\": 0.01390501118006323\n },\n \"harness|hellaswag|10\": {\n \"acc\": 0.6458872734515037,\n \"acc_stderr\": 0.004772661659628838,\n \"acc_norm\": 0.8423620792670783,\n \"acc_norm_stderr\": 0.003636564286352667\n },\n \"harness|hendrycksTest-abstract_algebra|5\": {\n \"acc\": 0.38,\n \"acc_stderr\": 0.048783173121456316,\n \"acc_norm\": 0.38,\n \"acc_norm_stderr\": 0.048783173121456316\n },\n \"harness|hendrycksTest-anatomy|5\": {\n \"acc\": 0.7333333333333333,\n \"acc_stderr\": 0.038201699145179055,\n \"acc_norm\": 0.7333333333333333,\n \"acc_norm_stderr\": 0.038201699145179055\n },\n \"harness|hendrycksTest-astronomy|5\": {\n \"acc\": 0.8618421052631579,\n \"acc_stderr\": 0.028081042939576552,\n \"acc_norm\": 0.8618421052631579,\n \"acc_norm_stderr\": 0.028081042939576552\n },\n \"harness|hendrycksTest-business_ethics|5\": {\n \"acc\": 0.74,\n \"acc_stderr\": 0.0440844002276808,\n \"acc_norm\": 0.74,\n \"acc_norm_stderr\": 0.0440844002276808\n },\n \"harness|hendrycksTest-clinical_knowledge|5\": {\n \"acc\": 0.7773584905660378,\n \"acc_stderr\": 0.025604233470899098,\n \"acc_norm\": 0.7773584905660378,\n \"acc_norm_stderr\": 0.025604233470899098\n },\n \"harness|hendrycksTest-college_biology|5\": {\n \"acc\": 0.8611111111111112,\n \"acc_stderr\": 0.0289198029561349,\n \"acc_norm\": 0.8611111111111112,\n \"acc_norm_stderr\": 0.0289198029561349\n },\n \"harness|hendrycksTest-college_chemistry|5\": {\n \"acc\": 0.48,\n \"acc_stderr\": 0.050211673156867795,\n \"acc_norm\": 0.48,\n \"acc_norm_stderr\": 0.050211673156867795\n },\n \"harness|hendrycksTest-college_computer_science|5\": {\n \"acc\": 0.62,\n \"acc_stderr\": 0.04878317312145633,\n \"acc_norm\": 0.62,\n \"acc_norm_stderr\": 0.04878317312145633\n },\n \"harness|hendrycksTest-college_mathematics|5\": {\n \"acc\": 0.44,\n \"acc_stderr\": 0.04988876515698589,\n \"acc_norm\": 0.44,\n \"acc_norm_stderr\": 0.04988876515698589\n },\n \"harness|hendrycksTest-college_medicine|5\": {\n \"acc\": 0.7514450867052023,\n \"acc_stderr\": 0.03295304696818318,\n \"acc_norm\": 0.7514450867052023,\n \"acc_norm_stderr\": 0.03295304696818318\n },\n \"harness|hendrycksTest-college_physics|5\": {\n \"acc\": 0.46078431372549017,\n \"acc_stderr\": 0.049598599663841815,\n \"acc_norm\": 0.46078431372549017,\n \"acc_norm_stderr\": 0.049598599663841815\n },\n \"harness|hendrycksTest-computer_security|5\": {\n \"acc\": 0.83,\n \"acc_stderr\": 0.03775251680686371,\n \"acc_norm\": 0.83,\n \"acc_norm_stderr\": 0.03775251680686371\n },\n \"harness|hendrycksTest-conceptual_physics|5\": {\n \"acc\": 0.7702127659574468,\n \"acc_stderr\": 0.02750175294441242,\n \"acc_norm\": 0.7702127659574468,\n \"acc_norm_stderr\": 0.02750175294441242\n },\n \"harness|hendrycksTest-econometrics|5\": {\n \"acc\": 0.5087719298245614,\n \"acc_stderr\": 0.04702880432049615,\n \"acc_norm\": 0.5087719298245614,\n \"acc_norm_stderr\": 0.04702880432049615\n },\n \"harness|hendrycksTest-electrical_engineering|5\": {\n \"acc\": 0.7448275862068966,\n \"acc_stderr\": 0.03632984052707842,\n \"acc_norm\": 0.7448275862068966,\n \"acc_norm_stderr\": 0.03632984052707842\n },\n \"harness|hendrycksTest-elementary_mathematics|5\": {\n \"acc\": 0.656084656084656,\n \"acc_stderr\": 0.024464426625596433,\n \"acc_norm\": 0.656084656084656,\n \"acc_norm_stderr\": 0.024464426625596433\n },\n \"harness|hendrycksTest-formal_logic|5\": {\n \"acc\": 0.5555555555555556,\n \"acc_stderr\": 0.04444444444444449,\n \"acc_norm\": 0.5555555555555556,\n \"acc_norm_stderr\": 0.04444444444444449\n },\n \"harness|hendrycksTest-global_facts|5\": {\n \"acc\": 0.48,\n \"acc_stderr\": 0.050211673156867795,\n \"acc_norm\": 0.48,\n \"acc_norm_stderr\": 0.050211673156867795\n },\n \"harness|hendrycksTest-high_school_biology|5\": {\n \"acc\": 0.8903225806451613,\n \"acc_stderr\": 0.017776778700485184,\n \"acc_norm\": 0.8903225806451613,\n \"acc_norm_stderr\": 0.017776778700485184\n },\n \"harness|hendrycksTest-high_school_chemistry|5\": {\n \"acc\": 0.6650246305418719,\n \"acc_stderr\": 0.0332085274234831,\n \"acc_norm\": 0.6650246305418719,\n \"acc_norm_stderr\": 0.0332085274234831\n },\n \"harness|hendrycksTest-high_school_computer_science|5\": {\n \"acc\": 0.81,\n \"acc_stderr\": 0.03942772444036625,\n \"acc_norm\": 0.81,\n \"acc_norm_stderr\": 0.03942772444036625\n },\n \"harness|hendrycksTest-high_school_european_history|5\": {\n \"acc\": 0.8484848484848485,\n \"acc_stderr\": 0.027998073798781668,\n \"acc_norm\": 0.8484848484848485,\n \"acc_norm_stderr\": 0.027998073798781668\n },\n \"harness|hendrycksTest-high_school_geography|5\": {\n \"acc\": 0.898989898989899,\n \"acc_stderr\": 0.021469735576055346,\n \"acc_norm\": 0.898989898989899,\n \"acc_norm_stderr\": 0.021469735576055346\n },\n \"harness|hendrycksTest-high_school_government_and_politics|5\": {\n \"acc\": 0.9637305699481865,\n \"acc_stderr\": 0.013492659751295136,\n \"acc_norm\": 0.9637305699481865,\n \"acc_norm_stderr\": 0.013492659751295136\n },\n \"harness|hendrycksTest-high_school_macroeconomics|5\": {\n \"acc\": 0.7692307692307693,\n \"acc_stderr\": 0.021362027725222717,\n \"acc_norm\": 0.7692307692307693,\n \"acc_norm_stderr\": 0.021362027725222717\n },\n \"harness|hendrycksTest-high_school_mathematics|5\": {\n \"acc\": 0.3925925925925926,\n \"acc_stderr\": 0.02977384701253297,\n \"acc_norm\": 0.3925925925925926,\n \"acc_norm_stderr\": 0.02977384701253297\n },\n \"harness|hendrycksTest-high_school_microeconomics|5\": {\n \"acc\": 0.8319327731092437,\n \"acc_stderr\": 0.024289102115692282,\n \"acc_norm\": 0.8319327731092437,\n \"acc_norm_stderr\": 0.024289102115692282\n },\n \"harness|hendrycksTest-high_school_physics|5\": {\n \"acc\": 0.4768211920529801,\n \"acc_stderr\": 0.04078093859163083,\n \"acc_norm\": 0.4768211920529801,\n \"acc_norm_stderr\": 0.04078093859163083\n },\n \"harness|hendrycksTest-high_school_psychology|5\": {\n \"acc\": 0.9119266055045872,\n \"acc_stderr\": 0.012150743719481688,\n \"acc_norm\": 0.9119266055045872,\n \"acc_norm_stderr\": 0.012150743719481688\n },\n \"harness|hendrycksTest-high_school_statistics|5\": {\n \"acc\": 0.6481481481481481,\n \"acc_stderr\": 0.03256850570293647,\n \"acc_norm\": 0.6481481481481481,\n \"acc_norm_stderr\": 0.03256850570293647\n },\n \"harness|hendrycksTest-high_school_us_history|5\": {\n \"acc\": 0.9068627450980392,\n \"acc_stderr\": 0.020397853969427,\n \"acc_norm\": 0.9068627450980392,\n \"acc_norm_stderr\": 0.020397853969427\n },\n \"harness|hendrycksTest-high_school_world_history|5\": {\n \"acc\": 0.8945147679324894,\n \"acc_stderr\": 0.01999556072375853,\n \"acc_norm\": 0.8945147679324894,\n \"acc_norm_stderr\": 0.01999556072375853\n },\n \"harness|hendrycksTest-human_aging|5\": {\n \"acc\": 0.7668161434977578,\n \"acc_stderr\": 0.028380391147094702,\n \"acc_norm\": 0.7668161434977578,\n \"acc_norm_stderr\": 0.028380391147094702\n },\n \"harness|hendrycksTest-human_sexuality|5\": {\n \"acc\": 0.8396946564885496,\n \"acc_stderr\": 0.03217829420744631,\n \"acc_norm\": 0.8396946564885496,\n \"acc_norm_stderr\": 0.03217829420744631\n },\n \"harness|hendrycksTest-international_law|5\": {\n \"acc\": 0.9090909090909091,\n \"acc_stderr\": 0.02624319405407388,\n \"acc_norm\": 0.9090909090909091,\n \"acc_norm_stderr\": 0.02624319405407388\n },\n \"harness|hendrycksTest-jurisprudence|5\": {\n \"acc\": 0.8611111111111112,\n \"acc_stderr\": 0.03343270062869621,\n \"acc_norm\": 0.8611111111111112,\n \"acc_norm_stderr\": 0.03343270062869621\n },\n \"harness|hendrycksTest-logical_fallacies|5\": {\n \"acc\": 0.8588957055214724,\n \"acc_stderr\": 0.027351605518389752,\n \"acc_norm\": 0.8588957055214724,\n \"acc_norm_stderr\": 0.027351605518389752\n },\n \"harness|hendrycksTest-machine_learning|5\": {\n \"acc\": 0.5535714285714286,\n \"acc_stderr\": 0.04718471485219587,\n \"acc_norm\": 0.5535714285714286,\n \"acc_norm_stderr\": 0.04718471485219587\n },\n \"harness|hendrycksTest-management|5\": {\n \"acc\": 0.8543689320388349,\n \"acc_stderr\": 0.03492606476623791,\n \"acc_norm\": 0.8543689320388349,\n \"acc_norm_stderr\": 0.03492606476623791\n },\n \"harness|hendrycksTest-marketing|5\": {\n \"acc\": 0.9273504273504274,\n \"acc_stderr\": 0.017004368568132342,\n \"acc_norm\": 0.9273504273504274,\n \"acc_norm_stderr\": 0.017004368568132342\n },\n \"harness|hendrycksTest-medical_genetics|5\": {\n \"acc\": 0.86,\n \"acc_stderr\": 0.03487350880197771,\n \"acc_norm\": 0.86,\n \"acc_norm_stderr\": 0.03487350880197771\n },\n \"harness|hendrycksTest-miscellaneous|5\": {\n \"acc\": 0.896551724137931,\n \"acc_stderr\": 0.010890452544691504,\n \"acc_norm\": 0.896551724137931,\n \"acc_norm_stderr\": 0.010890452544691504\n },\n \"harness|hendrycksTest-moral_disputes|5\": {\n \"acc\": 0.8034682080924855,\n \"acc_stderr\": 0.02139396140436385,\n \"acc_norm\": 0.8034682080924855,\n \"acc_norm_stderr\": 0.02139396140436385\n },\n \"harness|hendrycksTest-moral_scenarios|5\": {\n \"acc\": 0.6044692737430167,\n \"acc_stderr\": 0.016353415410075775,\n \"acc_norm\": 0.6044692737430167,\n \"acc_norm_stderr\": 0.016353415410075775\n },\n \"harness|hendrycksTest-nutrition|5\": {\n \"acc\": 0.826797385620915,\n \"acc_stderr\": 0.021668400256514293,\n \"acc_norm\": 0.826797385620915,\n \"acc_norm_stderr\": 0.021668400256514293\n },\n \"harness|hendrycksTest-philosophy|5\": {\n \"acc\": 0.8167202572347267,\n \"acc_stderr\": 0.021974198848265812,\n \"acc_norm\": 0.8167202572347267,\n \"acc_norm_stderr\": 0.021974198848265812\n },\n \"harness|hendrycksTest-prehistory|5\": {\n \"acc\": 0.8364197530864198,\n \"acc_stderr\": 0.020581466138257138,\n \"acc_norm\": 0.8364197530864198,\n \"acc_norm_stderr\": 0.020581466138257138\n },\n \"harness|hendrycksTest-professional_accounting|5\": {\n \"acc\": 0.648936170212766,\n \"acc_stderr\": 0.028473501272963758,\n \"acc_norm\": 0.648936170212766,\n \"acc_norm_stderr\": 0.028473501272963758\n },\n \"harness|hendrycksTest-professional_law|5\": {\n \"acc\": 0.5886571056062582,\n \"acc_stderr\": 0.012567882673803694,\n \"acc_norm\": 0.5886571056062582,\n \"acc_norm_stderr\": 0.012567882673803694\n },\n \"harness|hendrycksTest-professional_medicine|5\": {\n \"acc\": 0.8014705882352942,\n \"acc_stderr\": 0.0242310133705411,\n \"acc_norm\": 0.8014705882352942,\n \"acc_norm_stderr\": 0.0242310133705411\n },\n \"harness|hendrycksTest-professional_psychology|5\": {\n \"acc\": 0.8202614379084967,\n \"acc_stderr\": 0.01553374508338279,\n \"acc_norm\": 0.8202614379084967,\n \"acc_norm_stderr\": 0.01553374508338279\n },\n \"harness|hendrycksTest-public_relations|5\": {\n \"acc\": 0.7181818181818181,\n \"acc_stderr\": 0.04309118709946458,\n \"acc_norm\": 0.7181818181818181,\n \"acc_norm_stderr\": 0.04309118709946458\n },\n \"harness|hendrycksTest-security_studies|5\": {\n \"acc\": 0.8367346938775511,\n \"acc_stderr\": 0.023661699177098608,\n \"acc_norm\": 0.8367346938775511,\n \"acc_norm_stderr\": 0.023661699177098608\n },\n \"harness|hendrycksTest-sociology|5\": {\n \"acc\": 0.8805970149253731,\n \"acc_stderr\": 0.02292879327721974,\n \"acc_norm\": 0.8805970149253731,\n \"acc_norm_stderr\": 0.02292879327721974\n },\n \"harness|hendrycksTest-us_foreign_policy|5\": {\n \"acc\": 0.89,\n \"acc_stderr\": 0.03144660377352203,\n \"acc_norm\": 0.89,\n \"acc_norm_stderr\": 0.03144660377352203\n },\n \"harness|hendrycksTest-virology|5\": {\n \"acc\": 0.5662650602409639,\n \"acc_stderr\": 0.03858158940685515,\n \"acc_norm\": 0.5662650602409639,\n \"acc_norm_stderr\": 0.03858158940685515\n },\n \"harness|hendrycksTest-world_religions|5\": {\n \"acc\": 0.8654970760233918,\n \"acc_stderr\": 0.0261682213446623,\n \"acc_norm\": 0.8654970760233918,\n \"acc_norm_stderr\": 0.0261682213446623\n },\n \"harness|truthfulqa:mc|0\": {\n \"mc1\": 0.40269277845777235,\n \"mc1_stderr\": 0.01716883093518722,\n \"mc2\": 0.5606217649091164,\n \"mc2_stderr\": 0.01566716384108092\n },\n \"harness|winogrande|5\": {\n \"acc\": 0.8208366219415943,\n \"acc_stderr\": 0.010777949156047994\n },\n \"harness|gsm8k|5\": {\n \"acc\": 0.46853677028051555,\n \"acc_stderr\": 0.013745189948450419\n }\n}\n```", "repo_url": "https://huggingface.co/Azure99/blossom-v3_1-yi-34b", "leaderboard_url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard", "point_of_contact": "[email protected]", "configs": [{"config_name": "harness_arc_challenge_25", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|arc:challenge|25_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|arc:challenge|25_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_gsm8k_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|gsm8k|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|gsm8k|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hellaswag_10", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hellaswag|10_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hellaswag|10_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-abstract_algebra|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-anatomy|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-astronomy|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-business_ethics|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-clinical_knowledge|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-college_biology|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-college_chemistry|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-college_computer_science|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-college_mathematics|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-college_medicine|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-college_physics|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-computer_security|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-conceptual_physics|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-econometrics|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-electrical_engineering|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-elementary_mathematics|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-formal_logic|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-global_facts|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_biology|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_chemistry|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_computer_science|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_european_history|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_geography|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_mathematics|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_physics|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_psychology|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_statistics|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_us_history|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_world_history|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-human_aging|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-human_sexuality|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-international_law|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-jurisprudence|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-logical_fallacies|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-machine_learning|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-management|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-marketing|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-medical_genetics|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-miscellaneous|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-moral_disputes|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-moral_scenarios|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-nutrition|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-philosophy|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-prehistory|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-professional_accounting|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-professional_law|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-professional_medicine|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-professional_psychology|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-public_relations|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-security_studies|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-sociology|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-us_foreign_policy|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-virology|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-world_religions|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-abstract_algebra|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-anatomy|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-astronomy|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-business_ethics|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-clinical_knowledge|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-college_biology|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-college_chemistry|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-college_computer_science|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-college_mathematics|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-college_medicine|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-college_physics|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-computer_security|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-conceptual_physics|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-econometrics|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-electrical_engineering|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-elementary_mathematics|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-formal_logic|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-global_facts|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_biology|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_chemistry|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_computer_science|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_european_history|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_geography|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_mathematics|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_physics|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_psychology|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_statistics|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_us_history|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-high_school_world_history|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-human_aging|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-human_sexuality|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-international_law|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-jurisprudence|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-logical_fallacies|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-machine_learning|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-management|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-marketing|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-medical_genetics|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-miscellaneous|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-moral_disputes|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-moral_scenarios|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-nutrition|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-philosophy|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-prehistory|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-professional_accounting|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-professional_law|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-professional_medicine|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-professional_psychology|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-public_relations|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-security_studies|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-sociology|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-us_foreign_policy|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-virology|5_2023-12-16T12-07-38.687191.parquet", "**/details_harness|hendrycksTest-world_religions|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_abstract_algebra_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-abstract_algebra|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-abstract_algebra|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_anatomy_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-anatomy|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-anatomy|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_astronomy_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-astronomy|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-astronomy|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_business_ethics_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-business_ethics|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-business_ethics|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_clinical_knowledge_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-clinical_knowledge|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-clinical_knowledge|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_biology_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-college_biology|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_biology|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_chemistry_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-college_chemistry|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_chemistry|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_computer_science_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-college_computer_science|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_computer_science|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_mathematics_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-college_mathematics|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_mathematics|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_medicine_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-college_medicine|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_medicine|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_physics_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-college_physics|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_physics|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_computer_security_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-computer_security|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-computer_security|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_conceptual_physics_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-conceptual_physics|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-conceptual_physics|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_econometrics_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-econometrics|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-econometrics|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_electrical_engineering_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-electrical_engineering|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-electrical_engineering|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_elementary_mathematics_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-elementary_mathematics|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-elementary_mathematics|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_formal_logic_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-formal_logic|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-formal_logic|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_global_facts_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-global_facts|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-global_facts|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_biology_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-high_school_biology|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_biology|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_chemistry_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-high_school_chemistry|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_chemistry|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_computer_science_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-high_school_computer_science|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_computer_science|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_european_history_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-high_school_european_history|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_european_history|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_geography_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-high_school_geography|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_geography|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_government_and_politics_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_macroeconomics_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_mathematics_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-high_school_mathematics|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_mathematics|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_microeconomics_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_physics_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-high_school_physics|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_physics|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_psychology_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-high_school_psychology|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_psychology|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_statistics_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-high_school_statistics|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_statistics|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_us_history_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-high_school_us_history|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_us_history|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_world_history_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-high_school_world_history|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_world_history|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_human_aging_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-human_aging|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-human_aging|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_human_sexuality_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-human_sexuality|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-human_sexuality|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_international_law_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-international_law|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-international_law|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_jurisprudence_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-jurisprudence|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-jurisprudence|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_logical_fallacies_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-logical_fallacies|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-logical_fallacies|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_machine_learning_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-machine_learning|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-machine_learning|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_management_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-management|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-management|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_marketing_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-marketing|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-marketing|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_medical_genetics_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-medical_genetics|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-medical_genetics|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_miscellaneous_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-miscellaneous|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-miscellaneous|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_moral_disputes_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-moral_disputes|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-moral_disputes|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_moral_scenarios_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-moral_scenarios|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-moral_scenarios|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_nutrition_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-nutrition|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-nutrition|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_philosophy_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-philosophy|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-philosophy|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_prehistory_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-prehistory|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-prehistory|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_professional_accounting_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-professional_accounting|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-professional_accounting|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_professional_law_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-professional_law|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-professional_law|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_professional_medicine_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-professional_medicine|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-professional_medicine|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_professional_psychology_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-professional_psychology|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-professional_psychology|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_public_relations_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-public_relations|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-public_relations|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_security_studies_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-security_studies|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-security_studies|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_sociology_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-sociology|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-sociology|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_us_foreign_policy_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-us_foreign_policy|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-us_foreign_policy|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_virology_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-virology|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-virology|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_hendrycksTest_world_religions_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|hendrycksTest-world_religions|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-world_religions|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_truthfulqa_mc_0", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|truthfulqa:mc|0_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|truthfulqa:mc|0_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "harness_winogrande_5", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["**/details_harness|winogrande|5_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["**/details_harness|winogrande|5_2023-12-16T12-07-38.687191.parquet"]}]}, {"config_name": "results", "data_files": [{"split": "2023_12_16T12_07_38.687191", "path": ["results_2023-12-16T12-07-38.687191.parquet"]}, {"split": "latest", "path": ["results_2023-12-16T12-07-38.687191.parquet"]}]}]} | 2023-12-16T12:11:11+00:00 | [] | [] | TAGS
#region-us
|
# Dataset Card for Evaluation run of Azure99/blossom-v3_1-yi-34b
Dataset automatically created during the evaluation run of model Azure99/blossom-v3_1-yi-34b on the Open LLM Leaderboard.
The dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An additional configuration "results" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).
To load the details from a run, you can for instance do the following:
## Latest results
These are the latest results from run 2023-12-16T12:07:38.687191(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the "latest" split for each eval):
## Dataset Details
### Dataset Description
- Curated by:
- Funded by [optional]:
- Shared by [optional]:
- Language(s) (NLP):
- License:
### Dataset Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Out-of-Scope Use
## Dataset Structure
## Dataset Creation
### Curation Rationale
### Source Data
#### Data Collection and Processing
#### Who are the source data producers?
### Annotations [optional]
#### Annotation process
#### Who are the annotators?
#### Personal and Sensitive Information
## Bias, Risks, and Limitations
### Recommendations
Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Dataset Card Authors [optional]
## Dataset Card Contact
| [
"# Dataset Card for Evaluation run of Azure99/blossom-v3_1-yi-34b\n\n\n\nDataset automatically created during the evaluation run of model Azure99/blossom-v3_1-yi-34b on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:",
"## Latest results\n\nThese are the latest results from run 2023-12-16T12:07:38.687191(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):",
"## Dataset Details",
"### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:",
"### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Out-of-Scope Use",
"## Dataset Structure",
"## Dataset Creation",
"### Curation Rationale",
"### Source Data",
"#### Data Collection and Processing",
"#### Who are the source data producers?",
"### Annotations [optional]",
"#### Annotation process",
"#### Who are the annotators?",
"#### Personal and Sensitive Information",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Dataset Card Authors [optional]",
"## Dataset Card Contact"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for Evaluation run of Azure99/blossom-v3_1-yi-34b\n\n\n\nDataset automatically created during the evaluation run of model Azure99/blossom-v3_1-yi-34b on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:",
"## Latest results\n\nThese are the latest results from run 2023-12-16T12:07:38.687191(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):",
"## Dataset Details",
"### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:",
"### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Out-of-Scope Use",
"## Dataset Structure",
"## Dataset Creation",
"### Curation Rationale",
"### Source Data",
"#### Data Collection and Processing",
"#### Who are the source data producers?",
"### Annotations [optional]",
"#### Annotation process",
"#### Who are the annotators?",
"#### Personal and Sensitive Information",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Dataset Card Authors [optional]",
"## Dataset Card Contact"
] | [
6,
189,
67,
4,
40,
29,
3,
4,
9,
6,
5,
7,
4,
7,
10,
9,
5,
9,
8,
10,
46,
8,
7,
10,
5
] | [
"passage: TAGS\n#region-us \n# Dataset Card for Evaluation run of Azure99/blossom-v3_1-yi-34b\n\n\n\nDataset automatically created during the evaluation run of model Azure99/blossom-v3_1-yi-34b on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:## Latest results\n\nThese are the latest results from run 2023-12-16T12:07:38.687191(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):## Dataset Details### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Out-of-Scope Use## Dataset Structure## Dataset Creation### Curation Rationale### Source Data#### Data Collection and Processing#### Who are the source data producers?### Annotations [optional]#### Annotation process#### Who are the annotators?#### Personal and Sensitive Information## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Dataset Card Authors [optional]## Dataset Card Contact"
] |
46c5f54dabc31892a924506c42a7ee932182bbec |
Used the technique from [Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor](https://arxiv.org/abs/2212.09689) and Mixtral8x7B (Base Model)
to generate this diverse, fully-synthetic, fully open-source set of 30,000 conversation starters.
See also: [unnaturalhermes-questions-100k](https://huggingface.co/datasets/ericflo/unnaturalhermes-questions-100k), a distinct set of 100k examples just like this, if you want more training data. | ericflo/unnaturalhermes-questions-30k | [
"task_categories:question-answering",
"size_categories:10K<n<100K",
"language:en",
"license:apache-2.0",
"arxiv:2212.09689",
"region:us"
] | 2023-12-16T12:29:54+00:00 | {"language": ["en"], "license": "apache-2.0", "size_categories": ["10K<n<100K"], "task_categories": ["question-answering"]} | 2023-12-16T12:40:47+00:00 | [
"2212.09689"
] | [
"en"
] | TAGS
#task_categories-question-answering #size_categories-10K<n<100K #language-English #license-apache-2.0 #arxiv-2212.09689 #region-us
|
Used the technique from Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor and Mixtral8x7B (Base Model)
to generate this diverse, fully-synthetic, fully open-source set of 30,000 conversation starters.
See also: unnaturalhermes-questions-100k, a distinct set of 100k examples just like this, if you want more training data. | [] | [
"TAGS\n#task_categories-question-answering #size_categories-10K<n<100K #language-English #license-apache-2.0 #arxiv-2212.09689 #region-us \n"
] | [
51
] | [
"passage: TAGS\n#task_categories-question-answering #size_categories-10K<n<100K #language-English #license-apache-2.0 #arxiv-2212.09689 #region-us \n"
] |
4cdc0dd62fdbe19e63baa80b2cb7722e0567f775 |
Used the technique from [Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor](https://arxiv.org/abs/2212.09689) and Mixtral8x7B (Base Model)
to generate this diverse, fully-synthetic, fully open-source set of 100,000 conversation starters.
See also: [unnaturalhermes-questions-30k](https://huggingface.co/datasets/ericflo/unnaturalhermes-questions-30k), a distinct set of 30k examples just like this, if you want more training data. | ericflo/unnaturalhermes-questions-100k | [
"task_categories:question-answering",
"size_categories:10K<n<100K",
"language:en",
"license:apache-2.0",
"arxiv:2212.09689",
"region:us"
] | 2023-12-16T12:38:07+00:00 | {"language": ["en"], "license": "apache-2.0", "size_categories": ["10K<n<100K"], "task_categories": ["question-answering"]} | 2023-12-16T12:40:14+00:00 | [
"2212.09689"
] | [
"en"
] | TAGS
#task_categories-question-answering #size_categories-10K<n<100K #language-English #license-apache-2.0 #arxiv-2212.09689 #region-us
|
Used the technique from Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor and Mixtral8x7B (Base Model)
to generate this diverse, fully-synthetic, fully open-source set of 100,000 conversation starters.
See also: unnaturalhermes-questions-30k, a distinct set of 30k examples just like this, if you want more training data. | [] | [
"TAGS\n#task_categories-question-answering #size_categories-10K<n<100K #language-English #license-apache-2.0 #arxiv-2212.09689 #region-us \n"
] | [
51
] | [
"passage: TAGS\n#task_categories-question-answering #size_categories-10K<n<100K #language-English #license-apache-2.0 #arxiv-2212.09689 #region-us \n"
] |
d17c4b7e767da9491537cf49da450b6c0bf98491 | # Parlogs-Observations Dataset
## Dataset Summary
Parlogs-Observations is a comprehensive dataset that includes the Very Large Telescope (VLT) logs for Template Execution of PIONIER, GRAVITY, and MATISSE instruments when they used Auxiliary Telescopes (ATs). It also encompasses all VLTI subsystems and ATs logs. This dataset aggregates logs based on instruments, time ranges, and subsystems, and contains template executions from 2019 in the VLTI infrastructure at Paranal. The dataset is formatted in single Parket files, which can be conveniently loaded, for example, with Pandas in Python.
Parlogs-Observations is publicly available at 🤗 Hugging Face Dataset.
## Supported Tasks and Leaderboards
The `parlogs-observations` dataset is a resource for researchers and practitioners in astronomy, data analysis, and machine learning. It enables a wide range of tasks focused on enhancing the understanding and operation of the Very Large Telescope Interferometer (VLTI) infrastructure. The following tasks are supported by the dataset:
- **Anomaly Detection**: Users can identify unusual patterns or abnormal behavior in the log data that could indicate errors or bugs. This is crucial in providing operaional maintenance to the VLTI.
- **System Diagnosis**: The dataset allows for diagnosing system failures or performance issues. By analyzing error logs, trace logs, or event logs, researchers can pinpoint and address the root causes of various operational issues.
- **Performance Monitoring**: With this dataset, monitoring the performance of the VLTI systems becomes feasible. Users can track and analyze systems to understand resource usage, detect latency issues, or identify bottlenecks in the infrastructure.
- **Predictive Maintenance**: Leveraging the dataset for predictive maintenance helps in foreseeing system failures or issues before they occur. This is achieved by analyzing trends and patterns in the log data to implement timely interventions.
## Overview
### Observations at Paranal
At Paranal, the Very Large Telescope (VLT) is one of the world's most advanced optical telescopes, consisting of four Unit Telescopes and four movable Auxiliary Telescopes. Astronomical observations are configured into Observation Blocks (OBs), containing a sequence of Templates with parameters and scripts tailored to various scientific goals. Each template's execution follows a predictable behavior, allowing for detailed and systematic studies. The templates remain unchanged during a scientific period of six months, therefore the templates referred in parlogs-observations datasets can be considered as immutable source code.
### Machine Learning Techniques for parlogs-observations
Given the structured nature of the dataset, various machine learning techniques can be applied to extract insights and build models for the tasks mentioned above. Some of these techniques include:
- **Clustering Algorithms**: Such as K-means and hierarchical clustering to group similar log messages or events and identify nested patterns in log data.
- **Classification Algorithms**: Including Support Vector Machines (SVM), Random Forests, and Naive Bayes classifiers for categorizing log messages and detecting anomalies.
- **Sequence Analysis and Pattern Recognition**: Utilizing Hidden Markov Models (HMMs) and Frequent Pattern Mining to model sequences of log messages or events and discover common patterns in logs.
- **Anomaly Detection Techniques**: Applying Isolation Forest and other advanced methods to identify outliers and anomalies in log data.
- **Natural Language Processing (NLP) Techniques**: Leveraging Topic Modeling and Word Embeddings to uncover thematic structures in log messages and transform text into meaningful numerical representations.
- **Deep Learning Techniques**: Employing Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, Convolutional Neural Networks (CNNs), Graph Neural Networks (GNNs), Transformers, and Autoencoders for sophisticated modeling and analysis of time-series log data.
## Data Structure and Naming Conventions
The dataset is organized into Parket files follow a structured naming convention for easy identification and access based on the instrument, time range, and subsystems. This format ensures efficient data retrieval and manipulation, especially for large-scale data analysis:
```
{INSTRUMENT}-{TIME_RANGE}-{CONTENT}.parket
```
Where:
- `INSTRUMENT` can be PIONIER, GRAVITY, or MATISSE.
- `TIME_RANGE` is one of 1d, 1w, 1m, 6m.
- `CONTENT` can be meta, traces, traces-SUBSYSTEMS, or traces-TELESCOPES.
Example files:
- PIONIER-1w-meta.parket
- GRAVITY-1m-traces-SUBSYSTEMS.parket
The "meta" file includes information about the template execution, while "traces" files contain event logs.
The exisiting files are shown in the table below:
| GRAVITY | PIONIER | MATISSE |
|---------------------------|---------------------------|---------------------------|
| GRAVITY-1d-meta.parket | PIONIER-1d-meta.parket | MATISSE-1d-meta.parket |
| GRAVITY-1d-traces-SUBSYSTEMS.parket | PIONIER-1d-traces-SUBSYSTEMS.parket | MATISSE-1d-traces-SUBSYSTEMS.parket |
| GRAVITY-1d-traces-TELESCOPES.parket | PIONIER-1d-traces-TELESCOPES.parket | MATISSE-1d-traces-TELESCOPES.parket |
| GRAVITY-1d-traces.parket | PIONIER-1d-traces.parket | MATISSE-1d-traces.parket |
| GRAVITY-1m-meta.parket | PIONIER-1m-meta.parket | MATISSE-1m-meta.parket |
| GRAVITY-1m-traces-SUBSYSTEMS.parket | PIONIER-1m-traces-SUBSYSTEMS.parket | MATISSE-1m-traces-SUBSYSTEMS.parket |
| GRAVITY-1m-traces-TELESCOPES.parket | PIONIER-1m-traces-TELESCOPES.parket | MATISSE-1m-traces-TELESCOPES.parket |
| GRAVITY-1m-traces.parket | PIONIER-1m-traces.parket | MATISSE-1m-traces.parket |
| GRAVITY-1w-meta.parket | PIONIER-1w-meta.parket | MATISSE-1w-meta.parket |
| GRAVITY-1w-traces-SUBSYSTEMS.parket | PIONIER-1w-traces-SUBSYSTEMS.parket | MATISSE-1w-traces-SUBSYSTEMS.parket |
| GRAVITY-1w-traces-TELESCOPES.parket | PIONIER-1w-traces-TELESCOPES.parket | MATISSE-1w-traces-TELESCOPES.parket |
| GRAVITY-1w-traces.parket | PIONIER-1w-traces.parket | MATISSE-1w-traces.parket |
| GRAVITY-6m-meta.parket | PIONIER-6m-meta.parket | MATISSE-6m-meta.parket |
| GRAVITY-6m-traces-SUBSYSTEMS.parket | PIONIER-6m-traces-SUBSYSTEMS.parket | MATISSE-6m-traces-SUBSYSTEMS.parket |
| GRAVITY-6m-traces-TELESCOPES.parket | PIONIER-6m-traces-TELESCOPES.parket | MATISSE-6m-traces-TELESCOPES.parket |
| GRAVITY-6m-traces.parket | PIONIER-6m-traces.parket | MATISSE-6m-traces.parket |
## Combining Files
Files from same instrument and within the same time range belong to the same trace_id. For instance, in the files:
- PIONIER-1w-meta.parket
- PIONIER-1w-traces.parket
The trace_id=10 in PIONIER-1w-traces.parket file corresponds to the id=10 in the meta file PIONIER-1w-meta.parket.
## Data Instances
A typical entry in the dataset might look like this:
```python
# File: PIONIER-1m-traces.parket
# Row: 12268
{
"@timestamp": 1554253173950,
"system": "PIONIER",
"hostname": "wpnr",
"loghost": "wpnr",
"logtype": "LOG",
"envname": "wpnr",
"procname": "pnoControl",
"procid": 208,
"module": "boss",
"keywname": "",
"keywvalue": "",
"keywmask": "",
"logtext": "Executing START command ...",
"trace_id": 49
}
```
## Data Fields
The dataset contains structured logs from software operations related to astronomical instruments. Each entry in the log provides detailed information regarding specific actions or events recorded by the system. Below is the description of each field in the log entries:
| Field | Description |
|-------------|---------------------------------------------------------------------------------------------------|
| @timestamp | The timestamp of the log entry in milliseconds. |
| system | The name of the system (e.g., PIONIER) from which the log entry originates. |
| hostname | The hostname of the machine where the log entry was generated. |
| loghost | The host of the logging system that generated the entry. |
| logtype | Type of the log entry (e.g., LOG, FEVT, ERR), indicating its nature such as general log, event, or error. |
| envname | The environment name where the log was generated, providing context for the log entry. |
| procname | The name of the process that generated the log entry. |
| procid | The process ID associated with the log entry. |
| module | The module from which the log entry originated, indicating the specific part of the system. |
| keywname | Name of any keyword associated with the log entry, if applicable. It is always paired with keywvalue |
| keywvalue | Value of the keyword mentioned in `keywname`, if applicable. |
| keywmask | Mask or additional context for the keyword, if applicable. |
| logtext | The actual text of the log entry, providing detailed information about the event or action. |
| trace_id | A unique identifier associated with each log entry, corresponds to id in metadata table. |
## Dataset Metadata
Each Parket file contains metadata regarding its contents, which includes details about the instrument used, time range, and types of logs stored. This is the format of a sample template execution in the metadata:
```python
# File: PIONIER-1m-meta.parket
# Row: 49
{
"START": "2019-04-03 00:59:33.005000",
"END": "2019-04-03 01:01:25.719000",
"TIMEOUT": false,
"system": "PIONIER",
"procname": "bob_ins",
"TPL_ID": "PIONIER_obs_calibrator",
"ERROR": false,
"Aborted": false,
"SECONDS": 112.0,
"TEL": "AT"
}
```
Where the fields are:
| Field | Comment |
| --------- | -------------------------------------------------------- |
| START | The start timestamp of the template execution in milliseconds |
| END | The end timestamp of the template execution in milliseconds |
| TIMEOUT | Indicates if the execution exceeded a predefined time limit |
| system | The name of the system used (e.g., PIONIER) |
| procname | The process name associated with the template execution |
| TPL_ID | The filename of the corresponding template file |
| ERROR | Indicates if there was an error during execution |
| Aborted | Indicates if the template execution was aborted (manually or because an error) |
| SECONDS | The duration of the template execution in seconds |
| TEL | The class of telescope used in the observation, in this dataset it is only AT |
This structured format ensures a comprehensive understanding of each template's execution, providing insights into the operational dynamics of astronomical observations at Paranal.
## Loading Data
The dataset can be loaded using Python libraries like Pandas. Here's an example of how to load a Parket file:
```python
import pandas as pd
df = pd.read_parket('PIONIER-1w-meta.parket')
```
| Paranal/parlogs-observations | [
"language:en",
"license:lgpl-2.1",
"region:us"
] | 2023-12-16T12:40:35+00:00 | {"language": ["en"], "license": ["lgpl-2.1"], "pretty_name": "parlogs", "layout": "default", "title": "Home"} | 2024-01-09T21:58:38+00:00 | [] | [
"en"
] | TAGS
#language-English #license-lgpl-2.1 #region-us
| Parlogs-Observations Dataset
============================
Dataset Summary
---------------
Parlogs-Observations is a comprehensive dataset that includes the Very Large Telescope (VLT) logs for Template Execution of PIONIER, GRAVITY, and MATISSE instruments when they used Auxiliary Telescopes (ATs). It also encompasses all VLTI subsystems and ATs logs. This dataset aggregates logs based on instruments, time ranges, and subsystems, and contains template executions from 2019 in the VLTI infrastructure at Paranal. The dataset is formatted in single Parket files, which can be conveniently loaded, for example, with Pandas in Python.
Parlogs-Observations is publicly available at Hugging Face Dataset.
Supported Tasks and Leaderboards
--------------------------------
The 'parlogs-observations' dataset is a resource for researchers and practitioners in astronomy, data analysis, and machine learning. It enables a wide range of tasks focused on enhancing the understanding and operation of the Very Large Telescope Interferometer (VLTI) infrastructure. The following tasks are supported by the dataset:
* Anomaly Detection: Users can identify unusual patterns or abnormal behavior in the log data that could indicate errors or bugs. This is crucial in providing operaional maintenance to the VLTI.
* System Diagnosis: The dataset allows for diagnosing system failures or performance issues. By analyzing error logs, trace logs, or event logs, researchers can pinpoint and address the root causes of various operational issues.
* Performance Monitoring: With this dataset, monitoring the performance of the VLTI systems becomes feasible. Users can track and analyze systems to understand resource usage, detect latency issues, or identify bottlenecks in the infrastructure.
* Predictive Maintenance: Leveraging the dataset for predictive maintenance helps in foreseeing system failures or issues before they occur. This is achieved by analyzing trends and patterns in the log data to implement timely interventions.
Overview
--------
### Observations at Paranal
At Paranal, the Very Large Telescope (VLT) is one of the world's most advanced optical telescopes, consisting of four Unit Telescopes and four movable Auxiliary Telescopes. Astronomical observations are configured into Observation Blocks (OBs), containing a sequence of Templates with parameters and scripts tailored to various scientific goals. Each template's execution follows a predictable behavior, allowing for detailed and systematic studies. The templates remain unchanged during a scientific period of six months, therefore the templates referred in parlogs-observations datasets can be considered as immutable source code.
### Machine Learning Techniques for parlogs-observations
Given the structured nature of the dataset, various machine learning techniques can be applied to extract insights and build models for the tasks mentioned above. Some of these techniques include:
* Clustering Algorithms: Such as K-means and hierarchical clustering to group similar log messages or events and identify nested patterns in log data.
* Classification Algorithms: Including Support Vector Machines (SVM), Random Forests, and Naive Bayes classifiers for categorizing log messages and detecting anomalies.
* Sequence Analysis and Pattern Recognition: Utilizing Hidden Markov Models (HMMs) and Frequent Pattern Mining to model sequences of log messages or events and discover common patterns in logs.
* Anomaly Detection Techniques: Applying Isolation Forest and other advanced methods to identify outliers and anomalies in log data.
* Natural Language Processing (NLP) Techniques: Leveraging Topic Modeling and Word Embeddings to uncover thematic structures in log messages and transform text into meaningful numerical representations.
* Deep Learning Techniques: Employing Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, Convolutional Neural Networks (CNNs), Graph Neural Networks (GNNs), Transformers, and Autoencoders for sophisticated modeling and analysis of time-series log data.
Data Structure and Naming Conventions
-------------------------------------
The dataset is organized into Parket files follow a structured naming convention for easy identification and access based on the instrument, time range, and subsystems. This format ensures efficient data retrieval and manipulation, especially for large-scale data analysis:
Where:
* 'INSTRUMENT' can be PIONIER, GRAVITY, or MATISSE.
* 'TIME\_RANGE' is one of 1d, 1w, 1m, 6m.
* 'CONTENT' can be meta, traces, traces-SUBSYSTEMS, or traces-TELESCOPES.
Example files:
* URL
* URL
The "meta" file includes information about the template execution, while "traces" files contain event logs.
The exisiting files are shown in the table below:
GRAVITY: URL, PIONIER: URL, MATISSE: URL
GRAVITY: URL, PIONIER: URL, MATISSE: URL
GRAVITY: URL, PIONIER: URL, MATISSE: URL
GRAVITY: URL, PIONIER: URL, MATISSE: URL
GRAVITY: URL, PIONIER: URL, MATISSE: URL
GRAVITY: URL, PIONIER: URL, MATISSE: URL
GRAVITY: URL, PIONIER: URL, MATISSE: URL
GRAVITY: URL, PIONIER: URL, MATISSE: URL
GRAVITY: URL, PIONIER: URL, MATISSE: URL
GRAVITY: URL, PIONIER: URL, MATISSE: URL
GRAVITY: URL, PIONIER: URL, MATISSE: URL
GRAVITY: URL, PIONIER: URL, MATISSE: URL
GRAVITY: URL, PIONIER: URL, MATISSE: URL
GRAVITY: URL, PIONIER: URL, MATISSE: URL
GRAVITY: URL, PIONIER: URL, MATISSE: URL
GRAVITY: URL, PIONIER: URL, MATISSE: URL
Combining Files
---------------
Files from same instrument and within the same time range belong to the same trace\_id. For instance, in the files:
* URL
* URL
The trace\_id=10 in URL file corresponds to the id=10 in the meta file URL.
Data Instances
--------------
A typical entry in the dataset might look like this:
Data Fields
-----------
The dataset contains structured logs from software operations related to astronomical instruments. Each entry in the log provides detailed information regarding specific actions or events recorded by the system. Below is the description of each field in the log entries:
Dataset Metadata
----------------
Each Parket file contains metadata regarding its contents, which includes details about the instrument used, time range, and types of logs stored. This is the format of a sample template execution in the metadata:
Where the fields are:
This structured format ensures a comprehensive understanding of each template's execution, providing insights into the operational dynamics of astronomical observations at Paranal.
Loading Data
------------
The dataset can be loaded using Python libraries like Pandas. Here's an example of how to load a Parket file:
| [
"### Observations at Paranal\n\n\nAt Paranal, the Very Large Telescope (VLT) is one of the world's most advanced optical telescopes, consisting of four Unit Telescopes and four movable Auxiliary Telescopes. Astronomical observations are configured into Observation Blocks (OBs), containing a sequence of Templates with parameters and scripts tailored to various scientific goals. Each template's execution follows a predictable behavior, allowing for detailed and systematic studies. The templates remain unchanged during a scientific period of six months, therefore the templates referred in parlogs-observations datasets can be considered as immutable source code.",
"### Machine Learning Techniques for parlogs-observations\n\n\nGiven the structured nature of the dataset, various machine learning techniques can be applied to extract insights and build models for the tasks mentioned above. Some of these techniques include:\n\n\n* Clustering Algorithms: Such as K-means and hierarchical clustering to group similar log messages or events and identify nested patterns in log data.\n* Classification Algorithms: Including Support Vector Machines (SVM), Random Forests, and Naive Bayes classifiers for categorizing log messages and detecting anomalies.\n* Sequence Analysis and Pattern Recognition: Utilizing Hidden Markov Models (HMMs) and Frequent Pattern Mining to model sequences of log messages or events and discover common patterns in logs.\n* Anomaly Detection Techniques: Applying Isolation Forest and other advanced methods to identify outliers and anomalies in log data.\n* Natural Language Processing (NLP) Techniques: Leveraging Topic Modeling and Word Embeddings to uncover thematic structures in log messages and transform text into meaningful numerical representations.\n* Deep Learning Techniques: Employing Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, Convolutional Neural Networks (CNNs), Graph Neural Networks (GNNs), Transformers, and Autoencoders for sophisticated modeling and analysis of time-series log data.\n\n\nData Structure and Naming Conventions\n-------------------------------------\n\n\nThe dataset is organized into Parket files follow a structured naming convention for easy identification and access based on the instrument, time range, and subsystems. This format ensures efficient data retrieval and manipulation, especially for large-scale data analysis:\n\n\nWhere:\n\n\n* 'INSTRUMENT' can be PIONIER, GRAVITY, or MATISSE.\n* 'TIME\\_RANGE' is one of 1d, 1w, 1m, 6m.\n* 'CONTENT' can be meta, traces, traces-SUBSYSTEMS, or traces-TELESCOPES.\n\n\nExample files:\n\n\n* URL\n* URL\n\n\nThe \"meta\" file includes information about the template execution, while \"traces\" files contain event logs.\n\n\nThe exisiting files are shown in the table below:\n\n\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\n\n\nCombining Files\n---------------\n\n\nFiles from same instrument and within the same time range belong to the same trace\\_id. For instance, in the files:\n\n\n* URL\n* URL\n\n\nThe trace\\_id=10 in URL file corresponds to the id=10 in the meta file URL.\n\n\nData Instances\n--------------\n\n\nA typical entry in the dataset might look like this:\n\n\nData Fields\n-----------\n\n\nThe dataset contains structured logs from software operations related to astronomical instruments. Each entry in the log provides detailed information regarding specific actions or events recorded by the system. Below is the description of each field in the log entries:\n\n\n\nDataset Metadata\n----------------\n\n\nEach Parket file contains metadata regarding its contents, which includes details about the instrument used, time range, and types of logs stored. This is the format of a sample template execution in the metadata:\n\n\nWhere the fields are:\n\n\n\nThis structured format ensures a comprehensive understanding of each template's execution, providing insights into the operational dynamics of astronomical observations at Paranal.\n\n\nLoading Data\n------------\n\n\nThe dataset can be loaded using Python libraries like Pandas. Here's an example of how to load a Parket file:"
] | [
"TAGS\n#language-English #license-lgpl-2.1 #region-us \n",
"### Observations at Paranal\n\n\nAt Paranal, the Very Large Telescope (VLT) is one of the world's most advanced optical telescopes, consisting of four Unit Telescopes and four movable Auxiliary Telescopes. Astronomical observations are configured into Observation Blocks (OBs), containing a sequence of Templates with parameters and scripts tailored to various scientific goals. Each template's execution follows a predictable behavior, allowing for detailed and systematic studies. The templates remain unchanged during a scientific period of six months, therefore the templates referred in parlogs-observations datasets can be considered as immutable source code.",
"### Machine Learning Techniques for parlogs-observations\n\n\nGiven the structured nature of the dataset, various machine learning techniques can be applied to extract insights and build models for the tasks mentioned above. Some of these techniques include:\n\n\n* Clustering Algorithms: Such as K-means and hierarchical clustering to group similar log messages or events and identify nested patterns in log data.\n* Classification Algorithms: Including Support Vector Machines (SVM), Random Forests, and Naive Bayes classifiers for categorizing log messages and detecting anomalies.\n* Sequence Analysis and Pattern Recognition: Utilizing Hidden Markov Models (HMMs) and Frequent Pattern Mining to model sequences of log messages or events and discover common patterns in logs.\n* Anomaly Detection Techniques: Applying Isolation Forest and other advanced methods to identify outliers and anomalies in log data.\n* Natural Language Processing (NLP) Techniques: Leveraging Topic Modeling and Word Embeddings to uncover thematic structures in log messages and transform text into meaningful numerical representations.\n* Deep Learning Techniques: Employing Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, Convolutional Neural Networks (CNNs), Graph Neural Networks (GNNs), Transformers, and Autoencoders for sophisticated modeling and analysis of time-series log data.\n\n\nData Structure and Naming Conventions\n-------------------------------------\n\n\nThe dataset is organized into Parket files follow a structured naming convention for easy identification and access based on the instrument, time range, and subsystems. This format ensures efficient data retrieval and manipulation, especially for large-scale data analysis:\n\n\nWhere:\n\n\n* 'INSTRUMENT' can be PIONIER, GRAVITY, or MATISSE.\n* 'TIME\\_RANGE' is one of 1d, 1w, 1m, 6m.\n* 'CONTENT' can be meta, traces, traces-SUBSYSTEMS, or traces-TELESCOPES.\n\n\nExample files:\n\n\n* URL\n* URL\n\n\nThe \"meta\" file includes information about the template execution, while \"traces\" files contain event logs.\n\n\nThe exisiting files are shown in the table below:\n\n\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\nGRAVITY: URL, PIONIER: URL, MATISSE: URL\n\n\nCombining Files\n---------------\n\n\nFiles from same instrument and within the same time range belong to the same trace\\_id. For instance, in the files:\n\n\n* URL\n* URL\n\n\nThe trace\\_id=10 in URL file corresponds to the id=10 in the meta file URL.\n\n\nData Instances\n--------------\n\n\nA typical entry in the dataset might look like this:\n\n\nData Fields\n-----------\n\n\nThe dataset contains structured logs from software operations related to astronomical instruments. Each entry in the log provides detailed information regarding specific actions or events recorded by the system. Below is the description of each field in the log entries:\n\n\n\nDataset Metadata\n----------------\n\n\nEach Parket file contains metadata regarding its contents, which includes details about the instrument used, time range, and types of logs stored. This is the format of a sample template execution in the metadata:\n\n\nWhere the fields are:\n\n\n\nThis structured format ensures a comprehensive understanding of each template's execution, providing insights into the operational dynamics of astronomical observations at Paranal.\n\n\nLoading Data\n------------\n\n\nThe dataset can be loaded using Python libraries like Pandas. Here's an example of how to load a Parket file:"
] | [
18,
157,
1075
] | [
"passage: TAGS\n#language-English #license-lgpl-2.1 #region-us \n### Observations at Paranal\n\n\nAt Paranal, the Very Large Telescope (VLT) is one of the world's most advanced optical telescopes, consisting of four Unit Telescopes and four movable Auxiliary Telescopes. Astronomical observations are configured into Observation Blocks (OBs), containing a sequence of Templates with parameters and scripts tailored to various scientific goals. Each template's execution follows a predictable behavior, allowing for detailed and systematic studies. The templates remain unchanged during a scientific period of six months, therefore the templates referred in parlogs-observations datasets can be considered as immutable source code."
] |
5682d3ce61471359f77a0165edaa881659277deb |
# Dataset Card for Evaluation run of Ba2han/BruinsV2-OpHermesNeu-11B
<!-- Provide a quick summary of the dataset. -->
Dataset automatically created during the evaluation run of model [Ba2han/BruinsV2-OpHermesNeu-11B](https://huggingface.co/Ba2han/BruinsV2-OpHermesNeu-11B) on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
The dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An additional configuration "results" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).
To load the details from a run, you can for instance do the following:
```python
from datasets import load_dataset
data = load_dataset("open-llm-leaderboard/details_Ba2han__BruinsV2-OpHermesNeu-11B",
"harness_winogrande_5",
split="train")
```
## Latest results
These are the [latest results from run 2023-12-16T12:38:08.853335](https://huggingface.co/datasets/open-llm-leaderboard/details_Ba2han__BruinsV2-OpHermesNeu-11B/blob/main/results_2023-12-16T12-38-08.853335.json)(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the "latest" split for each eval):
```python
{
"all": {
"acc": 0.6442797430736888,
"acc_stderr": 0.032189382292323196,
"acc_norm": 0.646076779376777,
"acc_norm_stderr": 0.0328357234803993,
"mc1": 0.46266829865361075,
"mc1_stderr": 0.017454645150970588,
"mc2": 0.6276115895198878,
"mc2_stderr": 0.015378567971079934
},
"harness|arc:challenge|25": {
"acc": 0.6552901023890785,
"acc_stderr": 0.01388881628678211,
"acc_norm": 0.6808873720136519,
"acc_norm_stderr": 0.01362169611917331
},
"harness|hellaswag|10": {
"acc": 0.659928301135232,
"acc_stderr": 0.0047276480578979235,
"acc_norm": 0.847042421828321,
"acc_norm_stderr": 0.003592109743628618
},
"harness|hendrycksTest-abstract_algebra|5": {
"acc": 0.33,
"acc_stderr": 0.04725815626252606,
"acc_norm": 0.33,
"acc_norm_stderr": 0.04725815626252606
},
"harness|hendrycksTest-anatomy|5": {
"acc": 0.6518518518518519,
"acc_stderr": 0.04115324610336953,
"acc_norm": 0.6518518518518519,
"acc_norm_stderr": 0.04115324610336953
},
"harness|hendrycksTest-astronomy|5": {
"acc": 0.6578947368421053,
"acc_stderr": 0.03860731599316092,
"acc_norm": 0.6578947368421053,
"acc_norm_stderr": 0.03860731599316092
},
"harness|hendrycksTest-business_ethics|5": {
"acc": 0.64,
"acc_stderr": 0.04824181513244218,
"acc_norm": 0.64,
"acc_norm_stderr": 0.04824181513244218
},
"harness|hendrycksTest-clinical_knowledge|5": {
"acc": 0.7094339622641509,
"acc_stderr": 0.027943219989337135,
"acc_norm": 0.7094339622641509,
"acc_norm_stderr": 0.027943219989337135
},
"harness|hendrycksTest-college_biology|5": {
"acc": 0.7708333333333334,
"acc_stderr": 0.03514697467862388,
"acc_norm": 0.7708333333333334,
"acc_norm_stderr": 0.03514697467862388
},
"harness|hendrycksTest-college_chemistry|5": {
"acc": 0.46,
"acc_stderr": 0.05009082659620333,
"acc_norm": 0.46,
"acc_norm_stderr": 0.05009082659620333
},
"harness|hendrycksTest-college_computer_science|5": {
"acc": 0.54,
"acc_stderr": 0.05009082659620333,
"acc_norm": 0.54,
"acc_norm_stderr": 0.05009082659620333
},
"harness|hendrycksTest-college_mathematics|5": {
"acc": 0.29,
"acc_stderr": 0.04560480215720684,
"acc_norm": 0.29,
"acc_norm_stderr": 0.04560480215720684
},
"harness|hendrycksTest-college_medicine|5": {
"acc": 0.653179190751445,
"acc_stderr": 0.036291466701596636,
"acc_norm": 0.653179190751445,
"acc_norm_stderr": 0.036291466701596636
},
"harness|hendrycksTest-college_physics|5": {
"acc": 0.46078431372549017,
"acc_stderr": 0.04959859966384181,
"acc_norm": 0.46078431372549017,
"acc_norm_stderr": 0.04959859966384181
},
"harness|hendrycksTest-computer_security|5": {
"acc": 0.73,
"acc_stderr": 0.044619604333847394,
"acc_norm": 0.73,
"acc_norm_stderr": 0.044619604333847394
},
"harness|hendrycksTest-conceptual_physics|5": {
"acc": 0.548936170212766,
"acc_stderr": 0.032529096196131965,
"acc_norm": 0.548936170212766,
"acc_norm_stderr": 0.032529096196131965
},
"harness|hendrycksTest-econometrics|5": {
"acc": 0.4824561403508772,
"acc_stderr": 0.04700708033551038,
"acc_norm": 0.4824561403508772,
"acc_norm_stderr": 0.04700708033551038
},
"harness|hendrycksTest-electrical_engineering|5": {
"acc": 0.5724137931034483,
"acc_stderr": 0.04122737111370332,
"acc_norm": 0.5724137931034483,
"acc_norm_stderr": 0.04122737111370332
},
"harness|hendrycksTest-elementary_mathematics|5": {
"acc": 0.42328042328042326,
"acc_stderr": 0.025446365634406796,
"acc_norm": 0.42328042328042326,
"acc_norm_stderr": 0.025446365634406796
},
"harness|hendrycksTest-formal_logic|5": {
"acc": 0.42063492063492064,
"acc_stderr": 0.04415438226743744,
"acc_norm": 0.42063492063492064,
"acc_norm_stderr": 0.04415438226743744
},
"harness|hendrycksTest-global_facts|5": {
"acc": 0.35,
"acc_stderr": 0.047937248544110196,
"acc_norm": 0.35,
"acc_norm_stderr": 0.047937248544110196
},
"harness|hendrycksTest-high_school_biology|5": {
"acc": 0.7741935483870968,
"acc_stderr": 0.023785577884181012,
"acc_norm": 0.7741935483870968,
"acc_norm_stderr": 0.023785577884181012
},
"harness|hendrycksTest-high_school_chemistry|5": {
"acc": 0.47783251231527096,
"acc_stderr": 0.03514528562175008,
"acc_norm": 0.47783251231527096,
"acc_norm_stderr": 0.03514528562175008
},
"harness|hendrycksTest-high_school_computer_science|5": {
"acc": 0.75,
"acc_stderr": 0.04351941398892446,
"acc_norm": 0.75,
"acc_norm_stderr": 0.04351941398892446
},
"harness|hendrycksTest-high_school_european_history|5": {
"acc": 0.793939393939394,
"acc_stderr": 0.0315841532404771,
"acc_norm": 0.793939393939394,
"acc_norm_stderr": 0.0315841532404771
},
"harness|hendrycksTest-high_school_geography|5": {
"acc": 0.7676767676767676,
"acc_stderr": 0.030088629490217487,
"acc_norm": 0.7676767676767676,
"acc_norm_stderr": 0.030088629490217487
},
"harness|hendrycksTest-high_school_government_and_politics|5": {
"acc": 0.9067357512953368,
"acc_stderr": 0.020986854593289733,
"acc_norm": 0.9067357512953368,
"acc_norm_stderr": 0.020986854593289733
},
"harness|hendrycksTest-high_school_macroeconomics|5": {
"acc": 0.6743589743589744,
"acc_stderr": 0.02375966576741229,
"acc_norm": 0.6743589743589744,
"acc_norm_stderr": 0.02375966576741229
},
"harness|hendrycksTest-high_school_mathematics|5": {
"acc": 0.36666666666666664,
"acc_stderr": 0.029381620726465066,
"acc_norm": 0.36666666666666664,
"acc_norm_stderr": 0.029381620726465066
},
"harness|hendrycksTest-high_school_microeconomics|5": {
"acc": 0.6890756302521008,
"acc_stderr": 0.03006676158297793,
"acc_norm": 0.6890756302521008,
"acc_norm_stderr": 0.03006676158297793
},
"harness|hendrycksTest-high_school_physics|5": {
"acc": 0.33112582781456956,
"acc_stderr": 0.038425817186598696,
"acc_norm": 0.33112582781456956,
"acc_norm_stderr": 0.038425817186598696
},
"harness|hendrycksTest-high_school_psychology|5": {
"acc": 0.8495412844036697,
"acc_stderr": 0.015328563932669237,
"acc_norm": 0.8495412844036697,
"acc_norm_stderr": 0.015328563932669237
},
"harness|hendrycksTest-high_school_statistics|5": {
"acc": 0.5416666666666666,
"acc_stderr": 0.03398110890294636,
"acc_norm": 0.5416666666666666,
"acc_norm_stderr": 0.03398110890294636
},
"harness|hendrycksTest-high_school_us_history|5": {
"acc": 0.7745098039215687,
"acc_stderr": 0.029331162294251735,
"acc_norm": 0.7745098039215687,
"acc_norm_stderr": 0.029331162294251735
},
"harness|hendrycksTest-high_school_world_history|5": {
"acc": 0.8016877637130801,
"acc_stderr": 0.025955020841621115,
"acc_norm": 0.8016877637130801,
"acc_norm_stderr": 0.025955020841621115
},
"harness|hendrycksTest-human_aging|5": {
"acc": 0.6681614349775785,
"acc_stderr": 0.031602951437766785,
"acc_norm": 0.6681614349775785,
"acc_norm_stderr": 0.031602951437766785
},
"harness|hendrycksTest-human_sexuality|5": {
"acc": 0.7786259541984732,
"acc_stderr": 0.03641297081313729,
"acc_norm": 0.7786259541984732,
"acc_norm_stderr": 0.03641297081313729
},
"harness|hendrycksTest-international_law|5": {
"acc": 0.8016528925619835,
"acc_stderr": 0.03640118271990945,
"acc_norm": 0.8016528925619835,
"acc_norm_stderr": 0.03640118271990945
},
"harness|hendrycksTest-jurisprudence|5": {
"acc": 0.7407407407407407,
"acc_stderr": 0.042365112580946315,
"acc_norm": 0.7407407407407407,
"acc_norm_stderr": 0.042365112580946315
},
"harness|hendrycksTest-logical_fallacies|5": {
"acc": 0.7423312883435583,
"acc_stderr": 0.03436150827846917,
"acc_norm": 0.7423312883435583,
"acc_norm_stderr": 0.03436150827846917
},
"harness|hendrycksTest-machine_learning|5": {
"acc": 0.44642857142857145,
"acc_stderr": 0.04718471485219588,
"acc_norm": 0.44642857142857145,
"acc_norm_stderr": 0.04718471485219588
},
"harness|hendrycksTest-management|5": {
"acc": 0.8058252427184466,
"acc_stderr": 0.03916667762822584,
"acc_norm": 0.8058252427184466,
"acc_norm_stderr": 0.03916667762822584
},
"harness|hendrycksTest-marketing|5": {
"acc": 0.8846153846153846,
"acc_stderr": 0.020930193185179333,
"acc_norm": 0.8846153846153846,
"acc_norm_stderr": 0.020930193185179333
},
"harness|hendrycksTest-medical_genetics|5": {
"acc": 0.75,
"acc_stderr": 0.04351941398892446,
"acc_norm": 0.75,
"acc_norm_stderr": 0.04351941398892446
},
"harness|hendrycksTest-miscellaneous|5": {
"acc": 0.8160919540229885,
"acc_stderr": 0.01385372417092253,
"acc_norm": 0.8160919540229885,
"acc_norm_stderr": 0.01385372417092253
},
"harness|hendrycksTest-moral_disputes|5": {
"acc": 0.7138728323699421,
"acc_stderr": 0.024332146779134128,
"acc_norm": 0.7138728323699421,
"acc_norm_stderr": 0.024332146779134128
},
"harness|hendrycksTest-moral_scenarios|5": {
"acc": 0.3843575418994413,
"acc_stderr": 0.0162690886639594,
"acc_norm": 0.3843575418994413,
"acc_norm_stderr": 0.0162690886639594
},
"harness|hendrycksTest-nutrition|5": {
"acc": 0.7352941176470589,
"acc_stderr": 0.025261691219729474,
"acc_norm": 0.7352941176470589,
"acc_norm_stderr": 0.025261691219729474
},
"harness|hendrycksTest-philosophy|5": {
"acc": 0.6913183279742765,
"acc_stderr": 0.02623696588115327,
"acc_norm": 0.6913183279742765,
"acc_norm_stderr": 0.02623696588115327
},
"harness|hendrycksTest-prehistory|5": {
"acc": 0.7314814814814815,
"acc_stderr": 0.024659685185967284,
"acc_norm": 0.7314814814814815,
"acc_norm_stderr": 0.024659685185967284
},
"harness|hendrycksTest-professional_accounting|5": {
"acc": 0.4787234042553192,
"acc_stderr": 0.029800481645628693,
"acc_norm": 0.4787234042553192,
"acc_norm_stderr": 0.029800481645628693
},
"harness|hendrycksTest-professional_law|5": {
"acc": 0.4471968709256845,
"acc_stderr": 0.012698825252435108,
"acc_norm": 0.4471968709256845,
"acc_norm_stderr": 0.012698825252435108
},
"harness|hendrycksTest-professional_medicine|5": {
"acc": 0.6875,
"acc_stderr": 0.02815637344037142,
"acc_norm": 0.6875,
"acc_norm_stderr": 0.02815637344037142
},
"harness|hendrycksTest-professional_psychology|5": {
"acc": 0.6552287581699346,
"acc_stderr": 0.01922832201869664,
"acc_norm": 0.6552287581699346,
"acc_norm_stderr": 0.01922832201869664
},
"harness|hendrycksTest-public_relations|5": {
"acc": 0.6636363636363637,
"acc_stderr": 0.04525393596302506,
"acc_norm": 0.6636363636363637,
"acc_norm_stderr": 0.04525393596302506
},
"harness|hendrycksTest-security_studies|5": {
"acc": 0.710204081632653,
"acc_stderr": 0.02904308868330433,
"acc_norm": 0.710204081632653,
"acc_norm_stderr": 0.02904308868330433
},
"harness|hendrycksTest-sociology|5": {
"acc": 0.8557213930348259,
"acc_stderr": 0.024845753212306046,
"acc_norm": 0.8557213930348259,
"acc_norm_stderr": 0.024845753212306046
},
"harness|hendrycksTest-us_foreign_policy|5": {
"acc": 0.85,
"acc_stderr": 0.0358870281282637,
"acc_norm": 0.85,
"acc_norm_stderr": 0.0358870281282637
},
"harness|hendrycksTest-virology|5": {
"acc": 0.5421686746987951,
"acc_stderr": 0.038786267710023595,
"acc_norm": 0.5421686746987951,
"acc_norm_stderr": 0.038786267710023595
},
"harness|hendrycksTest-world_religions|5": {
"acc": 0.8187134502923976,
"acc_stderr": 0.02954774168764004,
"acc_norm": 0.8187134502923976,
"acc_norm_stderr": 0.02954774168764004
},
"harness|truthfulqa:mc|0": {
"mc1": 0.46266829865361075,
"mc1_stderr": 0.017454645150970588,
"mc2": 0.6276115895198878,
"mc2_stderr": 0.015378567971079934
},
"harness|winogrande|5": {
"acc": 0.7947908445146015,
"acc_stderr": 0.011350315707462057
},
"harness|gsm8k|5": {
"acc": 0.6004548900682335,
"acc_stderr": 0.01349166029881599
}
}
```
## Dataset Details
### Dataset Description
<!-- Provide a longer summary of what this dataset is. -->
- **Curated by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
### Dataset Sources [optional]
<!-- Provide the basic links for the dataset. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the dataset is intended to be used. -->
### Direct Use
<!-- This section describes suitable use cases for the dataset. -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the dataset will not work well for. -->
[More Information Needed]
## Dataset Structure
<!-- This section provides a description of the dataset fields, and additional information about the dataset structure such as criteria used to create the splits, relationships between data points, etc. -->
[More Information Needed]
## Dataset Creation
### Curation Rationale
<!-- Motivation for the creation of this dataset. -->
[More Information Needed]
### Source Data
<!-- This section describes the source data (e.g. news text and headlines, social media posts, translated sentences, ...). -->
#### Data Collection and Processing
<!-- This section describes the data collection and processing process such as data selection criteria, filtering and normalization methods, tools and libraries used, etc. -->
[More Information Needed]
#### Who are the source data producers?
<!-- This section describes the people or systems who originally created the data. It should also include self-reported demographic or identity information for the source data creators if this information is available. -->
[More Information Needed]
### Annotations [optional]
<!-- If the dataset contains annotations which are not part of the initial data collection, use this section to describe them. -->
#### Annotation process
<!-- This section describes the annotation process such as annotation tools used in the process, the amount of data annotated, annotation guidelines provided to the annotators, interannotator statistics, annotation validation, etc. -->
[More Information Needed]
#### Who are the annotators?
<!-- This section describes the people or systems who created the annotations. -->
[More Information Needed]
#### Personal and Sensitive Information
<!-- State whether the dataset contains data that might be considered personal, sensitive, or private (e.g., data that reveals addresses, uniquely identifiable names or aliases, racial or ethnic origins, sexual orientations, religious beliefs, political opinions, financial or health data, etc.). If efforts were made to anonymize the data, describe the anonymization process. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.
## Citation [optional]
<!-- If there is a paper or blog post introducing the dataset, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the dataset or dataset card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Dataset Card Authors [optional]
[More Information Needed]
## Dataset Card Contact
[More Information Needed] | open-llm-leaderboard/details_Ba2han__BruinsV2-OpHermesNeu-11B | [
"region:us"
] | 2023-12-16T12:41:03+00:00 | {"pretty_name": "Evaluation run of Ba2han/BruinsV2-OpHermesNeu-11B", "dataset_summary": "Dataset automatically created during the evaluation run of model [Ba2han/BruinsV2-OpHermesNeu-11B](https://huggingface.co/Ba2han/BruinsV2-OpHermesNeu-11B) on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).\n\nTo load the details from a run, you can for instance do the following:\n```python\nfrom datasets import load_dataset\ndata = load_dataset(\"open-llm-leaderboard/details_Ba2han__BruinsV2-OpHermesNeu-11B\",\n\t\"harness_winogrande_5\",\n\tsplit=\"train\")\n```\n\n## Latest results\n\nThese are the [latest results from run 2023-12-16T12:38:08.853335](https://huggingface.co/datasets/open-llm-leaderboard/details_Ba2han__BruinsV2-OpHermesNeu-11B/blob/main/results_2023-12-16T12-38-08.853335.json)(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):\n\n```python\n{\n \"all\": {\n \"acc\": 0.6442797430736888,\n \"acc_stderr\": 0.032189382292323196,\n \"acc_norm\": 0.646076779376777,\n \"acc_norm_stderr\": 0.0328357234803993,\n \"mc1\": 0.46266829865361075,\n \"mc1_stderr\": 0.017454645150970588,\n \"mc2\": 0.6276115895198878,\n \"mc2_stderr\": 0.015378567971079934\n },\n \"harness|arc:challenge|25\": {\n \"acc\": 0.6552901023890785,\n \"acc_stderr\": 0.01388881628678211,\n \"acc_norm\": 0.6808873720136519,\n \"acc_norm_stderr\": 0.01362169611917331\n },\n \"harness|hellaswag|10\": {\n \"acc\": 0.659928301135232,\n \"acc_stderr\": 0.0047276480578979235,\n \"acc_norm\": 0.847042421828321,\n \"acc_norm_stderr\": 0.003592109743628618\n },\n \"harness|hendrycksTest-abstract_algebra|5\": {\n \"acc\": 0.33,\n \"acc_stderr\": 0.04725815626252606,\n \"acc_norm\": 0.33,\n \"acc_norm_stderr\": 0.04725815626252606\n },\n \"harness|hendrycksTest-anatomy|5\": {\n \"acc\": 0.6518518518518519,\n \"acc_stderr\": 0.04115324610336953,\n \"acc_norm\": 0.6518518518518519,\n \"acc_norm_stderr\": 0.04115324610336953\n },\n \"harness|hendrycksTest-astronomy|5\": {\n \"acc\": 0.6578947368421053,\n \"acc_stderr\": 0.03860731599316092,\n \"acc_norm\": 0.6578947368421053,\n \"acc_norm_stderr\": 0.03860731599316092\n },\n \"harness|hendrycksTest-business_ethics|5\": {\n \"acc\": 0.64,\n \"acc_stderr\": 0.04824181513244218,\n \"acc_norm\": 0.64,\n \"acc_norm_stderr\": 0.04824181513244218\n },\n \"harness|hendrycksTest-clinical_knowledge|5\": {\n \"acc\": 0.7094339622641509,\n \"acc_stderr\": 0.027943219989337135,\n \"acc_norm\": 0.7094339622641509,\n \"acc_norm_stderr\": 0.027943219989337135\n },\n \"harness|hendrycksTest-college_biology|5\": {\n \"acc\": 0.7708333333333334,\n \"acc_stderr\": 0.03514697467862388,\n \"acc_norm\": 0.7708333333333334,\n \"acc_norm_stderr\": 0.03514697467862388\n },\n \"harness|hendrycksTest-college_chemistry|5\": {\n \"acc\": 0.46,\n \"acc_stderr\": 0.05009082659620333,\n \"acc_norm\": 0.46,\n \"acc_norm_stderr\": 0.05009082659620333\n },\n \"harness|hendrycksTest-college_computer_science|5\": {\n \"acc\": 0.54,\n \"acc_stderr\": 0.05009082659620333,\n \"acc_norm\": 0.54,\n \"acc_norm_stderr\": 0.05009082659620333\n },\n \"harness|hendrycksTest-college_mathematics|5\": {\n \"acc\": 0.29,\n \"acc_stderr\": 0.04560480215720684,\n \"acc_norm\": 0.29,\n \"acc_norm_stderr\": 0.04560480215720684\n },\n \"harness|hendrycksTest-college_medicine|5\": {\n \"acc\": 0.653179190751445,\n \"acc_stderr\": 0.036291466701596636,\n \"acc_norm\": 0.653179190751445,\n \"acc_norm_stderr\": 0.036291466701596636\n },\n \"harness|hendrycksTest-college_physics|5\": {\n \"acc\": 0.46078431372549017,\n \"acc_stderr\": 0.04959859966384181,\n \"acc_norm\": 0.46078431372549017,\n \"acc_norm_stderr\": 0.04959859966384181\n },\n \"harness|hendrycksTest-computer_security|5\": {\n \"acc\": 0.73,\n \"acc_stderr\": 0.044619604333847394,\n \"acc_norm\": 0.73,\n \"acc_norm_stderr\": 0.044619604333847394\n },\n \"harness|hendrycksTest-conceptual_physics|5\": {\n \"acc\": 0.548936170212766,\n \"acc_stderr\": 0.032529096196131965,\n \"acc_norm\": 0.548936170212766,\n \"acc_norm_stderr\": 0.032529096196131965\n },\n \"harness|hendrycksTest-econometrics|5\": {\n \"acc\": 0.4824561403508772,\n \"acc_stderr\": 0.04700708033551038,\n \"acc_norm\": 0.4824561403508772,\n \"acc_norm_stderr\": 0.04700708033551038\n },\n \"harness|hendrycksTest-electrical_engineering|5\": {\n \"acc\": 0.5724137931034483,\n \"acc_stderr\": 0.04122737111370332,\n \"acc_norm\": 0.5724137931034483,\n \"acc_norm_stderr\": 0.04122737111370332\n },\n \"harness|hendrycksTest-elementary_mathematics|5\": {\n \"acc\": 0.42328042328042326,\n \"acc_stderr\": 0.025446365634406796,\n \"acc_norm\": 0.42328042328042326,\n \"acc_norm_stderr\": 0.025446365634406796\n },\n \"harness|hendrycksTest-formal_logic|5\": {\n \"acc\": 0.42063492063492064,\n \"acc_stderr\": 0.04415438226743744,\n \"acc_norm\": 0.42063492063492064,\n \"acc_norm_stderr\": 0.04415438226743744\n },\n \"harness|hendrycksTest-global_facts|5\": {\n \"acc\": 0.35,\n \"acc_stderr\": 0.047937248544110196,\n \"acc_norm\": 0.35,\n \"acc_norm_stderr\": 0.047937248544110196\n },\n \"harness|hendrycksTest-high_school_biology|5\": {\n \"acc\": 0.7741935483870968,\n \"acc_stderr\": 0.023785577884181012,\n \"acc_norm\": 0.7741935483870968,\n \"acc_norm_stderr\": 0.023785577884181012\n },\n \"harness|hendrycksTest-high_school_chemistry|5\": {\n \"acc\": 0.47783251231527096,\n \"acc_stderr\": 0.03514528562175008,\n \"acc_norm\": 0.47783251231527096,\n \"acc_norm_stderr\": 0.03514528562175008\n },\n \"harness|hendrycksTest-high_school_computer_science|5\": {\n \"acc\": 0.75,\n \"acc_stderr\": 0.04351941398892446,\n \"acc_norm\": 0.75,\n \"acc_norm_stderr\": 0.04351941398892446\n },\n \"harness|hendrycksTest-high_school_european_history|5\": {\n \"acc\": 0.793939393939394,\n \"acc_stderr\": 0.0315841532404771,\n \"acc_norm\": 0.793939393939394,\n \"acc_norm_stderr\": 0.0315841532404771\n },\n \"harness|hendrycksTest-high_school_geography|5\": {\n \"acc\": 0.7676767676767676,\n \"acc_stderr\": 0.030088629490217487,\n \"acc_norm\": 0.7676767676767676,\n \"acc_norm_stderr\": 0.030088629490217487\n },\n \"harness|hendrycksTest-high_school_government_and_politics|5\": {\n \"acc\": 0.9067357512953368,\n \"acc_stderr\": 0.020986854593289733,\n \"acc_norm\": 0.9067357512953368,\n \"acc_norm_stderr\": 0.020986854593289733\n },\n \"harness|hendrycksTest-high_school_macroeconomics|5\": {\n \"acc\": 0.6743589743589744,\n \"acc_stderr\": 0.02375966576741229,\n \"acc_norm\": 0.6743589743589744,\n \"acc_norm_stderr\": 0.02375966576741229\n },\n \"harness|hendrycksTest-high_school_mathematics|5\": {\n \"acc\": 0.36666666666666664,\n \"acc_stderr\": 0.029381620726465066,\n \"acc_norm\": 0.36666666666666664,\n \"acc_norm_stderr\": 0.029381620726465066\n },\n \"harness|hendrycksTest-high_school_microeconomics|5\": {\n \"acc\": 0.6890756302521008,\n \"acc_stderr\": 0.03006676158297793,\n \"acc_norm\": 0.6890756302521008,\n \"acc_norm_stderr\": 0.03006676158297793\n },\n \"harness|hendrycksTest-high_school_physics|5\": {\n \"acc\": 0.33112582781456956,\n \"acc_stderr\": 0.038425817186598696,\n \"acc_norm\": 0.33112582781456956,\n \"acc_norm_stderr\": 0.038425817186598696\n },\n \"harness|hendrycksTest-high_school_psychology|5\": {\n \"acc\": 0.8495412844036697,\n \"acc_stderr\": 0.015328563932669237,\n \"acc_norm\": 0.8495412844036697,\n \"acc_norm_stderr\": 0.015328563932669237\n },\n \"harness|hendrycksTest-high_school_statistics|5\": {\n \"acc\": 0.5416666666666666,\n \"acc_stderr\": 0.03398110890294636,\n \"acc_norm\": 0.5416666666666666,\n \"acc_norm_stderr\": 0.03398110890294636\n },\n \"harness|hendrycksTest-high_school_us_history|5\": {\n \"acc\": 0.7745098039215687,\n \"acc_stderr\": 0.029331162294251735,\n \"acc_norm\": 0.7745098039215687,\n \"acc_norm_stderr\": 0.029331162294251735\n },\n \"harness|hendrycksTest-high_school_world_history|5\": {\n \"acc\": 0.8016877637130801,\n \"acc_stderr\": 0.025955020841621115,\n \"acc_norm\": 0.8016877637130801,\n \"acc_norm_stderr\": 0.025955020841621115\n },\n \"harness|hendrycksTest-human_aging|5\": {\n \"acc\": 0.6681614349775785,\n \"acc_stderr\": 0.031602951437766785,\n \"acc_norm\": 0.6681614349775785,\n \"acc_norm_stderr\": 0.031602951437766785\n },\n \"harness|hendrycksTest-human_sexuality|5\": {\n \"acc\": 0.7786259541984732,\n \"acc_stderr\": 0.03641297081313729,\n \"acc_norm\": 0.7786259541984732,\n \"acc_norm_stderr\": 0.03641297081313729\n },\n \"harness|hendrycksTest-international_law|5\": {\n \"acc\": 0.8016528925619835,\n \"acc_stderr\": 0.03640118271990945,\n \"acc_norm\": 0.8016528925619835,\n \"acc_norm_stderr\": 0.03640118271990945\n },\n \"harness|hendrycksTest-jurisprudence|5\": {\n \"acc\": 0.7407407407407407,\n \"acc_stderr\": 0.042365112580946315,\n \"acc_norm\": 0.7407407407407407,\n \"acc_norm_stderr\": 0.042365112580946315\n },\n \"harness|hendrycksTest-logical_fallacies|5\": {\n \"acc\": 0.7423312883435583,\n \"acc_stderr\": 0.03436150827846917,\n \"acc_norm\": 0.7423312883435583,\n \"acc_norm_stderr\": 0.03436150827846917\n },\n \"harness|hendrycksTest-machine_learning|5\": {\n \"acc\": 0.44642857142857145,\n \"acc_stderr\": 0.04718471485219588,\n \"acc_norm\": 0.44642857142857145,\n \"acc_norm_stderr\": 0.04718471485219588\n },\n \"harness|hendrycksTest-management|5\": {\n \"acc\": 0.8058252427184466,\n \"acc_stderr\": 0.03916667762822584,\n \"acc_norm\": 0.8058252427184466,\n \"acc_norm_stderr\": 0.03916667762822584\n },\n \"harness|hendrycksTest-marketing|5\": {\n \"acc\": 0.8846153846153846,\n \"acc_stderr\": 0.020930193185179333,\n \"acc_norm\": 0.8846153846153846,\n \"acc_norm_stderr\": 0.020930193185179333\n },\n \"harness|hendrycksTest-medical_genetics|5\": {\n \"acc\": 0.75,\n \"acc_stderr\": 0.04351941398892446,\n \"acc_norm\": 0.75,\n \"acc_norm_stderr\": 0.04351941398892446\n },\n \"harness|hendrycksTest-miscellaneous|5\": {\n \"acc\": 0.8160919540229885,\n \"acc_stderr\": 0.01385372417092253,\n \"acc_norm\": 0.8160919540229885,\n \"acc_norm_stderr\": 0.01385372417092253\n },\n \"harness|hendrycksTest-moral_disputes|5\": {\n \"acc\": 0.7138728323699421,\n \"acc_stderr\": 0.024332146779134128,\n \"acc_norm\": 0.7138728323699421,\n \"acc_norm_stderr\": 0.024332146779134128\n },\n \"harness|hendrycksTest-moral_scenarios|5\": {\n \"acc\": 0.3843575418994413,\n \"acc_stderr\": 0.0162690886639594,\n \"acc_norm\": 0.3843575418994413,\n \"acc_norm_stderr\": 0.0162690886639594\n },\n \"harness|hendrycksTest-nutrition|5\": {\n \"acc\": 0.7352941176470589,\n \"acc_stderr\": 0.025261691219729474,\n \"acc_norm\": 0.7352941176470589,\n \"acc_norm_stderr\": 0.025261691219729474\n },\n \"harness|hendrycksTest-philosophy|5\": {\n \"acc\": 0.6913183279742765,\n \"acc_stderr\": 0.02623696588115327,\n \"acc_norm\": 0.6913183279742765,\n \"acc_norm_stderr\": 0.02623696588115327\n },\n \"harness|hendrycksTest-prehistory|5\": {\n \"acc\": 0.7314814814814815,\n \"acc_stderr\": 0.024659685185967284,\n \"acc_norm\": 0.7314814814814815,\n \"acc_norm_stderr\": 0.024659685185967284\n },\n \"harness|hendrycksTest-professional_accounting|5\": {\n \"acc\": 0.4787234042553192,\n \"acc_stderr\": 0.029800481645628693,\n \"acc_norm\": 0.4787234042553192,\n \"acc_norm_stderr\": 0.029800481645628693\n },\n \"harness|hendrycksTest-professional_law|5\": {\n \"acc\": 0.4471968709256845,\n \"acc_stderr\": 0.012698825252435108,\n \"acc_norm\": 0.4471968709256845,\n \"acc_norm_stderr\": 0.012698825252435108\n },\n \"harness|hendrycksTest-professional_medicine|5\": {\n \"acc\": 0.6875,\n \"acc_stderr\": 0.02815637344037142,\n \"acc_norm\": 0.6875,\n \"acc_norm_stderr\": 0.02815637344037142\n },\n \"harness|hendrycksTest-professional_psychology|5\": {\n \"acc\": 0.6552287581699346,\n \"acc_stderr\": 0.01922832201869664,\n \"acc_norm\": 0.6552287581699346,\n \"acc_norm_stderr\": 0.01922832201869664\n },\n \"harness|hendrycksTest-public_relations|5\": {\n \"acc\": 0.6636363636363637,\n \"acc_stderr\": 0.04525393596302506,\n \"acc_norm\": 0.6636363636363637,\n \"acc_norm_stderr\": 0.04525393596302506\n },\n \"harness|hendrycksTest-security_studies|5\": {\n \"acc\": 0.710204081632653,\n \"acc_stderr\": 0.02904308868330433,\n \"acc_norm\": 0.710204081632653,\n \"acc_norm_stderr\": 0.02904308868330433\n },\n \"harness|hendrycksTest-sociology|5\": {\n \"acc\": 0.8557213930348259,\n \"acc_stderr\": 0.024845753212306046,\n \"acc_norm\": 0.8557213930348259,\n \"acc_norm_stderr\": 0.024845753212306046\n },\n \"harness|hendrycksTest-us_foreign_policy|5\": {\n \"acc\": 0.85,\n \"acc_stderr\": 0.0358870281282637,\n \"acc_norm\": 0.85,\n \"acc_norm_stderr\": 0.0358870281282637\n },\n \"harness|hendrycksTest-virology|5\": {\n \"acc\": 0.5421686746987951,\n \"acc_stderr\": 0.038786267710023595,\n \"acc_norm\": 0.5421686746987951,\n \"acc_norm_stderr\": 0.038786267710023595\n },\n \"harness|hendrycksTest-world_religions|5\": {\n \"acc\": 0.8187134502923976,\n \"acc_stderr\": 0.02954774168764004,\n \"acc_norm\": 0.8187134502923976,\n \"acc_norm_stderr\": 0.02954774168764004\n },\n \"harness|truthfulqa:mc|0\": {\n \"mc1\": 0.46266829865361075,\n \"mc1_stderr\": 0.017454645150970588,\n \"mc2\": 0.6276115895198878,\n \"mc2_stderr\": 0.015378567971079934\n },\n \"harness|winogrande|5\": {\n \"acc\": 0.7947908445146015,\n \"acc_stderr\": 0.011350315707462057\n },\n \"harness|gsm8k|5\": {\n \"acc\": 0.6004548900682335,\n \"acc_stderr\": 0.01349166029881599\n }\n}\n```", "repo_url": "https://huggingface.co/Ba2han/BruinsV2-OpHermesNeu-11B", "leaderboard_url": "https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard", "point_of_contact": "[email protected]", "configs": [{"config_name": "harness_arc_challenge_25", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|arc:challenge|25_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|arc:challenge|25_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_gsm8k_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|gsm8k|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|gsm8k|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hellaswag_10", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hellaswag|10_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hellaswag|10_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-abstract_algebra|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-anatomy|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-astronomy|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-business_ethics|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-clinical_knowledge|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-college_biology|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-college_chemistry|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-college_computer_science|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-college_mathematics|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-college_medicine|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-college_physics|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-computer_security|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-conceptual_physics|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-econometrics|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-electrical_engineering|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-elementary_mathematics|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-formal_logic|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-global_facts|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_biology|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_chemistry|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_computer_science|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_european_history|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_geography|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_mathematics|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_physics|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_psychology|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_statistics|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_us_history|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_world_history|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-human_aging|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-human_sexuality|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-international_law|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-jurisprudence|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-logical_fallacies|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-machine_learning|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-management|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-marketing|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-medical_genetics|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-miscellaneous|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-moral_disputes|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-moral_scenarios|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-nutrition|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-philosophy|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-prehistory|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-professional_accounting|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-professional_law|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-professional_medicine|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-professional_psychology|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-public_relations|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-security_studies|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-sociology|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-us_foreign_policy|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-virology|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-world_religions|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-abstract_algebra|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-anatomy|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-astronomy|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-business_ethics|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-clinical_knowledge|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-college_biology|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-college_chemistry|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-college_computer_science|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-college_mathematics|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-college_medicine|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-college_physics|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-computer_security|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-conceptual_physics|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-econometrics|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-electrical_engineering|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-elementary_mathematics|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-formal_logic|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-global_facts|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_biology|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_chemistry|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_computer_science|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_european_history|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_geography|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_mathematics|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_physics|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_psychology|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_statistics|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_us_history|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-high_school_world_history|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-human_aging|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-human_sexuality|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-international_law|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-jurisprudence|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-logical_fallacies|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-machine_learning|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-management|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-marketing|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-medical_genetics|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-miscellaneous|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-moral_disputes|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-moral_scenarios|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-nutrition|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-philosophy|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-prehistory|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-professional_accounting|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-professional_law|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-professional_medicine|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-professional_psychology|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-public_relations|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-security_studies|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-sociology|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-us_foreign_policy|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-virology|5_2023-12-16T12-38-08.853335.parquet", "**/details_harness|hendrycksTest-world_religions|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_abstract_algebra_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-abstract_algebra|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-abstract_algebra|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_anatomy_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-anatomy|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-anatomy|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_astronomy_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-astronomy|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-astronomy|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_business_ethics_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-business_ethics|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-business_ethics|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_clinical_knowledge_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-clinical_knowledge|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-clinical_knowledge|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_biology_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-college_biology|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_biology|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_chemistry_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-college_chemistry|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_chemistry|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_computer_science_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-college_computer_science|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_computer_science|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_mathematics_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-college_mathematics|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_mathematics|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_medicine_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-college_medicine|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_medicine|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_college_physics_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-college_physics|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-college_physics|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_computer_security_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-computer_security|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-computer_security|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_conceptual_physics_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-conceptual_physics|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-conceptual_physics|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_econometrics_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-econometrics|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-econometrics|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_electrical_engineering_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-electrical_engineering|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-electrical_engineering|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_elementary_mathematics_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-elementary_mathematics|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-elementary_mathematics|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_formal_logic_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-formal_logic|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-formal_logic|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_global_facts_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-global_facts|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-global_facts|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_biology_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-high_school_biology|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_biology|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_chemistry_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-high_school_chemistry|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_chemistry|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_computer_science_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-high_school_computer_science|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_computer_science|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_european_history_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-high_school_european_history|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_european_history|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_geography_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-high_school_geography|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_geography|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_government_and_politics_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_macroeconomics_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_mathematics_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-high_school_mathematics|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_mathematics|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_microeconomics_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_physics_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-high_school_physics|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_physics|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_psychology_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-high_school_psychology|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_psychology|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_statistics_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-high_school_statistics|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_statistics|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_us_history_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-high_school_us_history|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_us_history|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_high_school_world_history_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-high_school_world_history|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-high_school_world_history|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_human_aging_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-human_aging|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-human_aging|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_human_sexuality_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-human_sexuality|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-human_sexuality|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_international_law_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-international_law|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-international_law|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_jurisprudence_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-jurisprudence|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-jurisprudence|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_logical_fallacies_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-logical_fallacies|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-logical_fallacies|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_machine_learning_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-machine_learning|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-machine_learning|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_management_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-management|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-management|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_marketing_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-marketing|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-marketing|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_medical_genetics_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-medical_genetics|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-medical_genetics|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_miscellaneous_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-miscellaneous|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-miscellaneous|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_moral_disputes_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-moral_disputes|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-moral_disputes|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_moral_scenarios_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-moral_scenarios|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-moral_scenarios|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_nutrition_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-nutrition|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-nutrition|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_philosophy_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-philosophy|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-philosophy|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_prehistory_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-prehistory|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-prehistory|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_professional_accounting_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-professional_accounting|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-professional_accounting|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_professional_law_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-professional_law|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-professional_law|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_professional_medicine_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-professional_medicine|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-professional_medicine|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_professional_psychology_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-professional_psychology|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-professional_psychology|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_public_relations_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-public_relations|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-public_relations|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_security_studies_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-security_studies|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-security_studies|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_sociology_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-sociology|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-sociology|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_us_foreign_policy_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-us_foreign_policy|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-us_foreign_policy|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_virology_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-virology|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-virology|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_hendrycksTest_world_religions_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|hendrycksTest-world_religions|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|hendrycksTest-world_religions|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_truthfulqa_mc_0", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|truthfulqa:mc|0_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|truthfulqa:mc|0_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "harness_winogrande_5", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["**/details_harness|winogrande|5_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["**/details_harness|winogrande|5_2023-12-16T12-38-08.853335.parquet"]}]}, {"config_name": "results", "data_files": [{"split": "2023_12_16T12_38_08.853335", "path": ["results_2023-12-16T12-38-08.853335.parquet"]}, {"split": "latest", "path": ["results_2023-12-16T12-38-08.853335.parquet"]}]}]} | 2023-12-16T12:41:44+00:00 | [] | [] | TAGS
#region-us
|
# Dataset Card for Evaluation run of Ba2han/BruinsV2-OpHermesNeu-11B
Dataset automatically created during the evaluation run of model Ba2han/BruinsV2-OpHermesNeu-11B on the Open LLM Leaderboard.
The dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An additional configuration "results" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).
To load the details from a run, you can for instance do the following:
## Latest results
These are the latest results from run 2023-12-16T12:38:08.853335(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the "latest" split for each eval):
## Dataset Details
### Dataset Description
- Curated by:
- Funded by [optional]:
- Shared by [optional]:
- Language(s) (NLP):
- License:
### Dataset Sources [optional]
- Repository:
- Paper [optional]:
- Demo [optional]:
## Uses
### Direct Use
### Out-of-Scope Use
## Dataset Structure
## Dataset Creation
### Curation Rationale
### Source Data
#### Data Collection and Processing
#### Who are the source data producers?
### Annotations [optional]
#### Annotation process
#### Who are the annotators?
#### Personal and Sensitive Information
## Bias, Risks, and Limitations
### Recommendations
Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.
[optional]
BibTeX:
APA:
## Glossary [optional]
## More Information [optional]
## Dataset Card Authors [optional]
## Dataset Card Contact
| [
"# Dataset Card for Evaluation run of Ba2han/BruinsV2-OpHermesNeu-11B\n\n\n\nDataset automatically created during the evaluation run of model Ba2han/BruinsV2-OpHermesNeu-11B on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:",
"## Latest results\n\nThese are the latest results from run 2023-12-16T12:38:08.853335(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):",
"## Dataset Details",
"### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:",
"### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Out-of-Scope Use",
"## Dataset Structure",
"## Dataset Creation",
"### Curation Rationale",
"### Source Data",
"#### Data Collection and Processing",
"#### Who are the source data producers?",
"### Annotations [optional]",
"#### Annotation process",
"#### Who are the annotators?",
"#### Personal and Sensitive Information",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Dataset Card Authors [optional]",
"## Dataset Card Contact"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for Evaluation run of Ba2han/BruinsV2-OpHermesNeu-11B\n\n\n\nDataset automatically created during the evaluation run of model Ba2han/BruinsV2-OpHermesNeu-11B on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:",
"## Latest results\n\nThese are the latest results from run 2023-12-16T12:38:08.853335(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):",
"## Dataset Details",
"### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:",
"### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:",
"## Uses",
"### Direct Use",
"### Out-of-Scope Use",
"## Dataset Structure",
"## Dataset Creation",
"### Curation Rationale",
"### Source Data",
"#### Data Collection and Processing",
"#### Who are the source data producers?",
"### Annotations [optional]",
"#### Annotation process",
"#### Who are the annotators?",
"#### Personal and Sensitive Information",
"## Bias, Risks, and Limitations",
"### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:",
"## Glossary [optional]",
"## More Information [optional]",
"## Dataset Card Authors [optional]",
"## Dataset Card Contact"
] | [
6,
191,
67,
4,
40,
29,
3,
4,
9,
6,
5,
7,
4,
7,
10,
9,
5,
9,
8,
10,
46,
8,
7,
10,
5
] | [
"passage: TAGS\n#region-us \n# Dataset Card for Evaluation run of Ba2han/BruinsV2-OpHermesNeu-11B\n\n\n\nDataset automatically created during the evaluation run of model Ba2han/BruinsV2-OpHermesNeu-11B on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:## Latest results\n\nThese are the latest results from run 2023-12-16T12:38:08.853335(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):## Dataset Details### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:## Uses### Direct Use### Out-of-Scope Use## Dataset Structure## Dataset Creation### Curation Rationale### Source Data#### Data Collection and Processing#### Who are the source data producers?### Annotations [optional]#### Annotation process#### Who are the annotators?#### Personal and Sensitive Information## Bias, Risks, and Limitations### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:## Glossary [optional]## More Information [optional]## Dataset Card Authors [optional]"
] |
8dffe0781e049f6f66b1c0197ce382bdbeecc030 | # Dataset Card for "wikipedia_questions_big"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | bjoernp/wikipedia_questions_big | [
"region:us"
] | 2023-12-16T12:45:43+00:00 | {"dataset_info": {"features": [{"name": "id", "dtype": "string"}, {"name": "url", "dtype": "string"}, {"name": "title", "dtype": "string"}, {"name": "text", "dtype": "string"}, {"name": "prompt", "dtype": "string"}, {"name": "questions", "dtype": "string"}], "splits": [{"name": "train", "num_bytes": 6335284445, "num_examples": 836468}], "download_size": 441171260, "dataset_size": 6335284445}, "configs": [{"config_name": "default", "data_files": [{"split": "train", "path": "data/train-*"}]}]} | 2023-12-16T12:46:24+00:00 | [] | [] | TAGS
#region-us
| # Dataset Card for "wikipedia_questions_big"
More Information needed | [
"# Dataset Card for \"wikipedia_questions_big\"\n\nMore Information needed"
] | [
"TAGS\n#region-us \n",
"# Dataset Card for \"wikipedia_questions_big\"\n\nMore Information needed"
] | [
6,
16
] | [
"passage: TAGS\n#region-us \n# Dataset Card for \"wikipedia_questions_big\"\n\nMore Information needed"
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.