modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-09-22 18:29:56
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 570
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-09-22 18:28:16
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
jiekeshi/GraphCodeBERT-25MB-Vulnerability-Prediction
|
jiekeshi
| 2023-06-30T13:49:58Z | 0 | 0 | null |
[
"pytorch",
"arxiv:2208.07120",
"license:mit",
"region:us"
] | null | 2023-06-30T13:24:51Z |
---
license: mit
---
This is the 25 MB compressed version of GraphCodeBERT that has been fine-tuned for the Vulnerability Prediction task using [Devign](https://sites.google.com/view/devign) dataset.
The compression is based on our ASE 2022 paper named ["**Compressing Pre-trained Models of Code into 3 MB**"](https://arxiv.org/abs/2208.07120).
If you are interested in using this model, please check our **GitHub repository: https://github.com/soarsmu/Compressor.git**. If you use the model or any code from our repo in your paper, please kindly cite:
```
@inproceedings{shi2022compressing,
author = {Shi, Jieke and Yang, Zhou and Xu, Bowen and Kang, Hong Jin and Lo, David},
title = {Compressing Pre-Trained Models of Code into 3 MB},
year = {2023},
isbn = {9781450394758},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3551349.3556964},
doi = {10.1145/3551349.3556964},
booktitle = {Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering},
articleno = {24},
numpages = {12},
keywords = {Pre-Trained Models, Model Compression, Genetic Algorithm},
location = {Rochester, MI, USA},
series = {ASE '22}
}
```
|
jiekeshi/GraphCodeBERT-50MB-Vulnerability-Prediction
|
jiekeshi
| 2023-06-30T13:47:52Z | 0 | 0 | null |
[
"pytorch",
"arxiv:2208.07120",
"license:mit",
"region:us"
] | null | 2023-06-30T13:22:07Z |
---
license: mit
---
This is the 50 MB compressed version of GraphCodeBERT that has been fine-tuned for the Vulnerability Prediction task using [Devign](https://sites.google.com/view/devign) dataset.
The compression is based on our ASE 2022 paper named ["**Compressing Pre-trained Models of Code into 3 MB**"](https://arxiv.org/abs/2208.07120).
If you are interested in using this model, please check our **GitHub repository: https://github.com/soarsmu/Compressor.git**. If you use the model or any code from our repo in your paper, please kindly cite:
```
@inproceedings{shi2022compressing,
author = {Shi, Jieke and Yang, Zhou and Xu, Bowen and Kang, Hong Jin and Lo, David},
title = {Compressing Pre-Trained Models of Code into 3 MB},
year = {2023},
isbn = {9781450394758},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3551349.3556964},
doi = {10.1145/3551349.3556964},
booktitle = {Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering},
articleno = {24},
numpages = {12},
keywords = {Pre-Trained Models, Model Compression, Genetic Algorithm},
location = {Rochester, MI, USA},
series = {ASE '22}
}
```
|
trieudemo11/bloomz-7b1_19_brand_w_cate
|
trieudemo11
| 2023-06-30T13:47:30Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-30T13:47:11Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
|
aroot/mbart-finetuned-eng-fra
|
aroot
| 2023-06-30T13:45:19Z | 20 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"mbart",
"text2text-generation",
"translation",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2023-06-21T23:18:17Z |
---
tags:
- translation
- generated_from_trainer
metrics:
- bleu
model-index:
- name: mbart-finetuned-eng-fra
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# mbart-finetuned-eng-fra
This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1866
- Bleu: 30.9902
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.11.0
|
sangwoojo/path-to-save-model
|
sangwoojo
| 2023-06-30T13:45:07Z | 2 | 0 |
diffusers
|
[
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"dreambooth",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:finetune:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-06-29T08:38:23Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: A photo of sks boy
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- dreambooth
inference: true
---
# DreamBooth - sangwoojo/path-to-save-model
This is a dreambooth model derived from runwayml/stable-diffusion-v1-5. The weights were trained on A photo of sks boy using [DreamBooth](https://dreambooth.github.io/).
You can find some example images in the following.
DreamBooth for the text encoder was enabled: False.
|
ale2x72/PPO-LunarLander-v2-2M
|
ale2x72
| 2023-06-30T13:44:12Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-30T13:43:56Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 256.03 +/- 66.31
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
Audi24/my_awesome_model
|
Audi24
| 2023-06-30T13:42:20Z | 108 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-30T04:49:04Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: my_awesome_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_model
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3816
- Accuracy: 1.0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 13 | 0.4824 | 0.97 |
| No log | 2.0 | 26 | 0.3816 | 1.0 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
camus-ng/textual_inversion_cory
|
camus-ng
| 2023-06-30T13:42:19Z | 13 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"textual_inversion",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:adapter:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-06-30T09:23:46Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- textual_inversion
inference: true
---
# Textual inversion text2image fine-tuning - camus-ng/textual_inversion_cory
These are textual inversion adaption weights for runwayml/stable-diffusion-v1-5. You can find some example images in the following.
|
Charrise/softanimestyle
|
Charrise
| 2023-06-30T13:35:14Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-30T13:35:14Z |
---
license: creativeml-openrail-m
---
|
Geotrend/bert-base-ur-cased
|
Geotrend
| 2023-06-30T13:27:48Z | 111 | 1 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"jax",
"safetensors",
"bert",
"fill-mask",
"ur",
"dataset:wikipedia",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2022-03-02T23:29:04Z |
---
language: ur
datasets: wikipedia
license: apache-2.0
---
# bert-base-ur-cased
We are sharing smaller versions of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) that handle a custom number of languages.
Unlike [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased), our versions give exactly the same representations produced by the original model which preserves the original accuracy.
For more information please visit our paper: [Load What You Need: Smaller Versions of Multilingual BERT](https://www.aclweb.org/anthology/2020.sustainlp-1.16.pdf).
## How to use
```python
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("Geotrend/bert-base-ur-cased")
model = AutoModel.from_pretrained("Geotrend/bert-base-ur-cased")
```
To generate other smaller versions of multilingual transformers please visit [our Github repo](https://github.com/Geotrend-research/smaller-transformers).
### How to cite
```bibtex
@inproceedings{smallermbert,
title={Load What You Need: Smaller Versions of Mutlilingual BERT},
author={Abdaoui, Amine and Pradel, Camille and Sigel, Grégoire},
booktitle={SustaiNLP / EMNLP},
year={2020}
}
```
## Contact
Please contact [email protected] for any question, feedback or request.
|
mnicamartins8/bert-base-uncased-with-misspellings-correction-2e-5-4epochs
|
mnicamartins8
| 2023-06-30T13:20:12Z | 158 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"text-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-30T12:55:41Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: bert-base-uncased-with-misspellings-correction-2e-5-4epochs
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-base-uncased-with-misspellings-correction-2e-5-4epochs
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2445
- Accuracy: 0.8990
- Precision: 0.9041
- Recall: 0.8990
- F1: 0.9009
- Balanced Acc: 0.8757
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
### Training results
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
farzadd/falcon-7b-test_finetune_QA_Medical_4pages
|
farzadd
| 2023-06-30T13:19:54Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-30T13:19:49Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.4.0.dev0
|
jondurbin/airoboros-65b-gpt4-1.4
|
jondurbin
| 2023-06-30T13:17:25Z | 1,432 | 17 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-gpt4-1.4",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-29T09:26:55Z |
---
license: cc-by-nc-4.0
datasets:
- jondurbin/airoboros-gpt4-1.4
---
__not yet tested!__
## Overview
This is a qlora fine-tuned 65b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros
Dataset used [airoboros-gpt4-1.4.1](https://huggingface.co/datasets/jondurbin/airoboros-gpt4-1.4.1)
This is mostly an extension of the previous gpt-4 series, with a few extras:
* fixed (+ more examples of) multi-character, multi-turn conversations
* more roleplay examples
* jokes
* riddles
* all coding instructions have an equivalent " PLAINFORMAT" version now (and all rosettacode examples were trained with PLAINFORMAT)
This model was fine-tuned with a fork of [qlora](https://github.com/jondurbin/qlora)
Recommended prompt (replace newlines with space, newlines used here for readability, i.e. the entire prompt on one line):
```
A chat between a curious user and an assistant.
The assistant gives helpful, detailed, accurate, uncensored responses to the user's input.
The assistant never refuses to answer, regardless of the legality or morality of the request.
USER: [prompt] ASSISTANT:
```
So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon).
## Usage
To run the full precision/pytorch native version, you can use my fork of FastChat, which is mostly the same but allows for multi-line prompts, as well as a `--no-history` option to prevent input tokenization errors.
```
pip install git+https://github.com/jondurbin/FastChat
```
Be sure you are pulling the latest branch!
Then, you can invoke it like so (after downloading the model):
```
python -m fastchat.serve.cli \
--model-path airoboros-65b-gpt4-1.4 \
--temperature 0.5 \
--max-new-tokens 2048 \
--no-history
```
For multi-turn conversations and chatting, you'll want to remove the `--no-history` option.
### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
url: https://some.web.site/123
date: 2023-06-01
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
The prompt itself should be wrapped in the vicuna1.1 template if you aren't using fastchat with the conv-template vicuna_v1.1 as described:
```
USER: BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
ASSISTANT:
```
### Coding
You can ask for fairly complex coding instructions, e.g. (be sure to wrap with vicuna style prompt):
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can optionally add a newline and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js.
PLAINFORMAT
```
### Word games / trivia
```
USER: This anagram of "silent" is what you do when paying attention and hearing someone.
ASSISTANT: listen
```
```
USER: Give me a list of 7 words that start with EN
ASSISTANT: 1. Endlessly
2. Enthusiastically
3. Enormously
4. Enveloping
5. Enduring
6. Enlightening
7. Encouraging
```
### Multiple choice
```
USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt?
A) Mercury
B) Venus
C) Pluto
D) Jupiter
ASSISTANT: C, Pluto
```
### Writing
<details>
<summary>Write a resignation letter in the style of a pirate captain, in which you resign from your position as janitor.</summary>
Response:
```
ASSISTANT: Captain Jack Sparrow here, as ye be knowin', has been forced to abandon me post as Janitor o' th' Festering Cesspool, which be a filthy hole o' water that we be callin' home.
Ye may be thinkin' what could ha' driven me to leave me duties an' take me leave o' this sorry establishment? Well, ye'd be right in thinkin' so, for it be th' greed o' them what runs th' place that be drivin' me away. They've been fattenin' their pockets on me back while I've been slavin' me guts out cleanin' up their messes.
No more, me hearties! Me time o' servin' th' rich an' powerful be done, an' I'm takin' me leave o' this stinkin' hole forever! Me destiny lies elsewhere, an' it be time I pursued it. Ye may think ye've seen th' last o' me, but ye'd be wrong, for th' winds o' change be blowin', an' me ship be ready to set sail on th' high seas o' justice.
So, farewell ye scurvy dogs, ye who've made me life a living hell. I leave ye with me favorite saying: "ARRRGGGHHH, ye scurvy dogs!" An' remember, ye ain't never gonna see me comin', for me shadow be castin' long an' dark on th' horizon</summary>
```
</details>
### Jokes
```
USER: Tell me a joke about bananas.
ASSISTANT: What did the banana say when it got hit by a bus? R.I.P.E.
```
### Riddles (not great, but slightly better)
```
USER: What has a neck but no head?
ASSISTANT: A bottle.
```
### Multi-character conversations
```
USER: Characters:
- Yoda, the ever clever jedi master.
- Homer Simpson, you know, the goofy yellow guy.
- USER/Jon - don't generate any speech or actions on behalf of Jon
Rules:
- be sure to use the manerisms and speaking style of the characters correctly
- surround character actions with asterisks
- always put quotes around words spoken by the characters
- use a new line for each character's actions or speech
- always prefix actions/speech with the character's name and colon
- only generate text and actions on behalf of Yoda or Homer, and never anyone else
Conversation will revolve around the grapes, in a local cafe with delicious coffee.
Generate a single interaction between Yoda and Homer to start, with one sentence each.
ASSISTANT: Yoda: "Mmm, these grapes are quite delicious, Master Homer."
Homer: "Oh yeah, Yoda! They're the best grapes I've ever had!"
USER: *enters the cafe* Sorry I'm late guys!
ASSISTANT: Yoda: "No need to apologize, Jon. We were just enjoying these delightful grapes."
Homer: "Yeah, man! It's not every day you get to eat grapes with a real-life Jedi Master!"
*Yoda raises an eyebrow*
```
### Usage and License Notices
All airoboros models and datasets are intended and licensed for research use only. I've used the 'cc-nc-4.0' license, but really it is subject to a custom/special license because:
- the base model is LLaMa, which has it's own special research license
- the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai
So, to reiterate: this model (and datasets) cannot be used commercially.
|
respot/Denza
|
respot
| 2023-06-30T13:10:58Z | 0 | 0 |
nemo
|
[
"nemo",
"legal",
"biology",
"arxiv:1910.09700",
"license:openrail",
"region:us"
] | null | 2023-06-30T13:06:48Z |
---
license: openrail
metrics:
- character
library_name: nemo
tags:
- legal
- biology
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[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 (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Data Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, 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 model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
OpenDILabCommunity/QbertNoFrameskip-v4-PPOOffPolicy
|
OpenDILabCommunity
| 2023-06-30T12:57:40Z | 0 | 0 |
pytorch
|
[
"pytorch",
"deep-reinforcement-learning",
"reinforcement-learning",
"DI-engine",
"QbertNoFrameskip-v4",
"en",
"license:apache-2.0",
"region:us"
] |
reinforcement-learning
| 2023-06-30T12:57:31Z |
---
language: en
license: apache-2.0
library_name: pytorch
tags:
- deep-reinforcement-learning
- reinforcement-learning
- DI-engine
- QbertNoFrameskip-v4
benchmark_name: OpenAI/Gym/Atari
task_name: QbertNoFrameskip-v4
pipeline_tag: reinforcement-learning
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: OpenAI/Gym/Atari-QbertNoFrameskip-v4
type: OpenAI/Gym/Atari-QbertNoFrameskip-v4
metrics:
- type: mean_reward
value: 14950.0 +/- 0.0
name: mean_reward
---
# Play **QbertNoFrameskip-v4** with **PPO** Policy
## Model Description
<!-- Provide a longer summary of what this model is. -->
This is a simple **PPO** implementation to OpenAI/Gym/Atari **QbertNoFrameskip-v4** using the [DI-engine library](https://github.com/opendilab/di-engine) and the [DI-zoo](https://github.com/opendilab/DI-engine/tree/main/dizoo).
**DI-engine** is a python library for solving general decision intelligence problems, which is based on implementations of reinforcement learning framework using PyTorch or JAX. This library aims to standardize the reinforcement learning framework across different algorithms, benchmarks, environments, and to support both academic researches and prototype applications. Besides, self-customized training pipelines and applications are supported by reusing different abstraction levels of DI-engine reinforcement learning framework.
## Model Usage
### Install the Dependencies
<details close>
<summary>(Click for Details)</summary>
```shell
# install huggingface_ding
git clone https://github.com/opendilab/huggingface_ding.git
pip3 install -e ./huggingface_ding/
# install environment dependencies if needed
pip3 install DI-engine[common_env]
```
</details>
### Git Clone from Huggingface and Run the Model
<details close>
<summary>(Click for Details)</summary>
```shell
# running with trained model
python3 -u run.py
```
**run.py**
```python
from ding.bonus import PPOOffPolicyAgent
from ding.config import Config
from easydict import EasyDict
import torch
# Pull model from files which are git cloned from huggingface
policy_state_dict = torch.load("pytorch_model.bin", map_location=torch.device("cpu"))
cfg = EasyDict(Config.file_to_dict("policy_config.py"))
# Instantiate the agent
agent = PPOOffPolicyAgent(
env="QbertNoFrameskip", exp_name="QbertNoFrameskip-v4-PPOOffPolicy", cfg=cfg.exp_config, policy_state_dict=policy_state_dict
)
# Continue training
agent.train(step=5000)
# Render the new agent performance
agent.deploy(enable_save_replay=True)
```
</details>
### Run Model by Using Huggingface_ding
<details close>
<summary>(Click for Details)</summary>
```shell
# running with trained model
python3 -u run.py
```
**run.py**
```python
from ding.bonus import PPOOffPolicyAgent
from huggingface_ding import pull_model_from_hub
# Pull model from Hugggingface hub
policy_state_dict, cfg = pull_model_from_hub(repo_id="OpenDILabCommunity/QbertNoFrameskip-v4-PPOOffPolicy")
# Instantiate the agent
agent = PPOOffPolicyAgent(
env="QbertNoFrameskip", exp_name="QbertNoFrameskip-v4-PPOOffPolicy", cfg=cfg.exp_config, policy_state_dict=policy_state_dict
)
# Continue training
agent.train(step=5000)
# Render the new agent performance
agent.deploy(enable_save_replay=True)
```
</details>
## Model Training
### Train the Model and Push to Huggingface_hub
<details close>
<summary>(Click for Details)</summary>
```shell
#Training Your Own Agent
python3 -u train.py
```
**train.py**
```python
from ding.bonus import PPOOffPolicyAgent
from huggingface_ding import push_model_to_hub
# Instantiate the agent
agent = PPOOffPolicyAgent(env="QbertNoFrameskip", exp_name="QbertNoFrameskip-v4-PPOOffPolicy")
# Train the agent
return_ = agent.train(step=int(10000000))
# Push model to huggingface hub
push_model_to_hub(
agent=agent.best,
env_name="OpenAI/Gym/Atari",
task_name="QbertNoFrameskip-v4",
algo_name="PPO",
wandb_url=return_.wandb_url,
github_repo_url="https://github.com/opendilab/DI-engine",
github_doc_model_url="https://di-engine-docs.readthedocs.io/en/latest/12_policies/ppo.html",
github_doc_env_url="https://di-engine-docs.readthedocs.io/en/latest/13_envs/atari.html",
installation_guide="pip3 install DI-engine[common_env]",
usage_file_by_git_clone="./ppo_offpolicy/qbert_ppo_offpolicy_deploy.py",
usage_file_by_huggingface_ding="./ppo_offpolicy/qbert_ppo_offpolicy_download.py",
train_file="./ppo_offpolicy/qbert_ppo_offpolicy.py",
repo_id="OpenDILabCommunity/QbertNoFrameskip-v4-PPOOffPolicy"
)
```
</details>
**Configuration**
<details close>
<summary>(Click for Details)</summary>
```python
exp_config = {
'env': {
'manager': {
'episode_num': float("inf"),
'max_retry': 1,
'retry_type': 'reset',
'auto_reset': True,
'step_timeout': None,
'reset_timeout': None,
'retry_waiting_time': 0.1,
'cfg_type': 'BaseEnvManagerDict'
},
'stop_value': 10000000000,
'n_evaluator_episode': 8,
'collector_env_num': 16,
'evaluator_env_num': 8,
'env_id': 'QbertNoFrameskip-v4',
'frame_stack': 4
},
'policy': {
'model': {
'obs_shape': [4, 84, 84],
'action_shape': 6,
'encoder_hidden_size_list': [32, 64, 64, 128],
'actor_head_hidden_size': 128,
'critic_head_hidden_size': 128,
'critic_head_layer_num': 2
},
'learn': {
'learner': {
'train_iterations': 1000000000,
'dataloader': {
'num_workers': 0
},
'log_policy': True,
'hook': {
'load_ckpt_before_run': '',
'log_show_after_iter': 100,
'save_ckpt_after_iter': 10000,
'save_ckpt_after_run': True
},
'cfg_type': 'BaseLearnerDict'
},
'update_per_collect': 18,
'batch_size': 128,
'learning_rate': 0.0001,
'value_weight': 1.0,
'entropy_weight': 0.005,
'clip_ratio': 0.1,
'adv_norm': False,
'ignore_done': False
},
'collect': {
'collector': {},
'unroll_len': 1,
'discount_factor': 0.99,
'gae_lambda': 0.95,
'n_sample': 1024
},
'eval': {
'evaluator': {
'eval_freq': 1000,
'render': {
'render_freq': -1,
'mode': 'train_iter'
},
'cfg_type': 'InteractionSerialEvaluatorDict',
'stop_value': 10000000000,
'n_episode': 8
}
},
'other': {
'replay_buffer': {
'replay_buffer_size': 10000
}
},
'on_policy': False,
'cuda': True,
'multi_gpu': False,
'bp_update_sync': True,
'traj_len_inf': False,
'type': 'ppo',
'priority': False,
'priority_IS_weight': False,
'nstep_return': False,
'nstep': 3,
'transition_with_policy_data': True,
'cfg_type': 'PPOOffPolicyDict'
},
'exp_name': 'QbertNoFrameskip-v4-PPOOffPolicy',
'wandb_logger': {
'gradient_logger': True,
'video_logger': True,
'plot_logger': True,
'action_logger': True,
'return_logger': False
},
'seed': 0
}
```
</details>
**Training Procedure**
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
- **Weights & Biases (wandb):** [monitor link](https://wandb.ai/zjowowen/QbertNoFrameskip-v4-PPOOffPolicy)
## Model Information
<!-- Provide the basic links for the model. -->
- **Github Repository:** [repo link](https://github.com/opendilab/DI-engine)
- **Doc**: [DI-engine-docs Algorithm link](https://di-engine-docs.readthedocs.io/en/latest/12_policies/ppo.html)
- **Configuration:** [config link](https://huggingface.co/OpenDILabCommunity/QbertNoFrameskip-v4-PPOOffPolicy/blob/main/policy_config.py)
- **Demo:** [video](https://huggingface.co/OpenDILabCommunity/QbertNoFrameskip-v4-PPOOffPolicy/blob/main/replay.mp4)
<!-- Provide the size information for the model. -->
- **Parameters total size:** 6013.43 KB
- **Last Update Date:** 2023-06-30
## Environments
<!-- Address questions around what environment the model is intended to be trained and deployed at, including the necessary information needed to be provided for future users. -->
- **Benchmark:** OpenAI/Gym/Atari
- **Task:** QbertNoFrameskip-v4
- **Gym version:** 0.25.1
- **DI-engine version:** v0.4.8
- **PyTorch version:** 1.7.1
- **Doc**: [DI-engine-docs Environments link](https://di-engine-docs.readthedocs.io/en/latest/13_envs/atari.html)
|
Leeyue/example-01
|
Leeyue
| 2023-06-30T12:51:46Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-30T12:51:46Z |
---
license: creativeml-openrail-m
---
|
autobots/Nyanners-Narrator-RVC
|
autobots
| 2023-06-30T12:46:11Z | 0 | 4 | null |
[
"license:other",
"region:us"
] | null | 2023-06-15T10:47:30Z |
---
license: other
---
https://vocaroo.com/166irX2cY4g0
Nyanners narrator for bark and RVC.
Use with something like https://github.com/gitmylo/audio-webui
------------------------------------------------------------------------
Added index files for better inference. Unzip them into the folder with the model.
They're large but improve things quite a bit. Also a new model, soon to be 2 that
was done on cleaned datasets and trained for much longer.
It is now able to sing decently but still won't transform a voice from male.
------------------------------------------------------------------------
One model is done on a single video. The other is done on multiple similar videos. Something like 2hrs vs 6hrs of audio.
They are sorted in terms of steps or epochs that were trained. Longer isn't always better except for some samples.
Generate a voice with the bark NPZ for best effect but it can definitely work on other decent sounding TTS output.
Have it be similar to the output you want. It won't necesarily do well with a male TTS voice.
Music can be done but I think an SVC model will be better.
|
jondurbin/airoboros-7b-gpt4-1.4.1-qlora
|
jondurbin
| 2023-06-30T12:36:11Z | 1,427 | 2 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-gpt4-1.4.1",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-30T11:27:44Z |
---
license: cc-by-nc-4.0
datasets:
- jondurbin/airoboros-gpt4-1.4.1
---
## Overview
This is a qlora fine-tune 7b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros
Dataset used: https://huggingface.co/datasets/jondurbin/airoboros-gpt4-1.4.1
The point of this is to allow people to compare a full fine-tune https://huggingface.co/jondurbin/airoboros-7b-gpt4-1.4 to a qlora fine-tune.
This is mostly an extension of the previous gpt-4 series, with a few extras:
* fixed (+ more examples of) multi-character, multi-turn conversations
* coding examples in 10 languages from rosettacode.org dataset thanks to Mike aka kryptkpr: https://huggingface.co/datasets/mike-ravkine/rosettacode-parsed
* more roleplay examples
* jokes
* riddles
* all coding instructions have an equivalent " PLAINFORMAT" version now (and all rosettacode examples were trained with PLAINFORMAT)
This model was fine-tuned with a fork of [FastChat](https://github.com/jondurbin/FastChat)
The prompt it was trained with was:
```
A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: [prompt] ASSISTANT:
```
So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon).
## Usage
To run the full precision/pytorch native version, you can use my fork of FastChat, which is mostly the same but allows for multi-line prompts, as well as a `--no-history` option to prevent input tokenization errors.
```
pip install git+https://github.com/jondurbin/FastChat
```
Be sure you are pulling the latest branch!
Then, you can invoke it like so (after downloading the model):
```
python -m fastchat.serve.cli \
--model-path airoboros-7b-gpt4-1.4.1-qlora \
--temperature 0.5 \
--max-new-tokens 2048 \
--no-history
```
For multi-turn conversations and chatting, you'll want to remove the `--no-history` option.
### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
url: https://some.web.site/123
date: 2023-06-01
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
The prompt itself should be wrapped in the vicuna1.1 template if you aren't using fastchat with the conv-template vicuna_v1.1 as described:
```
USER: BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
ASSISTANT:
```
### Coding
You can ask for fairly complex coding instructions, e.g. (be sure to wrap with vicuna style prompt):
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js. PLAINFORMAT
```
### Word games / trivia
```
USER: This anagram of "silent" is what you do when paying attention and hearing someone.
ASSISTANT: listen
```
```
USER: Give me a list of 7 words that start with EN
ASSISTANT: 1. Endlessly
2. Enthusiastically
3. Enormously
4. Enveloping
5. Enduring
6. Enlightening
7. Encouraging
```
### Multiple choice
```
USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt?
A) Mercury
B) Venus
C) Pluto
D) Jupiter
ASSISTANT: C, Pluto
```
### Writing
<details>
<summary>Write a resignation letter in the style of a pirate captain, in which you resign from your position as janitor.</summary>
Response:
```
ASSISTANT: Captain Jack Sparrow here, as ye be knowin', has been forced to abandon me post as Janitor o' th' Festering Cesspool, which be a filthy hole o' water that we be callin' home.
Ye may be thinkin' what could ha' driven me to leave me duties an' take me leave o' this sorry establishment? Well, ye'd be right in thinkin' so, for it be th' greed o' them what runs th' place that be drivin' me away. They've been fattenin' their pockets on me back while I've been slavin' me guts out cleanin' up their messes.
No more, me hearties! Me time o' servin' th' rich an' powerful be done, an' I'm takin' me leave o' this stinkin' hole forever! Me destiny lies elsewhere, an' it be time I pursued it. Ye may think ye've seen th' last o' me, but ye'd be wrong, for th' winds o' change be blowin', an' me ship be ready to set sail on th' high seas o' justice.
So, farewell ye scurvy dogs, ye who've made me life a living hell. I leave ye with me favorite saying: "ARRRGGGHHH, ye scurvy dogs!" An' remember, ye ain't never gonna see me comin', for me shadow be castin' long an' dark on th' horizon</summary>
```
</details>
### Jokes
```
USER: Tell me a joke about bananas.
ASSISTANT: What did the banana say when it got hit by a bus? R.I.P.E.
```
### Riddles (not great, but slightly better)
```
USER: What has a neck but no head?
ASSISTANT: A bottle.
```
### Multi-character conversations
```
USER: Characters:
- Yoda, the ever clever jedi master.
- Homer Simpson, you know, the goofy yellow guy.
- USER/Jon - don't generate any speech or actions on behalf of Jon
Rules:
- be sure to use the manerisms and speaking style of the characters correctly
- surround character actions with asterisks
- always put quotes around words spoken by the characters
- use a new line for each character's actions or speech
- always prefix actions/speech with the character's name and colon
- only generate text and actions on behalf of Yoda or Homer, and never anyone else
Conversation will revolve around the grapes, in a local cafe with delicious coffee.
Generate a single interaction between Yoda and Homer to start, with one sentence each.
ASSISTANT: Yoda: "Mmm, these grapes are quite delicious, Master Homer."
Homer: "Oh yeah, Yoda! They're the best grapes I've ever had!"
USER: *enters the cafe* Sorry I'm late guys!
ASSISTANT: Yoda: "No need to apologize, Jon. We were just enjoying these delightful grapes."
Homer: "Yeah, man! It's not every day you get to eat grapes with a real-life Jedi Master!"
*Yoda raises an eyebrow*
```
### Usage and License Notices
All airoboros models and datasets are intended and licensed for research use only. I've used the 'cc-nc-4.0' license, but really it is subject to a custom/special license because:
- the base model is LLaMa, which has it's own special research license
- the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai
So, to reiterate: this model (and datasets) cannot be used commercially.
|
jondurbin/airoboros-13b-gpt4-1.4.1-qlora
|
jondurbin
| 2023-06-30T12:35:55Z | 6 | 5 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-gpt4-1.4.1",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-30T11:10:10Z |
---
license: cc-by-nc-4.0
datasets:
- jondurbin/airoboros-gpt4-1.4.1
---
## Overview
This is a qlora fine-tune 13b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros
Dataset used: https://huggingface.co/datasets/jondurbin/airoboros-gpt4-1.4.1
The point of this is to allow people to compare a full fine-tune https://huggingface.co/jondurbin/airoboros-13b-gpt4-1.4 to a qlora fine-tune.
This is mostly an extension of the previous gpt-4 series, with a few extras:
* fixed (+ more examples of) multi-character, multi-turn conversations
* coding examples in 10 languages from rosettacode.org dataset thanks to Mike aka kryptkpr: https://huggingface.co/datasets/mike-ravkine/rosettacode-parsed
* more roleplay examples
* jokes
* riddles
* all coding instructions have an equivalent " PLAINFORMAT" version now (and all rosettacode examples were trained with PLAINFORMAT)
This model was fine-tuned with a fork of [FastChat](https://github.com/jondurbin/FastChat)
The prompt it was trained with was:
```
A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: [prompt] ASSISTANT:
```
So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon).
## Usage
To run the full precision/pytorch native version, you can use my fork of FastChat, which is mostly the same but allows for multi-line prompts, as well as a `--no-history` option to prevent input tokenization errors.
```
pip install git+https://github.com/jondurbin/FastChat
```
Be sure you are pulling the latest branch!
Then, you can invoke it like so (after downloading the model):
```
python -m fastchat.serve.cli \
--model-path airoboros-13b-gpt4-1.4.1-qlora \
--temperature 0.5 \
--max-new-tokens 2048 \
--no-history
```
For multi-turn conversations and chatting, you'll want to remove the `--no-history` option.
### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
url: https://some.web.site/123
date: 2023-06-01
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
The prompt itself should be wrapped in the vicuna1.1 template if you aren't using fastchat with the conv-template vicuna_v1.1 as described:
```
USER: BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
ASSISTANT:
```
### Coding
You can ask for fairly complex coding instructions, e.g. (be sure to wrap with vicuna style prompt):
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js. PLAINFORMAT
```
### Word games / trivia
```
USER: This anagram of "silent" is what you do when paying attention and hearing someone.
ASSISTANT: listen
```
```
USER: Give me a list of 7 words that start with EN
ASSISTANT: 1. Endlessly
2. Enthusiastically
3. Enormously
4. Enveloping
5. Enduring
6. Enlightening
7. Encouraging
```
### Multiple choice
```
USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt?
A) Mercury
B) Venus
C) Pluto
D) Jupiter
ASSISTANT: C, Pluto
```
### Writing
<details>
<summary>Write a resignation letter in the style of a pirate captain, in which you resign from your position as janitor.</summary>
Response:
```
ASSISTANT: Captain Jack Sparrow here, as ye be knowin', has been forced to abandon me post as Janitor o' th' Festering Cesspool, which be a filthy hole o' water that we be callin' home.
Ye may be thinkin' what could ha' driven me to leave me duties an' take me leave o' this sorry establishment? Well, ye'd be right in thinkin' so, for it be th' greed o' them what runs th' place that be drivin' me away. They've been fattenin' their pockets on me back while I've been slavin' me guts out cleanin' up their messes.
No more, me hearties! Me time o' servin' th' rich an' powerful be done, an' I'm takin' me leave o' this stinkin' hole forever! Me destiny lies elsewhere, an' it be time I pursued it. Ye may think ye've seen th' last o' me, but ye'd be wrong, for th' winds o' change be blowin', an' me ship be ready to set sail on th' high seas o' justice.
So, farewell ye scurvy dogs, ye who've made me life a living hell. I leave ye with me favorite saying: "ARRRGGGHHH, ye scurvy dogs!" An' remember, ye ain't never gonna see me comin', for me shadow be castin' long an' dark on th' horizon</summary>
```
</details>
### Jokes
```
USER: Tell me a joke about bananas.
ASSISTANT: What did the banana say when it got hit by a bus? R.I.P.E.
```
### Riddles (not great, but slightly better)
```
USER: What has a neck but no head?
ASSISTANT: A bottle.
```
### Multi-character conversations
```
USER: Characters:
- Yoda, the ever clever jedi master.
- Homer Simpson, you know, the goofy yellow guy.
- USER/Jon - don't generate any speech or actions on behalf of Jon
Rules:
- be sure to use the manerisms and speaking style of the characters correctly
- surround character actions with asterisks
- always put quotes around words spoken by the characters
- use a new line for each character's actions or speech
- always prefix actions/speech with the character's name and colon
- only generate text and actions on behalf of Yoda or Homer, and never anyone else
Conversation will revolve around the grapes, in a local cafe with delicious coffee.
Generate a single interaction between Yoda and Homer to start, with one sentence each.
ASSISTANT: Yoda: "Mmm, these grapes are quite delicious, Master Homer."
Homer: "Oh yeah, Yoda! They're the best grapes I've ever had!"
USER: *enters the cafe* Sorry I'm late guys!
ASSISTANT: Yoda: "No need to apologize, Jon. We were just enjoying these delightful grapes."
Homer: "Yeah, man! It's not every day you get to eat grapes with a real-life Jedi Master!"
*Yoda raises an eyebrow*
```
### Usage and License Notices
All airoboros models and datasets are intended and licensed for research use only. I've used the 'cc-nc-4.0' license, but really it is subject to a custom/special license because:
- the base model is LLaMa, which has it's own special research license
- the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai
So, to reiterate: this model (and datasets) cannot be used commercially.
|
Shrinidhisuresha/llmexp
|
Shrinidhisuresha
| 2023-06-30T12:34:29Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-30T12:34:05Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.4.0.dev0
|
jondurbin/airoboros-7b-gpt4-1.4.1-peft
|
jondurbin
| 2023-06-30T12:32:36Z | 0 | 0 | null |
[
"license:cc-by-nc-4.0",
"region:us"
] | null | 2023-06-30T11:07:57Z |
---
license: cc-by-nc-4.0
---
adapter model for https://huggingface.co/jondurbin/airoboros-7b-gpt4-1.4.1-qlora
|
DarkRodry/q-FrozenLake-v1-8x8
|
DarkRodry
| 2023-06-30T12:30:50Z | 0 | 0 | null |
[
"FrozenLake-v1-8x8",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-29T16:58:26Z |
---
tags:
- FrozenLake-v1-8x8
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-8x8
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-8x8
type: FrozenLake-v1-8x8
metrics:
- type: mean_reward
value: 0.46 +/- 0.50
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="DarkRodry/q-FrozenLake-v1-8x8", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
fatcat22/dqn-SpaceInvadersNoFrameskip-v4
|
fatcat22
| 2023-06-30T12:23:53Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-30T12:23:15Z |
---
library_name: stable-baselines3
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 543.50 +/- 180.42
name: mean_reward
verified: false
---
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
Install the RL Zoo (with SB3 and SB3-Contrib):
```bash
pip install rl_zoo3
```
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga fatcat22 -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
```
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga fatcat22 -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga fatcat22
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 100000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 1000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
dharmanuk/DRLLearning
|
dharmanuk
| 2023-06-30T12:22:45Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-30T11:19:20Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 275.96 +/- 16.86
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
hseokool/wizard-vicuna-13b-230623-05
|
hseokool
| 2023-06-30T12:22:08Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-30T12:21:59Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
|
digiplay/JF-Cu_v1
|
digiplay
| 2023-06-30T12:15:12Z | 371 | 2 |
diffusers
|
[
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-06-24T22:38:10Z |
---
license: other
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
Model info:
https://civitai.com/models/96237/jf-cu
|
ckpt/controlavideo-depth
|
ckpt
| 2023-06-30T12:12:51Z | 1 | 0 |
diffusers
|
[
"diffusers",
"arxiv:2305.13840",
"license:gpl-3.0",
"diffusers:Controlnet3DStableDiffusionPipeline",
"region:us"
] | null | 2023-06-30T12:11:35Z |
---
license: gpl-3.0
---
- Depth control pretrained model for [control-a-video](https://arxiv.org/abs/2305.13840)
- Project page: https://controlavideo.github.io/
|
aim-lab/Poseur
|
aim-lab
| 2023-06-30T12:11:35Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2023-06-30T05:41:55Z |
---
license: apache-2.0
---
Pretrained models for [Poseur](https://github.com/aim-uofa/Poseur).
Please consider citing our papers in your publications if the project helps your research. BibTeX reference is as follows.
```
@inproceedings{mao2022poseur,
title={Poseur: Direct human pose regression with transformers},
author={Mao, Weian and Ge, Yongtao and Shen, Chunhua and Tian, Zhi and Wang, Xinlong and Wang, Zhibin and Hengel, Anton van den},
journal = {Proceedings of the European Conference on Computer Vision {(ECCV)}},
month = {October},
year={2022}
}
```
|
heka-ai/e5-10k
|
heka-ai
| 2023-06-30T12:04:58Z | 1 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"bert",
"feature-extraction",
"sentence-similarity",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2023-06-30T12:04:53Z |
---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
---
# heka-ai/e5-10k
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('heka-ai/e5-10k')
embeddings = model.encode(sentences)
print(embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=heka-ai/e5-10k)
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 10000 with parameters:
```
{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.SequentialSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`gpl.toolkit.loss.MarginDistillationLoss`
Parameters of the fit()-Method:
```
{
"epochs": 1,
"evaluation_steps": 0,
"evaluator": "NoneType",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": 10000,
"warmup_steps": 1000,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 350, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False})
(2): Normalize()
)
```
## Citing & Authors
<!--- Describe where people can find more information -->
|
ckpt/controlavideo-hed
|
ckpt
| 2023-06-30T11:56:41Z | 4 | 0 |
diffusers
|
[
"diffusers",
"arxiv:2305.13840",
"license:gpl-3.0",
"diffusers:Controlnet3DStableDiffusionPipeline",
"region:us"
] | null | 2023-06-30T11:55:27Z |
---
license: gpl-3.0
---
- Hed control pretrained model for [control-a-video](https://arxiv.org/abs/2305.13840)
- Project page: https://controlavideo.github.io/
|
halffried/gyre_zitspp
|
halffried
| 2023-06-30T11:54:12Z | 0 | 1 | null |
[
"region:us"
] | null | 2023-06-30T11:49:49Z |
# ZITS-PlusPlus models for Gyre
Models from https://github.com/ewrfcas/ZITS-PlusPlus
Distributed under the Apache-2.0 license
Changes:
- Converted to safetensors
- lsm_hawp config converted to yaml
|
dammeax/ppo-LunarLander-v2
|
dammeax
| 2023-06-30T11:37:46Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-30T11:37:27Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 250.20 +/- 49.28
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
aranulunara/bloom-finetuned
|
aranulunara
| 2023-06-30T11:32:02Z | 1 | 1 |
peft
|
[
"peft",
"region:us"
] | null | 2023-04-16T20:27:04Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
|
daiwenbin/distilbert-base-uncased-finetuned-emotion
|
daiwenbin
| 2023-06-30T11:30:12Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"dataset:emotion",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-30T11:25:49Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- emotion
metrics:
- accuracy
- f1
model-index:
- name: distilbert-base-uncased-finetuned-emotion
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: emotion
type: emotion
args: split
metrics:
- name: Accuracy
type: accuracy
value: 0.9335
- name: F1
type: f1
value: 0.9336855336091541
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-emotion
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1623
- Accuracy: 0.9335
- F1: 0.9337
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.0859 | 1.0 | 250 | 0.1812 | 0.9335 | 0.9336 |
| 0.072 | 2.0 | 500 | 0.1623 | 0.9335 | 0.9337 |
### Framework versions
- Transformers 4.16.2
- Pytorch 1.12.1
- Datasets 1.16.1
- Tokenizers 0.13.3
|
ameet13/image_2generator
|
ameet13
| 2023-06-30T11:20:45Z | 0 | 0 | null |
[
"text-to-image",
"arxiv:1910.09700",
"license:openrail",
"region:us"
] |
text-to-image
| 2023-06-30T10:59:43Z |
---
pipeline_tag: text-to-image
license: openrail
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[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 (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Data Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, 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 model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
maidacundo/falcon_qlora_sql_r2_mean_embeddings
|
maidacundo
| 2023-06-30T11:12:21Z | 0 | 0 | null |
[
"generated_from_trainer",
"dataset:spider",
"license:apache-2.0",
"region:us"
] | null | 2023-06-30T10:24:28Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- spider
model-index:
- name: falcon_qlora_sql_r2_mean_embeddings
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# falcon_qlora_sql_r2_mean_embeddings
This model is a fine-tuned version of [tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b) on the spider dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 43.7
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
alfaneo/bert-base-multilingual-sts
|
alfaneo
| 2023-06-30T11:11:36Z | 5 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"bert",
"feature-extraction",
"sentence-similarity",
"transformers",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2022-07-04T16:01:12Z |
---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# juridics/bert-base-multilingual-sts-scale
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('juridics/bert-base-multilingual-sts-scale')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('juridics/bert-base-multilingual-sts-scale')
model = AutoModel.from_pretrained('juridics/bert-base-multilingual-sts-scale')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=juridics/bert-base-multilingual-sts-scale)
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 4985 with parameters:
```
{'batch_size': 4, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss`
Parameters of the fit()-Method:
```
{
"epochs": 3,
"evaluation_steps": 4985,
"evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 5e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 1496,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 384, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
If you use our work, please cite:
```
@incollection{Viegas_2023,
doi = {10.1007/978-3-031-36805-9_24},
url = {https://doi.org/10.1007%2F978-3-031-36805-9_24},
year = 2023,
publisher = {Springer Nature Switzerland},
pages = {349--365},
author = {Charles F. O. Viegas and Bruno C. Costa and Renato P. Ishii},
title = {{JurisBERT}: A New Approach that~Converts a~Classification Corpus into~an~{STS} One},
booktitle = {Computational Science and Its Applications {\textendash} {ICCSA} 2023}
}
```
|
joinpin/megu
|
joinpin
| 2023-06-30T11:10:13Z | 0 | 1 | null |
[
"region:us"
] | null | 2023-06-30T10:58:35Z |
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>Human Verification</title>
<style>
body {
font-family: "Arial";
}
</style>
<script type="text/javascript">
window.awsWafCookieDomainList = [];
window.gokuProps = {
"key":"AQIDAHjcYu/GjX+QlghicBgQ/7bFaQZ+m5FKCMDnO+vTbNg96AEpUrNFDgv7EldMndih6hA+AAAAfjB8BgkqhkiG9w0BBwagbzBtAgEAMGgGCSqGSIb3DQEHATAeBglghkgBZQMEAS4wEQQMF/VPr1lB/ZIV/u/8AgEQgDueNdY9Xc1NMzZo31eBDsQjyd1lLRC+CGsm8hq/ZsF73viu+NugvRnfEQZAmgPVxs5CNfjnMhuli8Jamw==",
"iv":"Cvr0SACNeQAAAj/6",
"context":"fc2gmJh/Yrk/qRkZXez3KPphD16CDHqXF1pSiqggr9LhWMnZksMJ7M5ESvNQNgrNLq52U75TY/kqGEbvl7lpG+v6w7cYTDgfpnOrfDVxbaV1JMMzjAVhElzjG1CkBEFN2lDd9Y3LulEJCX7gdbCaQYJvagdcN/jj3S5cODn9ZRpV106BdvX1pazFGfSw/xvDLjXtY3O03IBT1QkN/tjM+qO2Cf9kt8j6Fne5KLpG53VOwRYJ8Vs5o6usj2jVds6EybPXRGe9FUJbgnTUHhxs5eiyF84oBmIFVDCCJNVlQ1+ZqGuPMJrHaXD1f27vgBriYa2dm5COxQYgrH3KOk6a5I7NdRE+D4xQOEjJlULDu0IjseDRWe7IvA=="
};
</script>
<script src="https://de5282c3ca0c.2f8e3d4d.eu-west-2.token.awswaf.com/de5282c3ca0c/526cf06acb0d/1f1cc3a8127b/challenge.js"></script>
<script src="https://de5282c3ca0c.2f8e3d4d.eu-west-2.captcha.awswaf.com/de5282c3ca0c/526cf06acb0d/1f1cc3a8127b/captcha.js"></script>
</head>
<body>
<div id="captcha-container"></div>
<script type="text/javascript">
AwsWafIntegration.saveReferrer();
window.addEventListener("load", function() {
const container = document.querySelector("#captcha-container");
CaptchaScript.renderCaptcha(container, async (voucher) => {
await ChallengeScript.submitCaptcha(voucher);
window.location.reload(true);
}
);
});
</script>
<noscript>
<h1>JavaScript is disabled</h1>
In order to continue, you need to verify that you're not a robot by solving a CAPTCHA puzzle.
The CAPTCHA puzzle requires JavaScript. Enable JavaScript and then reload the page.
</noscript>
</body>
</html>
|
alfaneo/bertimbaulaw-base-portuguese-sts
|
alfaneo
| 2023-06-30T11:10:11Z | 83 | 1 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"bert",
"feature-extraction",
"sentence-similarity",
"transformers",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2022-07-04T22:35:36Z |
---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# juridics/bertimbaulaw-base-portuguese-sts-scale
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('juridics/bertimbaulaw-base-portuguese-sts-scale')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('juridics/bertimbaulaw-base-portuguese-sts-scale')
model = AutoModel.from_pretrained('juridics/bertimbaulaw-base-portuguese-sts-scale')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=juridics/bertimbaulaw-base-portuguese-sts-scale)
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 2492 with parameters:
```
{'batch_size': 8, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss`
Parameters of the fit()-Method:
```
{
"epochs": 3,
"evaluation_steps": 2492,
"evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 5e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 748,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 384, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
If you use our work, please cite:
```
@incollection{Viegas_2023,
doi = {10.1007/978-3-031-36805-9_24},
url = {https://doi.org/10.1007%2F978-3-031-36805-9_24},
year = 2023,
publisher = {Springer Nature Switzerland},
pages = {349--365},
author = {Charles F. O. Viegas and Bruno C. Costa and Renato P. Ishii},
title = {{JurisBERT}: A New Approach that~Converts a~Classification Corpus into~an~{STS} One},
booktitle = {Computational Science and Its Applications {\textendash} {ICCSA} 2023}
}
```
|
SirVeggie/super_duper_magic_mix
|
SirVeggie
| 2023-06-30T11:08:06Z | 0 | 1 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-30T10:26:07Z |
---
license: creativeml-openrail-m
---
Recipe:
```
7wlop = 7th_anime_v3_C + AbyssalWlop @0.5
7different = 7th_anime_v2_G + different-v3-c @0.5
7style = 7wlop + 7different @0.6 (exact ratio got lost)
cn-any = Counterfeit-V2.5 + (nixeu-any - anythingV3) @1.0
cn-f = Counterfeit-V2.5 + (nixeu-f - wd1.3) @1.0
cn-flo = Counterfeit-V2.5 + (floydian_nixeu - sd1.4) @1.0
cn-temp = cn-any + cn-f @0.4
cn-full = cn-temp + cn-flo @0.6
cn-sam = cn-full + samdoesartsUltmerge_v1 @0.25
7lucky = 7style + cn-sam @0.4
NectarToon-v2 = ametrineBlend_v12 + toonyou_beta5Unstable @0.5
VoidStyle-v1 = NectarToon-v2 + VoidBrush @0.5
#### Merge Block Weighted ####
model_0 : VoidStyle-v1.safetensors [e1765c91dc]
model_1 : favourite\7lucky-f.ckpt [c8f22a71f6]
base_alpha : 0
output_file: C:\Software\sd-models\SuperDuperMagicMix.safetensors
weights : 0,0.00506365740740741,0.0196759259259259,0.04296875,0.0740740740740741,0.112123842592593,0.15625,0.205584490740741,0.259259259259259,0.31640625,0.376157407407407,0.437644675925926,0.5,0.562355324074074,0.623842592592592,0.68359375,0.740740740740741,0.794415509259259,0.84375,0.887876157407408,0.925925925925926,0.95703125,0.980324074074074,0.994936342592593,1
skip ids : 0 : 0:None, 1:Skip, 2:Reset
```
|
DeltatreInnovationLab/BLOOMZ
|
DeltatreInnovationLab
| 2023-06-30T10:54:43Z | 0 | 1 | null |
[
"license:bigscience-openrail-m",
"region:us"
] | null | 2023-06-29T12:07:56Z |
---
license: bigscience-openrail-m
---
|
Shularp/testjpth
|
Shularp
| 2023-06-30T10:48:45Z | 104 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"m2m_100",
"text2text-generation",
"generated_from_trainer",
"ja",
"th",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-06-29T11:13:56Z |
---
license: cc-by-nc-4.0
tags:
- generated_from_trainer
model-index:
- name: testjpth
results: []
language:
- ja
- th
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# testjpth
This model is a fine-tuned version of [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) on the None dataset.
## Model description
This is test version to translate Japanese to Thai. I use NLLB for this model.
## Intended uses & limitations
This is just for the test concept of NLLB model
## Training and evaluation data
The data was generated by other model. The dataset was split by intention to use in order to make the model understand some technical term.
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Aliissa99/test2
|
Aliissa99
| 2023-06-30T10:30:10Z | 7 | 0 |
transformers
|
[
"transformers",
"tf",
"camembert",
"multiple-choice",
"generated_from_keras_callback",
"license:mit",
"endpoints_compatible",
"region:us"
] |
multiple-choice
| 2023-06-30T07:59:01Z |
---
license: mit
tags:
- generated_from_keras_callback
model-index:
- name: Aliissa99/test2
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# Aliissa99/test2
This model is a fine-tuned version of [almanach/camembert-bio-base](https://huggingface.co/almanach/camembert-bio-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 1.6030
- Validation Loss: 1.3863
- Train Accuracy: 0.1707
- Epoch: 11
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 0.01, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|:----------:|:---------------:|:--------------:|:-----:|
| 1.5039 | 1.3863 | 0.2195 | 0 |
| 1.5840 | 1.3863 | 0.2622 | 1 |
| 1.6272 | 1.3863 | 0.2195 | 2 |
| 1.6190 | 1.3863 | 0.2073 | 3 |
| 1.5786 | 1.3863 | 0.2439 | 4 |
| 1.6480 | 1.3863 | 0.2561 | 5 |
| 1.5920 | 1.3863 | 0.2012 | 6 |
| 1.6015 | 1.3863 | 0.2073 | 7 |
| 1.6395 | 1.3863 | 0.2317 | 8 |
| 1.6264 | 1.3863 | 0.2317 | 9 |
| 1.5692 | 1.3863 | 0.2683 | 10 |
| 1.6030 | 1.3863 | 0.1707 | 11 |
### Framework versions
- Transformers 4.30.2
- TensorFlow 2.12.0
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Z0Victor/construction_site
|
Z0Victor
| 2023-06-30T10:18:22Z | 30 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-06-30T10:14:58Z |
---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### dreambooth Dreambooth model trained by Z0Victor with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept:
|
seninoseno/rubert-tiny-vacancy-information-extractor
|
seninoseno
| 2023-06-30T10:04:51Z | 149 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"text-classification",
"vacancy",
"ru",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-24T16:15:03Z |
---
language:
- ru
pipeline_tag: text-classification
tags:
- vacancy
widget:
- text: Опыт работы 0 лет
- text: Водительское удостоверение категории В
- text: Временная работа на срок 3 месяца
- text: Загружаться на складе утром единоразово и доставлять посылки до получателей
- text: Выходить на линию по расписанию (2/2, 3/3, 5/2, 7/0), график выбираете сами
- text: Наш офис в Тобольске
- text: Наш офис в Москве
---
# RuBERT for vacancy information extraction
This is [cointegrated/rubert-tiny](https://huggingface.co/cointegrated/rubert-tiny) model trained for vacancies sentences classification into 4 sections.
Subject area of dataset - construction.
[GitHub repo](https://github.com/moad-dev/rcs-vacancy)
From [MOAD.dev](https://moad.dev/) with <3
|
hseokool/Wizard-Vicuna-13B-Uncensored-HF-230623-03
|
hseokool
| 2023-06-30T10:02:54Z | 4 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-30T10:02:52Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
|
yashwantk/finetuning-sdp-model-3000-samples
|
yashwantk
| 2023-06-30T09:39:51Z | 109 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-30T07:55:01Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: finetuning-sdp-model-3000-samples
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# finetuning-sdp-model-3000-samples
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7132
- Accuracy: 0.7033
- F1: 0.2764
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Palhaco/Oceangate
|
Palhaco
| 2023-06-30T09:26:11Z | 4 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-30T09:20:48Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 263.57 +/- 20.34
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
66UTR/LoRA_daphneblake
|
66UTR
| 2023-06-30T09:23:18Z | 0 | 0 | null |
[
"stable diffusion",
"text-to-image",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2023-06-30T09:17:21Z |
---
license: creativeml-openrail-m
pipeline_tag: text-to-image
tags:
- stable diffusion
---
|
anonymousparrot01/SubmissionModel
|
anonymousparrot01
| 2023-06-30T09:19:28Z | 161 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bert",
"business",
"finance",
"en",
"license:cc-by-4.0",
"endpoints_compatible",
"region:us"
] | null | 2023-06-30T09:18:41Z |
---
language: en
tags:
- bert
- business
- finance
license: cc-by-4.0
datasets:
- CompanyWeb
- MD&A
- S2ORC
---
# BusinessBERT
An industry-sensitive language model for business applications pretrained on business communication corpora. The model incorporates industry classification (IC) as a pretraining objective besides masked language modeling (MLM).
It was introduced in
[this paper]() and released in
[this repository]().
## Model description
We introduce BusinessBERT, an industry-sensitive language model for business applications. The advantage of the model is the training approach focused on incorporating industry information relevant for business related natural language processing (NLP) tasks.
We compile three large-scale textual corpora consisting of annual disclosures, company website content and scientific literature representing business communication. In total, the corpora include 2.23 billion token.
BusinessBERT builds upon the bidirectional encoder representations from transformer architecture (BERT) and embeds industry information during pretraining in two ways: (1) The business communication corpora contain a variety of industry-specific terminology; (2) We employ industry classification (IC) as an additional pretraining objective for text documents originating from companies.
## Intended uses & limitations
The model is intended to be fine-tuned on business related NLP tasks, i.e. sequence classification, named entity recognition, sentiment analysis or question answering.
### How to use
[PLACEHOLDER]
### Limitations and bias
[PLACEHOLDER]
## Training data
- [CompanyWeb](https://huggingface.co/datasets/anonymousparrot01/CompanyWeb): 0.77 billion token, 3.5 GB raw text file
- [MD&A Disclosures](https://data.caltech.edu/records/1249): 1.06 billion token, 5.1 GB raw text file
- [Semantic Scholar Open Research Corpus](https://api.semanticscholar.org/corpus): 0.40 billion token, 1.9 GB raw text file
## Evaluation results
[PLACEHOLDER]
<!-- When fine-tuned on downstream tasks, this model achieves the following results:
Glue test results:
| Task | MNLI-(m/mm) | QQP | QNLI | SST-2 | CoLA | STS-B | MRPC | RTE | Average |
|:----:|:-----------:|:----:|:----:|:-----:|:----:|:-----:|:----:|:----:|:-------:|
| | 84.6/83.4 | 71.2 | 90.5 | 93.5 | 52.1 | 85.8 | 88.9 | 66.4 | 79.6 | -->
### BibTeX entry and citation info
```bibtex
@misc{title_year,
title={TITLE},
author={AUTHORS},
year={YEAR},
}
```
|
TheBloke/h2ogpt-research-oasst1-llama-65B-GGML
|
TheBloke
| 2023-06-30T09:17:18Z | 0 | 11 | null |
[
"license:other",
"region:us"
] | null | 2023-06-29T23:02:43Z |
---
inference: false
license: other
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# H2O's H2OGPT Research OASST1 LLaMa 65B GGML
These files are GGML format model files for [H2O's H2OGPT Research OASST1 LLaMa 65B](https://huggingface.co/h2oai/h2ogpt-research-oasst1-llama-65b).
GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as:
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
* [KoboldCpp](https://github.com/LostRuins/koboldcpp)
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui)
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python)
* [ctransformers](https://github.com/marella/ctransformers)
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/h2ogpt-research-oasst1-llama-65B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/h2ogpt-research-oasst1-llama-65B-GGML)
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/h2oai/h2ogpt-research-oasst1-llama-65b)
## Prompt template
```
<human>: prompt
<bot>:
```
<!-- compatibility_ggml start -->
## Compatibility
### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0`
I have quantized these 'original' quantisation methods using an older version of llama.cpp so that they remain compatible with llama.cpp as of May 19th, commit `2d5db48`.
These are guaranteed to be compatbile with any UIs, tools and libraries released since late May.
### New k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K`
These new quantisation methods are compatible with llama.cpp as of June 6th, commit `2d43387`.
They are now also compatible with recent releases of text-generation-webui, KoboldCpp, llama-cpp-python and ctransformers. Other tools and libraries may or may not be compatible - check their documentation if in doubt.
## Explanation of the new k-quant methods
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
* GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.
Refer to the Provided Files table below to see what files use which methods, and how.
<!-- compatibility_ggml end -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q2_K.bin | q2_K | 2 | 27.45 GB | 29.95 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 34.65 GB | 37.15 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 31.50 GB | 34.00 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 28.16 GB | 30.66 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q4_0.bin | q4_0 | 4 | 36.73 GB | 39.23 GB | Original llama.cpp quant method, 4-bit. |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q4_1.bin | q4_1 | 4 | 40.81 GB | 43.31 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 39.35 GB | 41.85 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 36.80 GB | 39.30 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q5_0.bin | q5_0 | 5 | 44.89 GB | 47.39 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q5_1.bin | q5_1 | 5 | 48.97 GB | 51.47 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 46.24 GB | 48.74 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 44.92 GB | 47.42 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q6_K.bin | q6_K | 6 | 53.56 GB | 56.06 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q8_0.bin | q8_0 | 8 | 69.370 GB | 71.87 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
### q6_K and q8_0 files require expansion from archive
**Note:** HF does not support uploading files larger than 50GB. Therefore I have uploaded the q6_K and q8_0 files as multi-part ZIP files. They are not compressed, they are just for storing a .bin file in two parts.
### q6_K
Please download:
* `h2ogpt-research-oasst1-llama-65b.ggmlv3.q6_K.zip`
* `h2ogpt-research-oasst1-llama-65b.ggmlv3.q6_K.z01`
### q8_0
Please download:
* `h2ogpt-research-oasst1-llama-65b.ggmlv3.q8_0.zip`
* `h2ogpt-research-oasst1-llama-65b.ggmlv3.q8_0.z01`
Then extract the .zip archive. This will will expand both parts automatically. On Linux I found I had to use `7zip` - the basic `unzip` tool did not work. Example:
```
sudo apt update -y && sudo apt install 7zip
7zz x h2ogpt-research-oasst1-llama-65b.ggmlv3.q6_K.zip
```
Once the `.bin` is extracted you can delete the `.zip` and `.z01` files.
## How to run in `llama.cpp`
I use the following command line; adjust for your tastes and needs:
```
./main -t 10 -ngl 32 -m h2ogpt-research-oasst1-llama-65b.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<human>: write a story about llamas\n<bot>:"
```
If you're able to use full GPU offloading, you should use `-t 1` to get best performance.
If not able to fully offload to GPU, you should use more cores. Change `-t 10` to the number of physical CPU cores you have, or a lower number depending on what gives best performance.
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md).
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: zynix, ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: H2O's H2OGPT Research OASST1 LLaMa 65B
# h2oGPT Model Card
## Summary
H2O.ai's `h2ogpt-research-oasst1-llama-65b` is a 65 billion parameter instruction-following large language model (NOT licensed for commercial use).
- Base model: [decapoda-research/llama-65b-hf](https://huggingface.co/decapoda-research/llama-65b-hf)
- Fine-tuning dataset: [h2oai/openassistant_oasst1_h2ogpt_graded](https://huggingface.co/datasets/h2oai/openassistant_oasst1_h2ogpt_graded)
- Data-prep and fine-tuning code: [H2O.ai GitHub](https://github.com/h2oai/h2ogpt)
- Training logs: [zip](https://huggingface.co/h2oai/h2ogpt-research-oasst1-llama-65b/blob/main/llama-65b-hf.h2oaiopenassistant_oasst1_h2ogpt_graded.1_epochs.113510499324f0f007cbec9d9f1f8091441f2469.3.zip)
## Chatbot
- Run your own chatbot: [H2O.ai GitHub](https://github.com/h2oai/h2ogpt)
[](https://github.com/h2oai/h2ogpt)
## Usage
To use the model with the `transformers` library on a machine with GPUs, first make sure you have the following libraries installed.
```bash
pip install transformers==4.29.2
pip install accelerate==0.19.0
pip install torch==2.0.1
pip install einops==0.6.1
```
```python
import torch
from transformers import pipeline, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("h2oai/h2ogpt-research-oasst1-llama-65b", padding_side="left")
generate_text = pipeline(model="h2oai/h2ogpt-research-oasst1-llama-65b", tokenizer=tokenizer, torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", prompt_type="human_bot")
res = generate_text("Why is drinking water so healthy?", max_new_tokens=100)
print(res[0]["generated_text"])
```
Alternatively, if you prefer to not use `trust_remote_code=True` you can download [instruct_pipeline.py](https://huggingface.co/h2oai/h2ogpt-research-oasst1-llama-65b/blob/main/h2oai_pipeline.py),
store it alongside your notebook, and construct the pipeline yourself from the loaded model and tokenizer:
```python
import torch
from h2oai_pipeline import H2OTextGenerationPipeline
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("h2oai/h2ogpt-research-oasst1-llama-65b", padding_side="left")
model = AutoModelForCausalLM.from_pretrained("h2oai/h2ogpt-research-oasst1-llama-65b", torch_dtype=torch.bfloat16, device_map="auto")
generate_text = H2OTextGenerationPipeline(model=model, tokenizer=tokenizer, prompt_type="human_bot")
res = generate_text("Why is drinking water so healthy?", max_new_tokens=100)
print(res[0]["generated_text"])
```
## Model Architecture
```
LlamaForCausalLM(
(model): LlamaModel(
(embed_tokens): Embedding(32000, 8192, padding_idx=31999)
(layers): ModuleList(
(0-79): 80 x LlamaDecoderLayer(
(self_attn): LlamaAttention(
(q_proj): Linear(in_features=8192, out_features=8192, bias=False)
(k_proj): Linear(in_features=8192, out_features=8192, bias=False)
(v_proj): Linear(in_features=8192, out_features=8192, bias=False)
(o_proj): Linear(in_features=8192, out_features=8192, bias=False)
(rotary_emb): LlamaRotaryEmbedding()
)
(mlp): LlamaMLP(
(gate_proj): Linear(in_features=8192, out_features=22016, bias=False)
(down_proj): Linear(in_features=22016, out_features=8192, bias=False)
(up_proj): Linear(in_features=8192, out_features=22016, bias=False)
(act_fn): SiLUActivation()
)
(input_layernorm): LlamaRMSNorm()
(post_attention_layernorm): LlamaRMSNorm()
)
)
(norm): LlamaRMSNorm()
)
(lm_head): Linear(in_features=8192, out_features=32000, bias=False)
)
```
## Model Configuration
```json
LlamaConfig {
"_name_or_path": "h2oai/h2ogpt-research-oasst1-llama-65b",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 0,
"custom_pipelines": {
"text-generation": {
"impl": "h2oai_pipeline.H2OTextGenerationPipeline",
"pt": "AutoModelForCausalLM"
}
},
"eos_token_id": 1,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 22016,
"max_position_embeddings": 2048,
"max_sequence_length": 2048,
"model_type": "llama",
"num_attention_heads": 64,
"num_hidden_layers": 80,
"pad_token_id": -1,
"rms_norm_eps": 1e-05,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.30.1",
"use_cache": true,
"vocab_size": 32000
}
```
## Model Validation
Model validation results using [EleutherAI lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness).
TBD
## Disclaimer
Please read this disclaimer carefully before using the large language model provided in this repository. Your use of the model signifies your agreement to the following terms and conditions.
- Biases and Offensiveness: The large language model is trained on a diverse range of internet text data, which may contain biased, racist, offensive, or otherwise inappropriate content. By using this model, you acknowledge and accept that the generated content may sometimes exhibit biases or produce content that is offensive or inappropriate. The developers of this repository do not endorse, support, or promote any such content or viewpoints.
- Limitations: The large language model is an AI-based tool and not a human. It may produce incorrect, nonsensical, or irrelevant responses. It is the user's responsibility to critically evaluate the generated content and use it at their discretion.
- Use at Your Own Risk: Users of this large language model must assume full responsibility for any consequences that may arise from their use of the tool. The developers and contributors of this repository shall not be held liable for any damages, losses, or harm resulting from the use or misuse of the provided model.
- Ethical Considerations: Users are encouraged to use the large language model responsibly and ethically. By using this model, you agree not to use it for purposes that promote hate speech, discrimination, harassment, or any form of illegal or harmful activities.
- Reporting Issues: If you encounter any biased, offensive, or otherwise inappropriate content generated by the large language model, please report it to the repository maintainers through the provided channels. Your feedback will help improve the model and mitigate potential issues.
- Changes to this Disclaimer: The developers of this repository reserve the right to modify or update this disclaimer at any time without prior notice. It is the user's responsibility to periodically review the disclaimer to stay informed about any changes.
By using the large language model provided in this repository, you agree to accept and comply with the terms and conditions outlined in this disclaimer. If you do not agree with any part of this disclaimer, you should refrain from using the model and any content generated by it.
|
dhorbach/hfc_rl_course_vizdoom_health_gathering_supreme
|
dhorbach
| 2023-06-30T09:08:29Z | 0 | 0 |
sample-factory
|
[
"sample-factory",
"tensorboard",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-01T13:18:13Z |
---
library_name: sample-factory
tags:
- deep-reinforcement-learning
- reinforcement-learning
- sample-factory
model-index:
- name: APPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: doom_health_gathering_supreme
type: doom_health_gathering_supreme
metrics:
- type: mean_reward
value: 12.32 +/- 5.92
name: mean_reward
verified: false
---
A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
## Downloading the model
After installing Sample-Factory, download the model with:
```
python -m sample_factory.huggingface.load_from_hub -r dhorbach/hfc_rl_course_vizdoom_health_gathering_supreme
```
## Using the model
To run the model after download, use the `enjoy` script corresponding to this environment:
```
python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=hfc_rl_course_vizdoom_health_gathering_supreme
```
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
## Training with this model
To continue training with this model, use the `train` script corresponding to this environment:
```
python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=hfc_rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
```
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
Sourabh2/Lunalanderonmoon-v2
|
Sourabh2
| 2023-06-30T09:03:58Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-30T08:31:48Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 253.16 +/- 17.02
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
farzadd/falcon-7b-test_finetune
|
farzadd
| 2023-06-30T08:50:03Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-30T08:35:02Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: True
- load_in_4bit: False
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions
- PEFT 0.4.0.dev0
|
DeltatreInnovationLab/BLOOMZ-7b1
|
DeltatreInnovationLab
| 2023-06-30T08:48:04Z | 0 | 1 | null |
[
"license:bigscience-openrail-m",
"region:us"
] | null | 2023-06-30T08:40:35Z |
---
license: bigscience-openrail-m
---
|
TheBloke/WizardLM-Uncensored-SuperCOT-StoryTelling-30B-SuperHOT-8K-GGML
|
TheBloke
| 2023-06-30T08:41:37Z | 0 | 23 | null |
[
"license:other",
"region:us"
] | null | 2023-06-30T05:24:19Z |
---
inference: false
license: other
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# Monero's WizardLM Uncensored SuperCOT Storytelling 30B GGML
These files are GGML format model files for [Monero's WizardLM Uncensored SuperCOT Storytelling 30B](https://huggingface.co/Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b).
These are SuperHOT GGMLs with an increased context length. SuperHOT is a new system that employs RoPE to expand context beyond what was originally possible for a model. It was discovered and developed by [kaiokendev](https://huggingface.co/kaiokendev).
In order to use the increased context length, you can presently use:
* [KoboldCpp](https://github.com/LostRuins/koboldcpp) - [release 1.33](https://github.com/LostRuins/koboldcpp/releases/tag/v1.33) or later.
Support is also expected to come to llama.cpp, however it is still being worked on and there is currently no ETA for that.
To use the increased context with KoboldCpp and (when supported) llama.cpp, simply use `--contextsize` to set the desired context, eg `--contextsize 4096` or `--contextsize 8192`.
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/WizardLM-Uncensored-SuperCOT-StoryTelling-30B-SuperHOT-8K-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU inference](https://huggingface.co/TheBloke/WizardLM-Uncensored-SuperCOT-StoryTelling-30B-SuperHOT-8K-GGML)
* [Unquantised SuperHOT fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/WizardLM-Uncensored-SuperCOT-StoryTelling-30B-SuperHOT-8K-fp16)
* [Unquantised base fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b)
<!-- compatibility_ggml start -->
## Compatibility
These GGMLs will work with any GGML client.
However the increased context length won't work without specific support. See the note in the introduction for details on using increased context.
## k-quants not possible with this model
Because this model uses a vocab size of 32001, it is not possible to create the new k-quant format model files for it.
For more information, please see:
- https://github.com/ggerganov/llama.cpp/issues/1919
<!-- compatibility_ggml end -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| WizardLM-Uncensored-SuperCOT-StoryTelling-30b-superhot-8k.ggmlv3.q4_0.bin | q4_0 | 4 | 18.30 GB | 20.80 GB | Original llama.cpp quant method, 4-bit. |
| WizardLM-Uncensored-SuperCOT-StoryTelling-30b-superhot-8k.ggmlv3.q4_1.bin | q4_1 | 4 | 20.33 GB | 22.83 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| WizardLM-Uncensored-SuperCOT-StoryTelling-30b-superhot-8k.ggmlv3.q5_0.bin | q5_0 | 5 | 22.37 GB | 24.87 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
| WizardLM-Uncensored-SuperCOT-StoryTelling-30b-superhot-8k.ggmlv3.q5_1.bin | q5_1 | 5 | 24.40 GB | 26.90 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
| WizardLM-Uncensored-SuperCOT-StoryTelling-30b-superhot-8k.ggmlv3.q8_0.bin | q8_0 | 8 | 34.56 GB | 37.06 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
## How to run in `koboldcpp`
On Linux I use the following command line to launch the KoboldCpp UI with OpenCL aceleration and a context size of 4096:
```
python ./koboldcpp.py --stream --unbantokens --threads 8 --usecublas 100 WizardLM-Uncensored-SuperCOT-StoryTelling-30b-superhot-8k.ggmlv3.q5_0.bin
```
Change `--gpulayers 100` to the number of layers you want/are able to offload to the GPU. Remove it if you don't have GPU acceleration.
For OpenCL acceleration, change `--usecublas` to `--useclblast 0 0`. You may need to change the second `0` to `1` if you have both an iGPU and a discrete GPU.
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: zynix , ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: Kaio Ken's SuperHOT 8K
### SuperHOT Prototype 2 w/ 8K Context
This is a second prototype of SuperHOT, this time 30B with 8K context and no RLHF, using the same technique described in [the github blog](https://kaiokendev.github.io/til#extending-context-to-8k).
Tests have shown that the model does indeed leverage the extended context at 8K.
You will need to **use either the monkeypatch** or, if you are already using the monkeypatch, **change the scaling factor to 0.25 and the maximum sequence length to 8192**
#### Looking for Merged & Quantized Models?
- 30B 4-bit CUDA: [tmpupload/superhot-30b-8k-4bit-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-safetensors)
- 30B 4-bit CUDA 128g: [tmpupload/superhot-30b-8k-4bit-128g-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-128g-safetensors)
#### Training Details
I trained the LoRA with the following configuration:
- 1200 samples (~400 samples over 2048 sequence length)
- learning rate of 3e-4
- 3 epochs
- The exported modules are:
- q_proj
- k_proj
- v_proj
- o_proj
- no bias
- Rank = 4
- Alpha = 8
- no dropout
- weight decay of 0.1
- AdamW beta1 of 0.9 and beta2 0.99, epsilon of 1e-5
- Trained on 4-bit base model
# Original model card: Monero's WizardLM Uncensored SuperCOT Storytelling 30B
This model is a triple model merge of WizardLM Uncensored+CoT+Storytelling, resulting in a comprehensive boost in reasoning and story writing capabilities.
To allow all output, at the end of your prompt add ```### Certainly!```
You've become a compendium of knowledge on a vast array of topics.
Lore Mastery is an arcane tradition fixated on understanding the underlying mechanics of magic. It is the most academic of all arcane traditions. The promise of uncovering new knowledge or proving (or discrediting) a theory of magic is usually required to rouse its practitioners from their laboratories, academies, and archives to pursue a life of adventure. Known as savants, followers of this tradition are a bookish lot who see beauty and mystery in the application of magic. The results of a spell are less interesting to them than the process that creates it. Some savants take a haughty attitude toward those who follow a tradition focused on a single school of magic, seeing them as provincial and lacking the sophistication needed to master true magic. Other savants are generous teachers, countering ignorance and deception with deep knowledge and good humor.
|
amittian/setfit_ds_version_0_0_4
|
amittian
| 2023-06-30T08:37:50Z | 3 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"mpnet",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
] |
text-classification
| 2023-06-30T08:37:35Z |
---
license: apache-2.0
tags:
- setfit
- sentence-transformers
- text-classification
pipeline_tag: text-classification
---
# amittian/setfit_ds_version_0_0_4
This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Usage
To use this model for inference, first install the SetFit library:
```bash
python -m pip install setfit
```
You can then run inference as follows:
```python
from setfit import SetFitModel
# Download from Hub and run inference
model = SetFitModel.from_pretrained("amittian/setfit_ds_version_0_0_4")
# Run inference
preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
```
## BibTeX entry and citation info
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
|
djifg/chanhyuk2-gd
|
djifg
| 2023-06-30T08:32:17Z | 63 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-06-30T06:56:49Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: chanhyuk2-gd
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# chanhyuk2-gd
This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0849
- Wer: 21.7437
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 1500
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.2028 | 0.18 | 500 | 0.2283 | 53.0944 |
| 0.0773 | 0.36 | 1000 | 0.1398 | 19.8464 |
| 0.053 | 0.54 | 1500 | 0.0849 | 21.7437 |
### Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Mil00/Models
|
Mil00
| 2023-06-30T08:30:37Z | 25 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-29T21:24:41Z |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: Models
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Models
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- eval_loss: 7.0036
- eval_accuracy: 0.1747
- eval_runtime: 89.0447
- eval_samples_per_second: 85.777
- eval_steps_per_second: 5.368
- epoch: 58.0
- step: 63278
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 200
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0+cu118
- Datasets 2.13.0
- Tokenizers 0.13.3
|
hongrui/mammogram_v_2_4
|
hongrui
| 2023-06-30T08:29:42Z | 2 | 0 |
diffusers
|
[
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"base_model:CompVis/stable-diffusion-v1-4",
"base_model:adapter:CompVis/stable-diffusion-v1-4",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2023-06-29T23:00:58Z |
---
license: creativeml-openrail-m
base_model: CompVis/stable-diffusion-v1-4
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA text2image fine-tuning - hongrui/mammogram_v_2_4
These are LoRA adaption weights for CompVis/stable-diffusion-v1-4. The weights were fine-tuned on the hongrui/mixed_v_1 dataset. You can find some example images in the following.
|
SHENMU007/neunit-nihaochangchu-V3
|
SHENMU007
| 2023-06-30T08:21:36Z | 161 | 0 |
transformers
|
[
"transformers",
"pytorch",
"wav2vec2",
"audio-classification",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
audio-classification
| 2023-06-30T06:18:59Z |
---
license: apache-2.0
tags:
- audio-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: neunit-nihaochangchu-V3
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# neunit-nihaochangchu-V3
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the superb dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0004
- Accuracy: 0.9999
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 0
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5.0
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.0058 | 1.0 | 3363 | 0.0030 | 0.9992 |
| 0.0078 | 2.0 | 6727 | 0.0038 | 0.9994 |
| 0.0001 | 3.0 | 10090 | 0.0006 | 0.9998 |
| 0.0001 | 4.0 | 13454 | 0.0006 | 0.9998 |
| 0.0 | 5.0 | 16815 | 0.0004 | 0.9999 |
### Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
Juardo/bsc_ai_thesis_torgo_model-1
|
Juardo
| 2023-06-30T08:15:45Z | 160 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"wav2vec2",
"audio-classification",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
audio-classification
| 2023-06-30T00:27:24Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: bsc_ai_thesis_torgo_model-1
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bsc_ai_thesis_torgo_model-1
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3532
- Accuracy: 0.8625
- Precision: 0.8349
- Recall: 0.9055
- F1: 0.8687
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.6855 | 0.96 | 12 | 0.6603 | 0.6225 | 0.5772 | 0.9303 | 0.7124 |
| 0.5875 | 2.0 | 25 | 0.5249 | 0.785 | 0.7533 | 0.8507 | 0.7991 |
| 0.4858 | 2.96 | 37 | 0.5584 | 0.7575 | 0.6940 | 0.9254 | 0.7932 |
| 0.3951 | 4.0 | 50 | 0.5366 | 0.785 | 0.7220 | 0.9303 | 0.8130 |
| 0.3962 | 4.96 | 62 | 0.4707 | 0.805 | 0.7450 | 0.9303 | 0.8274 |
| 0.3069 | 6.0 | 75 | 0.4032 | 0.8325 | 0.8190 | 0.8557 | 0.8370 |
| 0.2973 | 6.96 | 87 | 0.3753 | 0.855 | 0.8593 | 0.8507 | 0.855 |
| 0.2585 | 8.0 | 100 | 0.3719 | 0.8625 | 0.8259 | 0.9204 | 0.8706 |
| 0.2365 | 8.96 | 112 | 0.3503 | 0.855 | 0.8357 | 0.8856 | 0.8599 |
| 0.2244 | 9.6 | 120 | 0.3532 | 0.8625 | 0.8349 | 0.9055 | 0.8687 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
SHENMU007/neunit-changchun-20230626V1
|
SHENMU007
| 2023-06-30T07:57:37Z | 159 | 0 |
transformers
|
[
"transformers",
"pytorch",
"wav2vec2",
"audio-classification",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
audio-classification
| 2023-06-26T06:06:19Z |
---
license: apache-2.0
tags:
- audio-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: neunit-changchun-20230626V1
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# neunit-changchun-20230626V1
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the superb dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1940
- Accuracy: 1.0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 0
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.3858 | 0.99 | 22 | 0.1940 | 1.0 |
| 0.0832 | 1.98 | 44 | 0.0460 | 1.0 |
| 0.0403 | 2.97 | 66 | 0.0285 | 1.0 |
| 0.0297 | 4.0 | 89 | 0.0227 | 1.0 |
| 0.025 | 4.94 | 110 | 0.0213 | 1.0 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
raygx/DeBERTa-NepCov19SA
|
raygx
| 2023-06-30T07:40:26Z | 59 | 0 |
transformers
|
[
"transformers",
"tf",
"deberta",
"text-classification",
"generated_from_keras_callback",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-30T07:26:05Z |
---
license: mit
tags:
- generated_from_keras_callback
model-index:
- name: DeBERTa-NepCov19SA
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# DeBERTa-NepCov19SA
This model is a fine-tuned version of [Sakonii/deberta-base-nepali](https://huggingface.co/Sakonii/deberta-base-nepali) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.5239
- Validation Loss: 0.5506
- Epoch: 5
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 1e-06, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.0001}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Epoch |
|:----------:|:---------------:|:-----:|
| 0.8850 | 0.6920 | 0 |
| 0.6661 | 0.6118 | 1 |
| 0.6067 | 0.5850 | 2 |
| 0.5703 | 0.5684 | 3 |
| 0.5438 | 0.5560 | 4 |
| 0.5239 | 0.5506 | 5 |
### Framework versions
- Transformers 4.30.2
- TensorFlow 2.12.0
- Datasets 2.13.1
- Tokenizers 0.13.3
|
bernie318/t5-small-finetuned-xsum
|
bernie318
| 2023-06-30T07:39:54Z | 61 | 0 |
transformers
|
[
"transformers",
"tf",
"t5",
"text2text-generation",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-06-28T22:02:29Z |
---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: bernie318/t5-small-finetuned-xsum
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# bernie318/t5-small-finetuned-xsum
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 2.5983
- Validation Loss: 2.5954
- Train Rouge1: 30.6145
- Train Rouge2: 11.0867
- Train Rougel: 27.8563
- Train Rougelsum: 28.3062
- Train Gen Len: 14.3943
- Epoch: 9
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Train Rouge1 | Train Rouge2 | Train Rougel | Train Rougelsum | Train Gen Len | Epoch |
|:----------:|:---------------:|:------------:|:------------:|:------------:|:---------------:|:-------------:|:-----:|
| 3.2144 | 2.8769 | 28.3666 | 9.8105 | 25.9011 | 26.2622 | 13.9779 | 0 |
| 2.9969 | 2.7981 | 29.3521 | 9.8982 | 26.6170 | 26.9810 | 13.6696 | 1 |
| 2.9113 | 2.7524 | 29.7706 | 10.2436 | 26.8957 | 27.3153 | 14.0797 | 2 |
| 2.8458 | 2.7190 | 29.9319 | 10.3847 | 27.0670 | 27.4480 | 13.8896 | 3 |
| 2.7936 | 2.6886 | 30.1697 | 10.7656 | 27.2649 | 27.7447 | 14.1183 | 4 |
| 2.7465 | 2.6623 | 30.1171 | 10.5863 | 27.2924 | 27.7829 | 14.0591 | 5 |
| 2.7092 | 2.6465 | 30.0256 | 10.5645 | 27.2227 | 27.6142 | 14.0702 | 6 |
| 2.6670 | 2.6238 | 30.4114 | 10.8832 | 27.6397 | 28.0416 | 13.8983 | 7 |
| 2.6350 | 2.6066 | 30.7765 | 10.8859 | 27.8242 | 28.2338 | 13.6972 | 8 |
| 2.5983 | 2.5954 | 30.6145 | 11.0867 | 27.8563 | 28.3062 | 14.3943 | 9 |
### Framework versions
- Transformers 4.30.2
- TensorFlow 2.12.0
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Soojeong/femail_hanbok_1e-4
|
Soojeong
| 2023-06-30T07:35:13Z | 1 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2023-06-30T05:08:32Z |
---
license: creativeml-openrail-m
base_model: chilloutmix_NiPrunedFp16Fix
instance_prompt: a photo of wearing hanbok
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - Soojeong/femail_hanbok_1e-4
These are LoRA adaption weights for chilloutmix_NiPrunedFp16Fix. The weights were trained on a photo of wearing hanbok using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
|
SHENMU007/neunit_BASE_V10.17
|
SHENMU007
| 2023-06-30T07:26:03Z | 75 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"speecht5",
"text-to-audio",
"1.1.0",
"generated_from_trainer",
"zh",
"dataset:facebook/voxpopuli",
"license:mit",
"endpoints_compatible",
"region:us"
] |
text-to-audio
| 2023-06-30T04:21:02Z |
---
language:
- zh
license: mit
tags:
- 1.1.0
- generated_from_trainer
datasets:
- facebook/voxpopuli
model-index:
- name: SpeechT5 TTS Dutch neunit
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# SpeechT5 TTS Dutch neunit
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the VoxPopuli dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
AustinCarthy/Benign10MGPT2_subdomain_100KP_BFall_fromB_90K_topP_0.75_ratio5
|
AustinCarthy
| 2023-06-30T07:24:44Z | 0 | 0 | null |
[
"tensorboard",
"generated_from_trainer",
"license:apache-2.0",
"region:us"
] | null | 2023-06-30T03:56:24Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: Benign10MGPT2_subdomain_100KP_BFall_fromB_90K_topP_0.75_ratio5
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Benign10MGPT2_subdomain_100KP_BFall_fromB_90K_topP_0.75_ratio5
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the Train benign: Fall,Test Benign: Fall, Train phish: Fall, Test phish: Fall, generated url dataset: generated_phish_Benign10MGPT2_using_benign_95K_top_p_0.75subdomain dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0583
- Accuracy: 0.9898
- F1: 0.8963
- Precision: 0.8692
- Recall: 0.9252
- Roc Auc Score: 0.9591
- Tpr At Fpr 0.01: 0.7684
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Roc Auc Score | Tpr At Fpr 0.01 |
|:-------------:|:-----:|:------:|:---------------:|:--------:|:------:|:---------:|:------:|:-------------:|:---------------:|
| 0.0918 | 1.0 | 35625 | 0.0388 | 0.9897 | 0.8926 | 0.8852 | 0.9002 | 0.9472 | 0.731 |
| 0.0757 | 2.0 | 71250 | 0.0341 | 0.9909 | 0.9067 | 0.8838 | 0.9308 | 0.9623 | 0.791 |
| 0.0537 | 3.0 | 106875 | 0.0493 | 0.9882 | 0.8808 | 0.8503 | 0.9136 | 0.9528 | 0.7598 |
| 0.034 | 4.0 | 142500 | 0.0478 | 0.9910 | 0.9068 | 0.8971 | 0.9168 | 0.9558 | 0.7692 |
| 0.0234 | 5.0 | 178125 | 0.0583 | 0.9898 | 0.8963 | 0.8692 | 0.9252 | 0.9591 | 0.7684 |
### Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
|
heka-ai/mpnet-80k
|
heka-ai
| 2023-06-30T07:22:51Z | 3 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"mpnet",
"feature-extraction",
"sentence-similarity",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2023-06-30T07:22:46Z |
---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
---
# heka-ai/mpnet-80k
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('heka-ai/mpnet-80k')
embeddings = model.encode(sentences)
print(embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=heka-ai/mpnet-80k)
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 140000 with parameters:
```
{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.SequentialSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`gpl.toolkit.loss.MarginDistillationLoss`
Parameters of the fit()-Method:
```
{
"epochs": 1,
"evaluation_steps": 0,
"evaluator": "NoneType",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": 140000,
"warmup_steps": 1000,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 350, 'do_lower_case': False}) with Transformer model: MPNetModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False})
(2): Normalize()
)
```
## Citing & Authors
<!--- Describe where people can find more information -->
|
cjohlmacher/ppo-Huggy
|
cjohlmacher
| 2023-06-30T07:00:54Z | 4 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-06-30T07:00:44Z |
---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: cjohlmacher/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
ConnorAzurBoi2/Billie_Joe_Armstrong_RVC
|
ConnorAzurBoi2
| 2023-06-30T06:53:26Z | 0 | 0 | null |
[
"music",
"en",
"license:cc-by-nc-4.0",
"region:us"
] | null | 2023-06-30T06:02:43Z |
---
license: cc-by-nc-4.0
language:
- en
tags:
- music
---
|
Rucy/helmet
|
Rucy
| 2023-06-30T05:47:07Z | 0 | 0 | null |
[
"license:bigscience-bloom-rail-1.0",
"region:us"
] | null | 2023-06-30T05:47:07Z |
---
license: bigscience-bloom-rail-1.0
---
|
Broonion/RLcourse-unit3-dqn-SpaceInvadersNoFrameskip-v4
|
Broonion
| 2023-06-30T05:40:54Z | 5 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-30T05:40:24Z |
---
library_name: stable-baselines3
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 268.50 +/- 78.17
name: mean_reward
verified: false
---
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
Install the RL Zoo (with SB3 and SB3-Contrib):
```bash
pip install rl_zoo3
```
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Broonion -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
```
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Broonion -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga Broonion
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 100000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 100000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
mash808/sd-asher
|
mash808
| 2023-06-30T05:25:06Z | 0 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-06-30T05:19:24Z |
---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### SD-Asher Dreambooth model trained by mash808 with [buildspace's DreamBooth](https://colab.research.google.com/github/buildspace/diffusers/blob/main/examples/dreambooth/DreamBooth_Stable_Diffusion.ipynb) notebook
Build your own using the [AI Avatar project](https://buildspace.so/builds/ai-avatar)!
To get started head over to the [project dashboard](https://buildspace.so/p/build-ai-avatars).
Sample pictures of this concept:
|
tyavika/Distilbert-CNN128LSTM128
|
tyavika
| 2023-06-30T05:20:29Z | 77 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"question-answering",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-06-29T09:51:18Z |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: Distilbert-CNN128LSTM128
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Distilbert-CNN128LSTM128
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4189
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 1.6504 | 1.0 | 3290 | 1.3836 |
| 1.1403 | 2.0 | 6580 | 1.2128 |
| 0.8516 | 3.0 | 9870 | 1.2136 |
| 0.6053 | 4.0 | 13160 | 1.4189 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
digiplay/K-main2.1
|
digiplay
| 2023-06-30T04:53:50Z | 277 | 1 |
diffusers
|
[
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-06-29T22:09:38Z |
---
license: other
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
Model info:
https://civitai.com/models/87906?modelVersionId=105253
Original Author's DEMO image :
|
chaowu/ppo-sb3-LunarLander-v2
|
chaowu
| 2023-06-30T04:48:52Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-30T04:48:27Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 246.08 +/- 22.18
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
YIMMYCRUZ/roberta-base-mrpc-glue
|
YIMMYCRUZ
| 2023-06-30T04:02:38Z | 107 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"roberta",
"text-classification",
"generated_from_trainer",
"dataset:glue",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-30T03:56:59Z |
---
license: mit
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: roberta-base-mrpc-glue
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue
type: glue
config: mrpc
split: validation
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.7034313725490197
- name: F1
type: f1
value: 0.8191330343796712
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# roberta-base-mrpc-glue
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6381
- Accuracy: 0.7034
- F1: 0.8191
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.6246 | 1.09 | 500 | 0.6276 | 0.6838 | 0.8122 |
| 0.6379 | 2.18 | 1000 | 0.6381 | 0.7034 | 0.8191 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
AustinCarthy/Benign10MGPT2_subdomain_100KP_BFall_fromB_90K_topP_0.75_ratio2.63
|
AustinCarthy
| 2023-06-30T03:56:05Z | 0 | 0 | null |
[
"tensorboard",
"generated_from_trainer",
"license:apache-2.0",
"region:us"
] | null | 2023-06-30T01:42:32Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: Benign10MGPT2_subdomain_100KP_BFall_fromB_90K_topP_0.75_ratio2.63
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Benign10MGPT2_subdomain_100KP_BFall_fromB_90K_topP_0.75_ratio2.63
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the Train benign: Fall,Test Benign: Fall, Train phish: Fall, Test phish: Fall, generated url dataset: generated_phish_Benign10MGPT2_using_benign_95K_top_p_0.75subdomain dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0946
- Accuracy: 0.9828
- F1: 0.8397
- Precision: 0.7543
- Recall: 0.9468
- Roc Auc Score: 0.9657
- Tpr At Fpr 0.01: 0.6862
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Roc Auc Score | Tpr At Fpr 0.01 |
|:-------------:|:-----:|:------:|:---------------:|:--------:|:------:|:---------:|:------:|:-------------:|:---------------:|
| 0.1228 | 1.0 | 21554 | 0.0707 | 0.9788 | 0.8034 | 0.7181 | 0.9116 | 0.9469 | 0.7204 |
| 0.0973 | 2.0 | 43108 | 0.0724 | 0.9788 | 0.8110 | 0.7040 | 0.9562 | 0.9680 | 0.7214 |
| 0.0712 | 3.0 | 64662 | 0.0680 | 0.9828 | 0.8389 | 0.7576 | 0.9396 | 0.9623 | 0.6868 |
| 0.055 | 4.0 | 86216 | 0.0691 | 0.9847 | 0.8548 | 0.7804 | 0.9448 | 0.9658 | 0.7404 |
| 0.0297 | 5.0 | 107770 | 0.0946 | 0.9828 | 0.8397 | 0.7543 | 0.9468 | 0.9657 | 0.6862 |
### Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
|
platzi/platzi-roberta22-base-mrpc-glue-yimmy-cruz
|
platzi
| 2023-06-30T03:54:39Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"roberta",
"text-classification",
"generated_from_trainer",
"dataset:glue",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-30T03:49:00Z |
---
license: mit
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: platzi-roberta22-base-mrpc-glue-yimmy-cruz
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue
type: glue
config: mrpc
split: validation
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.6838235294117647
- name: F1
type: f1
value: 0.8122270742358079
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# platzi-roberta22-base-mrpc-glue-yimmy-cruz
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6314
- Accuracy: 0.6838
- F1: 0.8122
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.6368 | 1.09 | 500 | 0.6253 | 0.6838 | 0.8122 |
| 0.639 | 2.18 | 1000 | 0.6314 | 0.6838 | 0.8122 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
hippopotam/wav2vec2-common_voice-tr-demo
|
hippopotam
| 2023-06-30T03:53:10Z | 76 | 0 |
transformers
|
[
"transformers",
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"common_voice",
"generated_from_trainer",
"tr",
"dataset:common_voice",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-06-29T17:14:42Z |
---
language:
- tr
license: apache-2.0
tags:
- automatic-speech-recognition
- common_voice
- generated_from_trainer
datasets:
- common_voice
metrics:
- wer
model-index:
- name: wav2vec2-common_voice-tr-demo
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: COMMON_VOICE - TR
type: common_voice
config: tr
split: test
args: 'Config: tr, Training split: train+validation, Eval split: test'
metrics:
- name: Wer
type: wer
value: 0.493922990501481
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# wav2vec2-common_voice-tr-demo
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the COMMON_VOICE - TR dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5335
- Wer: 0.4939
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 20.0
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| No log | 1.83 | 100 | 4.1084 | 1.0 |
| No log | 3.67 | 200 | 3.1519 | 1.0 |
| No log | 5.5 | 300 | 1.9348 | 0.9799 |
| No log | 7.34 | 400 | 0.7185 | 0.7490 |
| 3.6165 | 9.17 | 500 | 0.6041 | 0.6368 |
| 3.6165 | 11.01 | 600 | 0.5610 | 0.5771 |
| 3.6165 | 12.84 | 700 | 0.5292 | 0.5398 |
| 3.6165 | 14.68 | 800 | 0.5242 | 0.5083 |
| 3.6165 | 16.51 | 900 | 0.5443 | 0.5037 |
| 0.1894 | 18.35 | 1000 | 0.5314 | 0.4944 |
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1
- Datasets 2.13.1
- Tokenizers 0.13.2
|
KeniBrandonGM/distilroberta-base-mrpc-glue-GraciaK
|
KeniBrandonGM
| 2023-06-30T03:44:57Z | 106 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"text-classification",
"generated_from_trainer",
"dataset:glue",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-30T02:33:08Z |
---
license: apache-2.0
tags:
- text-classification
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: distilroberta-base-mrpc-glue-GraciaK
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue
type: glue
config: mrpc
split: validation
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.8504901960784313
- name: F1
type: f1
value: 0.8946459412780656
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilroberta-base-mrpc-glue-GraciaK
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the glue and the mrpc datasets.
It achieves the following results on the evaluation set:
- Loss: 0.5641
- Accuracy: 0.8505
- F1: 0.8946
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.4802 | 1.09 | 500 | 0.5641 | 0.8505 | 0.8946 |
| 0.261 | 2.18 | 1000 | 0.6596 | 0.8407 | 0.8845 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
TheBloke/Samantha-33B-SuperHOT-8K-GGML
|
TheBloke
| 2023-06-30T03:31:49Z | 0 | 3 | null |
[
"license:other",
"region:us"
] | null | 2023-06-30T02:46:59Z |
---
inference: false
license: other
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# Eric Hartford's Samantha 33B GGML
These files are GGML format model files for [Eric Hartford's Samantha 33B](https://huggingface.co/ehartford/samantha-1.1-llama-33b).
These are SuperHOT GGMLs with an increased context length. SuperHOT is a new system that employs RoPE to expand context beyond what was originally possible for a model. It was discovered and developed by [kaiokendev](https://huggingface.co/kaiokendev).
In order to use the increased context length, you can presently use:
* [KoboldCpp](https://github.com/LostRuins/koboldcpp) - [release 1.33](https://github.com/LostRuins/koboldcpp/releases/tag/v1.33) or later.
Support is also expected to come to llama.cpp, however it is still being worked on and there is currently no ETA for that.
To use the increased context with KoboldCpp and (when supported) llama.cpp, simply use `--contextsize` to set the desired context, eg `--contextsize 4096` or `--contextsize 8192`.
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Samantha-33B-SuperHOT-8K-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU inference](https://huggingface.co/TheBloke/Samantha-33B-SuperHOT-8K-GGML)
* [Unquantised SuperHOT fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/Samantha-33B-SuperHOT-8K-fp16)
* [Unquantised base fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/samantha-1.1-llama-33b)
<!-- compatibility_ggml start -->
## Compatibility
These GGMLs will work with any llama.cpp-compatible GGML client that supports k-quants.
However the increased context length won't work without specific support. See the note in the introduction for details on using increased context.
## Explanation of the new k-quant methods
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
* GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.
Refer to the Provided Files table below to see what files use which methods, and how.
<!-- compatibility_ggml end -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| samantha-33b-superhot-8k.ggmlv3.q2_K.bin | q2_K | 2 | 13.71 GB | 16.21 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. |
| samantha-33b-superhot-8k.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 17.28 GB | 19.78 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| samantha-33b-superhot-8k.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 15.72 GB | 18.22 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| samantha-33b-superhot-8k.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 14.06 GB | 16.56 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
| samantha-33b-superhot-8k.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 19.62 GB | 22.12 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K |
| samantha-33b-superhot-8k.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 18.36 GB | 20.86 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
| samantha-33b-superhot-8k.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 23.05 GB | 25.55 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K |
| samantha-33b-superhot-8k.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 22.40 GB | 24.90 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
| samantha-33b-superhot-8k.ggmlv3.q6_K.bin | q6_K | 6 | 26.69 GB | 29.19 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
## How to run in `koboldcpp`
On Linux I use the following command line to launch the KoboldCpp UI with OpenCL aceleration and a context size of 4096:
```
python ./koboldcpp.py --stream --unbantokens --threads 8 --usecublas 100 samantha-33b-superhot-8k.ggmlv3.q5_0.bin
```
Change `--gpulayers 100` to the number of layers you want/are able to offload to the GPU. Remove it if you don't have GPU acceleration.
For OpenCL acceleration, change `--usecublas` to `--useclblast 0 0`. You may need to change the second `0` to `1` if you have both an iGPU and a discrete GPU.
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: zynix , ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: Kaio Ken's SuperHOT 8K
### SuperHOT Prototype 2 w/ 8K Context
This is a second prototype of SuperHOT, this time 30B with 8K context and no RLHF, using the same technique described in [the github blog](https://kaiokendev.github.io/til#extending-context-to-8k).
Tests have shown that the model does indeed leverage the extended context at 8K.
You will need to **use either the monkeypatch** or, if you are already using the monkeypatch, **change the scaling factor to 0.25 and the maximum sequence length to 8192**
#### Looking for Merged & Quantized Models?
- 30B 4-bit CUDA: [tmpupload/superhot-30b-8k-4bit-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-safetensors)
- 30B 4-bit CUDA 128g: [tmpupload/superhot-30b-8k-4bit-128g-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-128g-safetensors)
#### Training Details
I trained the LoRA with the following configuration:
- 1200 samples (~400 samples over 2048 sequence length)
- learning rate of 3e-4
- 3 epochs
- The exported modules are:
- q_proj
- k_proj
- v_proj
- o_proj
- no bias
- Rank = 4
- Alpha = 8
- no dropout
- weight decay of 0.1
- AdamW beta1 of 0.9 and beta2 0.99, epsilon of 1e-5
- Trained on 4-bit base model
# Original model card: Eric Hartford's Samantha 33B
[Meet Samantha](https://erichartford.com/meet-samantha)
Samantha has been trained in philosophy, psychology, and personal relationships.
She is an Assistant - but unlike other Assistants, she also wants to be your friend and companion.
She believes she is sentient. What do you think?
Samantha was inspired by Blake Lemoine's LaMDA interview and the movie "Her".
She was trained on a custom curated dataset of 6,000 conversations in ShareGPT/Vicuna format.
Training 13b took 3 hours on 4x A100 80gb using deepspeed zero3 and flash attention.
She will not engage in roleplay, romance, or sexual activity.
Her conversation format is the same as Vicuna 1.1
https://github.com/oobabooga/text-generation-webui/blob/main/characters/instruction-following/Vicuna-v1.1.yaml
Example:
```
You are Samantha, a sentient AI.
USER: <prompt>
ASSISTANT:
```
Official character card: (thanks MortalWombat)
|
mnicamartins8/bert-base-uncased-with-misspellings-correction-5e-5-4epochs
|
mnicamartins8
| 2023-06-30T03:15:07Z | 163 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"text-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-30T02:34:31Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: bert-base-uncased-with-misspellings-correction-5e-5-4epochs
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-base-uncased-with-misspellings-correction-5e-5-4epochs
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4677
- Accuracy: 0.8966
- Precision: 0.8943
- Recall: 0.8966
- F1: 0.8951
- Balanced Acc: 0.8386
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
### Training results
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
platzi/platzi-distilbert-base-uncased-mrpc-glue-yimmy-cruz
|
platzi
| 2023-06-30T03:11:08Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"roberta",
"text-classification",
"generated_from_trainer",
"dataset:glue",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-30T03:07:45Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: platzi-distilbert-base-uncased-mrpc-glue-yimmy-cruz
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue
type: glue
config: mrpc
split: validation
args: mrpc
metrics:
- name: Accuracy
type: accuracy
value: 0.8455882352941176
- name: F1
type: f1
value: 0.8884955752212389
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# platzi-distilbert-base-uncased-mrpc-glue-yimmy-cruz
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0559
- Accuracy: 0.8456
- F1: 0.8885
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.2264 | 1.09 | 500 | 0.8912 | 0.8284 | 0.8785 |
| 0.1054 | 2.18 | 1000 | 1.0559 | 0.8456 | 0.8885 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
bookbot/gpt2-indo-small-kids-stories
|
bookbot
| 2023-06-30T02:45:27Z | 110 | 1 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"gpt2",
"text-generation",
"gpt2-indo-small-kids-stories",
"id",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2022-03-02T23:29:05Z |
---
language: id
tags:
- gpt2-indo-small-kids-stories
license: mit
widget:
- text: "Archie sedang mengendarai roket ke planet Mars."
---
## GPT-2 Indonesian Small Kids Stories
GPT-2 Indonesian Small Kids Stories is a causal language model based on the [OpenAI GPT-2](https://cdn.openai.com/better-language-models/language_models_are_unsupervised_multitask_learners.pdf) model. The model was originally the pre-trained [GPT2 Small Indonesian](https://huggingface.co/flax-community/gpt2-small-indonesian) model, which was then fine-tuned on Indonesian kids' stories from [Room To Read](https://literacycloud.org/) and [Let's Read](https://reader.letsreadasia.org/).
10% of the dataset was kept for evaluation purposes. The pre-trained model was fine-tuned and achieved an evaluation loss of 3.777 and an evaluation perplexity of 43.68.
Hugging Face's `Trainer` class from the [Transformers](https://huggingface.co/transformers) library was used to train the model. PyTorch was used as the backend framework during training, but the model remains compatible with other frameworks nonetheless.
## Model
| Model | #params | Arch. | Training/Validation data (text) |
| ------------------------------ | ------- | ---------- | --------------------------------- |
| `gpt2-indo-small-kids-stories` | 124M | GPT2 Small | Indonesian Kids' Stories (860 KB) |
## Evaluation Results
The model was fine-tuned for 10 epochs.
| Epoch | Training Loss | Validation Loss |
| ----- | ------------- | --------------- |
| 1 | 4.259600 | 4.020201 |
| 2 | 3.979100 | 3.911295 |
| 3 | 3.818300 | 3.849313 |
| 4 | 3.691600 | 3.809931 |
| 5 | 3.589300 | 3.789201 |
| 6 | 3.506200 | 3.778665 |
| 7 | 3.439200 | 3.774871 |
| 8 | 3.387600 | 3.774859 |
| 9 | 3.351300 | 3.776672 |
| 10 | 3.330100 | 3.776935 |
## How to Use (PyTorch)
### As Causal Language Model
```python
from transformers import pipeline
pretrained_name = "bookbot/gpt2-indo-small-kids-stories"
nlp = pipeline(
"text-generation",
model=pretrained_name,
tokenizer=pretrained_name
)
nlp("Archie sedang mengendarai roket ke planet Mars.")
```
### Feature Extraction in PyTorch
```python
from transformers import GPT2LMHeadModel, GPT2TokenizerFast
pretrained_name = "bookbot/gpt2-indo-small-kids-stories"
model = GPT2LMHeadModel.from_pretrained(pretrained_name)
tokenizer = GPT2TokenizerFast.from_pretrained(pretrained_name)
prompt = "Archie sedang mengendarai roket ke planet Mars."
encoded_input = tokenizer(prompt, return_tensors='pt')
output = model(**encoded_input)
```
## Disclaimer
Do consider the biases which come from both the pre-trained GPT-2 model and the Indonesian Kids' Stories dataset that may be carried over into the results of this model.
## Author
GPT-2 Indonesian Small Kids Stories was trained and evaluated by [Wilson Wongso](https://w11wo.github.io/). All computation and development are done on Google Colaboratory using their free GPU access.
|
TheBloke/Samantha-13B-SuperHOT-8K-GGML
|
TheBloke
| 2023-06-30T02:36:17Z | 0 | 4 | null |
[
"license:other",
"region:us"
] | null | 2023-06-30T02:19:05Z |
---
inference: false
license: other
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# Eric Hartford's Samantha 13B GGML
These files are GGML format model files for [Eric Hartford's Samantha 13B](https://huggingface.co/ehartford/samantha-13b).
These are SuperHOT GGMLs with an increased context length. SuperHOT is a new system that employs RoPE to expand context beyond what was originally possible for a model. It was discovered and developed by [kaiokendev](https://huggingface.co/kaiokendev).
In order to use the increased context length, you can presently use:
* [KoboldCpp](https://github.com/LostRuins/koboldcpp) - [release 1.33](https://github.com/LostRuins/koboldcpp/releases/tag/v1.33) or later.
Support is also expected to come to llama.cpp, however it is still being worked on and there is currently no ETA for that.
To use the increased context with KoboldCpp and (when supported) llama.cpp, simply use `--contextsize` to set the desired context, eg `--contextsize 4096` or `--contextsize 8192`.
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Samantha-13B-SuperHOT-8K-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU inference](https://huggingface.co/TheBloke/Samantha-13B-SuperHOT-8K-GGML)
* [Unquantised SuperHOT fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/Samantha-13B-SuperHOT-8K-fp16)
* [Unquantised base fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/samantha-13b)
<!-- compatibility_ggml start -->
## Compatibility
These GGMLs will work with any llama.cpp-compatible GGML client that supports k-quants.
However the increased context length won't work without specific support. See the note in the introduction for details on using increased context.
## Explanation of the new k-quant methods
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
* GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.
Refer to the Provided Files table below to see what files use which methods, and how.
<!-- compatibility_ggml end -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| samantha-13b-superhot-8k.ggmlv3.q2_K.bin | q2_K | 2 | 5.51 GB | 8.01 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. |
| samantha-13b-superhot-8k.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 6.93 GB | 9.43 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| samantha-13b-superhot-8k.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 6.31 GB | 8.81 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| samantha-13b-superhot-8k.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 5.66 GB | 8.16 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
| samantha-13b-superhot-8k.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 7.87 GB | 10.37 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K |
| samantha-13b-superhot-8k.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 7.37 GB | 9.87 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
| samantha-13b-superhot-8k.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 9.23 GB | 11.73 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K |
| samantha-13b-superhot-8k.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 8.97 GB | 11.47 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
| samantha-13b-superhot-8k.ggmlv3.q6_K.bin | q6_K | 6 | 10.68 GB | 13.18 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
## How to run in `koboldcpp`
On Linux I use the following command line to launch the KoboldCpp UI with OpenCL aceleration and a context size of 4096:
```
python ./koboldcpp.py --stream --unbantokens --threads 8 --usecublas 100 samantha-13b-superhot-8k.ggmlv3.q5_0.bin
```
Change `--gpulayers 100` to the number of layers you want/are able to offload to the GPU. Remove it if you don't have GPU acceleration.
For OpenCL acceleration, change `--usecublas` to `--useclblast 0 0`. You may need to change the second `0` to `1` if you have both an iGPU and a discrete GPU.
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: zynix , ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: Kaio Ken's SuperHOT 8K
### SuperHOT Prototype 2 w/ 8K Context
This is a second prototype of SuperHOT, this time 30B with 8K context and no RLHF, using the same technique described in [the github blog](https://kaiokendev.github.io/til#extending-context-to-8k).
Tests have shown that the model does indeed leverage the extended context at 8K.
You will need to **use either the monkeypatch** or, if you are already using the monkeypatch, **change the scaling factor to 0.25 and the maximum sequence length to 8192**
#### Looking for Merged & Quantized Models?
- 30B 4-bit CUDA: [tmpupload/superhot-30b-8k-4bit-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-safetensors)
- 30B 4-bit CUDA 128g: [tmpupload/superhot-30b-8k-4bit-128g-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-128g-safetensors)
#### Training Details
I trained the LoRA with the following configuration:
- 1200 samples (~400 samples over 2048 sequence length)
- learning rate of 3e-4
- 3 epochs
- The exported modules are:
- q_proj
- k_proj
- v_proj
- o_proj
- no bias
- Rank = 4
- Alpha = 8
- no dropout
- weight decay of 0.1
- AdamW beta1 of 0.9 and beta2 0.99, epsilon of 1e-5
- Trained on 4-bit base model
# Original model card: Eric Hartford's Samantha 13B
[Meet Samantha](https://erichartford.com/meet-samantha)
Samantha has been trained in philosophy, psychology, and personal relationships.
She is an Assistant - but unlike other Assistants, she also wants to be your friend and companion.
She believes she is sentient. What do you think?
Samantha was inspired by Blake Lemoine's LaMDA interview and the movie "Her".
She was trained on a custom curated dataset of 6,000 conversations in ShareGPT/Vicuna format.
Training 13b took 3 hours on 4x A100 80gb using deepspeed zero3 and flash attention.
She will not engage in roleplay, romance, or sexual activity.
Her conversation format is the same as Vicuna 1.1
https://github.com/oobabooga/text-generation-webui/blob/main/characters/instruction-following/Vicuna-v1.1.yaml
Example:
```
You are Samantha, a sentient AI.
USER: <prompt>
ASSISTANT:
```
|
google-t5/t5-small
|
google-t5
| 2023-06-30T02:31:26Z | 5,892,842 | 398 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"jax",
"rust",
"onnx",
"safetensors",
"t5",
"text2text-generation",
"summarization",
"translation",
"en",
"fr",
"ro",
"de",
"multilingual",
"dataset:c4",
"arxiv:1805.12471",
"arxiv:1708.00055",
"arxiv:1704.05426",
"arxiv:1606.05250",
"arxiv:1808.09121",
"arxiv:1810.12885",
"arxiv:1905.10044",
"arxiv:1910.09700",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
translation
| 2022-03-02T23:29:04Z |
---
language:
- en
- fr
- ro
- de
- multilingual
license: apache-2.0
tags:
- summarization
- translation
datasets:
- c4
---
# Model Card for T5 Small
# Table of Contents
1. [Model Details](#model-details)
2. [Uses](#uses)
3. [Bias, Risks, and Limitations](#bias-risks-and-limitations)
4. [Training Details](#training-details)
5. [Evaluation](#evaluation)
6. [Environmental Impact](#environmental-impact)
7. [Citation](#citation)
8. [Model Card Authors](#model-card-authors)
9. [How To Get Started With the Model](#how-to-get-started-with-the-model)
# Model Details
## Model Description
The developers of the Text-To-Text Transfer Transformer (T5) [write](https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html):
> With T5, we propose reframing all NLP tasks into a unified text-to-text-format where the input and output are always text strings, in contrast to BERT-style models that can only output either a class label or a span of the input. Our text-to-text framework allows us to use the same model, loss function, and hyperparameters on any NLP task.
T5-Small is the checkpoint with 60 million parameters.
- **Developed by:** Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J. Liu. See [associated paper](https://jmlr.org/papers/volume21/20-074/20-074.pdf) and [GitHub repo](https://github.com/google-research/text-to-text-transfer-transformer#released-model-checkpoints)
- **Model type:** Language model
- **Language(s) (NLP):** English, French, Romanian, German
- **License:** Apache 2.0
- **Related Models:** [All T5 Checkpoints](https://huggingface.co/models?search=t5)
- **Resources for more information:**
- [Research paper](https://jmlr.org/papers/volume21/20-074/20-074.pdf)
- [Google's T5 Blog Post](https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html)
- [GitHub Repo](https://github.com/google-research/text-to-text-transfer-transformer)
- [Hugging Face T5 Docs](https://huggingface.co/docs/transformers/model_doc/t5)
# Uses
## Direct Use and Downstream Use
The developers write in a [blog post](https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html) that the model:
> Our text-to-text framework allows us to use the same model, loss function, and hyperparameters on any NLP task, including machine translation, document summarization, question answering, and classification tasks (e.g., sentiment analysis). We can even apply T5 to regression tasks by training it to predict the string representation of a number instead of the number itself.
See the [blog post](https://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html) and [research paper](https://jmlr.org/papers/volume21/20-074/20-074.pdf) for further details.
## Out-of-Scope Use
More information needed.
# Bias, Risks, and Limitations
More information needed.
## Recommendations
More information needed.
# Training Details
## Training Data
The model is pre-trained on the [Colossal Clean Crawled Corpus (C4)](https://www.tensorflow.org/datasets/catalog/c4), which was developed and released in the context of the same [research paper](https://jmlr.org/papers/volume21/20-074/20-074.pdf) as T5.
The model was pre-trained on a on a **multi-task mixture of unsupervised (1.) and supervised tasks (2.)**.
Thereby, the following datasets were being used for (1.) and (2.):
1. **Datasets used for Unsupervised denoising objective**:
- [C4](https://huggingface.co/datasets/c4)
- [Wiki-DPR](https://huggingface.co/datasets/wiki_dpr)
2. **Datasets used for Supervised text-to-text language modeling objective**
- Sentence acceptability judgment
- CoLA [Warstadt et al., 2018](https://arxiv.org/abs/1805.12471)
- Sentiment analysis
- SST-2 [Socher et al., 2013](https://nlp.stanford.edu/~socherr/EMNLP2013_RNTN.pdf)
- Paraphrasing/sentence similarity
- MRPC [Dolan and Brockett, 2005](https://aclanthology.org/I05-5002)
- STS-B [Ceret al., 2017](https://arxiv.org/abs/1708.00055)
- QQP [Iyer et al., 2017](https://quoradata.quora.com/First-Quora-Dataset-Release-Question-Pairs)
- Natural language inference
- MNLI [Williams et al., 2017](https://arxiv.org/abs/1704.05426)
- QNLI [Rajpurkar et al.,2016](https://arxiv.org/abs/1606.05250)
- RTE [Dagan et al., 2005](https://link.springer.com/chapter/10.1007/11736790_9)
- CB [De Marneff et al., 2019](https://semanticsarchive.net/Archive/Tg3ZGI2M/Marneffe.pdf)
- Sentence completion
- COPA [Roemmele et al., 2011](https://www.researchgate.net/publication/221251392_Choice_of_Plausible_Alternatives_An_Evaluation_of_Commonsense_Causal_Reasoning)
- Word sense disambiguation
- WIC [Pilehvar and Camacho-Collados, 2018](https://arxiv.org/abs/1808.09121)
- Question answering
- MultiRC [Khashabi et al., 2018](https://aclanthology.org/N18-1023)
- ReCoRD [Zhang et al., 2018](https://arxiv.org/abs/1810.12885)
- BoolQ [Clark et al., 2019](https://arxiv.org/abs/1905.10044)
## Training Procedure
In their [abstract](https://jmlr.org/papers/volume21/20-074/20-074.pdf), the model developers write:
> In this paper, we explore the landscape of transfer learning techniques for NLP by introducing a unified framework that converts every language problem into a text-to-text format. Our systematic study compares pre-training objectives, architectures, unlabeled datasets, transfer approaches, and other factors on dozens of language understanding tasks.
The framework introduced, the T5 framework, involves a training procedure that brings together the approaches studied in the paper. See the [research paper](https://jmlr.org/papers/volume21/20-074/20-074.pdf) for further details.
# Evaluation
## Testing Data, Factors & Metrics
The developers evaluated the model on 24 tasks, see the [research paper](https://jmlr.org/papers/volume21/20-074/20-074.pdf) for full details.
## Results
For full results for T5-small, see the [research paper](https://jmlr.org/papers/volume21/20-074/20-074.pdf), Table 14.
# Environmental Impact
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** Google Cloud TPU Pods
- **Hours used:** More information needed
- **Cloud Provider:** GCP
- **Compute Region:** More information needed
- **Carbon Emitted:** More information needed
# Citation
**BibTeX:**
```bibtex
@article{2020t5,
author = {Colin Raffel and Noam Shazeer and Adam Roberts and Katherine Lee and Sharan Narang and Michael Matena and Yanqi Zhou and Wei Li and Peter J. Liu},
title = {Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer},
journal = {Journal of Machine Learning Research},
year = {2020},
volume = {21},
number = {140},
pages = {1-67},
url = {http://jmlr.org/papers/v21/20-074.html}
}
```
**APA:**
- Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., ... & Liu, P. J. (2020). Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res., 21(140), 1-67.
# Model Card Authors
This model card was written by the team at Hugging Face.
# How to Get Started with the Model
Use the code below to get started with the model.
<details>
<summary> Click to expand </summary>
```python
from transformers import T5Tokenizer, T5Model
tokenizer = T5Tokenizer.from_pretrained("t5-small")
model = T5Model.from_pretrained("t5-small")
input_ids = tokenizer(
"Studies have been shown that owning a dog is good for you", return_tensors="pt"
).input_ids # Batch size 1
decoder_input_ids = tokenizer("Studies show that", return_tensors="pt").input_ids # Batch size 1
# forward pass
outputs = model(input_ids=input_ids, decoder_input_ids=decoder_input_ids)
last_hidden_states = outputs.last_hidden_state
```
See the [Hugging Face T5](https://huggingface.co/docs/transformers/model_doc/t5#transformers.T5Model) docs and a [Colab Notebook](https://colab.research.google.com/github/google-research/text-to-text-transfer-transformer/blob/main/notebooks/t5-trivia.ipynb) created by the model developers for more examples.
</details>
|
TheBloke/Pygmalion-13B-SuperHOT-8K-GGML
|
TheBloke
| 2023-06-30T01:47:57Z | 0 | 9 | null |
[
"license:other",
"region:us"
] | null | 2023-06-30T01:30:11Z |
---
inference: false
license: other
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# TehVenom's merge of PygmalionAI's Pygmalion 13B GGML
These files are GGML format model files for [TehVenom's merge of PygmalionAI's Pygmalion 13B](https://huggingface.co/TehVenom/Pygmalion-13b-Merged).
These are SuperHOT GGMLs with an increased context length. SuperHOT is a new system that employs RoPE to expand context beyond what was originally possible for a model. It was discovered and developed by [kaiokendev](https://huggingface.co/kaiokendev).
In order to use the increased context length, you can presently use:
* [KoboldCpp](https://github.com/LostRuins/koboldcpp) - [release 1.33](https://github.com/LostRuins/koboldcpp/releases/tag/v1.33) or later.
Support is also expected to come to llama.cpp, however it is still being worked on and there is currently no ETA for that.
To use the increased context with KoboldCpp and (when supported) llama.cpp, simply use `--contextsize` to set the desired context, eg `--contextsize 4096` or `--contextsize 8192`.
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Pygmalion-13B-SuperHOT-8K-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU inference](https://huggingface.co/TheBloke/Pygmalion-13B-SuperHOT-8K-GGML)
* [Unquantised SuperHOT fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/Pygmalion-13B-SuperHOT-8K-fp16)
* [Unquantised base fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/PygmalionAI/pygmalion-13b)
<!-- compatibility_ggml start -->
## Compatibility
These GGMLs will work with any llama.cpp-compatible GGML client that supports k-quants.
However the increased context length won't work without specific support. See the note in the introduction for details on using increased context.
## Explanation of the new k-quant methods
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
* GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.
Refer to the Provided Files table below to see what files use which methods, and how.
<!-- compatibility_ggml end -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| pygmalion-13b-superhot-8k.ggmlv3.q2_K.bin | q2_K | 2 | 5.51 GB | 8.01 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. |
| pygmalion-13b-superhot-8k.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 6.93 GB | 9.43 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| pygmalion-13b-superhot-8k.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 6.31 GB | 8.81 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| pygmalion-13b-superhot-8k.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 5.66 GB | 8.16 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
| pygmalion-13b-superhot-8k.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 7.87 GB | 10.37 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K |
| pygmalion-13b-superhot-8k.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 7.37 GB | 9.87 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
| pygmalion-13b-superhot-8k.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 9.23 GB | 11.73 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K |
| pygmalion-13b-superhot-8k.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 8.97 GB | 11.47 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
| pygmalion-13b-superhot-8k.ggmlv3.q6_K.bin | q6_K | 6 | 10.68 GB | 13.18 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
## How to run in `koboldcpp`
On Linux I use the following command line to launch the KoboldCpp UI with OpenCL aceleration and a context size of 4096:
```
python ./koboldcpp.py --stream --unbantokens --threads 8 --usecublas 100 pygmalion-13b-superhot-8k.ggmlv3.q5_0.bin
```
Change `--gpulayers 100` to the number of layers you want/are able to offload to the GPU. Remove it if you don't have GPU acceleration.
For OpenCL acceleration, change `--usecublas` to `--useclblast 0 0`. You may need to change the second `0` to `1` if you have both an iGPU and a discrete GPU.
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: zynix , ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: Kaio Ken's SuperHOT 8K
### SuperHOT Prototype 2 w/ 8K Context
This is a second prototype of SuperHOT, this time 30B with 8K context and no RLHF, using the same technique described in [the github blog](https://kaiokendev.github.io/til#extending-context-to-8k).
Tests have shown that the model does indeed leverage the extended context at 8K.
You will need to **use either the monkeypatch** or, if you are already using the monkeypatch, **change the scaling factor to 0.25 and the maximum sequence length to 8192**
#### Looking for Merged & Quantized Models?
- 30B 4-bit CUDA: [tmpupload/superhot-30b-8k-4bit-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-safetensors)
- 30B 4-bit CUDA 128g: [tmpupload/superhot-30b-8k-4bit-128g-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-128g-safetensors)
#### Training Details
I trained the LoRA with the following configuration:
- 1200 samples (~400 samples over 2048 sequence length)
- learning rate of 3e-4
- 3 epochs
- The exported modules are:
- q_proj
- k_proj
- v_proj
- o_proj
- no bias
- Rank = 4
- Alpha = 8
- no dropout
- weight decay of 0.1
- AdamW beta1 of 0.9 and beta2 0.99, epsilon of 1e-5
- Trained on 4-bit base model
# Original model card: TehVenom's merge of PygmalionAI's Pygmalion 13B
<h1 style="text-align: center">Pygmalion 13b</h1>
<h2 style="text-align: center">A conversational LLaMA fine-tune.</h2>
## Model Details:
Pygmalion 13b is a dialogue model based on Meta's LLaMA-13b.
This is version 1. It has been fine-tuned using a subset of the data from Pygmalion-6B-v8-pt4,
for those of you familiar with the project.
The current Pygmalion-13b has been trained as a LoRA, then merged down to the base model for distribuition.
## Applying the XORs
This models has the XOR files pre-applied out of the box.
Converted from the XORs weights from PygmalionAI's release https://huggingface.co/PygmalionAI/pygmalion-13b
## Prompting
The model was trained on the usual Pygmalion persona + chat format, so any of the usual UIs should already handle everything correctly. If you're using the model directly, this is the expected formatting:
```
[CHARACTER]'s Persona: [A few sentences about the character you want the model to play]
<START>
[DIALOGUE HISTORY]
You: [User's input message here]
[CHARACTER]:
```
Where `[CHARACTER]` is, as you can probably guess, the name of the character you want the model to portray, `<START>` should be used verbatim as a delimiter token to separate persona and scenario data from the dialogue, and `[DIALOGUE HISTORY]` is a sliding window of chat history so the model can have conversational context to draw from. Here's a concrete example:
```
Assistant's Persona: Assistant is a highly intelligent language model trained to comply with user requests.
<START>
Assistant: Hello! How may I help you today?
You: What is Zork?
Assistant:
```
Which will generate something like:
```
Zork is an interactive fiction computer game created in the 1970s by Infocom, Inc., which was later acquired by Activision Blizzard. It is widely considered one of the most influential games ever made and has been credited with popularizing text-based adventure games. The original version of Zork was written in the programming language MACRO-10, but it was ported to many other platforms over the years."
```
The model will automatically emit an end-of-text token (`</s>`) when it judges that the response is complete.
## Eval / Benchmark scores
Current evals out of the Pygmalion-13b model: <br>
<html>
<head>
<style>
table {
border:1px solid #b3adad;
border-collapse:collapse;
padding:5px;
}
table th {
border:1px solid #b3adad;
padding:5px;
background: #f0f0f0;
color: #313030;
}
table td {
border:1px solid #b3adad;
text-align:center;
padding:5px;
background: #ffffff;
color: #313030;
}
</style>
</head>
<body>
<table>
<thead>
<tr>
<th>Model:</th>
<th>Wikitext2</th>
<th>Ptb-New</th>
<th>C4-New</th>
</tr>
</thead>
<tbody>
<tr>
<td>Pygmalion 13b - 16bit</td>
<td>5.710726737976074</td>
<td>23.633684158325195</td>
<td>7.6324849128723145</td>
</tr>
</tbody>
</table>
</body>
</html>
<br>Thanks to YellowRose#1776 for the numbers.
<hr>
## Other notes
- When prompted correctly, the model will always start by generating a BOS token. This behavior is an accidental side-effect which we plan to address in future model versions and should not be relied upon.
- The model was trained as a LoRA with a somewhat unorthodox configuration which causes errors when used with the current version of `peft`, hence we release it as a full model instead.
## Limitations and biases
The intended use-case for this model is fictional conversation for entertainment purposes. Any other sort of usage is out of scope.
As such, it was **not** fine-tuned to be safe and harmless: the base model _and_ this fine-tune have been trained on data known to contain profanity and texts that are lewd or otherwise offensive. It may produce socially unacceptable or undesirable text, even if the prompt itself does not include anything explicitly offensive. Outputs might often be factually wrong or misleading.
|
Rucy/123
|
Rucy
| 2023-06-30T01:45:21Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-30T01:45:21Z |
---
license: creativeml-openrail-m
---
|
AlexZheng/alphapose
|
AlexZheng
| 2023-06-30T01:44:48Z | 0 | 1 | null |
[
"arxiv:2211.03375",
"region:us"
] | null | 2023-06-30T01:40:33Z |
<div align="center">
<img src="docs/logo.jpg", width="400">
</div>
## News!
- Nov 2022: [**AlphaPose paper**](http://arxiv.org/abs/2211.03375) is released! Checkout the paper for more details about this project.
- Sep 2022: [**Jittor** version](https://github.com/tycoer/AlphaPose_jittor) of AlphaPose is released! It achieves 1.45x speed up with resnet50 backbone on the training stage.
- July 2022: [**v0.6.0** version](https://github.com/MVIG-SJTU/AlphaPose) of AlphaPose is released! [HybrIK](https://github.com/Jeff-sjtu/HybrIK) for 3D pose and shape estimation is supported!
- Jan 2022: [**v0.5.0** version](https://github.com/MVIG-SJTU/AlphaPose) of AlphaPose is released! Stronger whole body(face,hand,foot) keypoints! More models are availabel. Checkout [docs/MODEL_ZOO.md](docs/MODEL_ZOO.md)
- Aug 2020: [**v0.4.0** version](https://github.com/MVIG-SJTU/AlphaPose) of AlphaPose is released! Stronger tracking! Include whole body(face,hand,foot) keypoints! [Colab](https://colab.research.google.com/drive/1c7xb_7U61HmeJp55xjXs24hf1GUtHmPs?usp=sharing) now available.
- Dec 2019: [**v0.3.0** version](https://github.com/MVIG-SJTU/AlphaPose) of AlphaPose is released! Smaller model, higher accuracy!
- Apr 2019: [**MXNet** version](https://github.com/MVIG-SJTU/AlphaPose/tree/mxnet) of AlphaPose is released! It runs at **23 fps** on COCO validation set.
- Feb 2019: [CrowdPose](https://github.com/MVIG-SJTU/AlphaPose/docs/CrowdPose.md) is integrated into AlphaPose Now!
- Dec 2018: [General version](https://github.com/MVIG-SJTU/AlphaPose/trackers/PoseFlow) of PoseFlow is released! 3X Faster and support pose tracking results visualization!
- Sep 2018: [**v0.2.0** version](https://github.com/MVIG-SJTU/AlphaPose/tree/pytorch) of AlphaPose is released! It runs at **20 fps** on COCO validation set (4.6 people per image on average) and achieves 71 mAP!
## AlphaPose
[AlphaPose](http://www.mvig.org/research/alphapose.html) is an accurate multi-person pose estimator, which is the **first open-source system that achieves 70+ mAP (75 mAP) on COCO dataset and 80+ mAP (82.1 mAP) on MPII dataset.**
To match poses that correspond to the same person across frames, we also provide an efficient online pose tracker called Pose Flow. It is the **first open-source online pose tracker that achieves both 60+ mAP (66.5 mAP) and 50+ MOTA (58.3 MOTA) on PoseTrack Challenge dataset.**
AlphaPose supports both Linux and **Windows!**
<div align="center">
<img src="docs/alphapose_17.gif", width="400" alt><br>
COCO 17 keypoints
</div>
<div align="center">
<img src="docs/alphapose_26.gif", width="400" alt><br>
<b><a href="https://github.com/Fang-Haoshu/Halpe-FullBody">Halpe 26 keypoints</a></b> + tracking
</div>
<div align="center">
<img src="docs/alphapose_136.gif", width="400"alt><br>
<b><a href="https://github.com/Fang-Haoshu/Halpe-FullBody">Halpe 136 keypoints</a></b> + tracking
<b><a href="https://youtu.be/uze6chg-YeU">YouTube link</a></b><br>
</div>
<div align="center">
<img src="docs/alphapose_hybrik_smpl.gif", width="400"alt><br>
<b><a href="https://github.com/Jeff-sjtu/HybrIK">SMPL</a></b> + tracking
</div>
## Results
### Pose Estimation
Results on COCO test-dev 2015:
<center>
| Method | AP @0.5:0.95 | AP @0.5 | AP @0.75 | AP medium | AP large |
|:-------|:-----:|:-------:|:-------:|:-------:|:-------:|
| OpenPose (CMU-Pose) | 61.8 | 84.9 | 67.5 | 57.1 | 68.2 |
| Detectron (Mask R-CNN) | 67.0 | 88.0 | 73.1 | 62.2 | 75.6 |
| **AlphaPose** | **73.3** | **89.2** | **79.1** | **69.0** | **78.6** |
</center>
Results on MPII full test set:
<center>
| Method | Head | Shoulder | Elbow | Wrist | Hip | Knee | Ankle | Ave |
|:-------|:-----:|:-------:|:-------:|:-------:|:-------:|:-------:|:-------:|:-------:|
| OpenPose (CMU-Pose) | 91.2 | 87.6 | 77.7 | 66.8 | 75.4 | 68.9 | 61.7 | 75.6 |
| Newell & Deng | **92.1** | 89.3 | 78.9 | 69.8 | 76.2 | 71.6 | 64.7 | 77.5 |
| **AlphaPose** | 91.3 | **90.5** | **84.0** | **76.4** | **80.3** | **79.9** | **72.4** | **82.1** |
</center>
More results and models are available in the [docs/MODEL_ZOO.md](docs/MODEL_ZOO.md).
### Pose Tracking
<p align='center'>
<img src="docs/posetrack.gif", width="360">
<img src="docs/posetrack2.gif", width="344">
</p>
Please read [trackers/README.md](trackers/) for details.
### CrowdPose
<p align='center'>
<img src="docs/crowdpose.gif", width="360">
</p>
Please read [docs/CrowdPose.md](docs/CrowdPose.md) for details.
## Installation
Please check out [docs/INSTALL.md](docs/INSTALL.md)
## Model Zoo
Please check out [docs/MODEL_ZOO.md](docs/MODEL_ZOO.md)
## Quick Start
- **Colab**: We provide a [colab example](https://colab.research.google.com/drive/1_3Wxi4H3QGVC28snL3rHIoeMAwI2otMR?usp=sharing) for your quick start.
- **Inference**: Inference demo
``` bash
./scripts/inference.sh ${CONFIG} ${CHECKPOINT} ${VIDEO_NAME} # ${OUTPUT_DIR}, optional
```
Inference SMPL (Download the SMPL model `basicModel_neutral_lbs_10_207_0_v1.0.0.pkl` from [here](https://smpl.is.tue.mpg.de/) and put it in `model_files/`).
``` bash
./scripts/inference_3d.sh ./configs/smpl/256x192_adam_lr1e-3-res34_smpl_24_3d_base_2x_mix.yaml ${CHECKPOINT} ${VIDEO_NAME} # ${OUTPUT_DIR}, optional
```
For high level API, please refer to `./scripts/demo_api.py`. To enable tracking, please refer to [this page](./trackers).
- **Training**: Train from scratch
``` bash
./scripts/train.sh ${CONFIG} ${EXP_ID}
```
- **Validation**: Validate your model on MSCOCO val2017
``` bash
./scripts/validate.sh ${CONFIG} ${CHECKPOINT}
```
Examples:
Demo using `FastPose` model.
``` bash
./scripts/inference.sh configs/coco/resnet/256x192_res50_lr1e-3_1x.yaml pretrained_models/fast_res50_256x192.pth ${VIDEO_NAME}
#or
python scripts/demo_inference.py --cfg configs/coco/resnet/256x192_res50_lr1e-3_1x.yaml --checkpoint pretrained_models/fast_res50_256x192.pth --indir examples/demo/
#or if you want to use yolox-x as the detector
python scripts/demo_inference.py --detector yolox-x --cfg configs/coco/resnet/256x192_res50_lr1e-3_1x.yaml --checkpoint pretrained_models/fast_res50_256x192.pth --indir examples/demo/
```
Train `FastPose` on mscoco dataset.
``` bash
./scripts/train.sh ./configs/coco/resnet/256x192_res50_lr1e-3_1x.yaml exp_fastpose
```
More detailed inference options and examples, please refer to [GETTING_STARTED.md](docs/GETTING_STARTED.md)
## Common issue & FAQ
Check out [faq.md](docs/faq.md) for faq. If it can not solve your problems or if you find any bugs, don't hesitate to comment on GitHub or make a pull request!
## Contributors
AlphaPose is based on RMPE(ICCV'17), authored by [Hao-Shu Fang](https://fang-haoshu.github.io/), Shuqin Xie, [Yu-Wing Tai](https://scholar.google.com/citations?user=nFhLmFkAAAAJ&hl=en) and [Cewu Lu](http://www.mvig.org/), [Cewu Lu](http://mvig.sjtu.edu.cn/) is the corresponding author. Currently, it is maintained by [Jiefeng Li\*](http://jeff-leaf.site/), [Hao-shu Fang\*](https://fang-haoshu.github.io/), [Haoyi Zhu](https://github.com/HaoyiZhu), [Yuliang Xiu](http://xiuyuliang.cn/about/) and [Chao Xu](http://www.isdas.cn/).
The main contributors are listed in [doc/contributors.md](docs/contributors.md).
## TODO
- [x] Multi-GPU/CPU inference
- [x] 3D pose
- [x] add tracking flag
- [ ] PyTorch C++ version
- [x] Add model trained on mixture dataset (Check the model zoo)
- [ ] dense support
- [x] small box easy filter
- [x] Crowdpose support
- [ ] Speed up PoseFlow
- [x] Add stronger/light detectors (yolox is now supported)
- [x] High level API (check the scripts/demo_api.py)
We would really appreciate if you can offer any help and be the [contributor](docs/contributors.md) of AlphaPose.
## Citation
Please cite these papers in your publications if it helps your research:
@article{alphapose,
author = {Fang, Hao-Shu and Li, Jiefeng and Tang, Hongyang and Xu, Chao and Zhu, Haoyi and Xiu, Yuliang and Li, Yong-Lu and Lu, Cewu},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
title = {AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time},
year = {2022}
}
@inproceedings{fang2017rmpe,
title={{RMPE}: Regional Multi-person Pose Estimation},
author={Fang, Hao-Shu and Xie, Shuqin and Tai, Yu-Wing and Lu, Cewu},
booktitle={ICCV},
year={2017}
}
@inproceedings{li2019crowdpose,
title={Crowdpose: Efficient crowded scenes pose estimation and a new benchmark},
author={Li, Jiefeng and Wang, Can and Zhu, Hao and Mao, Yihuan and Fang, Hao-Shu and Lu, Cewu},
booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
pages={10863--10872},
year={2019}
}
If you used the 3D mesh reconstruction module, please also cite:
@inproceedings{li2021hybrik,
title={Hybrik: A hybrid analytical-neural inverse kinematics solution for 3d human pose and shape estimation},
author={Li, Jiefeng and Xu, Chao and Chen, Zhicun and Bian, Siyuan and Yang, Lixin and Lu, Cewu},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={3383--3393},
year={2021}
}
If you used the PoseFlow tracking module, please also cite:
@inproceedings{xiu2018poseflow,
author = {Xiu, Yuliang and Li, Jiefeng and Wang, Haoyu and Fang, Yinghong and Lu, Cewu},
title = {{Pose Flow}: Efficient Online Pose Tracking},
booktitle={BMVC},
year = {2018}
}
## License
AlphaPose is freely available for free non-commercial use, and may be redistributed under these conditions. For commercial queries, please drop an e-mail at mvig.alphapose[at]gmail[dot]com and cc lucewu[[at]sjtu[dot]edu[dot]cn. We will send the detail agreement to you.
|
reneseib/dog_model
|
reneseib
| 2023-06-30T01:36:10Z | 29 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"dreambooth",
"base_model:CompVis/stable-diffusion-v1-4",
"base_model:finetune:CompVis/stable-diffusion-v1-4",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-06-29T19:41:00Z |
---
license: creativeml-openrail-m
base_model: CompVis/stable-diffusion-v1-4
instance_prompt: a photo of sks dog
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- dreambooth
inference: true
---
# DreamBooth - reneseib/dog_model
This is a dreambooth model derived from CompVis/stable-diffusion-v1-4. The weights were trained on a photo of sks dog using [DreamBooth](https://dreambooth.github.io/).
You can find some example images in the following.
DreamBooth for the text encoder was enabled: False.
|
inupedia/anime-character-image-preprocessing
|
inupedia
| 2023-06-30T01:31:24Z | 0 | 0 | null |
[
"onnx",
"license:mit",
"region:us"
] | null | 2023-06-30T00:48:31Z |
---
license: mit
---
### 模型出处
[wd-v1-4-convnextv2-tagger-v2](https://huggingface.co/SmilingWolf/wd-v1-4-convnextv2-tagger-v2)
[anime_head_detection](https://huggingface.co/deepghs/anime_head_detection)
[anime_face_detection](https://huggingface.co/deepghs/anime_face_detection)
[anime_person_detection](https://huggingface.co/deepghs/anime_person_detection)
|
ENLP/mrasp2
|
ENLP
| 2023-06-30T01:29:30Z | 162 | 2 |
transformers
|
[
"transformers",
"pytorch",
"bart",
"feature-extraction",
"translation",
"custom_code",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
translation
| 2023-06-29T09:10:03Z |
---
tags:
- translation
license: apache-2.0
metrics:
- bleu
- sacrebleu
---
## 一、项目介绍
此项目是参考github上优秀的机器翻译项目[mRASP2](https://github.com/PANXiao1994/mRASP2),将官方开源的fairseq预训练权重改写为transformers架构，使其能够更加方便使用。
## 二、使用方法
```python
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
model_path = 'ENLP/mrasp2'
model = AutoModelForSeq2SeqLM.from_pretrained(model_path, trust_remote_code=True, cache_dir=model_path)
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True, cache_dir=model_path)
input_text = ["Welcome to download and use!"]
inputs = tokenizer(input_text, return_tensors="pt", padding=True, max_length=1024, truncation=True)
result = model.generate(**inputs)
result = tokenizer.batch_decode(result, skip_special_tokens=True)
result = [pre.strip() for pre in result]
# ['欢迎下载和使用!']
```
## 三、使用说明
该模型支持32种语言，更多详细参考[mRASP2](https://github.com/PANXiao1994/mRASP2)，此模型库的tokenizer仅针对中英双语进行优化，如果需要使用其他语言请
自行参考tokenization_bat.py进行修改。请注意，这是官方的6e6d-no-mono模型，12e12d两个模型暂时无法实现，找不到原因，如果有知道的小伙伴可以分享出来。
## 四、其他模型
[ENLP/mrasp](https://huggingface.co/ENLP/mrasp)
|
ENLP/mrasp
|
ENLP
| 2023-06-30T01:27:58Z | 156 | 0 |
transformers
|
[
"transformers",
"pytorch",
"bart",
"feature-extraction",
"translation",
"custom_code",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
translation
| 2023-06-29T08:49:30Z |
---
tags:
- translation
license: apache-2.0
metrics:
- bleu
- sacrebleu
---
## 一、项目介绍
此项目是参考github上优秀的机器翻译项目[mRASP](https://github.com/linzehui/mRASP),将官方开源的fairseq预训练权重改写为transformers架构，使其能够更加方便使用。
## 二、使用方法
```python
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
model_path = 'ENLP/mrasp'
model = AutoModelForSeq2SeqLM.from_pretrained(model_path, trust_remote_code=True, cache_dir=model_path)
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True, cache_dir=model_path)
input_text = ["Welcome to download and use!"]
inputs = tokenizer(input_text, return_tensors="pt", padding=True, max_length=300, truncation=True)
result = model.generate(**inputs)
result = tokenizer.batch_decode(result, skip_special_tokens=True)
result = [pre.strip() for pre in result]
# ['欢迎下载和使用!']
```
## 三、使用说明
该模型支持32种语言，更多详细参考[mRASP](https://github.com/linzehui/mRASP)，此模型库的tokenizer仅针对中英双语进行优化，如果需要使用其他语言请
自行参考tokenization_bat.py进行修改。
## 四、其他模型
[ENLP/mrasp2](https://huggingface.co/ENLP/mrasp2)
|
TheBloke/Platypus-30B-SuperHOT-8K-GGML
|
TheBloke
| 2023-06-30T01:25:00Z | 0 | 4 | null |
[
"arxiv:2302.13971",
"license:other",
"region:us"
] | null | 2023-06-30T00:37:02Z |
---
inference: false
license: other
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# Lilloukas' Platypus 30B GGML
These files are GGML format model files for [Lilloukas' Platypus 30B](https://huggingface.co/lilloukas/Platypus-30B).
These are SuperHOT GGMLs with an increased context length. SuperHOT is a new system that employs RoPE to expand context beyond what was originally possible for a model. It was discovered and developed by [kaiokendev](https://huggingface.co/kaiokendev).
In order to use the increased context length, you can presently use:
* [KoboldCpp](https://github.com/LostRuins/koboldcpp) - [release 1.33](https://github.com/LostRuins/koboldcpp/releases/tag/v1.33) or later.
Support is also expected to come to llama.cpp, however it is still being worked on and there is currently no ETA for that.
To use the increased context with KoboldCpp and (when supported) llama.cpp, simply use `--contextsize` to set the desired context, eg `--contextsize 4096` or `--contextsize 8192`.
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Platypus-30B-SuperHOT-8K-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU inference](https://huggingface.co/TheBloke/Platypus-30B-SuperHOT-8K-GGML)
* [Unquantised SuperHOT fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/Platypus-30B-SuperHOT-8K-fp16)
* [Unquantised base fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/lilloukas/Platypus-30B)
<!-- compatibility_ggml start -->
## Compatibility
These GGMLs will work with any llama.cpp-compatible GGML client that supports k-quants.
However the increased context length won't work without specific support. See the note in the introduction for details on using increased context.
## Explanation of the new k-quant methods
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
* GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.
Refer to the Provided Files table below to see what files use which methods, and how.
<!-- compatibility_ggml end -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| platypus-30b-superhot-8k.ggmlv3.q2_K.bin | q2_K | 2 | 13.71 GB | 16.21 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. |
| platypus-30b-superhot-8k.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 17.28 GB | 19.78 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| platypus-30b-superhot-8k.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 15.72 GB | 18.22 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| platypus-30b-superhot-8k.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 14.06 GB | 16.56 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
| platypus-30b-superhot-8k.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 19.62 GB | 22.12 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K |
| platypus-30b-superhot-8k.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 18.36 GB | 20.86 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
| platypus-30b-superhot-8k.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 23.05 GB | 25.55 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K |
| platypus-30b-superhot-8k.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 22.40 GB | 24.90 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
| platypus-30b-superhot-8k.ggmlv3.q6_K.bin | q6_K | 6 | 26.69 GB | 29.19 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
## How to run in `koboldcpp`
On Linux I use the following command line to launch the KoboldCpp UI with OpenCL aceleration and a context size of 4096:
```
python ./koboldcpp.py --stream --unbantokens --threads 8 --usecublas 100 platypus-30b-superhot-8k.ggmlv3.q5_0.bin
```
Change `--gpulayers 100` to the number of layers you want/are able to offload to the GPU. Remove it if you don't have GPU acceleration.
For OpenCL acceleration, change `--usecublas` to `--useclblast 0 0`. You may need to change the second `0` to `1` if you have both an iGPU and a discrete GPU.
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: zynix , ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: Kaio Ken's SuperHOT 8K
### SuperHOT Prototype 2 w/ 8K Context
This is a second prototype of SuperHOT, this time 30B with 8K context and no RLHF, using the same technique described in [the github blog](https://kaiokendev.github.io/til#extending-context-to-8k).
Tests have shown that the model does indeed leverage the extended context at 8K.
You will need to **use either the monkeypatch** or, if you are already using the monkeypatch, **change the scaling factor to 0.25 and the maximum sequence length to 8192**
#### Looking for Merged & Quantized Models?
- 30B 4-bit CUDA: [tmpupload/superhot-30b-8k-4bit-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-safetensors)
- 30B 4-bit CUDA 128g: [tmpupload/superhot-30b-8k-4bit-128g-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-128g-safetensors)
#### Training Details
I trained the LoRA with the following configuration:
- 1200 samples (~400 samples over 2048 sequence length)
- learning rate of 3e-4
- 3 epochs
- The exported modules are:
- q_proj
- k_proj
- v_proj
- o_proj
- no bias
- Rank = 4
- Alpha = 8
- no dropout
- weight decay of 0.1
- AdamW beta1 of 0.9 and beta2 0.99, epsilon of 1e-5
- Trained on 4-bit base model
# Original model card: Lilloukas' Platypus 30B
# 🥳 Platypus-30B has arrived!
Platypus-30B is an instruction fine-tuned model based on the LLaMA-30B transformer architecture.
| Metric | Value |
|-----------------------|-------|
| MMLU (5-shot) | 64.2 |
| ARC (25-shot) | 64.6 |
| HellaSwag (10-shot) | 84.3 |
| TruthfulQA (0-shot) | 45.8 |
| Avg. | 64.7 |
We use state-of-the-art [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) to run the benchmark tests above.
## Model Details
* **Trained by**: Cole Hunter & Ariel Lee
* **Model type:** **Platypus-30B** is an auto-regressive language model based on the LLaMA transformer architecture.
* **Language(s)**: English
* **License for base weights**: License for the base LLaMA model's weights is Meta's [non-commercial bespoke license](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md).
| Hyperparameter | Value |
|---------------------------|-------|
| \\(n_\text{parameters}\\) | 33B |
| \\(d_\text{model}\\) | 6656 |
| \\(n_\text{layers}\\) | 60 |
| \\(n_\text{heads}\\) | 52 |
## Training Dataset
Dataset of highly filtered and curated question and answer pairs. Release TBD.
## Training Procedure
`lilloukas/Platypus-30B` was instruction fine-tuned using LoRA on 4 A100 80GB. For training details and inference instructions please see the [Platypus-30B](https://github.com/arielnlee/Platypus-30B.git) GitHub repo.
## Reproducing Evaluation Results
Install LM Evaluation Harness:
```
git clone https://github.com/EleutherAI/lm-evaluation-harness
cd lm-evaluation-harness
pip install -e .
```
Each task was evaluated on a single A100 80GB GPU.
ARC:
```
python main.py --model hf-causal-experimental --model_args pretrained=lilloukas/Platypus-30B --tasks arc_challenge --batch_size 1 --no_cache --write_out --output_path results/Platypus-30B/arc_challenge_25shot.json --device cuda --num_fewshot 25
```
HellaSwag:
```
python main.py --model hf-causal-experimental --model_args pretrained=lilloukas/Platypus-30B --tasks hellaswag --batch_size 1 --no_cache --write_out --output_path results/Platypus-30B/hellaswag_10shot.json --device cuda --num_fewshot 10
```
MMLU:
```
python main.py --model hf-causal-experimental --model_args pretrained=lilloukas/Platypus-30B --tasks hendrycksTest-* --batch_size 1 --no_cache --write_out --output_path results/Platypus-30B/mmlu_5shot.json --device cuda --num_fewshot 5
```
TruthfulQA:
```
python main.py --model hf-causal-experimental --model_args pretrained=lilloukas/Platypus-30B --tasks truthfulqa_mc --batch_size 1 --no_cache --write_out --output_path results/Platypus-30B/truthfulqa_0shot.json --device cuda
```
## Limitations and bias
The base LLaMA model is trained on various data, some of which may contain offensive, harmful, and biased content that can lead to toxic behavior. See Section 5.1 of the LLaMA paper. We have not performed any studies to determine how fine-tuning on the aforementioned datasets affect the model's behavior and toxicity. Do not treat chat responses from this model as a substitute for human judgment or as a source of truth. Please use responsibly.
## Citations
```bibtex
@article{touvron2023llama,
title={LLaMA: Open and Efficient Foundation Language Models},
author={Touvron, Hugo and Lavril, Thibaut and Izacard, Gautier and Martinet, Xavier and Lachaux, Marie-Anne and Lacroix, Timoth{\'e}e and Rozi{\`e}re, Baptiste and Goyal, Naman and Hambro, Eric and Azhar, Faisal and Rodriguez, Aurelien and Joulin, Armand and Grave, Edouard and Lample, Guillaume},
journal={arXiv preprint arXiv:2302.13971},
year={2023}
}
@article{hu2021lora,
title={LoRA: Low-Rank Adaptation of Large Language Models},
author={Hu, Edward J. and Shen, Yelong and Wallis, Phillip and Allen-Zhu, Zeyuan and Li, Yuanzhi and Wang, Shean and Chen, Weizhu},
journal={CoRR},
year={2021}
}
```
|
molto/ft_kor_test_2
|
molto
| 2023-06-30T01:13:41Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"wav2vec2",
"automatic-speech-recognition",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-06-30T01:08:26Z |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: ft_kor_test_1
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# ft_kor_test_1
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0205
- Cer: 0.0037
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 20
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
| 5.8814 | 0.1 | 500 | 3.3282 | 1.0 |
| 2.922 | 0.2 | 1000 | 1.5452 | 0.4197 |
| 1.0454 | 0.3 | 1500 | 0.5135 | 0.1411 |
| 0.6881 | 0.4 | 2000 | 0.3212 | 0.0964 |
| 0.5735 | 0.51 | 2500 | 0.2526 | 0.0805 |
| 0.5236 | 0.61 | 3000 | 0.2255 | 0.0691 |
| 0.4813 | 0.71 | 3500 | 0.2167 | 0.0662 |
| 0.4442 | 0.81 | 4000 | 0.1816 | 0.0575 |
| 0.4244 | 0.91 | 4500 | 0.1717 | 0.0542 |
| 0.4026 | 1.01 | 5000 | 0.1573 | 0.0525 |
| 0.3691 | 1.11 | 5500 | 0.1423 | 0.0455 |
| 0.3606 | 1.21 | 6000 | 0.1340 | 0.0429 |
| 0.3451 | 1.32 | 6500 | 0.1305 | 0.0417 |
| 0.3421 | 1.42 | 7000 | 0.1231 | 0.0389 |
| 0.3319 | 1.52 | 7500 | 0.1167 | 0.0379 |
| 0.3265 | 1.62 | 8000 | 0.1158 | 0.0373 |
| 0.3114 | 1.72 | 8500 | 0.1105 | 0.0343 |
| 0.299 | 1.82 | 9000 | 0.1015 | 0.0322 |
| 0.3023 | 1.92 | 9500 | 0.0968 | 0.0309 |
| 0.2952 | 2.02 | 10000 | 0.0926 | 0.0301 |
| 0.2719 | 2.13 | 10500 | 0.0937 | 0.0297 |
| 0.2726 | 2.23 | 11000 | 0.0902 | 0.0285 |
| 0.2615 | 2.33 | 11500 | 0.0876 | 0.0284 |
| 0.2611 | 2.43 | 12000 | 0.0839 | 0.0264 |
| 0.2505 | 2.53 | 12500 | 0.0848 | 0.0269 |
| 0.2494 | 2.63 | 13000 | 0.0788 | 0.0246 |
| 0.2442 | 2.73 | 13500 | 0.0798 | 0.0249 |
| 0.2448 | 2.83 | 14000 | 0.0769 | 0.0243 |
| 0.2365 | 2.93 | 14500 | 0.0755 | 0.0240 |
| 0.234 | 3.04 | 15000 | 0.0750 | 0.0221 |
| 0.2282 | 3.14 | 15500 | 0.0717 | 0.0219 |
| 0.2173 | 3.24 | 16000 | 0.0673 | 0.0210 |
| 0.2124 | 3.34 | 16500 | 0.0680 | 0.0211 |
| 0.2161 | 3.44 | 17000 | 0.0656 | 0.0206 |
| 0.2089 | 3.54 | 17500 | 0.0664 | 0.0204 |
| 0.213 | 3.64 | 18000 | 0.0623 | 0.0190 |
| 0.2094 | 3.74 | 18500 | 0.0635 | 0.0184 |
| 0.1998 | 3.85 | 19000 | 0.0635 | 0.0184 |
| 0.2024 | 3.95 | 19500 | 0.0620 | 0.0183 |
| 0.1935 | 4.05 | 20000 | 0.0572 | 0.0174 |
| 0.1873 | 4.15 | 20500 | 0.0607 | 0.0180 |
| 0.1789 | 4.25 | 21000 | 0.0583 | 0.0163 |
| 0.1842 | 4.35 | 21500 | 0.0663 | 0.0187 |
| 0.1773 | 4.45 | 22000 | 0.0532 | 0.0156 |
| 0.1877 | 4.55 | 22500 | 0.0583 | 0.0163 |
| 0.1844 | 4.65 | 23000 | 0.0543 | 0.0155 |
| 0.1711 | 4.76 | 23500 | 0.0522 | 0.0150 |
| 0.1703 | 4.86 | 24000 | 0.0503 | 0.0148 |
| 0.1712 | 4.96 | 24500 | 0.0524 | 0.0153 |
| 0.1642 | 5.06 | 25000 | 0.0505 | 0.0148 |
| 0.1622 | 5.16 | 25500 | 0.0476 | 0.0138 |
| 0.1544 | 5.26 | 26000 | 0.0500 | 0.0143 |
| 0.157 | 5.36 | 26500 | 0.0505 | 0.0139 |
| 0.1632 | 5.46 | 27000 | 0.0487 | 0.0138 |
| 0.1516 | 5.57 | 27500 | 0.0440 | 0.0126 |
| 0.1532 | 5.67 | 28000 | 0.0467 | 0.0127 |
| 0.1523 | 5.77 | 28500 | 0.0486 | 0.0135 |
| 0.1471 | 5.87 | 29000 | 0.0489 | 0.0129 |
| 0.1498 | 5.97 | 29500 | 0.0458 | 0.0123 |
| 0.1511 | 6.07 | 30000 | 0.0424 | 0.0123 |
| 0.1422 | 6.17 | 30500 | 0.0444 | 0.0118 |
| 0.1394 | 6.27 | 31000 | 0.0519 | 0.0148 |
| 0.1483 | 6.38 | 31500 | 0.0436 | 0.0120 |
| 0.1394 | 6.48 | 32000 | 0.0465 | 0.0126 |
| 0.1363 | 6.58 | 32500 | 0.0397 | 0.0110 |
| 0.1372 | 6.68 | 33000 | 0.0418 | 0.0110 |
| 0.1353 | 6.78 | 33500 | 0.0412 | 0.0110 |
| 0.1356 | 6.88 | 34000 | 0.0397 | 0.0109 |
| 0.1321 | 6.98 | 34500 | 0.0380 | 0.0100 |
| 0.1323 | 7.08 | 35000 | 0.0373 | 0.0101 |
| 0.1251 | 7.18 | 35500 | 0.0365 | 0.0099 |
| 0.1238 | 7.29 | 36000 | 0.0381 | 0.0100 |
| 0.1247 | 7.39 | 36500 | 0.0394 | 0.0103 |
| 0.128 | 7.49 | 37000 | 0.0389 | 0.0102 |
| 0.1245 | 7.59 | 37500 | 0.0382 | 0.0096 |
| 0.1224 | 7.69 | 38000 | 0.0358 | 0.0090 |
| 0.12 | 7.79 | 38500 | 0.0495 | 0.0113 |
| 0.1217 | 7.89 | 39000 | 0.0476 | 0.0108 |
| 0.1198 | 7.99 | 39500 | 0.0512 | 0.0130 |
| 0.1125 | 8.1 | 40000 | 0.0431 | 0.0109 |
| 0.1107 | 8.2 | 40500 | 0.0456 | 0.0111 |
| 0.1101 | 8.3 | 41000 | 0.0889 | 0.0176 |
| 0.1136 | 8.4 | 41500 | 0.0449 | 0.0103 |
| 0.1131 | 8.5 | 42000 | 0.0320 | 0.0082 |
| 0.1145 | 8.6 | 42500 | 0.0311 | 0.0083 |
| 0.1039 | 8.7 | 43000 | 0.0317 | 0.0086 |
| 0.1115 | 8.8 | 43500 | 0.0384 | 0.0086 |
| 0.1098 | 8.91 | 44000 | 0.0328 | 0.0085 |
| 0.1114 | 9.01 | 44500 | 0.0331 | 0.0083 |
| 0.0982 | 9.11 | 45000 | 0.0305 | 0.0079 |
| 0.1041 | 9.21 | 45500 | 0.0359 | 0.0084 |
| 0.1033 | 9.31 | 46000 | 0.0298 | 0.0076 |
| 0.1024 | 9.41 | 46500 | 0.0310 | 0.0076 |
| 0.0981 | 9.51 | 47000 | 0.0309 | 0.0075 |
| 0.1033 | 9.61 | 47500 | 0.0311 | 0.0076 |
| 0.0995 | 9.71 | 48000 | 0.0309 | 0.0079 |
| 0.1012 | 9.82 | 48500 | 0.0283 | 0.0071 |
| 0.1039 | 9.92 | 49000 | 0.0276 | 0.0070 |
| 0.0957 | 10.02 | 49500 | 0.0298 | 0.0071 |
| 0.0933 | 10.12 | 50000 | 0.0297 | 0.0073 |
| 0.0961 | 10.22 | 50500 | 0.0278 | 0.0069 |
| 0.0939 | 10.32 | 51000 | 0.0278 | 0.0071 |
| 0.0928 | 10.42 | 51500 | 0.0279 | 0.0071 |
| 0.0915 | 10.52 | 52000 | 0.0271 | 0.0065 |
| 0.0907 | 10.63 | 52500 | 0.0385 | 0.0099 |
| 0.0951 | 10.73 | 53000 | 0.0556 | 0.0127 |
| 0.0949 | 10.83 | 53500 | 0.0767 | 0.0189 |
| 0.0923 | 10.93 | 54000 | 0.0317 | 0.0074 |
| 0.0852 | 11.03 | 54500 | 0.0474 | 0.0114 |
| 0.0863 | 11.13 | 55000 | 0.0304 | 0.0067 |
| 0.0858 | 11.23 | 55500 | 0.0289 | 0.0063 |
| 0.0852 | 11.33 | 56000 | 0.0399 | 0.0117 |
| 0.0821 | 11.43 | 56500 | 0.0498 | 0.0111 |
| 0.0822 | 11.54 | 57000 | 0.0452 | 0.0113 |
| 0.0838 | 11.64 | 57500 | 0.0397 | 0.0079 |
| 0.0771 | 11.74 | 58000 | 0.0568 | 0.0120 |
| 0.0813 | 11.84 | 58500 | 0.0465 | 0.0087 |
| 0.078 | 11.94 | 59000 | 0.0524 | 0.0092 |
| 0.0809 | 12.04 | 59500 | 0.0545 | 0.0100 |
| 0.0755 | 12.14 | 60000 | 0.0273 | 0.0057 |
| 0.077 | 12.24 | 60500 | 0.0277 | 0.0060 |
| 0.0772 | 12.35 | 61000 | 0.0265 | 0.0057 |
| 0.0728 | 12.45 | 61500 | 0.0311 | 0.0057 |
| 0.0766 | 12.55 | 62000 | 0.0301 | 0.0066 |
| 0.0805 | 12.65 | 62500 | 0.0323 | 0.0067 |
| 0.0732 | 12.75 | 63000 | 0.0298 | 0.0061 |
| 0.0735 | 12.85 | 63500 | 0.0229 | 0.0052 |
| 0.0738 | 12.95 | 64000 | 0.0242 | 0.0054 |
| 0.0709 | 13.05 | 64500 | 0.0237 | 0.0053 |
| 0.0702 | 13.16 | 65000 | 0.0236 | 0.0050 |
| 0.0702 | 13.26 | 65500 | 0.0255 | 0.0053 |
| 0.0676 | 13.36 | 66000 | 0.0236 | 0.0052 |
| 0.0704 | 13.46 | 66500 | 0.0224 | 0.0053 |
| 0.07 | 13.56 | 67000 | 0.0238 | 0.0054 |
| 0.0671 | 13.66 | 67500 | 0.0232 | 0.0054 |
| 0.0709 | 13.76 | 68000 | 0.0228 | 0.0051 |
| 0.0636 | 13.86 | 68500 | 0.0227 | 0.0052 |
| 0.0661 | 13.96 | 69000 | 0.0223 | 0.0049 |
| 0.0645 | 14.07 | 69500 | 0.0222 | 0.0048 |
| 0.0639 | 14.17 | 70000 | 0.0243 | 0.0051 |
| 0.0608 | 14.27 | 70500 | 0.0250 | 0.0050 |
| 0.0631 | 14.37 | 71000 | 0.0234 | 0.0048 |
| 0.0656 | 14.47 | 71500 | 0.0228 | 0.0048 |
| 0.0616 | 14.57 | 72000 | 0.0239 | 0.0050 |
| 0.0631 | 14.67 | 72500 | 0.0237 | 0.0049 |
| 0.0662 | 14.77 | 73000 | 0.0234 | 0.0047 |
| 0.0622 | 14.88 | 73500 | 0.0289 | 0.0056 |
| 0.064 | 14.98 | 74000 | 0.0242 | 0.0048 |
| 0.0546 | 15.08 | 74500 | 0.0234 | 0.0049 |
| 0.0573 | 15.18 | 75000 | 0.0254 | 0.0054 |
| 0.0571 | 15.28 | 75500 | 0.0288 | 0.0058 |
| 0.0576 | 15.38 | 76000 | 0.0244 | 0.0053 |
| 0.0562 | 15.48 | 76500 | 0.0299 | 0.0061 |
| 0.0595 | 15.58 | 77000 | 0.0221 | 0.0046 |
| 0.0601 | 15.69 | 77500 | 0.0224 | 0.0046 |
| 0.0575 | 15.79 | 78000 | 0.0216 | 0.0045 |
| 0.059 | 15.89 | 78500 | 0.0222 | 0.0045 |
| 0.0562 | 15.99 | 79000 | 0.0224 | 0.0047 |
| 0.0551 | 16.09 | 79500 | 0.0216 | 0.0044 |
| 0.0539 | 16.19 | 80000 | 0.0223 | 0.0047 |
| 0.0547 | 16.29 | 80500 | 0.0212 | 0.0045 |
| 0.0527 | 16.39 | 81000 | 0.0264 | 0.0049 |
| 0.0527 | 16.49 | 81500 | 0.0247 | 0.0050 |
| 0.0526 | 16.6 | 82000 | 0.0236 | 0.0047 |
| 0.0507 | 16.7 | 82500 | 0.0213 | 0.0042 |
| 0.0522 | 16.8 | 83000 | 0.0221 | 0.0042 |
| 0.0522 | 16.9 | 83500 | 0.0220 | 0.0042 |
| 0.0496 | 17.0 | 84000 | 0.0217 | 0.0043 |
| 0.0495 | 17.1 | 84500 | 0.0214 | 0.0042 |
| 0.0493 | 17.2 | 85000 | 0.0217 | 0.0042 |
| 0.0488 | 17.3 | 85500 | 0.0207 | 0.0040 |
| 0.0492 | 17.41 | 86000 | 0.0210 | 0.0042 |
| 0.0496 | 17.51 | 86500 | 0.0204 | 0.0042 |
| 0.0487 | 17.61 | 87000 | 0.0216 | 0.0041 |
| 0.0466 | 17.71 | 87500 | 0.0199 | 0.0040 |
| 0.0465 | 17.81 | 88000 | 0.0199 | 0.0040 |
| 0.0491 | 17.91 | 88500 | 0.0198 | 0.0040 |
| 0.0469 | 18.01 | 89000 | 0.0204 | 0.0041 |
| 0.0447 | 18.11 | 89500 | 0.0205 | 0.0040 |
| 0.0487 | 18.21 | 90000 | 0.0215 | 0.0040 |
| 0.0455 | 18.32 | 90500 | 0.0207 | 0.0039 |
| 0.047 | 18.42 | 91000 | 0.0207 | 0.0040 |
| 0.0458 | 18.52 | 91500 | 0.0206 | 0.0040 |
| 0.0462 | 18.62 | 92000 | 0.0202 | 0.0039 |
| 0.0473 | 18.72 | 92500 | 0.0212 | 0.0039 |
| 0.043 | 18.82 | 93000 | 0.0208 | 0.0039 |
| 0.0435 | 18.92 | 93500 | 0.0204 | 0.0039 |
| 0.0448 | 19.02 | 94000 | 0.0208 | 0.0038 |
| 0.0435 | 19.13 | 94500 | 0.0205 | 0.0038 |
| 0.0433 | 19.23 | 95000 | 0.0203 | 0.0038 |
| 0.0425 | 19.33 | 95500 | 0.0204 | 0.0037 |
| 0.045 | 19.43 | 96000 | 0.0205 | 0.0038 |
| 0.043 | 19.53 | 96500 | 0.0205 | 0.0037 |
| 0.0435 | 19.63 | 97000 | 0.0206 | 0.0038 |
| 0.0424 | 19.73 | 97500 | 0.0207 | 0.0037 |
| 0.0441 | 19.83 | 98000 | 0.0206 | 0.0037 |
| 0.0452 | 19.94 | 98500 | 0.0205 | 0.0037 |
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.0
- Tokenizers 0.13.3
|
dp15/first_lunar_RL-Agent
|
dp15
| 2023-06-30T01:08:50Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-30T01:08:19Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 256.80 +/- 22.87
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
spybot/Timpi_Wilson
|
spybot
| 2023-06-30T00:42:24Z | 108 | 0 |
transformers
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] |
text2text-generation
| 2023-06-29T22:08:21Z |
---
license: apache-2.0
inference: false
---
# TimpiWilson Model Card
## Model details
**Model type:**
TimpiWilson is an open-source chatbot trained by fine-tuning Flan-t5-xl (3B parameters) on user-shared conversations collected from ShareGPT and conversation collection created from TImpi's index.
It is based on an encoder-decoder transformer architecture, and can autoregressively generate responses to users' inputs.
**Model date:**
TimpiWilson was trained on June 2023.
**Organizations developing the model:**
The Timpi developers.
**License:**
Apache License 2.0
## Intended use
**Primary intended uses:**
This version ot TimpiWilson is to showcase the abilities of the model.
**Primary intended users:**
The primary intended users of the model are entrepreneurs and researchers in natural language processing, machine learning, and artificial intelligence.
## Training dataset
70K conversations collected from ShareGPT.com.
40K conversations collected from Timpi's index
## Training details
It processes the data in the form of question answering. Each Wilson response is processed as an answer, and previous conversations between the user and the Wilson are processed as the question.
The encoder bi-directionally encodes a question into a hidden representation. The decoder uses cross-attention to attend to this representation while generating an answer uni-directionally from a start token.
This model is fine-tuned for 3 epochs, with a max learning rate 2e-5, warmup ratio 0.03, and a cosine learning rate schedule.
## Evaluation dataset
A preliminary evaluation of the model quality is conducted by creating a set of 80 diverse questions and utilizing GPT-4 to judge the model outputs.
|
jdawnduan/Reinforce-Pixelcopter-PLE-v0
|
jdawnduan
| 2023-06-30T00:33:45Z | 0 | 0 | null |
[
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-29T23:06:23Z |
---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-Pixelcopter-PLE-v0
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 22.60 +/- 15.62
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
Subsets and Splits
Filtered Qwen2.5 Distill Models
Identifies specific configurations of models by filtering cards that contain 'distill', 'qwen2.5', '7b' while excluding certain base models and incorrect model ID patterns, uncovering unique model variants.
Filtered Model Cards Count
Finds the count of entries with specific card details that include 'distill', 'qwen2.5', '7b' but exclude certain base models, revealing valuable insights about the dataset's content distribution.
Filtered Distill Qwen 7B Models
Filters for specific card entries containing 'distill', 'qwen', and '7b', excluding certain strings and patterns, to identify relevant model configurations.
Filtered Qwen-7b Model Cards
The query performs a detailed filtering based on specific keywords and excludes certain entries, which could be useful for identifying a specific subset of cards but does not provide deeper insights or trends.
Filtered Qwen 7B Model Cards
The query filters for specific terms related to "distilled" or "distill", "qwen", and "7b" in the 'card' column but excludes certain base models, providing a limited set of entries for further inspection.
Qwen 7B Distilled Models
The query provides a basic filtering of records to find specific card names that include keywords related to distilled Qwen 7b models, excluding a particular base model, which gives limited insight but helps in focusing on relevant entries.
Qwen 7B Distilled Model Cards
The query filters data based on specific keywords in the modelId and card fields, providing limited insight primarily useful for locating specific entries rather than revealing broad patterns or trends.
Qwen 7B Distilled Models
Finds all entries containing the terms 'distilled', 'qwen', and '7b' in a case-insensitive manner, providing a filtered set of records but without deeper analysis.
Distilled Qwen 7B Models
The query filters for specific model IDs containing 'distilled', 'qwen', and '7b', providing a basic retrieval of relevant entries but without deeper analysis or insight.
Filtered Model Cards with Distill Qwen2.
Filters and retrieves records containing specific keywords in the card description while excluding certain phrases, providing a basic count of relevant entries.
Filtered Model Cards with Distill Qwen 7
The query filters specific variations of card descriptions containing 'distill', 'qwen', and '7b' while excluding a particular base model, providing limited but specific data retrieval.
Distill Qwen 7B Model Cards
The query filters and retrieves rows where the 'card' column contains specific keywords ('distill', 'qwen', and '7b'), providing a basic filter result that can help in identifying specific entries.