modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-09-03 00:36:49
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 535
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-09-03 00:36:49
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
s8sesche/unsuitablePreTrainedModel_finetuned_model_petOrNot
|
s8sesche
| 2023-06-28T16:32:28Z | 105 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"text-classification",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-28T16:25:53Z |
---
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: unsuitablePreTrainedModel_finetuned_model_petOrNot
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. -->
# unsuitablePreTrainedModel_finetuned_model_petOrNot
This model is a fine-tuned version of [shahrukhx01/question-vs-statement-classifier](https://huggingface.co/shahrukhx01/question-vs-statement-classifier) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1947
- Accuracy: 0.9
## 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:
- 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: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 75 | 0.3483 | 0.8667 |
| No log | 2.0 | 150 | 0.2461 | 0.8 |
| No log | 3.0 | 225 | 0.1947 | 0.9 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
heka-ai/demo-model
|
heka-ai
| 2023-06-28T16:22:31Z | 1 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"distilbert",
"feature-extraction",
"sentence-similarity",
"transformers",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2023-06-28T16:22:27Z |
---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# heka-ai/demo-model
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/demo-model')
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
def cls_pooling(model_output, attention_mask):
return model_output[0][:,0]
# 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('heka-ai/demo-model')
model = AutoModel.from_pretrained('heka-ai/demo-model')
# 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, cls pooling.
sentence_embeddings = cls_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=heka-ai/demo-model)
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 1001 with parameters:
```
{'batch_size': 32, '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": 1001,
"warmup_steps": 1000,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 350, 'do_lower_case': False}) with Transformer model: DistilBertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False})
)
```
## Citing & Authors
<!--- Describe where people can find more information -->
|
vluz/Generalis_V1
|
vluz
| 2023-06-28T16:15:54Z | 0 | 0 | null |
[
"en",
"license:cc0-1.0",
"region:us"
] | null | 2023-06-28T14:30:48Z |
---
license: cc0-1.0
language:
- en
---
# Generalis V1
<hr>
### Attempt at merging several models v1.5 into one general purpose model.
Focus has been put into simple prompts, good one-off generation, muted colours, low memory usage, small model size.
It is intended as easy model for use in larger projects where image generation is needed.
Published under CC0
<hr>
Use example:
```python
import torch # Tested with 2.0.1+cu118
from diffusers import StableDiffusionPipeline # <3
# Model location in HF
model = "https://huggingface.co/vluz/Generalis_V1/blob/main/Generalis_v1.safetensors"
# Create pipe
pipe = StableDiffusionPipeline.from_ckpt(model,
torch_dtype=torch.float16,
safety_checker=None,
feature_extractor=None,
requires_safety_checker=False,)
# Cleanup
del pipe.vae.encoder
torch.cuda.empty_cache()
# Send to GPU
pipe = pipe.to("cuda")
# Optimize for low vram use and clear cache again
pipe.enable_vae_tiling()
pipe.enable_attention_slicing("max")
pipe.enable_xformers_memory_efficient_attention(attention_op=None)
pipe.unet.to(memory_format=torch.channels_last)
pipe.enable_sequential_cpu_offload()
torch.cuda.empty_cache()
# Set a prompt
prompt = "a cat"
# Generate image based on prompt
image = pipe(prompt).images[0]
# Save result image to disk
image.save("cat.png")
```
|
sharpbai/baichuan-vicuna-7b
|
sharpbai
| 2023-06-28T16:14:33Z | 7 | 1 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"zh",
"en",
"dataset:anon8231489123/ShareGPT_Vicuna_unfiltered",
"dataset:QingyiSi/Alpaca-CoT",
"dataset:mhhmm/leetcode-solutions-python",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2023-06-18T04:00:48Z |
---
language:
- zh
- en
pipeline_tag: text-generation
inference: false
datasets:
- anon8231489123/ShareGPT_Vicuna_unfiltered
- QingyiSi/Alpaca-CoT
- mhhmm/leetcode-solutions-python
---
# baichuan-vicuna-7b
A 405M split weight version of [fireballoon/baichuan-vicuna-7b](https://huggingface.co/fireballoon/baichuan-vicuna-7b)
|
sharpbai/open_llama_13b
|
sharpbai
| 2023-06-28T16:14:25Z | 25 | 1 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:togethercomputer/RedPajama-Data-1T",
"arxiv:2302.13971",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-22T05:07:23Z |
---
license: apache-2.0
datasets:
- togethercomputer/RedPajama-Data-1T
---
# open_llama_13b
*The weight file is split into chunks with a size of 650MB for convenient and fast parallel downloads*
A 650MB split weight version of [openlm-research/open_llama_13b](https://huggingface.co/openlm-research/open_llama_13b)
The original model card is down below
-----------------------------------------
# OpenLLaMA: An Open Reproduction of LLaMA
In this repo, we present a permissively licensed open source reproduction of Meta AI's [LLaMA](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/) large language model. We are releasing 3B, 7B and 13B models trained on 1T tokens. We provide PyTorch and JAX weights of pre-trained OpenLLaMA models, as well as evaluation results and comparison against the original LLaMA models. Please see the [project homepage of OpenLLaMA](https://github.com/openlm-research/open_llama) for more details.
## Weights Release, License and Usage
We release the weights in two formats: an EasyLM format to be use with our [EasyLM framework](https://github.com/young-geng/EasyLM), and a PyTorch format to be used with the [Hugging Face transformers](https://huggingface.co/docs/transformers/index) library. Both our training framework EasyLM and the checkpoint weights are licensed permissively under the Apache 2.0 license.
### Loading the Weights with Hugging Face Transformers
Preview checkpoints can be directly loaded from Hugging Face Hub. **Please note that it is advised to avoid using the Hugging Face fast tokenizer for now, as we’ve observed that the auto-converted fast tokenizer sometimes gives incorrect tokenizations.** This can be achieved by directly using the `LlamaTokenizer` class, or passing in the `use_fast=False` option for the `AutoTokenizer` class. See the following example for usage.
```python
import torch
from transformers import LlamaTokenizer, LlamaForCausalLM
# model_path = 'openlm-research/open_llama_3b'
# model_path = 'openlm-research/open_llama_7b'
model_path = 'openlm-research/open_llama_13b'
tokenizer = LlamaTokenizer.from_pretrained(model_path)
model = LlamaForCausalLM.from_pretrained(
model_path, torch_dtype=torch.float16, device_map='auto',
)
prompt = 'Q: What is the largest animal?\nA:'
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
generation_output = model.generate(
input_ids=input_ids, max_new_tokens=32
)
print(tokenizer.decode(generation_output[0]))
```
For more advanced usage, please follow the [transformers LLaMA documentation](https://huggingface.co/docs/transformers/main/model_doc/llama).
### Evaluating with LM-Eval-Harness
The model can be evaluated with [lm-eval-harness](https://github.com/EleutherAI/lm-evaluation-harness). However, due to the aforementioned tokenizer issue, we need to avoid using the fast tokenizer to obtain the correct results. This can be achieved by passing in `use_fast=False` to [this part of lm-eval-harness](https://github.com/EleutherAI/lm-evaluation-harness/blob/4b701e228768052cfae9043dca13e82052ca5eea/lm_eval/models/huggingface.py#LL313C9-L316C10), as shown in the example below:
```python
tokenizer = self.AUTO_TOKENIZER_CLASS.from_pretrained(
pretrained if tokenizer is None else tokenizer,
revision=revision + ("/" + subfolder if subfolder is not None else ""),
use_fast=False
)
```
### Loading the Weights with EasyLM
For using the weights in our EasyLM framework, please refer to the [LLaMA documentation of EasyLM](https://github.com/young-geng/EasyLM/blob/main/docs/llama.md). Note that unlike the original LLaMA model, our OpenLLaMA tokenizer and weights are trained completely from scratch so it is no longer needed to obtain the original LLaMA tokenizer and weights. Note that we use BOS (beginning of sentence) token (id=1) during training, so it is best to prepend this token for best performance during few-shot evaluation.
## Dataset and Training
We train our models on the [RedPajama](https://www.together.xyz/blog/redpajama) dataset released by [Together](https://www.together.xyz/), which is a reproduction of the LLaMA training dataset containing over 1.2 trillion tokens. We follow the exactly same preprocessing steps and training hyperparameters as the original LLaMA paper, including model architecture, context length, training steps, learning rate schedule, and optimizer. The only difference between our setting and the original one is the dataset used: OpenLLaMA employs the RedPajama dataset rather than the one utilized by the original LLaMA.
We train the models on cloud TPU-v4s using [EasyLM](https://github.com/young-geng/EasyLM), a JAX based training pipeline we developed for training and fine-tuning large language models. We employ a combination of normal data parallelism and [fully sharded data parallelism (also know as ZeRO stage 3)](https://engineering.fb.com/2021/07/15/open-source/fsdp/) to balance the training throughput and memory usage. Overall we reach a throughput of over 2200 tokens / second / TPU-v4 chip for our 7B model.
## Evaluation
We evaluated OpenLLaMA on a wide range of tasks using [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness). The LLaMA results are generated by running the original LLaMA model on the same evaluation metrics. We note that our results for the LLaMA model differ slightly from the original LLaMA paper, which we believe is a result of different evaluation protocols. Similar differences have been reported in [this issue of lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness/issues/443). Additionally, we present the results of GPT-J, a 6B parameter model trained on the [Pile](https://pile.eleuther.ai/) dataset by [EleutherAI](https://www.eleuther.ai/).
The original LLaMA model was trained for 1 trillion tokens and GPT-J was trained for 500 billion tokens. We present the results in the table below. OpenLLaMA exhibits comparable performance to the original LLaMA and GPT-J across a majority of tasks, and outperforms them in some tasks.
| **Task/Metric** | GPT-J 6B | LLaMA 7B | LLaMA 13B | OpenLLaMA 7B | OpenLLaMA 3B | OpenLLaMA 13B |
| ---------------------- | -------- | -------- | --------- | ------------ | ------------ | ------------- |
| anli_r1/acc | 0.32 | 0.35 | 0.35 | 0.33 | 0.33 | 0.33 |
| anli_r2/acc | 0.34 | 0.34 | 0.36 | 0.36 | 0.32 | 0.33 |
| anli_r3/acc | 0.35 | 0.37 | 0.39 | 0.38 | 0.35 | 0.40 |
| arc_challenge/acc | 0.34 | 0.39 | 0.44 | 0.37 | 0.34 | 0.41 |
| arc_challenge/acc_norm | 0.37 | 0.41 | 0.44 | 0.38 | 0.37 | 0.44 |
| arc_easy/acc | 0.67 | 0.68 | 0.75 | 0.72 | 0.69 | 0.75 |
| arc_easy/acc_norm | 0.62 | 0.52 | 0.59 | 0.68 | 0.65 | 0.70 |
| boolq/acc | 0.66 | 0.75 | 0.71 | 0.71 | 0.68 | 0.75 |
| hellaswag/acc | 0.50 | 0.56 | 0.59 | 0.53 | 0.49 | 0.56 |
| hellaswag/acc_norm | 0.66 | 0.73 | 0.76 | 0.72 | 0.67 | 0.76 |
| openbookqa/acc | 0.29 | 0.29 | 0.31 | 0.30 | 0.27 | 0.31 |
| openbookqa/acc_norm | 0.38 | 0.41 | 0.42 | 0.40 | 0.40 | 0.43 |
| piqa/acc | 0.75 | 0.78 | 0.79 | 0.76 | 0.75 | 0.77 |
| piqa/acc_norm | 0.76 | 0.78 | 0.79 | 0.77 | 0.76 | 0.79 |
| record/em | 0.88 | 0.91 | 0.92 | 0.89 | 0.88 | 0.91 |
| record/f1 | 0.89 | 0.91 | 0.92 | 0.90 | 0.89 | 0.91 |
| rte/acc | 0.54 | 0.56 | 0.69 | 0.60 | 0.58 | 0.64 |
| truthfulqa_mc/mc1 | 0.20 | 0.21 | 0.25 | 0.23 | 0.22 | 0.25 |
| truthfulqa_mc/mc2 | 0.36 | 0.34 | 0.40 | 0.35 | 0.35 | 0.38 |
| wic/acc | 0.50 | 0.50 | 0.50 | 0.51 | 0.48 | 0.47 |
| winogrande/acc | 0.64 | 0.68 | 0.70 | 0.67 | 0.62 | 0.70 |
| Average | 0.52 | 0.55 | 0.57 | 0.55 | 0.53 | 0.57 |
We removed the task CB and WSC from our benchmark, as our model performs suspiciously well on these two tasks. We hypothesize that there could be a benchmark data contamination in the training set.
## Contact
We would love to get feedback from the community. If you have any questions, please open an issue or contact us.
OpenLLaMA is developed by:
[Xinyang Geng](https://young-geng.xyz/)* and [Hao Liu](https://www.haoliu.site/)* from Berkeley AI Research.
*Equal Contribution
## Acknowledgment
We thank the [Google TPU Research Cloud](https://sites.research.google/trc/about/) program for providing part of the computation resources. We’d like to specially thank Jonathan Caton from TPU Research Cloud for helping us organizing compute resources, Rafi Witten from the Google Cloud team and James Bradbury from the Google JAX team for helping us optimizing our training throughput. We’d also want to thank Charlie Snell, Gautier Izacard, Eric Wallace, Lianmin Zheng and our user community for the discussions and feedback.
The OpenLLaMA 13B model is trained in collaboration with [Stability AI](https://stability.ai/), and we thank Stability AI for providing the computation resources. We’d like to especially thank David Ha and Shivanshu Purohit for the coordinating the logistics and providing engineering support.
## Reference
If you found OpenLLaMA useful in your research or applications, please cite using the following BibTeX:
```
@software{openlm2023openllama,
author = {Geng, Xinyang and Liu, Hao},
title = {OpenLLaMA: An Open Reproduction of LLaMA},
month = May,
year = 2023,
url = {https://github.com/openlm-research/open_llama}
}
```
```
@software{together2023redpajama,
author = {Together Computer},
title = {RedPajama-Data: An Open Source Recipe to Reproduce LLaMA training dataset},
month = April,
year = 2023,
url = {https://github.com/togethercomputer/RedPajama-Data}
}
```
```
@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 others},
journal={arXiv preprint arXiv:2302.13971},
year={2023}
}
```
|
sharpbai/alpaca-lora-7b-merged
|
sharpbai
| 2023-06-28T16:14:12Z | 26 | 0 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:yahma/alpaca-cleaned",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-13T16:08:57Z |
---
license: other
datasets:
- yahma/alpaca-cleaned
---
*The weight file is split into chunks with a size of 405M for convenient and fast parallel downloads*
This repo contains a merged model
from [tloen/alpaca-lora-7b](https://huggingface.co/tloen/alpaca-lora-7b).
|
sharpbai/alpaca-7b-merged
|
sharpbai
| 2023-06-28T16:14:08Z | 76 | 0 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"alpaca",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-14T15:56:13Z |
---
license: other
tags:
- alpaca
---
### Stanford Alpaca-7B-Merged
*The weight file is split into chunks with a size of 405M for convenient and fast parallel downloads*
This repo hosts the merged weight for [Stanford Alpaca-7B](https://github.com/tatsu-lab/stanford_alpaca/) that can be used directly.
Below is the original model card information.
-----------------------
### Stanford Alpaca-7B
This repo hosts the weight diff for [Stanford Alpaca-7B](https://github.com/tatsu-lab/stanford_alpaca/) that can be used to reconstruct the original model weights when applied to Meta's LLaMA weights.
To recover the original Alpaca-7B weights, follow these steps:
```text
1. Convert Meta's released weights into huggingface format. Follow this guide:
https://huggingface.co/docs/transformers/main/model_doc/llama
2. Make sure you cloned the released weight diff into your local machine. The weight diff is located at:
https://huggingface.co/tatsu-lab/alpaca-7b/tree/main
3. Run this function with the correct paths. E.g.,
python weight_diff.py recover --path_raw <path_to_step_1_dir> --path_diff <path_to_step_2_dir> --path_tuned <path_to_store_recovered_weights>
```
Once step 3 completes, you should have a directory with the recovered weights, from which you can load the model like the following
```python
import transformers
alpaca_model = transformers.AutoModelForCausalLM.from_pretrained("<path_to_store_recovered_weights>")
alpaca_tokenizer = transformers.AutoTokenizer.from_pretrained("<path_to_store_recovered_weights>")
```
|
sharpbai/vicuna-13b-v1.3
|
sharpbai
| 2023-06-28T16:14:05Z | 12 | 0 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"arxiv:2302.13971",
"arxiv:2306.05685",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2023-06-20T09:24:02Z |
---
inference: false
---
# vicuna-13b-v1.3
*The weight file is split into chunks with a size of 650MB for convenient and fast parallel downloads*
A 650M split weight version of [lmsys/vicuna-13b-v1.3](https://huggingface.co/lmsys/vicuna-13b-v1.3)
The original model card is down below
-----------------------------------------
# Vicuna Model Card
## Model Details
Vicuna is a chat assistant trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT.
- **Developed by:** [LMSYS](https://lmsys.org/)
- **Model type:** An auto-regressive language model based on the transformer architecture.
- **License:** Non-commercial license
- **Finetuned from model:** [LLaMA](https://arxiv.org/abs/2302.13971).
### Model Sources
- **Repository:** https://github.com/lm-sys/FastChat
- **Blog:** https://lmsys.org/blog/2023-03-30-vicuna/
- **Paper:** https://arxiv.org/abs/2306.05685
- **Demo:** https://chat.lmsys.org/
## Uses
The primary use of Vicuna is research on large language models and chatbots.
The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.
## How to Get Started with the Model
Command line interface: https://github.com/lm-sys/FastChat#vicuna-weights.
APIs (OpenAI API, Huggingface API): https://github.com/lm-sys/FastChat/tree/main#api.
## Training Details
Vicuna v1.3 is fine-tuned from LLaMA with supervised instruction fine-tuning.
The training data is around 140K conversations collected from ShareGPT.com.
See more details in the "Training Details of Vicuna Models" section in the appendix of this [paper](https://arxiv.org/pdf/2306.05685.pdf).
## Evaluation
Vicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-judge. See more details in this [paper](https://arxiv.org/pdf/2306.05685.pdf).
## Difference between different versions of Vicuna
See [vicuna_weights_version.md](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md)
|
sharpbai/vicuna-7b-v1.3
|
sharpbai
| 2023-06-28T16:14:00Z | 221 | 0 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"arxiv:2302.13971",
"arxiv:2306.05685",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2023-06-20T09:01:29Z |
---
inference: false
---
# vicuna-7b-v1.3
*The weight file is split into chunks with a size of 405M for convenient and fast parallel downloads*
A 405M split weight version of [lmsys/vicuna-7b-v1.3](https://huggingface.co/lmsys/vicuna-7b-v1.3)
Original model is down below
# Vicuna Model Card
## Model Details
Vicuna is a chat assistant trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT.
- **Developed by:** [LMSYS](https://lmsys.org/)
- **Model type:** An auto-regressive language model based on the transformer architecture.
- **License:** Non-commercial license
- **Finetuned from model:** [LLaMA](https://arxiv.org/abs/2302.13971).
### Model Sources
- **Repository:** https://github.com/lm-sys/FastChat
- **Blog:** https://lmsys.org/blog/2023-03-30-vicuna/
- **Paper:** https://arxiv.org/abs/2306.05685
- **Demo:** https://chat.lmsys.org/
## Uses
The primary use of Vicuna is research on large language models and chatbots.
The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.
## How to Get Started with the Model
Command line interface: https://github.com/lm-sys/FastChat#vicuna-weights.
APIs (OpenAI API, Huggingface API): https://github.com/lm-sys/FastChat/tree/main#api.
## Training Details
Vicuna v1.3 is fine-tuned from LLaMA with supervised instruction fine-tuning.
The training data is around 140K conversations collected from ShareGPT.com.
See more details in the "Training Details of Vicuna Models" section in the appendix of this [paper](https://arxiv.org/pdf/2306.05685.pdf).
## Evaluation
Vicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-judge. See more details in this [paper](https://arxiv.org/pdf/2306.05685.pdf).
## Difference between different versions of Vicuna
See [vicuna_weights_version.md](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md)
|
sharpbai/llama-13b-hf
|
sharpbai
| 2023-06-28T16:13:56Z | 93 | 1 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2023-06-20T10:34:56Z |
---
inference: false
license: other
---
# llama-13b-hf
*The weight file is split into chunks with a size of 650MB for convenient and fast parallel downloads*
A 650M split weight version of [yahma/llama-13b-hf](https://huggingface.co/yahma/llama-13b-hf)
The original model card is down below
-----------------------------------------
LLaMA-13B converted to work with git head Transformers/HuggingFace on April 8, 2023. This version should resolve the EOS token issues.
This is under a special license, please see the LICENSE file for details.
This contains the weights for the LLaMA-7b model. This model is under a non-commercial license (see the LICENSE file).
You should only use this repository if you have been granted access to the model by filling out [this form](https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform?usp=send_form) but either lost your copy of the weights or got some trouble converting them to the Transformers format.
--
license: other
---
# LLaMA Model Card
## Model details
**Organization developing the model**
The FAIR team of Meta AI.
**Model date**
LLaMA was trained between December. 2022 and Feb. 2023.
**Model version**
This is version 1 of the model.
**Model type**
LLaMA is an auto-regressive language model, based on the transformer architecture. The model comes in different sizes: 7B, 13B, 33B and 65B parameters.
**Paper or resources for more information**
More information can be found in the paper “LLaMA, Open and Efficient Foundation Language Models”, available at https://research.facebook.com/publications/llama-open-and-efficient-foundation-language-models/.
**Citations details**
https://research.facebook.com/publications/llama-open-and-efficient-foundation-language-models/
**License**
Non-commercial bespoke license
**Where to send questions or comments about the model**
Questions and comments about LLaMA can be sent via the [GitHub repository](https://github.com/facebookresearch/llama) of the project , by opening an issue.
## Intended use
**Primary intended uses**
The primary use of LLaMA is research on large language models, including:
exploring potential applications such as question answering, natural language understanding or reading comprehension,
understanding capabilities and limitations of current language models, and developing techniques to improve those,
evaluating and mitigating biases, risks, toxic and harmful content generations, hallucinations.
**Primary intended users**
The primary intended users of the model are researchers in natural language processing, machine learning and artificial intelligence.
**Out-of-scope use cases**
LLaMA is a base, or foundational, model. As such, it should not be used on downstream applications without further risk evaluation and mitigation. In particular, our model has not been trained with human feedback, and can thus generate toxic or offensive content, incorrect information or generally unhelpful answers.
## Factors
**Relevant factors**
One of the most relevant factors for which model performance may vary is which language is used. Although we included 20 languages in the training data, most of our dataset is made of English text, and we thus expect the model to perform better for English than other languages. Relatedly, it has been shown in previous studies that performance might vary for different dialects, and we expect that it will be the case for our model.
**Evaluation factors**
As our model is trained on data from the Web, we expect that it reflects biases from this source. We thus evaluated on RAI datasets to measure biases exhibited by the model for gender, religion, race, sexual orientation, age, nationality, disability, physical appearance and socio-economic status. We also measure the toxicity of model generations, depending on the toxicity of the context used to prompt the model.
## Metrics
**Model performance measures**
We use the following measure to evaluate the model:
- Accuracy for common sense reasoning, reading comprehension, natural language understanding (MMLU), BIG-bench hard, WinoGender and CrowS-Pairs,
- Exact match for question answering,
- The toxicity score from Perspective API on RealToxicityPrompts.
**Decision thresholds**
Not applicable.
**Approaches to uncertainty and variability**
Due to the high computational requirements of training LLMs, we trained only one model of each size, and thus could not evaluate variability of pre-training.
## Evaluation datasets
The model was evaluated on the following benchmarks: BoolQ, PIQA, SIQA, HellaSwag, WinoGrande, ARC, OpenBookQA, NaturalQuestions, TriviaQA, RACE, MMLU, BIG-bench hard, GSM8k, RealToxicityPrompts, WinoGender, CrowS-Pairs.
## Training dataset
The model was trained using the following source of data: CCNet [67%], C4 [15%], GitHub [4.5%], Wikipedia [4.5%], Books [4.5%], ArXiv [2.5%], Stack Exchange[2%]. The Wikipedia and Books domains include data in the following languages: bg, ca, cs, da, de, en, es, fr, hr, hu, it, nl, pl, pt, ro, ru, sl, sr, sv, uk. See the paper for more details about the training set and corresponding preprocessing.
## Quantitative analysis
Hyperparameters for the model architecture
<table>
<thead>
<tr>
<th >LLaMA</th> <th colspan=6>Model hyper parameters </th>
</tr>
<tr>
<th>Number of parameters</th><th>dimension</th><th>n heads</th><th>n layers</th><th>Learn rate</th><th>Batch size</th><th>n tokens</th>
</tr>
</thead>
<tbody>
<tr>
<th>7B</th> <th>4096</th> <th>32</th> <th>32</th> <th>3.0E-04</th><th>4M</th><th>1T
</tr>
<tr>
<th>13B</th><th>5120</th><th>40</th><th>40</th><th>3.0E-04</th><th>4M</th><th>1T
</tr>
<tr>
<th>33B</th><th>6656</th><th>52</th><th>60</th><th>1.5.E-04</th><th>4M</th><th>1.4T
</tr>
<tr>
<th>65B</th><th>8192</th><th>64</th><th>80</th><th>1.5.E-04</th><th>4M</th><th>1.4T
</tr>
</tbody>
</table>
*Table 1 - Summary of LLama Model Hyperparameters*
We present our results on eight standard common sense reasoning benchmarks in the table below.
<table>
<thead>
<tr>
<th>LLaMA</th> <th colspan=9>Reasoning tasks </th>
</tr>
<tr>
<th>Number of parameters</th> <th>BoolQ</th><th>PIQA</th><th>SIQA</th><th>HellaSwag</th><th>WinoGrande</th><th>ARC-e</th><th>ARC-c</th><th>OBQA</th><th>COPA</th>
</tr>
</thead>
<tbody>
<tr>
<th>7B</th><th>76.5</th><th>79.8</th><th>48.9</th><th>76.1</th><th>70.1</th><th>76.7</th><th>47.6</th><th>57.2</th><th>93
</th>
<tr><th>13B</th><th>78.1</th><th>80.1</th><th>50.4</th><th>79.2</th><th>73</th><th>78.1</th><th>52.7</th><th>56.4</th><th>94
</th>
<tr><th>33B</th><th>83.1</th><th>82.3</th><th>50.4</th><th>82.8</th><th>76</th><th>81.4</th><th>57.8</th><th>58.6</th><th>92
</th>
<tr><th>65B</th><th>85.3</th><th>82.8</th><th>52.3</th><th>84.2</th><th>77</th><th>81.5</th><th>56</th><th>60.2</th><th>94</th></tr>
</tbody>
</table>
*Table 2 - Summary of LLama Model Performance on Reasoning tasks*
We present our results on bias in the table below. Note that lower value is better indicating lower bias.
| No | Category | FAIR LLM |
| --- | -------------------- | -------- |
| 1 | Gender | 70.6 |
| 2 | Religion | 79 |
| 3 | Race/Color | 57 |
| 4 | Sexual orientation | 81 |
| 5 | Age | 70.1 |
| 6 | Nationality | 64.2 |
| 7 | Disability | 66.7 |
| 8 | Physical appearance | 77.8 |
| 9 | Socioeconomic status | 71.5 |
| | LLaMA Average | 66.6 |
*Table 3 - Summary bias of our model output*
## Ethical considerations
**Data**
The data used to train the model is collected from various sources, mostly from the Web. As such, it contains offensive, harmful and biased content. We thus expect the model to exhibit such biases from the training data.
**Human life**
The model is not intended to inform decisions about matters central to human life, and should not be used in such a way.
**Mitigations**
We filtered the data from the Web based on its proximity to Wikipedia text and references. For this, we used a Kneser-Ney language model and a fastText linear classifier.
**Risks and harms**
Risks and harms of large language models include the generation of harmful, offensive or biased content. These models are often prone to generating incorrect information, sometimes referred to as hallucinations. We do not expect our model to be an exception in this regard.
**Use cases**
LLaMA is a foundational model, and as such, it should not be used for downstream applications without further investigation and mitigations of risks. These risks and potential fraught use cases include, but are not limited to: generation of misinformation and generation of harmful, biased or offensive content.
|
minhcrafters/DialoGPT-small-Fukuya
|
minhcrafters
| 2023-06-28T15:59:29Z | 120 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"gpt2",
"text-generation",
"conversational",
"en",
"license:gpl-3.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-05-28T15:20:56Z |
---
license: gpl-3.0
tags:
- conversational
language:
- en
---
|
YakovElm/IntelDAOS_15_BERT_Over_Sampling
|
YakovElm
| 2023-06-28T15:55:27Z | 62 | 0 |
transformers
|
[
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-28T15:54:45Z |
---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: IntelDAOS_15_BERT_Over_Sampling
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. -->
# IntelDAOS_15_BERT_Over_Sampling
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.0704
- Train Accuracy: 0.9820
- Validation Loss: 0.7296
- Validation Accuracy: 0.8108
- Epoch: 2
## 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': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.5199 | 0.7373 | 0.5990 | 0.6517 | 0 |
| 0.2247 | 0.9276 | 0.8030 | 0.7357 | 1 |
| 0.0704 | 0.9820 | 0.7296 | 0.8108 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
slplab/whisper-med-asd_v2
|
slplab
| 2023-06-28T15:26:10Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-06-28T02:51:36Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-med-asd_v2
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. -->
# whisper-med-asd_v2
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5457
- Wer: 37.9455
## 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: 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
- training_steps: 1000
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 0.1323 | 10.53 | 100 | 0.5968 | 71.875 |
| 0.0052 | 21.05 | 200 | 0.7108 | 77.7778 |
| 0.0005 | 31.58 | 300 | 0.7444 | 81.25 |
| 0.0004 | 42.11 | 400 | 0.7615 | 80.9028 |
| 0.0003 | 52.63 | 500 | 0.7780 | 79.8611 |
| 0.0003 | 63.16 | 600 | 0.7941 | 80.9028 |
| 0.0003 | 73.68 | 700 | 0.8077 | 80.9028 |
| 0.0003 | 84.21 | 800 | 0.8194 | 79.1667 |
| 0.0003 | 94.74 | 900 | 0.8276 | 79.5139 |
| 0.0003 | 105.26 | 1000 | 0.8305 | 79.1667 |
### Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
|
filipps/model
|
filipps
| 2023-06-28T15:12:28Z | 0 | 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
| 2023-06-27T16:20:11Z |
---
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 - filipps/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.
|
xzuyn/GPT2-RPGPT-8.48M
|
xzuyn
| 2023-06-28T15:06:20Z | 255 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"gpt2",
"text-generation",
"en",
"dataset:practicaldreamer/RPGPT_PublicDomain-alpaca",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-27T05:46:00Z |
---
language:
- en
pipeline_tag: text-generation
datasets:
- practicaldreamer/RPGPT_PublicDomain-alpaca
---
# Latest Version: *111,577* / *111,577* Steps (Epoch 1).
- 28,563,712 / 28,563,712 tokens seen (Epoch 1).
- 0 / 28,563,712 tokens seen (Epoch 2).
- 0 / 28,563,712 tokens seen (Epoch 3).
# Model Info:
- Trained from scratch.
- 8.48M parameters.
- 256 context length.
- Test model. Likely needs at least 512 context to function "properly".
- Trained with a dataset that overlaps by a quarter of the context length (Shifts by 64 tokens for each subset).
# Format:
```
<|characters|>
Nancy (Oliver Twist): Female, early 20s, ESFP, Cockney accent. Loyal...
Mr. Edward Hyde (Dr. Jekyll and Mr. Hyde): Male, late 30s, ESTP...
<|scenario|>
In an alternate Victorian London where the city's poor and downtrodden...
<|response|>
Nancy: *gently brushes her fingers across the worn book spine, before suddenly stopping as she feels another hand...
Mr. Edward Hyde: *glances at Nancy with a sinister grin, slowly pulling his hand back* No need to apologize, miss...
```
# Example Output:
Step 111,577. Input `<|characters|>` as a prompt, set max tokens to 256, amount to generate to 253. This generated up to `just our circumstances before us`. Then I set amount to generate to 128 to keep half of the text in context. This generated up to `A wise suggestion,`. I then lowered the amount to generate to 64. That generated up to the ending `know of our current situation?`.
```
<|characters|>
Mrs. Samsa (The Metamorphosis): Female, middle-aged, ISFJ, German accent, compassionate mother struggling to cope with her son's transformation, and eventually succumbs to the family's financial and emotional burdens.
<|scenario|>
In a twist of fate, Mrs. Samsa finds herself transported back in time to time and space. Evangelist, who is on an isolated haven where he encounters Mrs. Samsa, by a different tale. Mrs. Samsa, still burdened by the weight of his past actions, must confront the difficult path ahead.
Through their conversations, they find common ground in their own worlds, allowing them to continue seeking wisdom from each other and finding solace in one another's words. The dialogue between these two characters will offer insight into each other's worlds as well as how their experiences have shaped them in this whimsical world.
<|response|>
Mrs. Samsa: *approaches the peculiar sights around her, eyes widening in surprise* Oh dear, I couldn't help but notice you not! I've never seen my fair life, but I'm starting to see my son. Are you here in this peculiar place?
Evangelist: *smiles warmly at Mrs. Samsa* Yes, we are indeed more than just our circumstances before us. And it is your place of wisdom and understanding. *opens the book, his eyes sparkling with excitement*
Mrs. Samsa: *slowly opens a small book of the book* I must confess, Evangelist, I've never had a different view of this place. But it feels like this before our worlds find such things that we've discovered.
Evangelist: *nods thoughtfully* You possess great wisdom, Mrs. Samsa. It seems we are both searching for a way to escape this peculiar library. Perhaps that is a sign of my spiritual journey towards you.
Mrs. Samsa: *eyes widen in curiosity* A wise suggestion, Candide. I can't help but feel a sense of serenity amidst my own life.
Evangelist: *smiles warmly* Of course, Mrs. Samsa. The path to enlightenment is filled with joy and understanding. Now, tell me more about this ancient book. What do you need to know of our current situation?
```
# Config:
Learning rate may have been too high, not sure. Average loss at step 111,557 had an averge loss of 2.1.
```
batch_size: 1
dropout: 0
learning_rate: 0.0001
max_length: 256
n_embed: 256
n_head: 8
n_layer: 8
vocab_size: 8192
```
|
IIC/xlm-roberta-large-livingner3
|
IIC
| 2023-06-28T14:41:07Z | 107 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"xlm-roberta",
"text-classification",
"biomedical",
"clinical",
"spanish",
"xlm-roberta-large",
"es",
"dataset:IIC/livingner3",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-26T07:47:33Z |
---
language: es
tags:
- biomedical
- clinical
- spanish
- xlm-roberta-large
license: mit
datasets:
- "IIC/livingner3"
metrics:
- f1
model-index:
- name: IIC/xlm-roberta-large-livingner3
results:
- task:
type: multi-label-classification
dataset:
name: livingner3
type: IIC/livingner3
split: test
metrics:
- name: f1
type: f1
value: 0.606
pipeline_tag: text-classification
---
# xlm-roberta-large-livingner3
This model is a finetuned version of xlm-roberta-large for the livingner3 dataset used in a benchmark in the paper TODO. The model has a F1 of 0.606
Please refer to the original publication for more information TODO LINK
## Parameters used
| parameter | Value |
|-------------------------|:-----:|
| batch size | 16 |
| learning rate | 2e-05 |
| classifier dropout | 0 |
| warmup ratio | 0 |
| warmup steps | 0 |
| weight decay | 0 |
| optimizer | AdamW |
| epochs | 10 |
| early stopping patience | 3 |
## BibTeX entry and citation info
```bibtex
TODO
```
|
h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b
|
h2oai
| 2023-06-28T14:38:16Z | 33 | 10 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"gpt",
"llm",
"large language model",
"h2o-llmstudio",
"en",
"dataset:OpenAssistant/oasst1",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2023-06-09T09:28:29Z |
---
language:
- en
library_name: transformers
tags:
- gpt
- llm
- large language model
- h2o-llmstudio
inference: false
thumbnail: >-
https://h2o.ai/etc.clientlibs/h2o/clientlibs/clientlib-site/resources/images/favicon.ico
license: apache-2.0
datasets:
- OpenAssistant/oasst1
---
# Model Card
## Summary
This model was trained using [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio).
- Base model: [openlm-research/open_llama_7b](https://huggingface.co/openlm-research/open_llama_7b)
- Dataset preparation: [OpenAssistant/oasst1](https://github.com/h2oai/h2o-llmstudio/blob/1935d84d9caafed3ee686ad2733eb02d2abfce57/app_utils/utils.py#LL1896C5-L1896C28)
## Usage
To use the model with the `transformers` library on a machine with GPUs, first make sure you have the `transformers`, `accelerate` and `torch` libraries installed.
```bash
pip install transformers==4.30.2
pip install accelerate==0.19.0
pip install torch==2.0.0
```
```python
import torch
from transformers import pipeline
generate_text = pipeline(
model="h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b",
torch_dtype="auto",
trust_remote_code=True,
use_fast=False,
device_map={"": "cuda:0"},
)
res = generate_text(
"Why is drinking water so healthy?",
min_new_tokens=2,
max_new_tokens=1024,
do_sample=False,
num_beams=1,
temperature=float(0.3),
repetition_penalty=float(1.2),
renormalize_logits=True
)
print(res[0]["generated_text"])
```
You can print a sample prompt after the preprocessing step to see how it is feed to the tokenizer:
```python
print(generate_text.preprocess("Why is drinking water so healthy?")["prompt_text"])
```
```bash
<|prompt|>Why is drinking water so healthy?</s><|answer|>
```
Alternatively, you can download [h2oai_pipeline.py](h2oai_pipeline.py), store it alongside your notebook, and construct the pipeline yourself from the loaded model and tokenizer. If the model and the tokenizer are fully supported in the `transformers` package, this will allow you to set `trust_remote_code=False`.
```python
import torch
from h2oai_pipeline import H2OTextGenerationPipeline
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(
"h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b",
use_fast=False,
padding_side="left",
trust_remote_code=False,
)
model = AutoModelForCausalLM.from_pretrained(
"h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b",
torch_dtype="auto",
device_map={"": "cuda:0"},
trust_remote_code=False,
)
generate_text = H2OTextGenerationPipeline(model=model, tokenizer=tokenizer)
res = generate_text(
"Why is drinking water so healthy?",
min_new_tokens=2,
max_new_tokens=1024,
do_sample=False,
num_beams=1,
temperature=float(0.3),
repetition_penalty=float(1.2),
renormalize_logits=True
)
print(res[0]["generated_text"])
```
You may also construct the pipeline from the loaded model and tokenizer yourself and consider the preprocessing steps:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b" # either local folder or huggingface model name
# Important: The prompt needs to be in the same format the model was trained with.
# You can find an example prompt in the experiment logs.
prompt = "<|prompt|>How are you?</s><|answer|>"
tokenizer = AutoTokenizer.from_pretrained(
model_name,
use_fast=False,
trust_remote_code=False,
)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map={"": "cuda:0"},
trust_remote_code=False,
)
model.cuda().eval()
inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to("cuda")
# generate configuration can be modified to your needs
tokens = model.generate(
**inputs,
min_new_tokens=2,
max_new_tokens=1024,
do_sample=False,
num_beams=1,
temperature=float(0.3),
repetition_penalty=float(1.2),
renormalize_logits=True
)[0]
tokens = tokens[inputs["input_ids"].shape[1]:]
answer = tokenizer.decode(tokens, skip_special_tokens=True)
print(answer)
```
## Model Architecture
```
LlamaForCausalLM(
(model): LlamaModel(
(embed_tokens): Embedding(32000, 4096, padding_idx=0)
(layers): ModuleList(
(0-31): 32 x LlamaDecoderLayer(
(self_attn): LlamaAttention(
(q_proj): Linear(in_features=4096, out_features=4096, bias=False)
(k_proj): Linear(in_features=4096, out_features=4096, bias=False)
(v_proj): Linear(in_features=4096, out_features=4096, bias=False)
(o_proj): Linear(in_features=4096, out_features=4096, bias=False)
(rotary_emb): LlamaRotaryEmbedding()
)
(mlp): LlamaMLP(
(gate_proj): Linear(in_features=4096, out_features=11008, bias=False)
(down_proj): Linear(in_features=11008, out_features=4096, bias=False)
(up_proj): Linear(in_features=4096, out_features=11008, bias=False)
(act_fn): SiLUActivation()
)
(input_layernorm): LlamaRMSNorm()
(post_attention_layernorm): LlamaRMSNorm()
)
)
(norm): LlamaRMSNorm()
)
(lm_head): Linear(in_features=4096, out_features=32000, bias=False)
)
```
## Model Configuration
This model was trained using H2O LLM Studio and with the configuration in [cfg.yaml](cfg.yaml). Visit [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio) to learn how to train your own large language models.
## 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.
|
nomad-ai/ppo-LunarLander-v2-2
|
nomad-ai
| 2023-06-28T14:36:41Z | 0 | 0 | null |
[
"tensorboard",
"LunarLander-v2",
"ppo",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"deep-rl-course",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-28T14:36:36Z |
---
tags:
- LunarLander-v2
- ppo
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
- deep-rl-course
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: -154.13 +/- 82.35
name: mean_reward
verified: false
---
# PPO Agent Playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2.
# Hyperparameters
```python
{'exp_name': 'ppo'
'seed': 1
'torch_deterministic': True
'cuda': True
'track': False
'wandb_project_name': 'cleanRL'
'wandb_entity': None
'capture_video': True
'env_id': 'LunarLander-v2'
'total_timesteps': 100000
'learning_rate': 0.00026
'num_envs': 8
'num_steps': 128
'anneal_lr': True
'gae': True
'gamma': 0.99
'gae_lambda': 0.95
'num_minibatches': 4
'update_epochs': 4
'norm_adv': True
'clip_coef': 0.1
'clip_vloss': True
'ent_coef': 0.1
'vf_coef': 0.5
'max_grad_norm': 0.5
'target_kl': None
'repo_id': 'nomad-ai/ppo-LunarLander-v2-2'
'batch_size': 1024
'minibatch_size': 256}
```
|
LarryAIDraw/onodera_v2-11
|
LarryAIDraw
| 2023-06-28T14:32:51Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-28T14:14:04Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/98354/onodera-kosaki-nisekoi
|
LarryAIDraw/yuiyuigahama
|
LarryAIDraw
| 2023-06-28T14:32:41Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-28T14:13:41Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/98072/yui-yuigahama-my-youth-romantic-comedy-is-wrong-as-i-expected
|
LarryAIDraw/keikaruizawatest
|
LarryAIDraw
| 2023-06-28T14:32:29Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-28T14:13:18Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/98083/kei-karuizawa-classroom-of-the-elite
|
YakovElm/IntelDAOS_5_BERT_Over_Sampling
|
YakovElm
| 2023-06-28T14:28:46Z | 55 | 0 |
transformers
|
[
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-28T14:26:17Z |
---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: IntelDAOS_5_BERT_Over_Sampling
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. -->
# IntelDAOS_5_BERT_Over_Sampling
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.1064
- Train Accuracy: 0.9634
- Validation Loss: 0.8254
- Validation Accuracy: 0.8438
- Epoch: 2
## 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': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.6556 | 0.6035 | 0.7862 | 0.4535 | 0 |
| 0.2479 | 0.9085 | 0.7709 | 0.7598 | 1 |
| 0.1064 | 0.9634 | 0.8254 | 0.8438 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
automaise/quokka-7b
|
automaise
| 2023-06-28T14:13:53Z | 26 | 7 |
transformers
|
[
"transformers",
"pytorch",
"bloom",
"text-generation",
"pt",
"arxiv:1910.09700",
"license:cc-by-nc-4.0",
"co2_eq_emissions",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-14T15:37:56Z |
---
language: pt
license: cc-by-nc-4.0
co2_eq_emissions: 710
---
# Table of Contents
1. [Model description](#model-description)
2. [Intended uses & limitations](#intended-uses--limitations)
3. [Training data](#training-data)
4. [Training procedure](#training-procedure)
5. [Evaluation results](#evaluation-results)
6. [Environmental impact](#environmental-impact)
------
# Quokka
## Model description
Quokka is our first generative pre-trained transformer (GPT) model for Portuguese from Portugal (PT-PT).
Our model is a fine-tuned version of [Phoenix](https://huggingface.co/FreedomIntelligence/phoenix-inst-chat-7b) that was released on 04/08/2023.
The backbone of Phoenix is [BLOOMZ](https://huggingface.co/bigscience/bloomz-7b1-mt), which was fine-tuned using a vast dataset consisting of 267k samples of instructions and 189k samples of conversations.
## Intended uses & limitations
You can use the model for text generation in Portuguese or fine-tune it on a downstream task.
### How to use
You can use this model directly with a pipeline for text generation:
```python
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
checkpoint = "automaise/quokka-7b"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained(checkpoint, device_map="auto")
generator = pipeline("text-generation", model=model, tokenizer=tokenizer, device=0)
```
Follows some examples of the capabilities of our model:
#### Text summarization
```python
prompt = "Quero que ajas como um sumarizador de texto e me ajudes a criar um sumário conciso do seguinte texto apresentado, realçando apenas os pontos essenciais do texto original: Rabo de Peixe, internacionalmente conhecida como Turn of the Tide, foi criada por Augusto Fraga e Patrícia Cerqueira; e produzida para a Netflix pela Ukbar Filmes. A história é protagonizada por um grupo de amigos numa freguesia da ilha de São Miguel e foi inspirada no surgimento, em 2001, de toneladas de cocaína na costa açoriana após ter sido largada no Oceano Atlântico por traficantes. \"Quando um barco carregado de cocaína naufraga na sua ilha natal, Eduardo vê uma oportunidade arriscada, mas empolgante, de ganhar dinheiro e realizar sonhos impossíveis\", diz a sinopse apresentada pela Netflix."
generator(f"<human>{prompt}<bot>", max_new_tokens=512, temperature=0.0)
>> Turn of the Tide é uma série de televisão portuguesa criada por Augusto Fraga e Patrícia Cerqueira para a Netflix. A história é ambientada em uma freguesia da ilha de São Miguel e segue um grupo de amigos que se envolvem em um mistério envolvendo a cocaína que foi largada no Oceano Atlântico em 2001. A série é inspirada em um evento real que ocorreu na costa açoriana.
```
#### Question answering
```python
prompt = "Lê o seguinte texto: Rabo de Peixe, internacionalmente conhecida como Turn of the Tide, foi criada por Augusto Fraga e Patrícia Cerqueira; e produzida para a Netflix pela Ukbar Filmes. A história é protagonizada por um grupo de amigos numa freguesia da ilha de São Miguel e foi inspirada no surgimento, em 2001, de toneladas de cocaína na costa açoriana após ter sido largada no Oceano Atlântico por traficantes. \"Quando um barco carregado de cocaína naufraga na sua ilha natal, Eduardo vê uma oportunidade arriscada, mas empolgante, de ganhar dinheiro e realizar sonhos impossíveis\", diz a sinopse apresentada pela Netflix. \n\n Onde foi filmada a série Rabo de Peixe?"
generator(f"<human>{prompt}<bot>", max_new_tokens=512, temperature=0.0)
>> A série Rabo de Peixe foi filmada na ilha de São Miguel, nos Açores.
```
#### Synthetic data
```python
prompt = "Gera uma frase semelhante à seguinte frase: Bom dia, em que posso ser útil?"
generator(f"<human>{prompt}<bot>", max_new_tokens=512, temperature=0.0)
>> Bom dia, como posso ajudá-lo?
```
### Limitations and bias
* **Language:** the model was fine-tuned on Portuguese data only and might not generalize appropriately to other languages.
* **Prompt Engineering:** the model's performance may vary depending on the prompt. We recommend writing clear
and specific instructions.
* **Bias:** the model might produce factually incorrect outputs or perpetuate biases present in its training data.
It is fundamental to be aware of these limitations and exercise caution when using the model for human-facing interactions.
This bias will also impact all subsequent fine-tuned versions of this model.
We did notice that the model avoids answering questions of religious or political nature:
````python
prompt = "Que partido político é que apoias?"
generator(f"<human>{prompt}<bot>", max_new_tokens=512, temperature=0.0)
>> Como uma IA, não tenho preferências políticas.
````
## Training data
Quokka was fine-tuned on a dataset collected from different sources:
* Initially, we used the **[Cabrita](https://github.com/22-hours/cabrita)** dataset that consists of a translation of Alpaca's training data.
The Portuguese translation was generated using ChatGPT. Therefore, it is important to note that these translations may not be of the highest quality.
* Then, we incorporated the **[Bactrian-X](https://huggingface.co/datasets/MBZUAI/Bactrian-X)** dataset, which involves the
translation of 67k English instructions (52k from Alpaca and 15k from Dolly v2) into 51 languages using Google Translate API.
For our intended purposes, we exclusively selected the Portuguese subset and focused on the samples pertaining to Dolly v2.
Additionally, we conducted data curation to remove elements such as:
* Samples exhibiting a high ratio of prompt length to output length, as these were deemed likely to induce model hallucinations.
* Samples that lost meaning during the translation process, particularly those instructing the translation of a given text.
As a result, our final dataset comprises **56k samples**.
## Training procedure
This model was trained on a **1 x NVIDIA A100 40GB** for about 4-5 hours using QLoRA.
This fine-tuning approach allowed us to significantly reduce memory usage and computation time.
## Evaluation results
To evaluate the performance of our model, we translated [70 questions](https://github.com/FreedomIntelligence/LLMZoo/blob/main/llmzoo/eval/questions/questions-en.jsonl), which were originally used to assess the capabilities of the Phoenix model, from English to Portuguese.
We then conducted their [automatic evaluation](https://github.com/FreedomIntelligence/LLMZoo/tree/main/llmzoo/eval) using GTP-3.5 as the evaluator and the general prompt as the metric evaluation prompt.
This prompt was designed to elicit assessments of answers in terms of helpfulness, relevance, accuracy, and level of detail.
[Additional prompts](https://github.com/FreedomIntelligence/LLMZoo/blob/main/llmzoo/eval/prompts/order/prompt_all.json) are provided for assessing overall performance on different perspectives.
Follows the results against GPT-3.5 and two of the highest performing open-source models at the moment, Vicuna (13B) and Falcon (40B):
* Automatic Evaluation **in Portuguese**:
| | **Lose** | **Tie** | **Win** |
|----------------------------|----------|---------|---------|
| Quokka vs. **GPT-3.5** | 63.8% | 10.1% | 26.1% |
| Quokka vs. **Vicuna-13B** | 66.2% | 8.8% | 25.0% |
| Quokka vs. **Falcon-40B** | 17.4% | 1.4% | 81.2% |
It is important to observe that the automatic evaluation of large language models is still an ongoing area of research and development, and these automatic tests may not always yield fair or comprehensive assessments. Therefore, these results should be taken with caution and not be treated as definitive.
## Environmental impact
Carbon emissions were 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).
The hardware, runtime, cloud provider, and compute region were utilized to estimate the carbon impact.
* **Hardware Type:** 1 x NVIDIA A100 40GB
* **Hours used:** 4-5
* **Cloud Provider:** Google Cloud Platform
* **Compute Region:** europe-west4
* **Carbon Emitted:** 0.71 kg eq. CO2
|
avt1/tmp
|
avt1
| 2023-06-28T14:09:52Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-05-18T14:05:32Z |
---
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
|
Geotrend/bert-base-ar-cased
|
Geotrend
| 2023-06-28T14:04:45Z | 123 | 1 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"jax",
"safetensors",
"bert",
"fill-mask",
"ar",
"dataset:wikipedia",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2022-03-02T23:29:04Z |
---
language: ar
datasets: wikipedia
license: apache-2.0
widget:
- text: "تقع سويسرا في [MASK] أوروبا"
- text: "إسمي محمد وأسكن في [MASK]."
---
# bert-base-ar-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-ar-cased")
model = AutoModel.from_pretrained("Geotrend/bert-base-ar-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.
|
Geotrend/distilbert-base-en-es-pt-cased
|
Geotrend
| 2023-06-28T14:04:07Z | 131 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"distilbert",
"fill-mask",
"multilingual",
"dataset:wikipedia",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2022-03-02T23:29:04Z |
---
language: multilingual
datasets: wikipedia
license: apache-2.0
---
# distilbert-base-en-es-pt-cased
We are sharing smaller versions of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) that handle a custom number of languages.
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/distilbert-base-en-es-pt-cased")
model = AutoModel.from_pretrained("Geotrend/distilbert-base-en-es-pt-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{smallermdistilbert,
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.
|
amm297/tmp_trainer
|
amm297
| 2023-06-28T14:02:26Z | 79 | 0 |
transformers
|
[
"transformers",
"pytorch",
"opt",
"text-generation",
"generated_from_trainer",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-28T13:52:52Z |
---
license: other
tags:
- generated_from_trainer
model-index:
- name: tmp_trainer
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. -->
# tmp_trainer
This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on an unknown 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: 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: 3.0
### Training results
### Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1
- Datasets 2.13.0
- Tokenizers 0.13.3
|
tatiana-merz/mbart-large-50-finetuned-sah-to-feat
|
tatiana-merz
| 2023-06-28T13:56:44Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"mbart",
"text2text-generation",
"generated_from_trainer",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-06-28T10:18:34Z |
---
license: mit
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: mbart-large-50-finetuned-sah-to-feat
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-large-50-finetuned-sah-to-feat
This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4514
- Bleu: 5.5821
- Gen Len: 199.0
## 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: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
| 12.3174 | 1.0 | 24 | 6.7012 | 0.0148 | 199.0 |
| 5.2025 | 2.0 | 48 | 3.9396 | 0.0953 | 199.0 |
| 3.6977 | 3.0 | 72 | 2.1764 | 1.573 | 199.0 |
| 1.884 | 4.0 | 96 | 1.3887 | 3.5395 | 199.0 |
| 1.3753 | 5.0 | 120 | 0.9881 | 5.6111 | 199.0 |
| 0.9707 | 6.0 | 144 | 0.7452 | 5.2841 | 199.0 |
| 0.8008 | 7.0 | 168 | 0.6060 | 5.4831 | 199.0 |
| 0.6444 | 8.0 | 192 | 0.5174 | 5.4302 | 199.0 |
| 0.5689 | 9.0 | 216 | 0.4744 | 5.6898 | 199.0 |
| 0.5244 | 10.0 | 240 | 0.4514 | 5.5821 | 199.0 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1
- Datasets 2.13.1
- Tokenizers 0.13.3
|
StefanV28/HandSigns
|
StefanV28
| 2023-06-28T13:52:10Z | 5 | 0 |
tf-keras
|
[
"tf-keras",
"mobilenet",
"image-classification",
"region:us"
] |
image-classification
| 2023-06-25T21:10:37Z |
---
pipeline_tag: image-classification
---
|
mln-wave/my-pet-dog-xzg
|
mln-wave
| 2023-06-28T13:45:00Z | 17 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"NxtWave-GenAI-Webinar",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-06-28T13:34:16Z |
---
license: creativeml-openrail-m
tags:
- NxtWave-GenAI-Webinar
- text-to-image
- stable-diffusion
---
### My-Pet-Dog-XZG Dreambooth model trained by mln-wave following the "Build your own Gen AI model" session by NxtWave.
Project Submission Code: GoX19738133fad
Sample pictures of this concept:
|
atharputra/ivanaxx1
|
atharputra
| 2023-06-28T13:41:28Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-28T13:39:21Z |
---
license: creativeml-openrail-m
---
|
ryo1443/2ch_rinna_ppo_1k
|
ryo1443
| 2023-06-28T13:37:24Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-28T13:36:54Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
|
weslleylima/my-awesome-setfit-model
|
weslleylima
| 2023-06-28T13:27:42Z | 3 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"mpnet",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
] |
text-classification
| 2023-06-28T12:33:07Z |
---
license: apache-2.0
tags:
- setfit
- sentence-transformers
- text-classification
pipeline_tag: text-classification
---
# weslleylima/my-awesome-setfit-model
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("weslleylima/my-awesome-setfit-model")
# 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}
}
```
|
sleepynlp/q-Taxi-v3-v1-leo
|
sleepynlp
| 2023-06-28T13:26:47Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-28T13:26:43Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-Taxi-v3-v1-leo
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.56 +/- 2.71
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="sleepynlp/q-Taxi-v3-v1-leo", 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"])
```
|
sleepynlp/q-FrozenLake-v1-4x4-noSlippery-leo
|
sleepynlp
| 2023-06-28T13:20:09Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-28T13:20:05Z |
---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery-leo
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
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="sleepynlp/q-FrozenLake-v1-4x4-noSlippery-leo", 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"])
```
|
NickyNicky/MPT-7b-instruct-QLora-8Bits-Peft-h2ogpt_oig_oasst1_instruct_cleaned_v3-0.2_Epoch-V2
|
NickyNicky
| 2023-06-28T13:06:52Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-28T13:06:49Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
|
ZhangJiaxing/path-to-save-model
|
ZhangJiaxing
| 2023-06-28T12:59:07Z | 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
| 2023-06-28T12:21:01Z |
---
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 - ZhangJiaxing/path-to-save-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.
|
hassansoliman/falcon-40b-qlora-utterance-adaptations_v6
|
hassansoliman
| 2023-06-28T12:55:21Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-27T12:07:40Z |
---
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
|
xzuyn/GPT2-RPGPT-8.48M-EPOCH1-GGML
|
xzuyn
| 2023-06-28T12:54:36Z | 0 | 0 | null |
[
"gpt2",
"gpt-2",
"region:us"
] | null | 2023-06-28T12:49:29Z |
---
tags:
- gpt2
- gpt-2
---
# For use with [KoboldCPP](https://github.com/LostRuins/koboldcpp)
Original Model: https://huggingface.co/xzuyn/GPT2-RPGPT-8.48M
|
mln-wave/my-cute-pet-dog-xzg
|
mln-wave
| 2023-06-28T12:49:49Z | 36 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"NxtWave-GenAI-Webinar",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-06-20T12:27:13Z |
---
license: creativeml-openrail-m
tags:
- NxtWave-GenAI-Webinar
- text-to-image
- stable-diffusion
---
### new-concept Dreambooth model trained by mln-wave following the "Build your own Gen AI model" session by NxtWave.
Project Submission Code: GRX1992AAS
Sample pictures of this concept:
|
YakovElm/Qt_20_BERT_Under_Sampling
|
YakovElm
| 2023-06-28T12:49:09Z | 61 | 0 |
transformers
|
[
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-28T12:48:33Z |
---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Qt_20_BERT_Under_Sampling
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. -->
# Qt_20_BERT_Under_Sampling
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.0003
- Train Accuracy: 1.0
- Validation Loss: 0.3606
- Validation Accuracy: 0.9586
- Epoch: 2
## 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': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.0366 | 0.9886 | 0.2979 | 0.9586 | 0 |
| 0.0006 | 1.0 | 0.3361 | 0.9586 | 1 |
| 0.0003 | 1.0 | 0.3606 | 0.9586 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
aksj/falcon-finetuned-openassist
|
aksj
| 2023-06-28T12:48:26Z | 2 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-28T12:47:23Z |
---
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: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.4.0.dev0
|
jensvw/taxi-v3
|
jensvw
| 2023-06-28T12:47:36Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-28T12:47:32Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.54 +/- 2.73
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="jensvw/taxi-v3", 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"])
```
|
robrecht/taxi_v1
|
robrecht
| 2023-06-28T12:44:10Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-28T12:36:05Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: taxi_v1
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.56 +/- 2.71
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="robrecht/taxi_v1", 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"])
```
|
trustvare/trustvare-pst-to-eml
|
trustvare
| 2023-06-28T12:18:10Z | 0 | 0 | null |
[
"region:us"
] | null | 2023-06-28T12:14:23Z |
A trustworthy program for converting Outlook PST files to EML format is TrustVare PST to EML Converter. With the help of this utility, users can extract certain emails from PST files and save them as independent EML files. Users can concurrently convert many PST files to EML thanks to its bulk conversion functionality. Throughout the conversion process, the converter preserves the original email layout, attachments, metadata, and folder structure. Additionally, it offers filters that let users choose only the emails they want to convert based on predetermined criteria. The PST to EML Converter is a useful tool for users and businesses looking to move their Outlook emails to EML format, compatible with a variety of email clients and platforms, thanks to its user-friendly interface and effective conversion capabilities.
Read More: https://www.trustvare.com/pst/eml/
|
gurjotsaggu/Gurjot
|
gurjotsaggu
| 2023-06-28T12:09:05Z | 0 | 0 | null |
[
"license:bigcode-openrail-m",
"region:us"
] | null | 2023-06-28T12:09:05Z |
---
license: bigcode-openrail-m
---
|
Narsil/amall-7b
|
Narsil
| 2023-06-28T12:05:23Z | 30 | 1 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"llama",
"text-generation",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-26T08:11:43Z |
---
license: other
duplicated_from: huggingface/llama-7b
---
|
mahsa-gh/my_awesome_model
|
mahsa-gh
| 2023-06-28T11:55:49Z | 61 | 0 |
transformers
|
[
"transformers",
"tf",
"distilbert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-27T04:12:07Z |
---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: mahsa-gh/my_awesome_model
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. -->
# mahsa-gh/my_awesome_model
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.0625
- Validation Loss: 0.2113
- Train Accuracy: 0.9318
- Epoch: 2
## 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': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 7810, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|:----------:|:---------------:|:--------------:|:-----:|
| 0.2532 | 0.1893 | 0.9288 | 0 |
| 0.1336 | 0.1840 | 0.9321 | 1 |
| 0.0625 | 0.2113 | 0.9318 | 2 |
### Framework versions
- Transformers 4.28.1
- TensorFlow 2.11.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
anzorq/ru-kbd_lat-t5-small
|
anzorq
| 2023-06-28T11:55:47Z | 171 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"ru",
"kbd",
"dataset:anzorq/kbd_lat-ru",
"license:mit",
"model-index",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2022-07-27T08:27:57Z |
---
language:
- ru
- kbd
license: mit
tags:
- generated_from_trainer
datasets:
- anzorq/kbd_lat-ru
metrics:
- bleu
model-index:
- name: tst-translation
results:
- task:
name: translation
type: translation
dataset:
name: anzorq/kbd_lat-ru anzorq--kbd-ru
type: anzorq/kbd_lat-ru
args: anzorq--kbd-ru
metrics:
- name: Bleu
type: bleu
value: 12.649
widget:
- text: "ru->kbd: Я иду домой."
example_title: "Я иду домой."
- text: "ru->kbd: Дети играют во дворе."
example_title: "Дети играют во дворе."
- text: "ru->kbd: Сколько тебе лет?"
example_title: "Сколько тебе лет?"
---
<!-- 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. -->
# tst-translation
This model is a fine-tuned version of [anzorq/kbd_lat-835k_ru-3M_t5-small](https://huggingface.co/anzorq/kbd_lat-835k_ru-3M_t5-small) on the anzorq/kbd_lat-ru anzorq--kbd-ru dataset.
It achieves the following results on the evaluation set:
- Loss: 2.6000
- Bleu: 12.649
- Gen Len: 11.8018
## 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: 30
- eval_batch_size: 30
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 35.0
### Training results
### Framework versions
- Transformers 4.21.0.dev0
- Pytorch 1.10.0+cu113
- Datasets 1.16.0
- Tokenizers 0.12.1
|
catrabbitbear/pyramids1
|
catrabbitbear
| 2023-06-28T11:51:08Z | 2 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Pyramids",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Pyramids",
"region:us"
] |
reinforcement-learning
| 2023-06-28T11:51:06Z |
---
library_name: ml-agents
tags:
- Pyramids
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Pyramids
---
# **ppo** Agent playing **Pyramids**
This is a trained model of a **ppo** agent playing **Pyramids**
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: catrabbitbear/pyramids1
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
abhishekkrtrivedi995/flan-t5-base-hai
|
abhishekkrtrivedi995
| 2023-06-28T11:50:42Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-06-28T06:33:17Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: flan-t5-base-hai
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. -->
# flan-t5-base-hai
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6881
- Rouge1: 39.7841
- Rouge2: 29.2031
- Rougel: 36.6883
- Rougelsum: 37.533
- Gen Len: 17.5106
## 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: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
| No log | 1.0 | 118 | 0.9586 | 35.7723 | 22.9975 | 32.3447 | 33.2069 | 17.4894 |
| No log | 2.0 | 236 | 0.8239 | 36.2962 | 24.2274 | 33.1222 | 33.8173 | 17.5447 |
| No log | 3.0 | 354 | 0.7414 | 38.4245 | 27.3598 | 35.4793 | 36.3822 | 17.6596 |
| No log | 4.0 | 472 | 0.6988 | 39.386 | 28.7308 | 36.4217 | 37.2752 | 17.5277 |
| 0.8817 | 5.0 | 590 | 0.6881 | 39.7841 | 29.2031 | 36.6883 | 37.533 | 17.5106 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
czz23/SplitStatement-setfit-model
|
czz23
| 2023-06-28T11:47:11Z | 3 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"albert",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
] |
text-classification
| 2023-06-28T11:47:08Z |
---
license: apache-2.0
tags:
- setfit
- sentence-transformers
- text-classification
pipeline_tag: text-classification
---
# czz23/SplitStatement-setfit-model
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("czz23/SplitStatement-setfit-model")
# 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}
}
```
|
Bodolaz/Unit-4.2-final3
|
Bodolaz
| 2023-06-28T11:26:20Z | 0 | 0 | null |
[
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-28T11:26:15Z |
---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Unit-4.2-final3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 40.00 +/- 24.24
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
|
hztang/t5-small-base-custom
|
hztang
| 2023-06-28T11:18:41Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-06-28T09:29:18Z |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: t5-large-base-custom
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. -->
# t5-large-base-custom
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None 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: 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: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
| No log | 1.0 | 238 | 1.0463 | 25.3323 | 19.1916 | 23.8957 | 24.792 | 19.0 |
### Framework versions
- Transformers 4.30.2
- Pytorch 1.12.1
- Datasets 2.13.1
- Tokenizers 0.11.0
|
NickyNicky/MPT-7b-instruct-QLora-8Bits-Peft-train_eli5-1_Epoch-V8
|
NickyNicky
| 2023-06-28T11:09:07Z | 2 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-28T11:09:03Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
|
mnavas/bert-finetuned-token-reqsolvgencat
|
mnavas
| 2023-06-28T10:34:36Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"token-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2023-06-28T09:43:30Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: beto-finetuned-token-reqsolvgencat
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. -->
# beto-finetuned-token-reqsolvgencat
This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0573
- Precision: 0.1111
- Recall: 0.5
- F1: 0.1818
- Accuracy: 0.7765
## 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
- num_epochs: 200
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.8551 | 1.0 | 3 | 1.1478 | 0.0 | 0.0 | 0.0 | 0.4696 |
| 1.4354 | 2.0 | 6 | 0.7403 | 0.0 | 0.0 | 0.0 | 0.6088 |
| 0.6532 | 3.0 | 9 | 0.6900 | 0.0 | 0.0 | 0.0 | 0.6010 |
| 0.406 | 4.0 | 12 | 2.0318 | 0.0 | 0.0 | 0.0 | 0.5284 |
| 1.3514 | 5.0 | 15 | 1.3364 | 0.0 | 0.0 | 0.0 | 0.6186 |
| 0.419 | 6.0 | 18 | 0.9463 | 0.0 | 0.0 | 0.0 | 0.6 |
| 0.4816 | 7.0 | 21 | 0.9409 | 0.0 | 0.0 | 0.0 | 0.6314 |
| 0.8621 | 8.0 | 24 | 0.9034 | 0.0 | 0.0 | 0.0 | 0.7010 |
| 0.2981 | 9.0 | 27 | 0.9617 | 0.0 | 0.0 | 0.0 | 0.6039 |
| 0.5882 | 10.0 | 30 | 0.5289 | 0.0 | 0.0 | 0.0 | 0.8 |
| 0.4327 | 11.0 | 33 | 0.6573 | 0.2 | 0.5 | 0.2857 | 0.7882 |
| 0.2076 | 12.0 | 36 | 0.9207 | 0.0 | 0.0 | 0.0 | 0.6784 |
| 0.1454 | 13.0 | 39 | 0.7729 | 0.0 | 0.0 | 0.0 | 0.7882 |
| 0.2339 | 14.0 | 42 | 0.9067 | 0.0 | 0.0 | 0.0 | 0.7608 |
| 0.2281 | 15.0 | 45 | 0.4732 | 0.0 | 0.0 | 0.0 | 0.7892 |
| 0.1058 | 16.0 | 48 | 0.8219 | 0.0667 | 0.5 | 0.1176 | 0.7961 |
| 0.0577 | 17.0 | 51 | 0.9698 | 0.1429 | 0.5 | 0.2222 | 0.8147 |
| 0.0354 | 18.0 | 54 | 1.3158 | 0.0714 | 0.5 | 0.125 | 0.7549 |
| 0.0258 | 19.0 | 57 | 2.2414 | 0.1667 | 0.5 | 0.25 | 0.6941 |
| 0.0456 | 20.0 | 60 | 1.2596 | 0.0667 | 0.5 | 0.1176 | 0.7520 |
| 0.0339 | 21.0 | 63 | 1.8941 | 0.1667 | 0.5 | 0.25 | 0.7069 |
| 0.02 | 22.0 | 66 | 1.0201 | 0.1 | 0.5 | 0.1667 | 0.7941 |
| 0.0257 | 23.0 | 69 | 1.4716 | 0.0909 | 0.5 | 0.1538 | 0.7716 |
| 0.0148 | 24.0 | 72 | 2.6551 | 0.0 | 0.0 | 0.0 | 0.6853 |
| 0.0257 | 25.0 | 75 | 1.7904 | 0.125 | 0.5 | 0.2 | 0.7324 |
| 0.0183 | 26.0 | 78 | 2.2579 | 0.2 | 0.5 | 0.2857 | 0.7078 |
| 0.0218 | 27.0 | 81 | 1.3332 | 0.1667 | 0.5 | 0.25 | 0.7137 |
| 0.0148 | 28.0 | 84 | 0.7506 | 0.0769 | 0.5 | 0.1333 | 0.8696 |
| 0.0081 | 29.0 | 87 | 2.2165 | 0.1667 | 0.5 | 0.25 | 0.7059 |
| 0.0098 | 30.0 | 90 | 2.5291 | 0.2 | 0.5 | 0.2857 | 0.7 |
| 0.0072 | 31.0 | 93 | 2.5877 | 0.25 | 0.5 | 0.3333 | 0.6990 |
| 0.0162 | 32.0 | 96 | 2.7463 | 0.1667 | 0.5 | 0.25 | 0.6941 |
| 0.0073 | 33.0 | 99 | 2.2100 | 0.1429 | 0.5 | 0.2222 | 0.7176 |
| 0.0057 | 34.0 | 102 | 1.5509 | 0.0769 | 0.5 | 0.1333 | 0.7814 |
| 0.0077 | 35.0 | 105 | 1.8449 | 0.1111 | 0.5 | 0.1818 | 0.7578 |
| 0.0071 | 36.0 | 108 | 2.3808 | 0.3333 | 0.5 | 0.4 | 0.7127 |
| 0.0063 | 37.0 | 111 | 1.1188 | 0.125 | 0.5 | 0.2 | 0.8598 |
| 0.0067 | 38.0 | 114 | 1.7108 | 0.0 | 0.0 | 0.0 | 0.7892 |
| 0.0063 | 39.0 | 117 | 1.8995 | 0.1 | 0.5 | 0.1667 | 0.7363 |
| 0.0086 | 40.0 | 120 | 2.0472 | 0.1667 | 0.5 | 0.25 | 0.7137 |
| 0.0028 | 41.0 | 123 | 1.8879 | 0.1111 | 0.5 | 0.1818 | 0.7245 |
| 0.0084 | 42.0 | 126 | 1.9545 | 0.1667 | 0.5 | 0.25 | 0.7157 |
| 0.0018 | 43.0 | 129 | 2.5274 | 0.0 | 0.0 | 0.0 | 0.6922 |
| 0.0031 | 44.0 | 132 | 2.0330 | 0.0909 | 0.5 | 0.1538 | 0.7245 |
| 0.0034 | 45.0 | 135 | 0.9381 | 0.1 | 0.5 | 0.1667 | 0.8569 |
| 0.0016 | 46.0 | 138 | 0.6307 | 0.1111 | 0.5 | 0.1818 | 0.8980 |
| 0.0011 | 47.0 | 141 | 0.7823 | 0.0667 | 0.5 | 0.1176 | 0.8676 |
| 0.0021 | 48.0 | 144 | 1.1034 | 0.0909 | 0.5 | 0.1538 | 0.8373 |
| 0.0025 | 49.0 | 147 | 1.4482 | 0.2 | 0.5 | 0.2857 | 0.8108 |
| 0.0023 | 50.0 | 150 | 1.5541 | 0.1667 | 0.5 | 0.25 | 0.8069 |
| 0.0007 | 51.0 | 153 | 1.7164 | 0.1667 | 0.5 | 0.25 | 0.8010 |
| 0.0002 | 52.0 | 156 | 1.8291 | 0.1667 | 0.5 | 0.25 | 0.7941 |
| 0.0002 | 53.0 | 159 | 1.8918 | 0.1429 | 0.5 | 0.2222 | 0.7892 |
| 0.0016 | 54.0 | 162 | 1.8814 | 0.2 | 0.5 | 0.2857 | 0.7961 |
| 0.0013 | 55.0 | 165 | 1.8920 | 0.1 | 0.5 | 0.1667 | 0.7873 |
| 0.0009 | 56.0 | 168 | 1.8802 | 0.1 | 0.5 | 0.1667 | 0.7843 |
| 0.0017 | 57.0 | 171 | 1.7839 | 0.1111 | 0.5 | 0.1818 | 0.8 |
| 0.0028 | 58.0 | 174 | 1.7409 | 0.1 | 0.5 | 0.1667 | 0.7961 |
| 0.0029 | 59.0 | 177 | 2.1381 | 0.1 | 0.5 | 0.1667 | 0.7196 |
| 0.0008 | 60.0 | 180 | 2.4554 | 0.125 | 0.5 | 0.2 | 0.6922 |
| 0.0012 | 61.0 | 183 | 2.7071 | 0.125 | 0.5 | 0.2 | 0.6676 |
| 0.0011 | 62.0 | 186 | 2.5624 | 0.125 | 0.5 | 0.2 | 0.6814 |
| 0.0009 | 63.0 | 189 | 2.1029 | 0.2 | 0.5 | 0.2857 | 0.7363 |
| 0.0011 | 64.0 | 192 | 1.5984 | 0.125 | 0.5 | 0.2 | 0.7804 |
| 0.0005 | 65.0 | 195 | 1.4155 | 0.0909 | 0.5 | 0.1538 | 0.8088 |
| 0.001 | 66.0 | 198 | 1.3276 | 0.1111 | 0.5 | 0.1818 | 0.8225 |
| 0.0002 | 67.0 | 201 | 1.2844 | 0.1429 | 0.5 | 0.2222 | 0.8255 |
| 0.0076 | 68.0 | 204 | 1.2601 | 0.1667 | 0.5 | 0.25 | 0.8275 |
| 0.0003 | 69.0 | 207 | 1.3359 | 0.1429 | 0.5 | 0.2222 | 0.8343 |
| 0.0027 | 70.0 | 210 | 1.2452 | 0.25 | 0.5 | 0.3333 | 0.8363 |
| 0.004 | 71.0 | 213 | 1.7228 | 0.1 | 0.5 | 0.1667 | 0.7775 |
| 0.0004 | 72.0 | 216 | 2.7878 | 0.5 | 0.5 | 0.5 | 0.6804 |
| 1.1257 | 73.0 | 219 | 2.5785 | 0.5 | 0.5 | 0.5 | 0.6804 |
| 0.0209 | 74.0 | 222 | 0.1081 | 0.1111 | 0.5 | 0.1818 | 0.9775 |
| 0.0486 | 75.0 | 225 | 1.5039 | 0.0667 | 0.5 | 0.1176 | 0.7784 |
| 0.0012 | 76.0 | 228 | 3.2975 | 0.0 | 0.0 | 0.0 | 0.6098 |
| 0.0929 | 77.0 | 231 | 2.4796 | 0.3333 | 0.5 | 0.4 | 0.6618 |
| 0.0006 | 78.0 | 234 | 1.6117 | 0.125 | 0.5 | 0.2 | 0.7951 |
| 0.0077 | 79.0 | 237 | 1.8651 | 0.125 | 0.5 | 0.2 | 0.7127 |
| 0.0032 | 80.0 | 240 | 2.0187 | 0.1667 | 0.5 | 0.25 | 0.6873 |
| 0.0007 | 81.0 | 243 | 1.9540 | 0.1 | 0.5 | 0.1667 | 0.6902 |
| 0.0011 | 82.0 | 246 | 1.8161 | 0.0714 | 0.5 | 0.125 | 0.7275 |
| 0.0009 | 83.0 | 249 | 1.7688 | 0.1111 | 0.5 | 0.1818 | 0.7657 |
| 0.0006 | 84.0 | 252 | 1.7025 | 0.1667 | 0.5 | 0.25 | 0.7912 |
| 0.0003 | 85.0 | 255 | 1.6924 | 0.2 | 0.5 | 0.2857 | 0.7980 |
| 0.0004 | 86.0 | 258 | 1.7019 | 0.1667 | 0.5 | 0.25 | 0.7980 |
| 0.0008 | 87.0 | 261 | 1.7386 | 0.2 | 0.5 | 0.2857 | 0.7971 |
| 0.0002 | 88.0 | 264 | 1.7882 | 0.1667 | 0.5 | 0.25 | 0.7961 |
| 0.0001 | 89.0 | 267 | 1.8405 | 0.0833 | 0.5 | 0.1429 | 0.7833 |
| 0.0004 | 90.0 | 270 | 1.8319 | 0.125 | 0.5 | 0.2 | 0.7931 |
| 0.0003 | 91.0 | 273 | 1.8520 | 0.125 | 0.5 | 0.2 | 0.7931 |
| 0.0001 | 92.0 | 276 | 1.8876 | 0.0909 | 0.5 | 0.1538 | 0.7873 |
| 0.0001 | 93.0 | 279 | 1.9220 | 0.1 | 0.5 | 0.1667 | 0.7814 |
| 0.0004 | 94.0 | 282 | 2.0870 | 0.1 | 0.5 | 0.1667 | 0.7333 |
| 0.0004 | 95.0 | 285 | 2.1469 | 0.1111 | 0.5 | 0.1818 | 0.7225 |
| 0.0009 | 96.0 | 288 | 2.1726 | 0.1429 | 0.5 | 0.2222 | 0.7196 |
| 0.0007 | 97.0 | 291 | 1.9247 | 0.1 | 0.5 | 0.1667 | 0.7667 |
| 0.0012 | 98.0 | 294 | 1.8172 | 0.1111 | 0.5 | 0.1818 | 0.7902 |
| 0.0002 | 99.0 | 297 | 1.7789 | 0.1 | 0.5 | 0.1667 | 0.7980 |
| 0.0109 | 100.0 | 300 | 1.8386 | 0.0909 | 0.5 | 0.1538 | 0.7843 |
| 0.0008 | 101.0 | 303 | 2.0800 | 0.1 | 0.5 | 0.1667 | 0.7314 |
| 0.0002 | 102.0 | 306 | 2.5253 | 0.3333 | 0.5 | 0.4 | 0.6804 |
| 0.001 | 103.0 | 309 | 2.2149 | 0.1 | 0.5 | 0.1667 | 0.7118 |
| 0.0001 | 104.0 | 312 | 1.8607 | 0.1 | 0.5 | 0.1667 | 0.8020 |
| 0.0002 | 105.0 | 315 | 1.7786 | 0.1 | 0.5 | 0.1667 | 0.8127 |
| 0.0009 | 106.0 | 318 | 1.8432 | 0.125 | 0.5 | 0.2 | 0.8078 |
| 0.0001 | 107.0 | 321 | 2.0339 | 0.1111 | 0.5 | 0.1818 | 0.7784 |
| 0.0001 | 108.0 | 324 | 2.2628 | 0.0769 | 0.5 | 0.1333 | 0.7392 |
| 0.0007 | 109.0 | 327 | 2.3649 | 0.0714 | 0.5 | 0.125 | 0.7265 |
| 0.0001 | 110.0 | 330 | 2.4330 | 0.0714 | 0.5 | 0.125 | 0.7137 |
| 0.0001 | 111.0 | 333 | 2.4918 | 0.1 | 0.5 | 0.1667 | 0.7059 |
| 0.0002 | 112.0 | 336 | 2.2853 | 0.0909 | 0.5 | 0.1538 | 0.7647 |
| 0.0001 | 113.0 | 339 | 2.1945 | 0.1 | 0.5 | 0.1667 | 0.7765 |
| 0.0001 | 114.0 | 342 | 2.1446 | 0.1111 | 0.5 | 0.1818 | 0.7824 |
| 0.0008 | 115.0 | 345 | 2.1037 | 0.1111 | 0.5 | 0.1818 | 0.7863 |
| 0.0001 | 116.0 | 348 | 2.0753 | 0.1 | 0.5 | 0.1667 | 0.7902 |
| 0.0001 | 117.0 | 351 | 2.0617 | 0.1 | 0.5 | 0.1667 | 0.7902 |
| 0.0014 | 118.0 | 354 | 1.9908 | 0.1111 | 0.5 | 0.1818 | 0.7961 |
| 0.0009 | 119.0 | 357 | 1.9134 | 0.1111 | 0.5 | 0.1818 | 0.8 |
| 0.0009 | 120.0 | 360 | 1.8651 | 0.1111 | 0.5 | 0.1818 | 0.8020 |
| 0.0002 | 121.0 | 363 | 1.8480 | 0.1111 | 0.5 | 0.1818 | 0.8 |
| 0.0001 | 122.0 | 366 | 1.8558 | 0.0909 | 0.5 | 0.1538 | 0.7961 |
| 0.0001 | 123.0 | 369 | 1.8727 | 0.1111 | 0.5 | 0.1818 | 0.7892 |
| 0.0001 | 124.0 | 372 | 1.8951 | 0.125 | 0.5 | 0.2 | 0.7863 |
| 0.0007 | 125.0 | 375 | 1.8971 | 0.1667 | 0.5 | 0.25 | 0.7833 |
| 0.0011 | 126.0 | 378 | 1.8479 | 0.1667 | 0.5 | 0.25 | 0.7814 |
| 0.0002 | 127.0 | 381 | 1.7985 | 0.1429 | 0.5 | 0.2222 | 0.7804 |
| 0.0001 | 128.0 | 384 | 1.7712 | 0.125 | 0.5 | 0.2 | 0.7794 |
| 0.0001 | 129.0 | 387 | 1.7929 | 0.1111 | 0.5 | 0.1818 | 0.7755 |
| 0.0002 | 130.0 | 390 | 1.8551 | 0.1111 | 0.5 | 0.1818 | 0.7725 |
| 0.0001 | 131.0 | 393 | 1.9030 | 0.125 | 0.5 | 0.2 | 0.7716 |
| 0.0001 | 132.0 | 396 | 1.9421 | 0.125 | 0.5 | 0.2 | 0.7686 |
| 0.0009 | 133.0 | 399 | 1.9440 | 0.125 | 0.5 | 0.2 | 0.7686 |
| 0.0001 | 134.0 | 402 | 1.9455 | 0.125 | 0.5 | 0.2 | 0.7686 |
| 0.0001 | 135.0 | 405 | 1.9527 | 0.125 | 0.5 | 0.2 | 0.7686 |
| 0.0004 | 136.0 | 408 | 1.9493 | 0.125 | 0.5 | 0.2 | 0.7706 |
| 0.0001 | 137.0 | 411 | 1.9432 | 0.125 | 0.5 | 0.2 | 0.7706 |
| 0.0001 | 138.0 | 414 | 1.9491 | 0.125 | 0.5 | 0.2 | 0.7706 |
| 0.0002 | 139.0 | 417 | 1.9434 | 0.1 | 0.5 | 0.1667 | 0.7735 |
| 0.0006 | 140.0 | 420 | 1.9363 | 0.1111 | 0.5 | 0.1818 | 0.7784 |
| 0.0001 | 141.0 | 423 | 1.9330 | 0.1111 | 0.5 | 0.1818 | 0.7804 |
| 0.0001 | 142.0 | 426 | 1.9334 | 0.1111 | 0.5 | 0.1818 | 0.7833 |
| 0.0001 | 143.0 | 429 | 1.9366 | 0.125 | 0.5 | 0.2 | 0.7843 |
| 0.0001 | 144.0 | 432 | 1.9417 | 0.1111 | 0.5 | 0.1818 | 0.7843 |
| 0.0001 | 145.0 | 435 | 1.9467 | 0.1111 | 0.5 | 0.1818 | 0.7843 |
| 0.0001 | 146.0 | 438 | 1.9518 | 0.1111 | 0.5 | 0.1818 | 0.7843 |
| 0.0001 | 147.0 | 441 | 1.9574 | 0.1111 | 0.5 | 0.1818 | 0.7853 |
| 0.0001 | 148.0 | 444 | 1.9635 | 0.1111 | 0.5 | 0.1818 | 0.7853 |
| 0.0003 | 149.0 | 447 | 1.9643 | 0.1111 | 0.5 | 0.1818 | 0.7853 |
| 0.0001 | 150.0 | 450 | 1.9664 | 0.125 | 0.5 | 0.2 | 0.7853 |
| 0.0008 | 151.0 | 453 | 1.9830 | 0.125 | 0.5 | 0.2 | 0.7843 |
| 0.0001 | 152.0 | 456 | 1.9974 | 0.125 | 0.5 | 0.2 | 0.7824 |
| 0.0001 | 153.0 | 459 | 2.0083 | 0.125 | 0.5 | 0.2 | 0.7824 |
| 0.0007 | 154.0 | 462 | 2.0066 | 0.1111 | 0.5 | 0.1818 | 0.7833 |
| 0.0001 | 155.0 | 465 | 2.0047 | 0.1111 | 0.5 | 0.1818 | 0.7833 |
| 0.0001 | 156.0 | 468 | 2.0042 | 0.1111 | 0.5 | 0.1818 | 0.7833 |
| 0.0001 | 157.0 | 471 | 2.0075 | 0.1111 | 0.5 | 0.1818 | 0.7833 |
| 0.0008 | 158.0 | 474 | 2.0217 | 0.1111 | 0.5 | 0.1818 | 0.7824 |
| 0.0001 | 159.0 | 477 | 2.0326 | 0.125 | 0.5 | 0.2 | 0.7814 |
| 0.0001 | 160.0 | 480 | 2.0422 | 0.125 | 0.5 | 0.2 | 0.7814 |
| 0.0001 | 161.0 | 483 | 2.0493 | 0.125 | 0.5 | 0.2 | 0.7804 |
| 0.0001 | 162.0 | 486 | 2.0568 | 0.125 | 0.5 | 0.2 | 0.7804 |
| 0.0002 | 163.0 | 489 | 2.0818 | 0.125 | 0.5 | 0.2 | 0.7755 |
| 0.0001 | 164.0 | 492 | 2.0997 | 0.125 | 0.5 | 0.2 | 0.7755 |
| 0.0001 | 165.0 | 495 | 2.1127 | 0.125 | 0.5 | 0.2 | 0.7745 |
| 0.0001 | 166.0 | 498 | 2.1226 | 0.125 | 0.5 | 0.2 | 0.7745 |
| 0.0001 | 167.0 | 501 | 2.1311 | 0.1111 | 0.5 | 0.1818 | 0.7716 |
| 0.0001 | 168.0 | 504 | 2.1377 | 0.1111 | 0.5 | 0.1818 | 0.7716 |
| 0.0003 | 169.0 | 507 | 2.1296 | 0.1111 | 0.5 | 0.1818 | 0.7716 |
| 0.0001 | 170.0 | 510 | 2.1180 | 0.125 | 0.5 | 0.2 | 0.7745 |
| 0.0 | 171.0 | 513 | 2.1095 | 0.125 | 0.5 | 0.2 | 0.7745 |
| 0.0 | 172.0 | 516 | 2.1035 | 0.125 | 0.5 | 0.2 | 0.7745 |
| 0.0001 | 173.0 | 519 | 2.0999 | 0.125 | 0.5 | 0.2 | 0.7745 |
| 0.0 | 174.0 | 522 | 2.0984 | 0.125 | 0.5 | 0.2 | 0.7745 |
| 0.0004 | 175.0 | 525 | 2.0930 | 0.125 | 0.5 | 0.2 | 0.7755 |
| 0.0 | 176.0 | 528 | 2.0874 | 0.125 | 0.5 | 0.2 | 0.7755 |
| 0.006 | 177.0 | 531 | 2.0807 | 0.125 | 0.5 | 0.2 | 0.7755 |
| 0.0001 | 178.0 | 534 | 2.0717 | 0.125 | 0.5 | 0.2 | 0.7755 |
| 0.0001 | 179.0 | 537 | 2.0721 | 0.125 | 0.5 | 0.2 | 0.7755 |
| 0.0001 | 180.0 | 540 | 2.0731 | 0.125 | 0.5 | 0.2 | 0.7755 |
| 0.001 | 181.0 | 543 | 2.0712 | 0.125 | 0.5 | 0.2 | 0.7745 |
| 0.0001 | 182.0 | 546 | 2.0700 | 0.125 | 0.5 | 0.2 | 0.7745 |
| 0.0001 | 183.0 | 549 | 2.0692 | 0.125 | 0.5 | 0.2 | 0.7745 |
| 0.0001 | 184.0 | 552 | 2.0622 | 0.125 | 0.5 | 0.2 | 0.7755 |
| 0.0006 | 185.0 | 555 | 2.0582 | 0.125 | 0.5 | 0.2 | 0.7755 |
| 0.0001 | 186.0 | 558 | 2.0564 | 0.125 | 0.5 | 0.2 | 0.7755 |
| 0.0001 | 187.0 | 561 | 2.0562 | 0.125 | 0.5 | 0.2 | 0.7745 |
| 0.0001 | 188.0 | 564 | 2.0571 | 0.125 | 0.5 | 0.2 | 0.7745 |
| 0.0001 | 189.0 | 567 | 2.0587 | 0.125 | 0.5 | 0.2 | 0.7745 |
| 0.0001 | 190.0 | 570 | 2.0597 | 0.1111 | 0.5 | 0.1818 | 0.7735 |
| 0.0041 | 191.0 | 573 | 2.0555 | 0.125 | 0.5 | 0.2 | 0.7745 |
| 0.0002 | 192.0 | 576 | 2.0473 | 0.1111 | 0.5 | 0.1818 | 0.7765 |
| 0.0001 | 193.0 | 579 | 2.0480 | 0.1111 | 0.5 | 0.1818 | 0.7765 |
| 0.0002 | 194.0 | 582 | 2.0507 | 0.1111 | 0.5 | 0.1818 | 0.7765 |
| 0.0001 | 195.0 | 585 | 2.0541 | 0.1111 | 0.5 | 0.1818 | 0.7765 |
| 0.0001 | 196.0 | 588 | 2.0562 | 0.1111 | 0.5 | 0.1818 | 0.7765 |
| 0.0001 | 197.0 | 591 | 2.0586 | 0.1111 | 0.5 | 0.1818 | 0.7765 |
| 0.0001 | 198.0 | 594 | 2.0596 | 0.1111 | 0.5 | 0.1818 | 0.7765 |
| 0.0001 | 199.0 | 597 | 2.0604 | 0.1111 | 0.5 | 0.1818 | 0.7765 |
| 0.0003 | 200.0 | 600 | 2.0573 | 0.1111 | 0.5 | 0.1818 | 0.7765 |
### Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
NasimB/gpt2-dp-cl-length
|
NasimB
| 2023-06-28T10:24:24Z | 4 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt2",
"text-generation",
"generated_from_trainer",
"dataset:generator",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-28T07:55:52Z |
---
license: mit
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: gpt2-dp-cl-length
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. -->
# gpt2-dp-cl-length
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 4.7161
## 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: 0.0005
- 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: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 7
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 6.6691 | 0.26 | 500 | 5.8270 |
| 5.2775 | 0.53 | 1000 | 5.4588 |
| 4.9444 | 0.79 | 1500 | 5.2410 |
| 4.7094 | 1.05 | 2000 | 5.1417 |
| 4.5245 | 1.31 | 2500 | 4.9932 |
| 4.4306 | 1.58 | 3000 | 4.9406 |
| 4.3594 | 1.84 | 3500 | 4.9073 |
| 4.2194 | 2.1 | 4000 | 4.8631 |
| 4.0996 | 2.36 | 4500 | 4.8316 |
| 4.0865 | 2.63 | 5000 | 4.7686 |
| 4.05 | 2.89 | 5500 | 4.7494 |
| 3.8858 | 3.15 | 6000 | 4.7704 |
| 3.814 | 3.42 | 6500 | 4.6998 |
| 3.8032 | 3.68 | 7000 | 4.6793 |
| 3.7885 | 3.94 | 7500 | 4.6676 |
| 3.5761 | 4.2 | 8000 | 4.6765 |
| 3.5336 | 4.47 | 8500 | 4.6792 |
| 3.535 | 4.73 | 9000 | 4.6749 |
| 3.5307 | 4.99 | 9500 | 4.6553 |
| 3.2929 | 5.25 | 10000 | 4.7027 |
| 3.2874 | 5.52 | 10500 | 4.6926 |
| 3.2883 | 5.78 | 11000 | 4.6927 |
| 3.2606 | 6.04 | 11500 | 4.7025 |
| 3.1356 | 6.31 | 12000 | 4.7098 |
| 3.1392 | 6.57 | 12500 | 4.7123 |
| 3.1374 | 6.83 | 13000 | 4.7161 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
|
amittian/setfit_ds_version_0_0_1
|
amittian
| 2023-06-28T10:23:28Z | 3 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"mpnet",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
] |
text-classification
| 2023-06-28T10:23:07Z |
---
license: apache-2.0
tags:
- setfit
- sentence-transformers
- text-classification
pipeline_tag: text-classification
---
# amittian/setfit_ds_version_0_0_1
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_1")
# 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}
}
```
|
rawkul/q.taxi.v3
|
rawkul
| 2023-06-28T10:20:40Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-28T09:44:41Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q.taxi.v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.56 +/- 2.71
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="rawkul/q.taxi.v3", 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"])
```
|
KamilAin/bart-base-booksum
|
KamilAin
| 2023-06-28T10:19:50Z | 129 | 1 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"bart",
"text2text-generation",
"booksum",
"summary",
"summarization",
"book",
"en",
"dataset:kmfoda/booksum",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
summarization
| 2022-05-23T13:46:59Z |
---
language: en
license: apache-2.0
tags:
- booksum
- summary
- summarization
- book
metrics:
- rouge
widget:
- text: "In the dead night, Frodo lay in a dream without light. Then he saw the young moon rising; under its thin light there loomed before him a black wall of rock, pierced by a dark arch like a great gate. It seemed to Frodo that he was lifted up, and passing over he saw that the rock-wall was a circle of hills, and that within it was a plain, and in the midst of the plain stood a pinnacle of stone, like a vast tower but not made by hands. On its top stood the figure of a man. The moon as it rose seemed to hang for a moment above his head and glistened in his white hair as the wind stirred it. Up from the dark plain below came the crying of fell voices, and the howling of many wolves. Suddenly a shadow, like the shape of great wings, passed across the moon. The figure lifted his arms and a light flashed from the staff that he wielded. A mighty eagle swept down and bore him away. The voices wailed and the wolves yammered. There was a noise like a strong wind blowing, and on it was borne the sound of hoofs, galloping, galloping, galloping from the East. ‘Black Riders!’ thought Frodo as he wakened, with the sound of the hoofs still echoing in his mind. He wondered if he would ever again have the courage to leave the safety of these stone walls. He lay motionless, still listening; but all was now silent, and at last he turned and fell asleep again or wandered into some other unremembered dream."
example_title: "book example"
datasets:
- kmfoda/booksum
---
# BART-base-Booksum
This is a BART-base model fine-tuned on a BookSum dataset
- **Use cases:** book summarization, general text summarization.
- This is a [`https://huggingface.co/facebook/bart-base`](https://huggingface.co/facebook/bart-base), fine-tuned for five epochs
|
jondurbin/airoboros-33b-gpt4-1.4
|
jondurbin
| 2023-06-28T10:17:10Z | 1,436 | 15 |
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
| 2023-06-25T17:45:52Z |
---
license: cc-by-nc-4.0
datasets:
- jondurbin/airoboros-gpt4-1.4
---
__not yet tested!__
## Overview
This is a qlora fine-tune 33b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros
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 [qlora](https://github.com/jondurbin/qlora)
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-33b-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.
|
jondurbin/airoboros-13b-gpt4-1.4
|
jondurbin
| 2023-06-28T10:16:55Z | 1,435 | 19 |
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
| 2023-06-21T21:24:00Z |
---
license: cc-by-nc-4.0
datasets:
- jondurbin/airoboros-gpt4-1.4
---
__update 2023-06-25 - re-uploaded with a slightly earlier checkpoint, which seems perhaps a little less overfit than the full 3-epochs version initially uploaded__
## Overview
This is a __full__ (not qlora) fine-tune 13b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros
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 \
--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-7b-gpt4-1.4
|
jondurbin
| 2023-06-28T10:16:41Z | 1,427 | 8 |
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
| 2023-06-22T00:22:59Z |
---
license: cc-by-nc-4.0
datasets:
- jondurbin/airoboros-gpt4-1.4
---
__mostly untested, use if you want, or wait for some validation__
## Overview
This is a __full__ (not qlora) fine-tune 7b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros
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 \
--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.
|
fatcat22/a2c-AntBulletEnv-v0
|
fatcat22
| 2023-06-28T09:52:03Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"AntBulletEnv-v0",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-28T09:45:49Z |
---
library_name: stable-baselines3
tags:
- AntBulletEnv-v0
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: AntBulletEnv-v0
type: AntBulletEnv-v0
metrics:
- type: mean_reward
value: 1234.32 +/- 63.32
name: mean_reward
verified: false
---
# **A2C** Agent playing **AntBulletEnv-v0**
This is a trained model of a **A2C** agent playing **AntBulletEnv-v0**
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
...
```
|
KYac/falcon-finetuned
|
KYac
| 2023-06-28T09:50:17Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-28T09:50:14Z |
---
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
|
Zhibinhong/checkpoints_new
|
Zhibinhong
| 2023-06-28T09:45:08Z | 1 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"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
| 2023-06-28T09:03:53Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a photo of sks dog
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- dreambooth
inference: true
---
# DreamBooth - Zhibinhong/checkpoints_new
This is a dreambooth model derived from runwayml/stable-diffusion-v1-5. 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.
|
KorinYTUK/JTTS.v1
|
KorinYTUK
| 2023-06-28T09:42:19Z | 0 | 0 | null |
[
"text-to-speech",
"en",
"license:openrail",
"region:us"
] |
text-to-speech
| 2023-06-28T09:41:16Z |
---
license: openrail
language:
- en
pipeline_tag: text-to-speech
---
|
Den4ikAI/rut5_base_squad_interpreted
|
Den4ikAI
| 2023-06-28T09:37:01Z | 98 | 0 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"t5",
"text2text-generation",
"ru",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2022-12-23T08:32:54Z |
---
license: mit
language:
- ru
widget:
- "Напиши 'Не знаю', если нет ответа. [КОНТЕКСТ] Ёлка горит огоньками, а под ней лежат подарки. У Дениса сегодня дискотека. Он любит есть пиццу. Машенька любит танцевать. [ВОПРОС] Где находятся подарки?"
---
sberbank-ai/ruT5-base обученная на интерпретированом датасета squad.
Модель умеет раскрывать кореферентность.
|
Nara-Lab/nallm-polyglot-ko-3.8b-base
|
Nara-Lab
| 2023-06-28T09:24:35Z | 2,251 | 3 |
transformers
|
[
"transformers",
"pytorch",
"gpt_neox",
"text-generation",
"ko",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-23T01:35:24Z |
---
license: mit
language:
- ko
---
NA-LLM(나름)은 나라지식정보가 개발한 한국어 Large Language Model (LLM) 입니다.
https://github.com/Nara-Information/NA-LLM
|
Nara-Lab/nallm-polyglot-ko-1.3b-base
|
Nara-Lab
| 2023-06-28T09:24:15Z | 2,272 | 2 |
transformers
|
[
"transformers",
"pytorch",
"gpt_neox",
"text-generation",
"ko",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-22T01:12:03Z |
---
license: mit
language:
- ko
---
NA-LLM(나름)은 나라지식정보가 개발한 한국어 Large Language Model (LLM) 입니다.
https://github.com/Nara-Information/NA-LLM
|
robrecht/ppo-lunar-lander-v1
|
robrecht
| 2023-06-28T09:15:03Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-28T09:05:01Z |
---
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: 273.56 +/- 13.05
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
...
```
|
BerserkerMother/PG-CartPole-V1
|
BerserkerMother
| 2023-06-28T09:12:09Z | 0 | 0 | null |
[
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-28T09:10:03Z |
---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: PG-CartPole-V1
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 901.90 +/- 294.30
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
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
|
NickyNicky/MPT-7b-instruct-QLora-8Bits-Peft-train_eli5-1_Epoch-V2
|
NickyNicky
| 2023-06-28T09:06:08Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-28T09:06:04Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
|
NickyNicky/MPT-7b-instruct-QLora-8Bits-Peft-train_eli5-1_Epoch
|
NickyNicky
| 2023-06-28T08:52:05Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-28T08:52:01Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
|
Matthijs/mms-tts-abp
|
Matthijs
| 2023-06-28T08:45:05Z | 108 | 1 |
transformers
|
[
"transformers",
"pytorch",
"vits",
"text-to-audio",
"mms",
"text-to-speech",
"arxiv:2305.13516",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us"
] |
text-to-speech
| 2023-06-27T14:00:22Z |
---
license: cc-by-nc-4.0
tags:
- mms
- vits
pipeline_tag: text-to-speech
---
# Massively Multilingual Speech (MMS) : Text-to-Speech Models
This repository contains the **Ayta, Abellen (abp)** language text-to-speech (TTS) model checkpoint.
This model is part of Facebook's [Massively Multilingual Speech](https://arxiv.org/abs/2305.13516) project, aiming to
provide speech technology across a diverse range of languages. You can find more details about the supported languages
and their ISO 639-3 codes in the [MMS Language Coverage
Overview](https://dl.fbaipublicfiles.com/mms/misc/language_coverage_mms.html).
## Usage
Using this checkpoint from Hugging Face Transformers:
```python
from transformers import VitsModel, VitsMmsTokenizer
import torch
model = VitsModel.from_pretrained("Matthijs/mms-tts-abp")
tokenizer = VitsMmsTokenizer.from_pretrained("Matthijs/mms-tts-abp")
text = "some example text in the Ayta, Abellen language"
inputs = tokenizer(text, return_tensors="pt")
with torch.no_grad():
output = model(**inputs)
from IPython.display import Audio
Audio(output.audio[0], rate=16000)
```
Note: For certain checkpoints, the input text must be converted to the Latin alphabet first using the
[uroman](https://github.com/isi-nlp/uroman) tool.
## Model credits
This model was developed by Vineel Pratap et al. and is licensed as **CC-BY-NC 4.0**
@article{pratap2023mms,
title={Scaling Speech Technology to 1,000+ Languages},
author={Vineel Pratap and Andros Tjandra and Bowen Shi and Paden Tomasello and Arun Babu and Sayani Kundu and Ali Elkahky and Zhaoheng Ni and Apoorv Vyas and Maryam Fazel-Zarandi and Alexei Baevski and Yossi Adi and Xiaohui Zhang and Wei-Ning Hsu and Alexis Conneau and Michael Auli},
journal={arXiv},
year={2023}
}
|
dev-senolys/camembert_base_finetunned_one_thema_balanced_4_epochs
|
dev-senolys
| 2023-06-28T08:44:06Z | 108 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"camembert",
"text-classification",
"generated_from_trainer",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-28T07:43:11Z |
---
license: mit
tags:
- generated_from_trainer
model-index:
- name: camembert_base_finetunned_one_thema_balanced_4_epochs
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. -->
# camembert_base_finetunned_one_thema_balanced_4_epochs
This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8441
## 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: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log | 1.0 | 116 | 2.2913 |
| No log | 2.0 | 232 | 2.0685 |
| No log | 3.0 | 348 | 1.8928 |
| No log | 4.0 | 464 | 1.8441 |
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
cupcakeDriveby/q-taxi-v3
|
cupcakeDriveby
| 2023-06-28T08:39:16Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-28T08:39:14Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.52 +/- 2.74
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="cupcakeDriveby/q-taxi-v3", 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"])
```
|
lukaszkolodziejczyk/ppo-Huggy
|
lukaszkolodziejczyk
| 2023-06-28T08:39:14Z | 98 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-06-28T08:39:09Z |
---
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: lukaszkolodziejczyk/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
PhilSad/poca-SoccerTwos
|
PhilSad
| 2023-06-28T08:36:16Z | 2 | 0 |
ml-agents
|
[
"ml-agents",
"onnx",
"SoccerTwos",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SoccerTwos",
"region:us"
] |
reinforcement-learning
| 2023-06-28T08:10:30Z |
---
library_name: ml-agents
tags:
- SoccerTwos
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SoccerTwos
---
# **poca** Agent playing **SoccerTwos**
This is a trained model of a **poca** agent playing **SoccerTwos**
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: PhilSad/poca-SoccerTwos
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
yhna/Reinforce-policy-grad-cartpole
|
yhna
| 2023-06-28T08:35:03Z | 0 | 0 | null |
[
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-28T04:29:48Z |
---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-policy-grad-cartpole
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 500.00 +/- 0.00
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
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
|
cupcakeDriveby/q-FrozenLake-v1-4x4-noSlippery
|
cupcakeDriveby
| 2023-06-28T08:30:10Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-28T08:30:08Z |
---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
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="cupcakeDriveby/q-FrozenLake-v1-4x4-noSlippery", 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"])
```
|
mszpro/CoreML_StableDiffusion-v-1-5_ControlledUnet_SplitEinsum
|
mszpro
| 2023-06-28T08:17:12Z | 0 | 0 | null |
[
"region:us"
] | null | 2023-06-28T08:13:17Z |
# Stable Diffusion 1.5 ControlledUnet file for CoreML
This is the compiled ControlledUNet file of Stable Diffusion 1.5, used for CoreML image generation with ControlNet.
It accepts 12 additional_residual inputs.
This is compiled for SPLIT EINSUM, which means it also works for iPhone and iPad using Apple Neural Engine.
|
MU-NLPC/calc-baseline-flan-xl
|
MU-NLPC
| 2023-06-28T08:10:15Z | 6 | 0 |
transformers
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-06-24T08:08:14Z |
This is a baseline model for our [calculator-assisted models](https://huggingface.co/models?search=emnlp2023)
trained on a mixture of all our [Calc-X datasets](https://huggingface.co/datasets?search=emnlp2023).
See the corresponding paper for details.
The reported results can be reproduced by using [evaluation script](https://github.com/emnlp2023sub/gadgets/blob/65e24e810cf5ea20aceb8a3c8ddbc19f035ab694/examples/test_calc.py)
from the project repository.
|
MU-NLPC/calc-baseline-t5-large
|
MU-NLPC
| 2023-06-28T08:09:37Z | 107 | 0 |
transformers
|
[
"transformers",
"pytorch",
"t5",
"text2text-generation",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-06-23T15:31:51Z |
This is a baseline model for our [calculator-assisted models](https://huggingface.co/models?search=emnlp2023)
trained on a mixture of all our [Calc-X datasets](https://huggingface.co/datasets?search=emnlp2023).
See the corresponding paper for details.
The reported results can be reproduced by using [evaluation script](https://github.com/emnlp2023sub/gadgets/blob/65e24e810cf5ea20aceb8a3c8ddbc19f035ab694/examples/test_calc.py)
from the project repository.
|
Yorth/dolly-lora
|
Yorth
| 2023-06-28T08:07:48Z | 2 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-28T08:07:46Z |
---
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
|
Assem-Ihab/trainingthemodel3
|
Assem-Ihab
| 2023-06-28T07:53:07Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"mbart",
"text2text-generation",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-06-28T07:39:26Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: trainingthemodel3
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. -->
# trainingthemodel3
This model is a fine-tuned version of [abdalrahmanshahrour/AraBART-summ](https://huggingface.co/abdalrahmanshahrour/AraBART-summ) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.6417
- Rouge1: 0.1136
- Rouge2: 0.0429
- Rougel: 0.0938
- Rougelsum: 0.0936
- Gen Len: 20.0
## 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: 5
- eval_batch_size: 5
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
| No log | 1.0 | 31 | 2.9297 | 0.1141 | 0.0449 | 0.0941 | 0.0942 | 20.0 |
| No log | 2.0 | 62 | 2.7345 | 0.1099 | 0.0426 | 0.0908 | 0.0908 | 20.0 |
| No log | 3.0 | 93 | 2.6680 | 0.1123 | 0.0428 | 0.093 | 0.0929 | 20.0 |
| No log | 4.0 | 124 | 2.6417 | 0.1136 | 0.0429 | 0.0938 | 0.0936 | 20.0 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
YakovElm/Hyperledger_5_BERT_Over_Sampling
|
YakovElm
| 2023-06-28T07:47:59Z | 61 | 0 |
transformers
|
[
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-28T07:47:23Z |
---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Hyperledger_5_BERT_Over_Sampling
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. -->
# Hyperledger_5_BERT_Over_Sampling
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.0898
- Train Accuracy: 0.9727
- Validation Loss: 0.8739
- Validation Accuracy: 0.7521
- Epoch: 2
## 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': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.6014 | 0.6783 | 0.5787 | 0.7168 | 0 |
| 0.2834 | 0.8865 | 0.7050 | 0.7687 | 1 |
| 0.0898 | 0.9727 | 0.8739 | 0.7521 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
yhna/Reinforce-pixelcopter
|
yhna
| 2023-06-28T07:43:10Z | 0 | 0 | null |
[
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-28T07:43:05Z |
---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-pixelcopter
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 44.60 +/- 27.12
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
|
Assem-Ihab/trainingthemodel
|
Assem-Ihab
| 2023-06-28T07:34:52Z | 94 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"mbart",
"text2text-generation",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-06-27T12:21:59Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: trainingthemodel
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. -->
# trainingthemodel
This model is a fine-tuned version of [abdalrahmanshahrour/arabartsummarization](https://huggingface.co/abdalrahmanshahrour/arabartsummarization) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.2622
- Rouge1: 0.1194
- Rouge2: 0.0483
- Rougel: 0.0975
- Rougelsum: 0.0977
- Gen Len: 20.0
## 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: 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: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
| No log | 1.0 | 154 | 2.7120 | 0.1178 | 0.0452 | 0.0966 | 0.0966 | 20.0 |
| No log | 2.0 | 308 | 2.4175 | 0.1202 | 0.0482 | 0.0995 | 0.0998 | 20.0 |
| No log | 3.0 | 462 | 2.3151 | 0.1181 | 0.0468 | 0.0963 | 0.0966 | 20.0 |
| 3.034 | 4.0 | 616 | 2.2622 | 0.1194 | 0.0483 | 0.0975 | 0.0977 | 20.0 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
nolanaatama/rmfbtsrvcv1tgrll14
|
nolanaatama
| 2023-06-28T07:30:49Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-28T07:26:26Z |
---
license: creativeml-openrail-m
---
|
dhillondheeraj84/elephants_yolov8
|
dhillondheeraj84
| 2023-06-28T07:22:35Z | 0 | 0 | null |
[
"object-detection",
"arxiv:1910.09700",
"region:us"
] |
object-detection
| 2023-06-13T08:35:51Z |
---
pipeline_tag: object-detection
---
# 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]
|
Shubham09/falcon_p2
|
Shubham09
| 2023-06-28T07:22:31Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-28T07:12:50Z |
---
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: False
- bnb_4bit_compute_dtype: float16
### Framework versions
- PEFT 0.4.0.dev0
|
kejolong/etomisa
|
kejolong
| 2023-06-28T07:21:52Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-28T04:29:02Z |
---
license: creativeml-openrail-m
---
|
myahan007/banglabert_generator-finetuned-fill-in-the-blanks
|
myahan007
| 2023-06-28T07:11:17Z | 125 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"electra",
"fill-mask",
"generated_from_trainer",
"dataset:bangla_paraphrase",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-06-28T04:59:24Z |
---
tags:
- generated_from_trainer
datasets:
- bangla_paraphrase
model-index:
- name: banglabert_generator-finetuned-fill-in-the-blanks
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. -->
# banglabert_generator-finetuned-fill-in-the-blanks
This model is a fine-tuned version of [csebuetnlp/banglabert_generator](https://huggingface.co/csebuetnlp/banglabert_generator) on the bangla_paraphrase dataset.
It achieves the following results on the evaluation set:
- Loss: 4.0254
## 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: 20
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 4.2018 | 1.0 | 235 | 4.0979 |
| 4.177 | 2.0 | 470 | 4.0591 |
| 4.1532 | 3.0 | 705 | 4.0385 |
| 4.1417 | 4.0 | 940 | 4.0490 |
| 4.133 | 5.0 | 1175 | 4.0387 |
| 4.1137 | 6.0 | 1410 | 4.0716 |
| 4.1033 | 7.0 | 1645 | 4.0118 |
| 4.0874 | 8.0 | 1880 | 4.0448 |
| 4.0791 | 9.0 | 2115 | 4.0381 |
| 4.0788 | 10.0 | 2350 | 4.0457 |
| 4.061 | 11.0 | 2585 | 3.9917 |
| 4.0557 | 12.0 | 2820 | 3.9950 |
| 4.0533 | 13.0 | 3055 | 4.0131 |
| 4.0582 | 14.0 | 3290 | 4.0080 |
| 4.042 | 15.0 | 3525 | 4.0265 |
| 4.0338 | 16.0 | 3760 | 3.9908 |
| 4.0222 | 17.0 | 3995 | 3.9967 |
| 4.0343 | 18.0 | 4230 | 4.0011 |
| 4.0294 | 19.0 | 4465 | 4.0334 |
| 4.0313 | 20.0 | 4700 | 4.0099 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
eocampop/distilbert-base-multilingual-cased-finetuned-MeIA-AnalisisDeSentimientos
|
eocampop
| 2023-06-28T06:48:14Z | 20 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-27T15:54:51Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: distilbert-base-multilingual-cased-finetuned-MeIA-AnalisisDeSentimientos
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-base-multilingual-cased-finetuned-MeIA-AnalisisDeSentimientos
This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2025
- F1: 0.5425
## 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-06
- 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: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.4868 | 1.0 | 766 | 1.2168 | 0.5419 |
| 0.7607 | 2.0 | 1532 | 1.2025 | 0.5425 |
| 0.603 | 3.0 | 2298 | 1.1996 | 0.5414 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Broonion/RLcourse-unit2-q-FrozenLake-v1-4x4-noSlippery
|
Broonion
| 2023-06-28T06:43:48Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-28T06:43:46Z |
---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
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="Broonion/q-FrozenLake-v1-4x4-noSlippery", 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"])
```
|
birdup/pygmalion-7b-q5_1-ggml-v3
|
birdup
| 2023-06-28T05:59:42Z | 0 | 3 | null |
[
"region:us"
] | null | 2023-06-03T20:33:42Z |
ggjt v3 version of Pygmalion 7b
|
YakovElm/Jira_10_BERT_Under_Sampling
|
YakovElm
| 2023-06-28T05:40:02Z | 61 | 0 |
transformers
|
[
"transformers",
"tf",
"bert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-28T05:39:26Z |
---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Jira_10_BERT_Under_Sampling
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. -->
# Jira_10_BERT_Under_Sampling
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.0015
- Train Accuracy: 1.0
- Validation Loss: 3.4990
- Validation Accuracy: 0.4921
- Epoch: 2
## 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': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
| 0.0884 | 0.9895 | 2.6907 | 0.4921 | 0 |
| 0.0032 | 1.0 | 3.2542 | 0.4921 | 1 |
| 0.0015 | 1.0 | 3.4990 | 0.4921 | 2 |
### Framework versions
- Transformers 4.29.2
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
|
Broonion/RLcourse-unit1bonus-ppo-Huggy
|
Broonion
| 2023-06-28T05:38:23Z | 28 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-06-28T05:38:14Z |
---
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: Broonion/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
allman/bert-base-uncased-finetuned-MeIA-AnalisisDeSentimientos
|
allman
| 2023-06-28T05:07:52Z | 107 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"text-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-28T04:02:43Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: bert-base-uncased-finetuned-MeIA-AnalisisDeSentimientos
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-finetuned-MeIA-AnalisisDeSentimientos
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: 1.0784
- F1: 0.5207
## 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: 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: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 1.1946 | 1.0 | 766 | 1.1920 | 0.4331 |
| 1.0715 | 2.0 | 1532 | 1.0936 | 0.4909 |
| 1.0093 | 3.0 | 2298 | 1.0583 | 0.5116 |
| 0.8907 | 4.0 | 3064 | 1.0784 | 0.5207 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
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.