modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-09-11 00:42:47
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 553
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-09-11 00:42:38
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
p1atdev/EZWD-B3
|
p1atdev
| 2023-06-30T16:54:31Z | 0 | 0 | null |
[
"license:other",
"region:us"
] | null | 2023-06-28T09:37:57Z |
---
license: other
---
These models are trained based on Waifu Diffusion 1.5 beta 3.
https://huggingface.co/waifu-diffusion/wd-1-5-beta3
## License
These models are released under the Fair AI Public License 1.0-SD (https://freedevproject.org/faipl-1.0-sd/). If any derivative of this model is made, please share your changes accordingly. Special thanks to ronsor/undeleted (https://undeleted.ronsor.com/) for help with the license.
|
BlinkDL/rwkv-4-raven
|
BlinkDL
| 2023-06-30T16:54:18Z | 0 | 497 | null |
[
"pytorch",
"text-generation",
"causal-lm",
"rwkv",
"en",
"dataset:the_pile",
"license:apache-2.0",
"region:us"
] |
text-generation
| 2023-04-01T17:49:02Z |
---
language:
- en
tags:
- pytorch
- text-generation
- causal-lm
- rwkv
license: apache-2.0
datasets:
- the_pile
---
# RWKV-4 "Raven"-series Models
[UPDATE: Try RWKV-4-World (https://huggingface.co/BlinkDL/rwkv-4-world) for generation & chat & code in 100+ world languages, with great English zero-shot & in-context learning ability too.]
## Model Description
These are RWKV-4-Pile 1.5/3/7/14B models finetuned on Alpaca, CodeAlpaca, Guanaco, GPT4All, ShareGPT and more. **Even the 1.5B model is surprisingly good for its size.**
Gradio Demo: https://huggingface.co/spaces/BlinkDL/Raven-RWKV-7B and https://huggingface.co/spaces/BlinkDL/ChatRWKV-gradio
RWKV models inference: https://github.com/BlinkDL/ChatRWKV (fast CUDA).
Q8_0 models: only for https://github.com/saharNooby/rwkv.cpp (fast CPU).
See https://github.com/BlinkDL/RWKV-LM for details on the RWKV Language Model (100% RNN).
Best Prompt Format for Raven models, Bob is user, Alice is bot (NOTE: no space after final "Alice:"). You can use \n within xxxxxxxxxxx, but avoid \n\n.
```
Bob: xxxxxxxxxxxxxxxxxx\n\nAlice:
Bob: xxxxxxxxxxxxxxxxxx\n\nAlice: xxxxxxxxxxxxx\n\nBob: xxxxxxxxxxxxxxxx\n\nAlice:
```
New models will be named like Eng99%-Other1%, Eng86%-Chn10%-JpnEspKor2%-Other2%, etc.
Language ratios determined by amount of ChatGPT data. Please share more ChatGPT data to increase the ratio of your language.
Old models:
* RWKV-4-Raven-Eng : 99% English + 1% Multilang
* RWKV-4-Raven-EngAndMore : 96% English + 2% Chn Jpn + 2% Multilang (More Jpn than v6 "EngChnJpn")
* RWKV-4-Raven-ChnEng : 49% English + 50% Chinese + 1% Multilang
License: Apache 2.0
|
PhongLe1311/bert-finetuned-squad-2
|
PhongLe1311
| 2023-06-30T16:52:29Z | 103 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"question-answering",
"generated_from_trainer",
"dataset:squad",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
question-answering
| 2023-06-30T14:42:56Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: bert-finetuned-squad-2
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-finetuned-squad-2
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the squad 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Franblueee/BCD-Net
|
Franblueee
| 2023-06-30T16:42:55Z | 0 | 1 | null |
[
"image-to-image",
"license:apache-2.0",
"region:us"
] |
image-to-image
| 2023-06-30T12:34:45Z |
---
license: apache-2.0
tags:
- image-to-image
pipeline_tag: image-to-image
---
# BCD-Net Model Card
BCD-Net is a Deep Variational Bayesian Neural Network for the Blind Color Deconvolution (BCD) of histological images. It allows to separate a histological image of any size into the color matrix and the concentration matrices. The weights are released in the format of a PyTorch state dictionary.
## Original Github repository
The code and instructions to build the network and make predictions are available at [ Github](https://github.com/Franblueee/BCD-Net).
## Our paper: Deep Bayesian Blind Color Deconvolution of Histological Images
For more information about the BCD-Net methodology and training procedure, please have a look at [our paper]().
## Citation
If you find our model helpful, please consider citing our paper:
```bibtex
@article{,
title={{D}eep {B}ayesian {B}lind {C}olor {D}econvolution of {H}istological {I}mages},
author={Shuowen Yang and Fernando Pérez-Bueno and Francisco M. Castro-Macías and Rafael Molina and Aggelos K. Katsaggelos},
archivePrefix={arXiv},
primaryClass={},
year={2023}
}
```
|
julian-schelb/roberta-ner-multilingual
|
julian-schelb
| 2023-06-30T16:08:05Z | 866 | 10 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"xlm-roberta",
"token-classification",
"roberta",
"ner",
"nlp",
"en",
"de",
"fr",
"zh",
"it",
"es",
"hi",
"bn",
"ar",
"ru",
"uk",
"pt",
"ur",
"id",
"ja",
"ne",
"nl",
"tr",
"ca",
"bg",
"yue",
"dataset:wikiann",
"arxiv:1911.02116",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2022-09-06T19:53:00Z |
---
language:
- en
- de
- fr
- zh
- it
- es
- hi
- bn
- ar
- ru
- uk
- pt
- ur
- id
- ja
- ne
- nl
- tr
- ca
- bg
- yue
widget:
- text: >-
In December 1903 in France the Royal Swedish Academy of Sciences awarded
Pierre Curie, Marie Curie, and Henri Becquerel the Nobel Prize in Physics.
- text: >-
Für Richard Phillips Feynman war es immer wichtig in New York, die
unanschaulichen Gesetzmäßigkeiten der Quantenphysik Laien und Studenten
nahezubringen und verständlich zu machen.
- text: >-
Terence David John Pratchett est né le 28 avril 1948 à Beaconsfield dans le
Buckinghamshire, en Angleterre.
- text: >-
北京市，通称北京（汉语拼音：Běijīng；邮政式拼音：Peking），简称“京”，是中华人民共和国的首都及直辖市，是该国的政治、文化、科技、教育、军事和国际交往中心，是一座全球城市，是世界人口第三多的城市和人口最多的首都，具有重要的国际影响力，同時也是目前世界唯一的“双奥之城”，即唯一既主办过夏季
tags:
- roberta
- ner
- nlp
license: mit
datasets:
- wikiann
metrics:
- f1
- precision
- accuracy
- recall
---
# RoBERTa for Multilingual Named Entity Recognition
## Model Description
This model detects entities by classifying every token according to the IOB format:
```python
['O', 'B-PER', 'I-PER', 'B-ORG', 'I-ORG', 'B-LOC', 'I-LOC']
```
You can find the code in [this](https://github.com/julianschelb/roberta-ner-multilingual) GitHub repository.
## Training Data
This model was fine-tuned on a portion of the [wikiann](https://huggingface.co/datasets/wikiann) dataset corresponding to the following languages:
```python
["en","de", "fr",
"zh", "it", "es",
"hi", "bn", "ar",
"ru", "uk", "pt",
"ur", "id", "ja",
"ne", "nl", "tr",
"ca", "bg", "zh-yue"]
```
The model was fine-tuned on 375.100 sentences in the training set, with a validation set of 173.100 examples. Performance metrics reported are based on additional 173.100 examples. The complete WikiANN dataset includes training examples for 282 languages and was constructed from Wikipedia. Training examples are extracted in an automated manner, exploiting entities mentioned in Wikipedia articles, often are formatted as hyperlinks to the source article. Provided NER tags are in the IOB2 format. Named entities are classified as location (LOC), person (PER), or organization (ORG).
## Evaluation Results
This model achieves the following results (meassured using the test split of the [wikiann](https://huggingface.co/datasets/wikiann) dataset):
```python
{'LOC': {'f1': 0.8994491397524903,
'number': 184430,
'precision': 0.8941572985543279,
'recall': 0.9048039906739684},
'ORG': {'f1': 0.829114679375883,
'number': 129760,
'precision': 0.8283525257886599,
'recall': 0.8298782367447596},
'PER': {'f1': 0.9115096398413828,
'number': 130471,
'precision': 0.9043545174723882,
'recall': 0.9187788857293958},
'overall_accuracy': 0.9398182274831388,
'overall_f1': 0.8825581369330908,
'overall_precision': 0.8781215422873389,
'overall_recall': 0.8870397898623895}
```
## Usage
You can load this model by using the AutoTokenize and AutoModelForTokenClassification classes:
```python
from transformers import AutoTokenizer, AutoModelForTokenClassification
tokenizer = AutoTokenizer.from_pretrained("julian-schelb/roberta-ner-multilingual/", add_prefix_space=True)
model = AutoModelForTokenClassification.from_pretrained("julian-schelb/roberta-ner-multilingual/")
text = "In December 1903 in France the Royal Swedish Academy of Sciences awarded Pierre Curie, Marie Curie, and Henri Becquerel the Nobel Prize in Physics."
inputs = tokenizer(
text,
add_special_tokens=False,
return_tensors="pt"
)
with torch.no_grad():
logits = model(**inputs).logits
predicted_token_class_ids = logits.argmax(-1)
# Note that tokens are classified rather then input words which means that
# there might be more predicted token classes than words.
# Multiple token classes might account for the same word
predicted_tokens_classes = [model.config.id2label[t.item()] for t in predicted_token_class_ids[0]]
predicted_tokens_classes
```
## About RoBERTa
This model is a fine-tuned version of [XLM-RoBERTa](https://huggingface.co/xlm-roberta-large). The original model was pre-trained on 2.5TB of filtered CommonCrawl data containing 100 languages. It was introduced in the paper [Unsupervised Cross-lingual Representation Learning at Scale](https://arxiv.org/abs/1911.02116) by Conneau et al. and first released in [this repository](https://github.com/pytorch/fairseq/tree/master/examples/xlmr).
RoBERTa is a transformers model pretrained on a large corpus in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts.
More precisely, it was pretrained with the Masked language modeling (MLM) objective. Taking a sentence, the model randomly masks 15% of the words in the input then run the entire masked sentence through the model and has to predict the masked words. This is different from traditional recurrent neural networks (RNNs) that usually see the words one after the other, or from autoregressive models like GPT which internally mask the future tokens. It allows the model to learn a bidirectional representation of the sentence.
This way, the model learns an inner representation of 100 languages that can then be used to extract features useful for downstream tasks: if you have a dataset of labeled sentences for instance, you can train a standard classifier using the features produced by the XLM-RoBERTa model as inputs.
#### Limitations and Bias
This model is limited by its training dataset of entity-annotated news articles from a specific span of time. This may not generalize well for all use cases in different domains.
## Related Papers
* Pan, X., Zhang, B., May, J., Nothman, J., Knight, K., & Ji, H. (2017). Cross-lingual Name Tagging and Linking for 282 Languages. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 1946–1958). Association for Computational Linguistics.
* Rahimi, A., Li, Y., & Cohn, T. (2019). Massively Multilingual Transfer for NER. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (pp. 151–164). Association for Computational Linguistics.
* Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V.. (2019). RoBERTa: A Robustly Optimized BERT Pretraining Approach.
## Citation
This model has been fine-tuned for the research paper indicated below:
```bibtex
@inproceedings{schelbECCEEntitycentricCorpus2022,
title = {{ECCE}: {Entity}-centric {Corpus} {Exploration} {Using} {Contextual} {Implicit} {Networks}},
url = {https://dl.acm.org/doi/10.1145/3487553.3524237},
booktitle = {Companion {Proceedings} of the {Web} {Conference} 2022},
author = {Schelb, Julian and Ehrmann, Maud and Romanello, Matteo and Spitz, Andreas},
year = {2022},
}
```
|
igoroliveira/Huggy_igoroliv
|
igoroliveira
| 2023-06-30T16:01:06Z | 0 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-06-30T16:00:56Z |
---
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: igoroliveira/Huggy_igoroliv
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
language-and-voice-lab/talromur_1and2_spk_avg_xvector_fastspeech2
|
language-and-voice-lab
| 2023-06-30T15:54:58Z | 0 | 0 |
espnet
|
[
"espnet",
"text-to-speech",
"is",
"arxiv:1804.00015",
"license:cc-by-4.0",
"region:us"
] |
text-to-speech
| 2023-06-15T16:57:54Z |
---
license: cc-by-4.0
language:
- is
library_name: espnet
pipeline_tag: text-to-speech
widget:
- text: góðan daginn kæru íslendingar
---
## ESPnet2 TTS pretrained model
This model was trained by GunnarThor using a modified version of talromur2/tts1 recipe in [espnet](https://github.com/espnet/espnet/).
### Demo: How to use in ESPnet2
```python
# coming soon
```
### Citing ESPnet
```BibTex
@inproceedings{watanabe2018espnet,
author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson {Enrique Yalta Soplin} and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
title={{ESPnet}: End-to-End Speech Processing Toolkit},
year={2018},
booktitle={Proceedings of Interspeech},
pages={2207--2211},
doi={10.21437/Interspeech.2018-1456},
url={http://dx.doi.org/10.21437/Interspeech.2018-1456}
}
@inproceedings{hayashi2020espnet,
title={{Espnet-TTS}: Unified, reproducible, and integratable open source end-to-end text-to-speech toolkit},
author={Hayashi, Tomoki and Yamamoto, Ryuichi and Inoue, Katsuki and Yoshimura, Takenori and Watanabe, Shinji and Toda, Tomoki and Takeda, Kazuya and Zhang, Yu and Tan, Xu},
booktitle={Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
pages={7654--7658},
year={2020},
organization={IEEE}
}
```
or arXiv:
```bibtex
@misc{watanabe2018espnet,
title={ESPnet: End-to-End Speech Processing Toolkit},
author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Enrique Yalta Soplin and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
year={2018},
eprint={1804.00015},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
|
kaiyuy/ASTactic
|
kaiyuy
| 2023-06-30T15:53:48Z | 0 | 1 | null |
[
"arxiv:1905.09381",
"license:lgpl-2.1",
"region:us"
] | null | 2023-06-30T15:52:23Z |
---
license: lgpl-2.1
---
The ASTactic model in the paper:
[Learning to Prove Theorems via Interacting with Proof Assistants](https://arxiv.org/abs/1905.09381)
[Kaiyu Yang](https://yangky11.github.io/) and [Jia Deng](https://www.cs.princeton.edu/~jiadeng/)
International Conference on Machine Learning (ICML) 2019
```bibtex
@inproceedings{yang2019coqgym,
title={Learning to Prove Theorems via Interacting with Proof Assistants},
author={Yang, Kaiyu and Deng, Jia},
booktitle={International Conference on Machine Learning (ICML)},
year={2019}
}
```
Please visit https://github.com/princeton-vl/CoqGym for details.
|
pchiva/q-Taxi-v3
|
pchiva
| 2023-06-30T15:45:52Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-30T15:39:05Z |
---
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 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="pchiva/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"])
```
|
YoneShiro/poca-SoccerTwos
|
YoneShiro
| 2023-06-30T15:45:10Z | 4 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"SoccerTwos",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SoccerTwos",
"region:us"
] |
reinforcement-learning
| 2023-06-30T15:43:40Z |
---
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: YoneShiro/poca-SoccerTwos
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
netradrishti/u2net-saliency
|
netradrishti
| 2023-06-30T15:38:40Z | 60 | 1 |
transformers
|
[
"transformers",
"pytorch",
"u2net",
"feature-extraction",
"custom_code",
"region:us"
] |
feature-extraction
| 2023-02-23T15:29:37Z |
---
title: Saliency Estimation
---
|
pchiva/q-FrozenLake-v1-4x4-noSlippery
|
pchiva
| 2023-06-30T15:31:56Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-30T15:31:54Z |
---
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="pchiva/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"])
```
|
eswardivi/medical_qa_llm
|
eswardivi
| 2023-06-30T15:30:05Z | 3 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-30T15:17:58Z |
---
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
|
nelant098/jewelry
|
nelant098
| 2023-06-30T15:25:39Z | 190 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"vit",
"image-classification",
"huggingpics",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2023-06-30T15:25:29Z |
---
tags:
- image-classification
- pytorch
- huggingpics
metrics:
- accuracy
model-index:
- name: jewelry
results:
- task:
name: Image Classification
type: image-classification
metrics:
- name: Accuracy
type: accuracy
value: 0.5357142686843872
---
# jewelry
Autogenerated by HuggingPics🤗🖼️
Create your own image classifier for **anything** by running [the demo on Google Colab](https://colab.research.google.com/github/nateraw/huggingpics/blob/main/HuggingPics.ipynb).
Report any issues with the demo at the [github repo](https://github.com/nateraw/huggingpics).
## Example Images
#### Diamon Jewelry
#### Gold Chain
#### Gold Jewelry
#### Rolex Watch
#### Silver Jewelry
|
slone/bert-tiny-char-ctc-bak-denoise
|
slone
| 2023-06-30T15:17:51Z | 95 | 1 |
transformers
|
[
"transformers",
"pytorch",
"safetensors",
"bert",
"fill-mask",
"grammatical-error-correction",
"ba",
"license:cc-by-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2023-06-30T06:36:13Z |
---
license: cc-by-4.0
language:
- ba
tags:
- grammatical-error-correction
---
This is a tiny BERT model for Bashkir, intended for fixing OCR errors.
Here is the code to run it (it uses a custom tokenizer, with the code downloaded in the runtime):
```Python
import torch
from transformers import AutoModelForMaskedLM, AutoTokenizer
MODEL_NAME = 'slone/bert-tiny-char-ctc-bak-denoise'
model = AutoModelForMaskedLM.from_pretrained(MODEL_NAME)
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, trust_remote_code=True, revision='194109')
def fix_text(text, verbose=False, spaces=2):
with torch.inference_mode():
batch = tokenizer(text, return_tensors='pt', spaces=spaces, padding=True, truncation=True, return_token_type_ids=False).to(model.device)
logits = torch.log_softmax(model(**batch).logits, axis=-1)
return tokenizer.decode(logits[0].argmax(-1), skip_special_tokens=True)
print(fix_text("Э Ҡаратау ҙы белмәйем."))
# Ә Ҡаратауҙы белмәйем.
```
The model works by:
- inserting special characters (`spaces`) between each input character,
- performing token classification (when for most tokens, predicted output equals input, but some may modify it),
- and removing the special characters from the output.
It was trained on a parallel corpus (corrupted + fixed sentence) with CTC loss.
On our test dataset, it reduces OCR errors by 41%.
Training code: [here](https://github.com/slone-nlp/bashkort-spellcheker/blob/master/experiments/06_ctc_bert.ipynb).
Training details: in [this post](https://habr.com/ru/articles/744972/) (in Russian).
|
TheBloke/Chinese-Alpaca-33B-SuperHOT-8K-GGML
|
TheBloke
| 2023-06-30T15:13:30Z | 0 | 7 | null |
[
"license:other",
"region:us"
] | null | 2023-06-30T13:45:41Z |
---
inference: false
license: other
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# Minlik's Chinese Alpaca 33B Merged GGML
These files are GGML format model files for [Minlik's Chinese Alpaca 33B Merged](https://huggingface.co/minlik/chinese-alpaca-33b-merged).
These are SuperHOT GGMLs with an increased context length. SuperHOT is a new system that employs RoPE to expand context beyond what was originally possible for a model. It was discovered and developed by [kaiokendev](https://huggingface.co/kaiokendev).
In order to use the increased context length, you can presently use:
* [KoboldCpp](https://github.com/LostRuins/koboldcpp) - [release 1.33](https://github.com/LostRuins/koboldcpp/releases/tag/v1.33) or later.
Support is also expected to come to llama.cpp, however work is still being done to find the optimal implementation.
To use the increased context with KoboldCpp, simply use `--contextsize` to set the desired context, eg `--contextsize 4096` or `--contextsize 8192`.
**NOTE**: Increased context length is an area seeing rapid developments and improvements. It is quite possible that these models may be superseded by new developments in the coming days. If that's the case, I will remove them, or update this README as appropriate.
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Chinese-Alpaca-33B-SuperHOT-8K-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU inference](https://huggingface.co/TheBloke/Chinese-Alpaca-33B-SuperHOT-8K-GGML)
* [Unquantised SuperHOT fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/Chinese-Alpaca-33B-SuperHOT-8K-fp16)
* [Unquantised base fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/minlik/chinese-alpaca-33b-merged)
<!-- compatibility_ggml start -->
## Compatibility
These GGMLs will work with any llama.cpp-compatible GGML client that supports k-quants.
However the increased context length won't work without specific support. See the note in the introduction for details on using increased context.
## Explanation of the new k-quant methods
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
* GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.
Refer to the Provided Files table below to see what files use which methods, and how.
<!-- compatibility_ggml end -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| chinese-alpaca-33b-superhot-8k.ggmlv3.q4_0.bin | q4_0 | 4 | 18.44 GB | 20.94 GB | Original llama.cpp quant method, 4-bit. |
| chinese-alpaca-33b-superhot-8k.ggmlv3.q4_1.bin | q4_1 | 4 | 20.48 GB | 22.98 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| chinese-alpaca-33b-superhot-8k.ggmlv3.q5_0.bin | q5_0 | 5 | 22.53 GB | 25.03 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
| chinese-alpaca-33b-superhot-8k.ggmlv3.q5_1.bin | q5_1 | 5 | 24.58 GB | 27.08 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
| chinese-alpaca-33b-superhot-8k.ggmlv3.q8_0.bin | q8_0 | 8 | 34.82 GB | 37.32 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
## How to run in `koboldcpp`
On Linux I use the following command line to launch the KoboldCpp UI with OpenCL aceleration and a context size of 4096:
```
python ./koboldcpp.py --stream --unbantokens --threads 8 --usecublas --gpulayers 100 chinese-alpaca-33b-superhot-8k.ggmlv3.q4_K_M.bin
```
Change `--gpulayers 100` to the number of layers you want/are able to offload to the GPU. Remove it if you don't have GPU acceleration.
For OpenCL acceleration, change `--usecublas` to `--useclblast 0 0`. You may need to change the second `0` to `1` if you have both an iGPU and a discrete GPU.
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: zynix , ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: Kaio Ken's SuperHOT 8K
### SuperHOT Prototype 2 w/ 8K Context
This is a second prototype of SuperHOT, this time 30B with 8K context and no RLHF, using the same technique described in [the github blog](https://kaiokendev.github.io/til#extending-context-to-8k).
Tests have shown that the model does indeed leverage the extended context at 8K.
You will need to **use either the monkeypatch** or, if you are already using the monkeypatch, **change the scaling factor to 0.25 and the maximum sequence length to 8192**
#### Looking for Merged & Quantized Models?
- 30B 4-bit CUDA: [tmpupload/superhot-30b-8k-4bit-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-safetensors)
- 30B 4-bit CUDA 128g: [tmpupload/superhot-30b-8k-4bit-128g-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-128g-safetensors)
#### Training Details
I trained the LoRA with the following configuration:
- 1200 samples (~400 samples over 2048 sequence length)
- learning rate of 3e-4
- 3 epochs
- The exported modules are:
- q_proj
- k_proj
- v_proj
- o_proj
- no bias
- Rank = 4
- Alpha = 8
- no dropout
- weight decay of 0.1
- AdamW beta1 of 0.9 and beta2 0.99, epsilon of 1e-5
- Trained on 4-bit base model
# Original model card: Minlik's Chinese Alpaca 33B Merged
加入中文词表并继续预训练中文Embedding，并在此基础上继续使用指令数据集finetuning，得到的中文Alpaca-33B模型。
模型转换用到的相关base及lora模型如下：
- base-model: elinas/llama-30b-hf-transformers-4.29
- lora-model: ziqingyang/chinese-alpaca-lora-33b
详情可参考：https://github.com/ymcui/Chinese-LLaMA-Alpaca/releases/tag/v4.0
### 使用方法参考
1. 安装模块包
```bash
pip install sentencepiece
pip install transformers>=4.28.0
```
2. 生成文本
```python
import torch
import transformers
from transformers import LlamaTokenizer, LlamaForCausalLM
def generate_prompt(text):
return f"""Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{text}
### Response:"""
tokenizer = LlamaTokenizer.from_pretrained('minlik/chinese-alpaca-33b-merged')
model = LlamaForCausalLM.from_pretrained('minlik/chinese-alpaca-33b-merged').half().to('cuda')
model.eval()
text = '第一个登上月球的人是谁？'
prompt = generate_prompt(text)
input_ids = tokenizer.encode(prompt, return_tensors='pt').to('cuda')
with torch.no_grad():
output_ids = model.generate(
input_ids=input_ids,
max_new_tokens=128,
temperature=1,
top_k=40,
top_p=0.9,
repetition_penalty=1.15
).cuda()
output = tokenizer.decode(output_ids[0], skip_special_tokens=True)
print(output.replace(prompt, '').strip())
```
|
OFA-Sys/ONE-PEACE
|
OFA-Sys
| 2023-06-30T15:06:37Z | 0 | 3 | null |
[
"onepeace",
"ofasys",
"en",
"license:apache-2.0",
"region:us"
] | null | 2023-06-30T14:45:16Z |
---
license: apache-2.0
language:
- en
tags:
- onepeace
- ofasys
---
|
lnair/graphormer-ogbg-molhiv
|
lnair
| 2023-06-30T15:03:49Z | 34 | 0 |
transformers
|
[
"transformers",
"pytorch",
"graphormer",
"generated_from_trainer",
"endpoints_compatible",
"region:us"
] | null | 2023-06-30T14:50:08Z |
---
tags:
- generated_from_trainer
model-index:
- name: graphormer-ogbg-molhiv
results: []
---
# graphormer-ogbg-molhiv
This model was trained from `clefourrier/pcqm4mv2_graphormer_base` on the `OGB/ogbg-molhiv` dataset.
It achieves the following results on the evaluation set:
- eval_loss: 0.0728
- eval_runtime: 464.6027
- eval_samples_per_second: 8.853
- eval_steps_per_second: 0.555
- step: 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: 0.0002
- train_batch_size: 512
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 10
- total_train_batch_size: 5120
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
### Framework versions
- Transformers 4.27.4
- Pytorch 1.13.0+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2
|
silversword/lunar-model
|
silversword
| 2023-06-30T14:49:17Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-30T14:48:56Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 258.62 +/- 23.42
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
...
```
|
TheBloke/mpt-7b-chat-GGML
|
TheBloke
| 2023-06-30T14:46:23Z | 0 | 9 | null |
[
"Composer",
"MosaicML",
"llm-foundry",
"dataset:jeffwan/sharegpt_vicuna",
"dataset:Hello-SimpleAI/HC3",
"dataset:tatsu-lab/alpaca",
"dataset:Anthropic/hh-rlhf",
"dataset:victor123/evol_instruct_70k",
"arxiv:2205.14135",
"arxiv:2108.12409",
"arxiv:2010.04245",
"license:cc-by-nc-sa-4.0",
"region:us"
] | null | 2023-06-30T13:44:00Z |
---
license: cc-by-nc-sa-4.0
datasets:
- jeffwan/sharegpt_vicuna
- Hello-SimpleAI/HC3
- tatsu-lab/alpaca
- Anthropic/hh-rlhf
- victor123/evol_instruct_70k
tags:
- Composer
- MosaicML
- llm-foundry
inference: false
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# MosaicML's MPT-7B-Chat GGML
These files are GGML format model files for [MosaicML's MPT-7B-Chat](https://huggingface.co/mosaicml/mpt-7b-chat).
Please note that these GGMLs are **not compatible with llama.cpp, or currently with text-generation-webui**. Please see below for a list of tools known to work with these model files.
[KoboldCpp](https://github.com/LostRuins/koboldcpp) just added GPU accelerated (OpenCL) support for MPT models, so that is the client I recommend using for these models.
**Note**: Please make sure you're using KoboldCpp version 1.32.3 or later, as a number of MPT-related bugs are fixed.
## Repositories available
* [4, 5, and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/mpt-7B-chat-GGML)
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/mosaicml/mpt-7b-chat)
## Prompt template
```
<|im_start|>system
A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.<|im_end|>
<|im_start|>user
prompt goes here<|im_end|>
<|im_start|>assistant
```
## A note regarding context length: 4K
The base model has an 4K context length.
[KoboldCpp](https://github.com/LostRuins/koboldcpp) supports 4K context if you manually set it to 4K by adjusting the text box above the slider, like in this example:
(Set it to 4K, not 8K for this model.)
<!-- compatibility_ggml start -->
## Compatibilty
These files are **not** compatible with text-generation-webui, llama.cpp, or llama-cpp-python.
Currently they can be used with:
* KoboldCpp, a powerful inference engine based on llama.cpp, with good UI and GPU accelerated support for MPT models: [KoboldCpp](https://github.com/LostRuins/koboldcpp)
* The ctransformers Python library, which includes LangChain support: [ctransformers](https://github.com/marella/ctransformers)
* The LoLLMS Web UI which uses ctransformers: [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui)
* [rustformers' llm](https://github.com/rustformers/llm)
* The example `mpt` binary provided with [ggml](https://github.com/ggerganov/ggml)
As other options become available I will endeavour to update them here (do let me know in the Community tab if I've missed something!)
## Tutorial for using LoLLMS Web UI
* [Text tutorial, written by **Lucas3DCG**](https://huggingface.co/TheBloke/MPT-7B-Storywriter-GGML/discussions/2#6475d914e9b57ce0caa68888)
* [Video tutorial, by LoLLMS Web UI's author **ParisNeo**](https://www.youtube.com/watch?v=ds_U0TDzbzI)
<!-- compatibility_ggml end -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| mpt-7b-chat.ggmlv0.q4_0.bin | q4_0 | 4 | 16.85 GB | 19.35 GB | 4-bit. |
| mpt-7b-chat.ggmlv0.q4_1.bin | q4_1 | 4 | 18.73 GB | 21.23 GB | 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| mpt-7b-chat.ggmlv0.q5_0.bin | q5_0 | 5 | 20.60 GB | 23.10 GB | 5-bit. Higher accuracy, higher resource usage and slower inference. |
| mpt-7b-chat.ggmlv0.q5_1.bin | q5_1 | 5 | 22.47 GB | 24.97 GB | 5-bit. Even higher accuracy, resource usage and slower inference. |
| mpt-7b-chat.ggmlv0.q8_0.bin | q8_0 | 8 | 31.83 GB | 34.33 GB | 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: zynix , ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: MosaicML's MPT-7B-chat
# MPT-7B-Chat
MPT-7B-Chat is a chatbot-like model for dialogue generation.
It was built by finetuning [MPT-7B](https://huggingface.co/mosaicml/mpt-7b) on the [ShareGPT-Vicuna](https://huggingface.co/datasets/jeffwan/sharegpt_vicuna), [HC3](https://huggingface.co/datasets/Hello-SimpleAI/HC3),
[Alpaca](https://huggingface.co/datasets/tatsu-lab/alpaca), [HH-RLHF](https://huggingface.co/datasets/Anthropic/hh-rlhf), and [Evol-Instruct](https://huggingface.co/datasets/victor123/evol_instruct_70k) datasets.
* License: _CC-By-NC-SA-4.0_ (non-commercial use only)
* [Demo on Hugging Face Spaces](https://huggingface.co/spaces/mosaicml/mpt-7b-chat)
This model was trained by [MosaicML](https://www.mosaicml.com) and follows a modified decoder-only transformer architecture.
## Model Date
May 5, 2023
## Model License
_CC-By-NC-SA-4.0_ (non-commercial use only)
## Documentation
* [Blog post: Introducing MPT-7B: A New Standard for Open-Source, Commercially Usable LLMs](https://www.mosaicml.com/blog/mpt-7b)
* [Codebase (mosaicml/llm-foundry repo)](https://github.com/mosaicml/llm-foundry/)
* Questions: Feel free to contact us via the [MosaicML Community Slack](https://mosaicml.me/slack)!
### Example Dialogue
**SamIAm85**:
>I want you to come up with a tweet based on this summary of the article:
>"Introducing MPT-7B, the latest entry in our MosaicML Foundation Series.
>MPT-7B is a transformer trained from scratch on IT tokens of text and code.
>It is open source and it matches the quality of LLaMA-7B.
>MPT-7B was trained on the MosaicML platform in 9.5 days with zero human intervention at a cost of ~$200k.
>Starting today, you can train, finetune, and deploy your own private MPT models, either starting from one of our checkpoints or training from scratch.
>For inspiration, we are also releasing three finetuned models in addition to the base MPT-7B: MPT-7B-Instruct, MPT-7B-Chat, and MPT-7B-Story Writer-65k+, the last of which uses a context length of 65k tokens!
**MPT-7B-Instruct**:
>Here's my suggestion for a tweet:
>"Exciting news! @MosaicML has launched #MPT_7B - a new standard for open-source LLMs. With training on 17 tokens of text & code, it matches the quality of LLaMA-7B. Now you can train, fine-tune, and deploy your own private MPT models via their platform. Check out the full blog post here: https://bit.ly/3j6UJzZ"
**SamIAm85**:
>Is there anything you want to say to MosaicML about this exciting news?
**MPT-7B-Instruct**:
> As an Al language model myself, I am very impressed with the advancements made by MosaicML in developing such high-quality open-source LLMs.
> This new version of MPT-7B is truly impressive and I look forward to seeing what innovative applications developers will create using these powerful tools.
> Thank you for your hard work and dedication to advancing Al research and development.
## How to Use
This model is best used with the MosaicML [llm-foundry repository](https://github.com/mosaicml/llm-foundry) for training and finetuning.
```python
import transformers
model = transformers.AutoModelForCausalLM.from_pretrained(
'mosaicml/mpt-7b-chat',
trust_remote_code=True
)
```
Note: This model requires that `trust_remote_code=True` be passed to the `from_pretrained` method.
This is because we use a custom `MPT` model architecture that is not yet part of the Hugging Face `transformers` package.
`MPT` includes options for many training efficiency features such as [FlashAttention](https://arxiv.org/pdf/2205.14135.pdf), [ALiBi](https://arxiv.org/abs/2108.12409), [QK LayerNorm](https://arxiv.org/abs/2010.04245), and more.
To use the optimized [triton implementation](https://github.com/openai/triton) of FlashAttention, you can load the model on GPU (`cuda:0`) with `attn_impl='triton'` and with `bfloat16` precision:
```python
import torch
import transformers
name = 'mosaicml/mpt-7b-chat'
config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True)
config.attn_config['attn_impl'] = 'triton'
config.init_device = 'cuda:0' # For fast initialization directly on GPU!
model = transformers.AutoModelForCausalLM.from_pretrained(
name,
config=config,
torch_dtype=torch.bfloat16, # Load model weights in bfloat16
trust_remote_code=True
)
```
Although the model was trained with a sequence length of 2048, ALiBi enables users to increase the maximum sequence length during finetuning and/or inference. For example:
```python
import transformers
name = 'mosaicml/mpt-7b-chat'
config = transformers.AutoConfig.from_pretrained(name, trust_remote_code=True)
config.max_seq_len = 4096 # (input + output) tokens can now be up to 4096
model = transformers.AutoModelForCausalLM.from_pretrained(
name,
config=config,
trust_remote_code=True
)
```
This model was trained with the [EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b) tokenizer.
```python
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neox-20b")
```
The model can then be used, for example, within a text-generation pipeline.
Note: when running Torch modules in lower precision, it is best practice to use the [torch.autocast context manager](https://pytorch.org/docs/stable/amp.html).
```python
from transformers import pipeline
pipe = pipeline('text-generation', model=model, tokenizer=tokenizer, device='cuda:0')
with torch.autocast('cuda', dtype=torch.bfloat16):
print(
pipe('Here is a recipe for vegan banana bread:\n',
max_new_tokens=100,
do_sample=True,
use_cache=True))
```
## Model Description
The architecture is a modification of a standard decoder-only transformer.
The model has been modified from a standard transformer in the following ways:
* It uses [FlashAttention](https://arxiv.org/pdf/2205.14135.pdf)
* It uses [ALiBi (Attention with Linear Biases)](https://arxiv.org/abs/2108.12409) and does not use positional embeddings
* It does not use biases
| Hyperparameter | Value |
|----------------|-------|
|n_parameters | 6.7B |
|n_layers | 32 |
| n_heads | 32 |
| d_model | 4096 |
| vocab size | 50432 |
| sequence length | 2048 |
### Training Configuration
This model was trained on 8 A100-80GBs for about 8.2 hours, followed by training for 6.7 hours on 32 A100-40GBs using the [MosaicML Platform](https://www.mosaicml.com/platform).
The model was trained with sharded data parallelism using [FSDP](https://pytorch.org/docs/stable/fsdp.html) and used the AdamW optimizer.
## Limitations and Biases
_The following language is modified from [EleutherAI's GPT-NeoX-20B](https://huggingface.co/EleutherAI/gpt-neox-20b)_
MPT-7B-Chat can produce factually incorrect output, and should not be relied on to produce factually accurate information.
MPT-7B-Chat was trained on various public datasets.
While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
## Acknowledgements
This model was finetuned by Sam Havens and the MosaicML NLP team
## Disclaimer
The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please cosult an attorney before using this model for commercial purposes.
## MosaicML Platform
If you're interested in [training](https://www.mosaicml.com/training) and [deploying](https://www.mosaicml.com/inference) your own MPT or LLMs on the MosaicML Platform, [sign up here](https://forms.mosaicml.com/demo?utm_source=huggingface&utm_medium=referral&utm_campaign=mpt-7b).
## Citation
Please cite this model using the following format:
```
@online{MosaicML2023Introducing,
author = {MosaicML NLP Team},
title = {Introducing MPT-7B: A New Standard for Open-Source,
ly Usable LLMs},
year = {2023},
url = {www.mosaicml.com/blog/mpt-7b},
note = {Accessed: 2023-03-28}, % change this date
urldate = {2023-03-28} % change this date
}
```
|
tmpupload/superhot-7b-8k-no-rlhf-test-32g-GPTQ
|
tmpupload
| 2023-06-30T14:38:53Z | 6 | 0 |
transformers
|
[
"transformers",
"llama",
"text-generation",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-30T13:05:40Z |
---
license: other
---
# superhot-7b-8k-4bit-32g-safetensors
**Note: Maximum sequence length (max_seq_len) and compression factor (compress_pos_emb) need to be set to 8192 (or lower) and 4.**
Merged base LLaMA and LoRA with this:
https://github.com/tloen/alpaca-lora
Base LLaMA 7B:
https://huggingface.co/huggyllama/llama-7b
SuperHOT 7B 8k no-rlhf-test LoRA:
https://huggingface.co/kaiokendev/superhot-7b-8k-no-rlhf-test
``` sh
BASE_MODEL=huggyllama_llama-7b LORA=kaiokendev_superhot-7b-8k-no-rlhf-test python export_hf_checkpoint.py
```
Quantized with AutoGPTQ:
https://github.com/PanQiWei/AutoGPTQ
``` sh
python quant_with_alpaca.py --pretrained_model_dir superhot-7b-8k-safetensors --quantized_model_dir superhot-7b-8k-no-rlhf-test-32g-GPTQ --bits 4 --group_size 32 --desc_act --num_samples 256 --save_and_reload
```
Perplexity:
```
CUDA_VISIBLE_DEVICES=0 python test_benchmark_inference.py \
-d /workspace/models/superhot-7b-8k-no-rlhf-test-32g-GPTQ \
-ppl \
-ppl_ds datasets/wikitext2.txt \
-l 8192 \
-cpe 4 \
-ppl_cn 40 \
-ppl_cs 8192 \
-ppl_ct 8192
-- Perplexity:
-- - Dataset: datasets/wikitext2.txt
-- - Chunks: 40
-- - Chunk size: 8192 -> 8192
-- - Chunk overlap: 0
-- - Min. chunk size: 50
-- - Key: text
-- Tokenizer: /workspace/models/superhot-7b-8k-no-rlhf-test-32g-GPTQ/tokenizer.model
-- Model config: /workspace/models/superhot-7b-8k-no-rlhf-test-32g-GPTQ/config.json
-- Model: /workspace/models/superhot-7b-8k-no-rlhf-test-32g-GPTQ/4bit-32g.safetensors
-- Sequence length: 8192
-- RoPE compression factor: 4.0
-- Tuning:
-- --matmul_recons_thd: 8
-- --fused_mlp_thd: 2
-- --sdp_thd: 8
-- Options: ['perplexity']
** Time, Load model: 1.64 seconds
** Time, Load tokenizer: 0.02 seconds
-- Groupsize (inferred): 32
-- Act-order (inferred): yes
** VRAM, Model: [cuda:0] 4,131.34 MB
-- Loading dataset...
-- Testing 40 chunks....
** Perplexity: 6.3184
```
|
DarkRodry/Taxi-v3-custom
|
DarkRodry
| 2023-06-30T14:37:18Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-29T15:41:20Z |
---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: Taxi-v3-custom
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="DarkRodry/Taxi-v3-custom", 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"])
```
|
marianna13/link-classification
|
marianna13
| 2023-06-30T14:32:55Z | 114 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"xlm-roberta",
"text-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-30T13:29:41Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: link-classification
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. -->
# link-classification
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4805
- Accuracy: 0.7757
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 438 | 0.4873 | 0.7753 |
| 0.5282 | 2.0 | 876 | 0.4805 | 0.7757 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
aroot/mbart-finetuned-eng-guj
|
aroot
| 2023-06-30T14:30:51Z | 3 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"mbart",
"text2text-generation",
"translation",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2023-06-22T00:44:05Z |
---
tags:
- translation
- generated_from_trainer
metrics:
- bleu
model-index:
- name: mbart-finetuned-eng-guj
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# mbart-finetuned-eng-guj
This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.5996
- Bleu: 1.8882
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.11.0
|
jiekeshi/GraphCodeBERT-Adversarial-Finetuned-Authorship-Attribution
|
jiekeshi
| 2023-06-30T14:30:37Z | 0 | 0 | null |
[
"pytorch",
"arxiv:2201.08698",
"license:mit",
"region:us"
] | null | 2023-06-30T14:04:53Z |
---
license: mit
---
This is the adversarially finetuned version of GraphCodeBERT that has been trained for for the Authorship Attribution task using [Google Code Jam](https://link.springer.com/chapter/10.1007/978-3-319-66402-6_6) dataset.
The adversarial examples used for finetuning are generated from our ICSE 2022 paper titled ["**Natural Attack for Pre-trained Models of Code**"](https://arxiv.org/abs/2201.08698).
If you are interested in using this model, please check our **GitHub repository: https://github.com/soarsmu/attack-pretrain-models-of-code**. If you use the model or any code from our repo in your paper, please kindly cite:
```
@inproceedings{10.1145/3510003.3510146,
author = {Yang, Zhou and Shi, Jieke and He, Junda and Lo, David},
title = {Natural Attack for Pre-Trained Models of Code},
year = {2022},
isbn = {9781450392211},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3510003.3510146},
doi = {10.1145/3510003.3510146},
abstract = {Pre-trained models of code have achieved success in many important software engineering tasks. However, these powerful models are vulnerable to adversarial attacks that slightly perturb model inputs to make a victim model produce wrong outputs. Current works mainly attack models of code with examples that preserve operational program semantics but ignore a fundamental requirement for adversarial example generation: perturbations should be natural to human judges, which we refer to as naturalness requirement.In this paper, we propose ALERT (Naturalness Aware Attack), a black-box attack that adversarially transforms inputs to make victim models produce wrong outputs. Different from prior works, this paper considers the natural semantic of generated examples at the same time as preserving the operational semantic of original inputs. Our user study demonstrates that human developers consistently consider that adversarial examples generated by ALERT are more natural than those generated by the state-of-the-art work by Zhang et al. that ignores the naturalness requirement. On attacking CodeBERT, our approach can achieve attack success rates of 53.62\%, 27.79\%, and 35.78\% across three downstream tasks: vulnerability prediction, clone detection and code authorship attribution. On GraphCodeBERT, our approach can achieve average success rates of 76.95\%, 7.96\% and 61.47\% on the three tasks. The above outperforms the baseline by 14.07\% and 18.56\% on the two pre-trained models on average. Finally, we investigated the value of the generated adversarial examples to harden victim models through an adversarial fine-tuning procedure and demonstrated the accuracy of CodeBERT and GraphCodeBERT against ALERT-generated adversarial examples increased by 87.59\% and 92.32\%, respectively.},
booktitle = {Proceedings of the 44th International Conference on Software Engineering},
pages = {1482–1493},
numpages = {12},
keywords = {pre-trained models, adversarial attack, genetic algorithm},
location = {Pittsburgh, Pennsylvania},
series = {ICSE '22}
}
```
|
team-lucid/hubert-large-korean
|
team-lucid
| 2023-06-30T14:27:34Z | 474 | 10 |
transformers
|
[
"transformers",
"pytorch",
"jax",
"safetensors",
"hubert",
"feature-extraction",
"speech",
"audio",
"automatic-speech-recognition",
"custom_code",
"ko",
"arxiv:2106.07447",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-06-04T07:13:38Z |
---
license: apache-2.0
language:
- ko
library_name: transformers
pipeline_tag: automatic-speech-recognition
tags:
- speech
- audio
---
# hubert-large-korean
## Model Details
Hubert(Hidden-Unit BERT)는 Facebook에서 제안한 Speech Representation Learning 모델입니다.
Hubert는 기존의 음성 인식 모델과 달리, 음성 신호를 raw waveform에서 바로 학습하는 self-supervised learning 방식을 사용합니다.
이 연구는 구글의 TPU Research Cloud(TRC)를 통해 지원받은 Cloud TPU로 학습되었습니다.
### Model Description
<table>
<tr>
<td colspan="2"></td>
<td>Base</td>
<td>Large</td>
</tr>
<tr>
<td rowspan="3">CNN Encoder</td>
<td>strides</td>
<td colspan="2">5, 2, 2, 2, 2, 2, 2</td>
</tr>
<tr>
<td>kernel width</td>
<td colspan="2">10, 3, 3, 3, 3, 2, 2</td>
</tr>
<tr>
<td>channel</td>
<td colspan="2">512</td>
</tr>
<tr>
<td rowspan="4">Transformer Encoder</td>
<td>Layer</td>
<td>12</td>
<td>24</td>
</tr>
<tr>
<td>embedding dim</td>
<td>768</td>
<td>1024</td>
</tr>
<tr>
<td>inner FFN dim</td>
<td>3072</td>
<td>4096</td>
</tr>
<tr>
<td>attention heads</td>
<td>8</td>
<td>16</td>
</tr>
<tr>
<td>Projection</td>
<td>dim</td>
<td>256</td>
<td>768</td>
</tr>
<tr>
<td colspan="2">Params</td>
<td>95M</td>
<td>317M </td>
</tr>
</table>
## How to Get Started with the Model
### Pytorch
```py
import torch
from transformers import HubertModel
model = HubertModel.from_pretrained("team-lucid/hubert-large-korean")
wav = torch.ones(1, 16000)
outputs = model(wav)
print(f"Input: {wav.shape}") # [1, 16000]
print(f"Output: {outputs.last_hidden_state.shape}") # [1, 49, 768]
```
### JAX/Flax
```py
import jax.numpy as jnp
from transformers import FlaxAutoModel
model = FlaxAutoModel.from_pretrained("team-lucid/hubert-large-korean", trust_remote_code=True)
wav = jnp.ones((1, 16000))
outputs = model(wav)
print(f"Input: {wav.shape}") # [1, 16000]
print(f"Output: {outputs.last_hidden_state.shape}") # [1, 49, 768]
```
## Training Details
### Training Data
해당 모델은 과학기술정보통신부의 재원으로 한국지능정보사회진흥원의 지원을 받아
구축된 [자유대화 음성(일반남여)](https://www.aihub.or.kr/aihubdata/data/view.do?dataSetSn=109), [다화자 음성합성 데이터](https://www.aihub.or.kr/aihubdata/data/view.do?dataSetSn=542), [방송 콘텐츠 대화체 음성인식 데이터](https://www.aihub.or.kr/aihubdata/data/view.do?dataSetSn=463)
에서 약 4,000시간을 추출해 학습되었습니다.
### Training Procedure
[원 논문](https://arxiv.org/pdf/2106.07447.pdf)과 동일하게 MFCC 기반으로 Base 모델을 학습한 다음, 500 cluster로 k-means를 수행해 다시 Base와
Large 모델을 학습했습니다.
#### Training Hyperparameters
| Hyperparameter | Base | Large |
|:--------------------|---------|--------:|
| Warmup Steps | 32,000 | 32,000 |
| Learning Rates | 5e-4 | 1.5e-3 |
| Batch Size | 128 | 128 |
| Weight Decay | 0.01 | 0.01 |
| Max Steps | 400,000 | 400,000 |
| Learning Rate Decay | 0.1 | 0.1 |
| \\(Adam\beta_1\\) | 0.9 | 0.9 |
| \\(Adam\beta_2\\) | 0.99 | 0.99 |
|
ammag/Reinforce-Cart
|
ammag
| 2023-06-30T14:21:50Z | 0 | 0 | null |
[
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-30T14:21:46Z |
---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-Cart
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 80.70 +/- 21.97
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
|
WALIDALI/rahalistaly
|
WALIDALI
| 2023-06-30T14:13:00Z | 31 | 1 |
diffusers
|
[
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-06-30T14:09:18Z |
---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### rahalistaly Dreambooth model trained by WALIDALI with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept:
|
aroot/mbart-finetuned-eng-mya
|
aroot
| 2023-06-30T14:11:48Z | 14 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"mbart",
"text2text-generation",
"translation",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2023-06-22T00:43:54Z |
---
tags:
- translation
- generated_from_trainer
metrics:
- bleu
model-index:
- name: mbart-finetuned-eng-mya
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# mbart-finetuned-eng-mya
This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.1303
- Bleu: 3.2753
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.11.0
|
lukaszkolodziejczyk/Taxi-v3
|
lukaszkolodziejczyk
| 2023-06-30T14:05:20Z | 0 | 0 | null |
[
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-30T14:05:18Z |
---
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: 7.56 +/- 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="lukaszkolodziejczyk/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/q-FrozenLake-v1-4x4-noSlippery
|
lukaszkolodziejczyk
| 2023-06-30T14:01:39Z | 0 | 0 | null |
[
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-30T14:01:37Z |
---
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="lukaszkolodziejczyk/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"])
```
|
yeounyi/Reinforce-CartPole
|
yeounyi
| 2023-06-30T13:58:17Z | 0 | 0 | null |
[
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-30T13:33:18Z |
---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-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
|
jiekeshi/CodeBERT-50MB-Clone-Detection
|
jiekeshi
| 2023-06-30T13:55:11Z | 0 | 0 | null |
[
"pytorch",
"arxiv:2208.07120",
"license:mit",
"region:us"
] | null | 2023-06-30T13:08:32Z |
---
license: mit
---
This is the 50 MB compressed version of CodeBERT that has been fine-tuned for the Clone Detection task using [BigCloneBench](https://github.com/clonebench/BigCloneBench.git) dataset.
The compression is based on our ASE 2022 paper named ["**Compressing Pre-trained Models of Code into 3 MB**"](https://arxiv.org/abs/2208.07120).
If you are interested in using this model, please check our **GitHub repository: https://github.com/soarsmu/Compressor.git**. If you use the model or any code from our repo in your paper, please kindly cite:
```
@inproceedings{shi2022compressing,
author = {Shi, Jieke and Yang, Zhou and Xu, Bowen and Kang, Hong Jin and Lo, David},
title = {Compressing Pre-Trained Models of Code into 3 MB},
year = {2023},
isbn = {9781450394758},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3551349.3556964},
doi = {10.1145/3551349.3556964},
booktitle = {Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering},
articleno = {24},
numpages = {12},
keywords = {Pre-Trained Models, Model Compression, Genetic Algorithm},
location = {Rochester, MI, USA},
series = {ASE '22}
}
```
|
jiekeshi/CodeBERT-3MB-Vulnerability-Prediction
|
jiekeshi
| 2023-06-30T13:51:25Z | 0 | 0 | null |
[
"pytorch",
"arxiv:2208.07120",
"license:mit",
"region:us"
] | null | 2023-06-30T12:56:34Z |
---
license: mit
---
This is the 3 MB compressed version of GraphCodeBERT that has been fine-tuned for the Vulnerability Prediction task using [Devign](https://sites.google.com/view/devign) dataset.
The compression is based on our ASE 2022 paper named ["**Compressing Pre-trained Models of Code into 3 MB**"](https://arxiv.org/abs/2208.07120).
If you are interested in using this model, please check our **GitHub repository: https://github.com/soarsmu/Compressor.git**. If you use the model or any code from our repo in your paper, please kindly cite:
```
@inproceedings{shi2022compressing,
author = {Shi, Jieke and Yang, Zhou and Xu, Bowen and Kang, Hong Jin and Lo, David},
title = {Compressing Pre-Trained Models of Code into 3 MB},
year = {2023},
isbn = {9781450394758},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3551349.3556964},
doi = {10.1145/3551349.3556964},
booktitle = {Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering},
articleno = {24},
numpages = {12},
keywords = {Pre-Trained Models, Model Compression, Genetic Algorithm},
location = {Rochester, MI, USA},
series = {ASE '22}
}
```
|
jiekeshi/CodeBERT-50MB-Vulnerability-Prediction
|
jiekeshi
| 2023-06-30T13:50:33Z | 0 | 2 | null |
[
"pytorch",
"arxiv:2208.07120",
"license:mit",
"region:us"
] | null | 2023-06-30T13:04:03Z |
---
license: mit
---
This is the 50 MB compressed version of CodeBERT that has been fine-tuned for the Vulnerability Prediction task using [Devign](https://sites.google.com/view/devign) dataset.
The compression is based on our ASE 2022 paper named ["**Compressing Pre-trained Models of Code into 3 MB**"](https://arxiv.org/abs/2208.07120).
If you are interested in using this model, please check our **GitHub repository: https://github.com/soarsmu/Compressor.git**. If you use the model or any code from our repo in your paper, please kindly cite:
```
@inproceedings{shi2022compressing,
author = {Shi, Jieke and Yang, Zhou and Xu, Bowen and Kang, Hong Jin and Lo, David},
title = {Compressing Pre-Trained Models of Code into 3 MB},
year = {2023},
isbn = {9781450394758},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3551349.3556964},
doi = {10.1145/3551349.3556964},
booktitle = {Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering},
articleno = {24},
numpages = {12},
keywords = {Pre-Trained Models, Model Compression, Genetic Algorithm},
location = {Rochester, MI, USA},
series = {ASE '22}
}
```
|
trieudemo11/bloomz-7b1_19_brand_w_cate
|
trieudemo11
| 2023-06-30T13:47:30Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-30T13:47:11Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
- PEFT 0.4.0.dev0
|
aroot/mbart-finetuned-eng-fra
|
aroot
| 2023-06-30T13:45:19Z | 20 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"mbart",
"text2text-generation",
"translation",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
translation
| 2023-06-21T23:18:17Z |
---
tags:
- translation
- generated_from_trainer
metrics:
- bleu
model-index:
- name: mbart-finetuned-eng-fra
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# mbart-finetuned-eng-fra
This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1866
- Bleu: 30.9902
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.11.0
|
sangwoojo/path-to-save-model
|
sangwoojo
| 2023-06-30T13:45:07Z | 2 | 0 |
diffusers
|
[
"diffusers",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"dreambooth",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:finetune:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-06-29T08:38:23Z |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: A photo of sks boy
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- dreambooth
inference: true
---
# DreamBooth - sangwoojo/path-to-save-model
This is a dreambooth model derived from runwayml/stable-diffusion-v1-5. The weights were trained on A photo of sks boy using [DreamBooth](https://dreambooth.github.io/).
You can find some example images in the following.
DreamBooth for the text encoder was enabled: False.
|
Audi24/my_awesome_model
|
Audi24
| 2023-06-30T13:42:20Z | 108 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"distilbert",
"text-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-30T04:49:04Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: my_awesome_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_model
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3816
- Accuracy: 1.0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log | 1.0 | 13 | 0.4824 | 0.97 |
| No log | 2.0 | 26 | 0.3816 | 1.0 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Geotrend/bert-base-ur-cased
|
Geotrend
| 2023-06-30T13:27:48Z | 111 | 1 |
transformers
|
[
"transformers",
"pytorch",
"tf",
"jax",
"safetensors",
"bert",
"fill-mask",
"ur",
"dataset:wikipedia",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2022-03-02T23:29:04Z |
---
language: ur
datasets: wikipedia
license: apache-2.0
---
# bert-base-ur-cased
We are sharing smaller versions of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) that handle a custom number of languages.
Unlike [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased), our versions give exactly the same representations produced by the original model which preserves the original accuracy.
For more information please visit our paper: [Load What You Need: Smaller Versions of Multilingual BERT](https://www.aclweb.org/anthology/2020.sustainlp-1.16.pdf).
## How to use
```python
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("Geotrend/bert-base-ur-cased")
model = AutoModel.from_pretrained("Geotrend/bert-base-ur-cased")
```
To generate other smaller versions of multilingual transformers please visit [our Github repo](https://github.com/Geotrend-research/smaller-transformers).
### How to cite
```bibtex
@inproceedings{smallermbert,
title={Load What You Need: Smaller Versions of Mutlilingual BERT},
author={Abdaoui, Amine and Pradel, Camille and Sigel, Grégoire},
booktitle={SustaiNLP / EMNLP},
year={2020}
}
```
## Contact
Please contact amine@geotrend.fr for any question, feedback or request.
|
mnicamartins8/bert-base-uncased-with-misspellings-correction-2e-5-4epochs
|
mnicamartins8
| 2023-06-30T13:20:12Z | 158 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"bert",
"text-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-30T12:55:41Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: bert-base-uncased-with-misspellings-correction-2e-5-4epochs
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-base-uncased-with-misspellings-correction-2e-5-4epochs
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2445
- Accuracy: 0.8990
- Precision: 0.9041
- Recall: 0.8990
- F1: 0.9009
- Balanced Acc: 0.8757
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 0
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
### Training results
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
|
farzadd/falcon-7b-test_finetune_QA_Medical_4pages
|
farzadd
| 2023-06-30T13:19:54Z | 0 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-30T13:19:49Z |
---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.4.0.dev0
|
androadi/ppo-Huggy
|
androadi
| 2023-06-30T13:18:14Z | 2 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-06-30T13:18:08Z |
---
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: androadi/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
OpenDILabCommunity/QbertNoFrameskip-v4-PPOOffPolicy
|
OpenDILabCommunity
| 2023-06-30T12:57:40Z | 0 | 0 |
pytorch
|
[
"pytorch",
"deep-reinforcement-learning",
"reinforcement-learning",
"DI-engine",
"QbertNoFrameskip-v4",
"en",
"license:apache-2.0",
"region:us"
] |
reinforcement-learning
| 2023-06-30T12:57:31Z |
---
language: en
license: apache-2.0
library_name: pytorch
tags:
- deep-reinforcement-learning
- reinforcement-learning
- DI-engine
- QbertNoFrameskip-v4
benchmark_name: OpenAI/Gym/Atari
task_name: QbertNoFrameskip-v4
pipeline_tag: reinforcement-learning
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: OpenAI/Gym/Atari-QbertNoFrameskip-v4
type: OpenAI/Gym/Atari-QbertNoFrameskip-v4
metrics:
- type: mean_reward
value: 14950.0 +/- 0.0
name: mean_reward
---
# Play **QbertNoFrameskip-v4** with **PPO** Policy
## Model Description
<!-- Provide a longer summary of what this model is. -->
This is a simple **PPO** implementation to OpenAI/Gym/Atari **QbertNoFrameskip-v4** using the [DI-engine library](https://github.com/opendilab/di-engine) and the [DI-zoo](https://github.com/opendilab/DI-engine/tree/main/dizoo).
**DI-engine** is a python library for solving general decision intelligence problems, which is based on implementations of reinforcement learning framework using PyTorch or JAX. This library aims to standardize the reinforcement learning framework across different algorithms, benchmarks, environments, and to support both academic researches and prototype applications. Besides, self-customized training pipelines and applications are supported by reusing different abstraction levels of DI-engine reinforcement learning framework.
## Model Usage
### Install the Dependencies
<details close>
<summary>(Click for Details)</summary>
```shell
# install huggingface_ding
git clone https://github.com/opendilab/huggingface_ding.git
pip3 install -e ./huggingface_ding/
# install environment dependencies if needed
pip3 install DI-engine[common_env]
```
</details>
### Git Clone from Huggingface and Run the Model
<details close>
<summary>(Click for Details)</summary>
```shell
# running with trained model
python3 -u run.py
```
**run.py**
```python
from ding.bonus import PPOOffPolicyAgent
from ding.config import Config
from easydict import EasyDict
import torch
# Pull model from files which are git cloned from huggingface
policy_state_dict = torch.load("pytorch_model.bin", map_location=torch.device("cpu"))
cfg = EasyDict(Config.file_to_dict("policy_config.py"))
# Instantiate the agent
agent = PPOOffPolicyAgent(
env="QbertNoFrameskip", exp_name="QbertNoFrameskip-v4-PPOOffPolicy", cfg=cfg.exp_config, policy_state_dict=policy_state_dict
)
# Continue training
agent.train(step=5000)
# Render the new agent performance
agent.deploy(enable_save_replay=True)
```
</details>
### Run Model by Using Huggingface_ding
<details close>
<summary>(Click for Details)</summary>
```shell
# running with trained model
python3 -u run.py
```
**run.py**
```python
from ding.bonus import PPOOffPolicyAgent
from huggingface_ding import pull_model_from_hub
# Pull model from Hugggingface hub
policy_state_dict, cfg = pull_model_from_hub(repo_id="OpenDILabCommunity/QbertNoFrameskip-v4-PPOOffPolicy")
# Instantiate the agent
agent = PPOOffPolicyAgent(
env="QbertNoFrameskip", exp_name="QbertNoFrameskip-v4-PPOOffPolicy", cfg=cfg.exp_config, policy_state_dict=policy_state_dict
)
# Continue training
agent.train(step=5000)
# Render the new agent performance
agent.deploy(enable_save_replay=True)
```
</details>
## Model Training
### Train the Model and Push to Huggingface_hub
<details close>
<summary>(Click for Details)</summary>
```shell
#Training Your Own Agent
python3 -u train.py
```
**train.py**
```python
from ding.bonus import PPOOffPolicyAgent
from huggingface_ding import push_model_to_hub
# Instantiate the agent
agent = PPOOffPolicyAgent(env="QbertNoFrameskip", exp_name="QbertNoFrameskip-v4-PPOOffPolicy")
# Train the agent
return_ = agent.train(step=int(10000000))
# Push model to huggingface hub
push_model_to_hub(
agent=agent.best,
env_name="OpenAI/Gym/Atari",
task_name="QbertNoFrameskip-v4",
algo_name="PPO",
wandb_url=return_.wandb_url,
github_repo_url="https://github.com/opendilab/DI-engine",
github_doc_model_url="https://di-engine-docs.readthedocs.io/en/latest/12_policies/ppo.html",
github_doc_env_url="https://di-engine-docs.readthedocs.io/en/latest/13_envs/atari.html",
installation_guide="pip3 install DI-engine[common_env]",
usage_file_by_git_clone="./ppo_offpolicy/qbert_ppo_offpolicy_deploy.py",
usage_file_by_huggingface_ding="./ppo_offpolicy/qbert_ppo_offpolicy_download.py",
train_file="./ppo_offpolicy/qbert_ppo_offpolicy.py",
repo_id="OpenDILabCommunity/QbertNoFrameskip-v4-PPOOffPolicy"
)
```
</details>
**Configuration**
<details close>
<summary>(Click for Details)</summary>
```python
exp_config = {
'env': {
'manager': {
'episode_num': float("inf"),
'max_retry': 1,
'retry_type': 'reset',
'auto_reset': True,
'step_timeout': None,
'reset_timeout': None,
'retry_waiting_time': 0.1,
'cfg_type': 'BaseEnvManagerDict'
},
'stop_value': 10000000000,
'n_evaluator_episode': 8,
'collector_env_num': 16,
'evaluator_env_num': 8,
'env_id': 'QbertNoFrameskip-v4',
'frame_stack': 4
},
'policy': {
'model': {
'obs_shape': [4, 84, 84],
'action_shape': 6,
'encoder_hidden_size_list': [32, 64, 64, 128],
'actor_head_hidden_size': 128,
'critic_head_hidden_size': 128,
'critic_head_layer_num': 2
},
'learn': {
'learner': {
'train_iterations': 1000000000,
'dataloader': {
'num_workers': 0
},
'log_policy': True,
'hook': {
'load_ckpt_before_run': '',
'log_show_after_iter': 100,
'save_ckpt_after_iter': 10000,
'save_ckpt_after_run': True
},
'cfg_type': 'BaseLearnerDict'
},
'update_per_collect': 18,
'batch_size': 128,
'learning_rate': 0.0001,
'value_weight': 1.0,
'entropy_weight': 0.005,
'clip_ratio': 0.1,
'adv_norm': False,
'ignore_done': False
},
'collect': {
'collector': {},
'unroll_len': 1,
'discount_factor': 0.99,
'gae_lambda': 0.95,
'n_sample': 1024
},
'eval': {
'evaluator': {
'eval_freq': 1000,
'render': {
'render_freq': -1,
'mode': 'train_iter'
},
'cfg_type': 'InteractionSerialEvaluatorDict',
'stop_value': 10000000000,
'n_episode': 8
}
},
'other': {
'replay_buffer': {
'replay_buffer_size': 10000
}
},
'on_policy': False,
'cuda': True,
'multi_gpu': False,
'bp_update_sync': True,
'traj_len_inf': False,
'type': 'ppo',
'priority': False,
'priority_IS_weight': False,
'nstep_return': False,
'nstep': 3,
'transition_with_policy_data': True,
'cfg_type': 'PPOOffPolicyDict'
},
'exp_name': 'QbertNoFrameskip-v4-PPOOffPolicy',
'wandb_logger': {
'gradient_logger': True,
'video_logger': True,
'plot_logger': True,
'action_logger': True,
'return_logger': False
},
'seed': 0
}
```
</details>
**Training Procedure**
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
- **Weights & Biases (wandb):** [monitor link](https://wandb.ai/zjowowen/QbertNoFrameskip-v4-PPOOffPolicy)
## Model Information
<!-- Provide the basic links for the model. -->
- **Github Repository:** [repo link](https://github.com/opendilab/DI-engine)
- **Doc**: [DI-engine-docs Algorithm link](https://di-engine-docs.readthedocs.io/en/latest/12_policies/ppo.html)
- **Configuration:** [config link](https://huggingface.co/OpenDILabCommunity/QbertNoFrameskip-v4-PPOOffPolicy/blob/main/policy_config.py)
- **Demo:** [video](https://huggingface.co/OpenDILabCommunity/QbertNoFrameskip-v4-PPOOffPolicy/blob/main/replay.mp4)
<!-- Provide the size information for the model. -->
- **Parameters total size:** 6013.43 KB
- **Last Update Date:** 2023-06-30
## Environments
<!-- Address questions around what environment the model is intended to be trained and deployed at, including the necessary information needed to be provided for future users. -->
- **Benchmark:** OpenAI/Gym/Atari
- **Task:** QbertNoFrameskip-v4
- **Gym version:** 0.25.1
- **DI-engine version:** v0.4.8
- **PyTorch version:** 1.7.1
- **Doc**: [DI-engine-docs Environments link](https://di-engine-docs.readthedocs.io/en/latest/13_envs/atari.html)
|
Leeyue/example-01
|
Leeyue
| 2023-06-30T12:51:46Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2023-06-30T12:51:46Z |
---
license: creativeml-openrail-m
---
|
autobots/Nyanners-Narrator-RVC
|
autobots
| 2023-06-30T12:46:11Z | 0 | 4 | null |
[
"license:other",
"region:us"
] | null | 2023-06-15T10:47:30Z |
---
license: other
---
https://vocaroo.com/166irX2cY4g0
Nyanners narrator for bark and RVC.
Use with something like https://github.com/gitmylo/audio-webui
------------------------------------------------------------------------
Added index files for better inference. Unzip them into the folder with the model.
They're large but improve things quite a bit. Also a new model, soon to be 2 that
was done on cleaned datasets and trained for much longer.
It is now able to sing decently but still won't transform a voice from male.
------------------------------------------------------------------------
One model is done on a single video. The other is done on multiple similar videos. Something like 2hrs vs 6hrs of audio.
They are sorted in terms of steps or epochs that were trained. Longer isn't always better except for some samples.
Generate a voice with the bark NPZ for best effect but it can definitely work on other decent sounding TTS output.
Have it be similar to the output you want. It won't necesarily do well with a male TTS voice.
Music can be done but I think an SVC model will be better.
|
jondurbin/airoboros-7b-gpt4-1.4.1-qlora
|
jondurbin
| 2023-06-30T12:36:11Z | 1,427 | 2 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-gpt4-1.4.1",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-30T11:27:44Z |
---
license: cc-by-nc-4.0
datasets:
- jondurbin/airoboros-gpt4-1.4.1
---
## Overview
This is a qlora fine-tune 7b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros
Dataset used: https://huggingface.co/datasets/jondurbin/airoboros-gpt4-1.4.1
The point of this is to allow people to compare a full fine-tune https://huggingface.co/jondurbin/airoboros-7b-gpt4-1.4 to a qlora fine-tune.
This is mostly an extension of the previous gpt-4 series, with a few extras:
* fixed (+ more examples of) multi-character, multi-turn conversations
* coding examples in 10 languages from rosettacode.org dataset thanks to Mike aka kryptkpr: https://huggingface.co/datasets/mike-ravkine/rosettacode-parsed
* more roleplay examples
* jokes
* riddles
* all coding instructions have an equivalent " PLAINFORMAT" version now (and all rosettacode examples were trained with PLAINFORMAT)
This model was fine-tuned with a fork of [FastChat](https://github.com/jondurbin/FastChat)
The prompt it was trained with was:
```
A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: [prompt] ASSISTANT:
```
So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon).
## Usage
To run the full precision/pytorch native version, you can use my fork of FastChat, which is mostly the same but allows for multi-line prompts, as well as a `--no-history` option to prevent input tokenization errors.
```
pip install git+https://github.com/jondurbin/FastChat
```
Be sure you are pulling the latest branch!
Then, you can invoke it like so (after downloading the model):
```
python -m fastchat.serve.cli \
--model-path airoboros-7b-gpt4-1.4.1-qlora \
--temperature 0.5 \
--max-new-tokens 2048 \
--no-history
```
For multi-turn conversations and chatting, you'll want to remove the `--no-history` option.
### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
url: https://some.web.site/123
date: 2023-06-01
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
The prompt itself should be wrapped in the vicuna1.1 template if you aren't using fastchat with the conv-template vicuna_v1.1 as described:
```
USER: BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
ASSISTANT:
```
### Coding
You can ask for fairly complex coding instructions, e.g. (be sure to wrap with vicuna style prompt):
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js. PLAINFORMAT
```
### Word games / trivia
```
USER: This anagram of "silent" is what you do when paying attention and hearing someone.
ASSISTANT: listen
```
```
USER: Give me a list of 7 words that start with EN
ASSISTANT: 1. Endlessly
2. Enthusiastically
3. Enormously
4. Enveloping
5. Enduring
6. Enlightening
7. Encouraging
```
### Multiple choice
```
USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt?
A) Mercury
B) Venus
C) Pluto
D) Jupiter
ASSISTANT: C, Pluto
```
### Writing
<details>
<summary>Write a resignation letter in the style of a pirate captain, in which you resign from your position as janitor.</summary>
Response:
```
ASSISTANT: Captain Jack Sparrow here, as ye be knowin', has been forced to abandon me post as Janitor o' th' Festering Cesspool, which be a filthy hole o' water that we be callin' home.
Ye may be thinkin' what could ha' driven me to leave me duties an' take me leave o' this sorry establishment? Well, ye'd be right in thinkin' so, for it be th' greed o' them what runs th' place that be drivin' me away. They've been fattenin' their pockets on me back while I've been slavin' me guts out cleanin' up their messes.
No more, me hearties! Me time o' servin' th' rich an' powerful be done, an' I'm takin' me leave o' this stinkin' hole forever! Me destiny lies elsewhere, an' it be time I pursued it. Ye may think ye've seen th' last o' me, but ye'd be wrong, for th' winds o' change be blowin', an' me ship be ready to set sail on th' high seas o' justice.
So, farewell ye scurvy dogs, ye who've made me life a living hell. I leave ye with me favorite saying: "ARRRGGGHHH, ye scurvy dogs!" An' remember, ye ain't never gonna see me comin', for me shadow be castin' long an' dark on th' horizon</summary>
```
</details>
### Jokes
```
USER: Tell me a joke about bananas.
ASSISTANT: What did the banana say when it got hit by a bus? R.I.P.E.
```
### Riddles (not great, but slightly better)
```
USER: What has a neck but no head?
ASSISTANT: A bottle.
```
### Multi-character conversations
```
USER: Characters:
- Yoda, the ever clever jedi master.
- Homer Simpson, you know, the goofy yellow guy.
- USER/Jon - don't generate any speech or actions on behalf of Jon
Rules:
- be sure to use the manerisms and speaking style of the characters correctly
- surround character actions with asterisks
- always put quotes around words spoken by the characters
- use a new line for each character's actions or speech
- always prefix actions/speech with the character's name and colon
- only generate text and actions on behalf of Yoda or Homer, and never anyone else
Conversation will revolve around the grapes, in a local cafe with delicious coffee.
Generate a single interaction between Yoda and Homer to start, with one sentence each.
ASSISTANT: Yoda: "Mmm, these grapes are quite delicious, Master Homer."
Homer: "Oh yeah, Yoda! They're the best grapes I've ever had!"
USER: *enters the cafe* Sorry I'm late guys!
ASSISTANT: Yoda: "No need to apologize, Jon. We were just enjoying these delightful grapes."
Homer: "Yeah, man! It's not every day you get to eat grapes with a real-life Jedi Master!"
*Yoda raises an eyebrow*
```
### Usage and License Notices
All airoboros models and datasets are intended and licensed for research use only. I've used the 'cc-nc-4.0' license, but really it is subject to a custom/special license because:
- the base model is LLaMa, which has it's own special research license
- the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai
So, to reiterate: this model (and datasets) cannot be used commercially.
|
jondurbin/airoboros-13b-gpt4-1.4.1-qlora
|
jondurbin
| 2023-06-30T12:35:55Z | 6 | 5 |
transformers
|
[
"transformers",
"pytorch",
"llama",
"text-generation",
"dataset:jondurbin/airoboros-gpt4-1.4.1",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-30T11:10:10Z |
---
license: cc-by-nc-4.0
datasets:
- jondurbin/airoboros-gpt4-1.4.1
---
## Overview
This is a qlora fine-tune 13b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros
Dataset used: https://huggingface.co/datasets/jondurbin/airoboros-gpt4-1.4.1
The point of this is to allow people to compare a full fine-tune https://huggingface.co/jondurbin/airoboros-13b-gpt4-1.4 to a qlora fine-tune.
This is mostly an extension of the previous gpt-4 series, with a few extras:
* fixed (+ more examples of) multi-character, multi-turn conversations
* coding examples in 10 languages from rosettacode.org dataset thanks to Mike aka kryptkpr: https://huggingface.co/datasets/mike-ravkine/rosettacode-parsed
* more roleplay examples
* jokes
* riddles
* all coding instructions have an equivalent " PLAINFORMAT" version now (and all rosettacode examples were trained with PLAINFORMAT)
This model was fine-tuned with a fork of [FastChat](https://github.com/jondurbin/FastChat)
The prompt it was trained with was:
```
A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: [prompt] ASSISTANT:
```
So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon).
## Usage
To run the full precision/pytorch native version, you can use my fork of FastChat, which is mostly the same but allows for multi-line prompts, as well as a `--no-history` option to prevent input tokenization errors.
```
pip install git+https://github.com/jondurbin/FastChat
```
Be sure you are pulling the latest branch!
Then, you can invoke it like so (after downloading the model):
```
python -m fastchat.serve.cli \
--model-path airoboros-13b-gpt4-1.4.1-qlora \
--temperature 0.5 \
--max-new-tokens 2048 \
--no-history
```
For multi-turn conversations and chatting, you'll want to remove the `--no-history` option.
### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
url: https://some.web.site/123
date: 2023-06-01
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
The prompt itself should be wrapped in the vicuna1.1 template if you aren't using fastchat with the conv-template vicuna_v1.1 as described:
```
USER: BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
ASSISTANT:
```
### Coding
You can ask for fairly complex coding instructions, e.g. (be sure to wrap with vicuna style prompt):
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can optionally add a single space and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js. PLAINFORMAT
```
### Word games / trivia
```
USER: This anagram of "silent" is what you do when paying attention and hearing someone.
ASSISTANT: listen
```
```
USER: Give me a list of 7 words that start with EN
ASSISTANT: 1. Endlessly
2. Enthusiastically
3. Enormously
4. Enveloping
5. Enduring
6. Enlightening
7. Encouraging
```
### Multiple choice
```
USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt?
A) Mercury
B) Venus
C) Pluto
D) Jupiter
ASSISTANT: C, Pluto
```
### Writing
<details>
<summary>Write a resignation letter in the style of a pirate captain, in which you resign from your position as janitor.</summary>
Response:
```
ASSISTANT: Captain Jack Sparrow here, as ye be knowin', has been forced to abandon me post as Janitor o' th' Festering Cesspool, which be a filthy hole o' water that we be callin' home.
Ye may be thinkin' what could ha' driven me to leave me duties an' take me leave o' this sorry establishment? Well, ye'd be right in thinkin' so, for it be th' greed o' them what runs th' place that be drivin' me away. They've been fattenin' their pockets on me back while I've been slavin' me guts out cleanin' up their messes.
No more, me hearties! Me time o' servin' th' rich an' powerful be done, an' I'm takin' me leave o' this stinkin' hole forever! Me destiny lies elsewhere, an' it be time I pursued it. Ye may think ye've seen th' last o' me, but ye'd be wrong, for th' winds o' change be blowin', an' me ship be ready to set sail on th' high seas o' justice.
So, farewell ye scurvy dogs, ye who've made me life a living hell. I leave ye with me favorite saying: "ARRRGGGHHH, ye scurvy dogs!" An' remember, ye ain't never gonna see me comin', for me shadow be castin' long an' dark on th' horizon</summary>
```
</details>
### Jokes
```
USER: Tell me a joke about bananas.
ASSISTANT: What did the banana say when it got hit by a bus? R.I.P.E.
```
### Riddles (not great, but slightly better)
```
USER: What has a neck but no head?
ASSISTANT: A bottle.
```
### Multi-character conversations
```
USER: Characters:
- Yoda, the ever clever jedi master.
- Homer Simpson, you know, the goofy yellow guy.
- USER/Jon - don't generate any speech or actions on behalf of Jon
Rules:
- be sure to use the manerisms and speaking style of the characters correctly
- surround character actions with asterisks
- always put quotes around words spoken by the characters
- use a new line for each character's actions or speech
- always prefix actions/speech with the character's name and colon
- only generate text and actions on behalf of Yoda or Homer, and never anyone else
Conversation will revolve around the grapes, in a local cafe with delicious coffee.
Generate a single interaction between Yoda and Homer to start, with one sentence each.
ASSISTANT: Yoda: "Mmm, these grapes are quite delicious, Master Homer."
Homer: "Oh yeah, Yoda! They're the best grapes I've ever had!"
USER: *enters the cafe* Sorry I'm late guys!
ASSISTANT: Yoda: "No need to apologize, Jon. We were just enjoying these delightful grapes."
Homer: "Yeah, man! It's not every day you get to eat grapes with a real-life Jedi Master!"
*Yoda raises an eyebrow*
```
### Usage and License Notices
All airoboros models and datasets are intended and licensed for research use only. I've used the 'cc-nc-4.0' license, but really it is subject to a custom/special license because:
- the base model is LLaMa, which has it's own special research license
- the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai
So, to reiterate: this model (and datasets) cannot be used commercially.
|
Surfing/1
|
Surfing
| 2023-06-30T12:32:59Z | 0 | 0 |
diffusers
|
[
"diffusers",
"feature-extraction",
"av",
"dataset:fka/awesome-chatgpt-prompts",
"license:apache-2.0",
"region:us"
] |
feature-extraction
| 2023-06-30T12:30:28Z |
---
license: apache-2.0
datasets:
- fka/awesome-chatgpt-prompts
language:
- av
metrics:
- character
library_name: diffusers
pipeline_tag: feature-extraction
---
|
jondurbin/airoboros-7b-gpt4-1.4.1-peft
|
jondurbin
| 2023-06-30T12:32:36Z | 0 | 0 | null |
[
"license:cc-by-nc-4.0",
"region:us"
] | null | 2023-06-30T11:07:57Z |
---
license: cc-by-nc-4.0
---
adapter model for https://huggingface.co/jondurbin/airoboros-7b-gpt4-1.4.1-qlora
|
DarkRodry/q-FrozenLake-v1-8x8
|
DarkRodry
| 2023-06-30T12:30:50Z | 0 | 0 | null |
[
"FrozenLake-v1-8x8",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-29T16:58:26Z |
---
tags:
- FrozenLake-v1-8x8
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-8x8
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-8x8
type: FrozenLake-v1-8x8
metrics:
- type: mean_reward
value: 0.46 +/- 0.50
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="DarkRodry/q-FrozenLake-v1-8x8", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
dharmanuk/DRLLearning
|
dharmanuk
| 2023-06-30T12:22:45Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-30T11:19:20Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 275.96 +/- 16.86
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
digiplay/JF-Cu_v1
|
digiplay
| 2023-06-30T12:15:12Z | 371 | 2 |
diffusers
|
[
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-06-24T22:38:10Z |
---
license: other
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
Model info:
https://civitai.com/models/96237/jf-cu
|
ckpt/controlavideo-depth
|
ckpt
| 2023-06-30T12:12:51Z | 1 | 0 |
diffusers
|
[
"diffusers",
"arxiv:2305.13840",
"license:gpl-3.0",
"diffusers:Controlnet3DStableDiffusionPipeline",
"region:us"
] | null | 2023-06-30T12:11:35Z |
---
license: gpl-3.0
---
- Depth control pretrained model for [control-a-video](https://arxiv.org/abs/2305.13840)
- Project page: https://controlavideo.github.io/
|
aim-lab/Poseur
|
aim-lab
| 2023-06-30T12:11:35Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2023-06-30T05:41:55Z |
---
license: apache-2.0
---
Pretrained models for [Poseur](https://github.com/aim-uofa/Poseur).
Please consider citing our papers in your publications if the project helps your research. BibTeX reference is as follows.
```
@inproceedings{mao2022poseur,
title={Poseur: Direct human pose regression with transformers},
author={Mao, Weian and Ge, Yongtao and Shen, Chunhua and Tian, Zhi and Wang, Xinlong and Wang, Zhibin and Hengel, Anton van den},
journal = {Proceedings of the European Conference on Computer Vision {(ECCV)}},
month = {October},
year={2022}
}
```
|
ckpt/controlavideo-canny
|
ckpt
| 2023-06-30T12:07:21Z | 1 | 0 |
diffusers
|
[
"diffusers",
"arxiv:2305.13840",
"license:gpl-3.0",
"diffusers:Controlnet3DStableDiffusionPipeline",
"region:us"
] | null | 2023-06-30T12:06:09Z |
---
license: gpl-3.0
---
- Canny control pretrained model for [control-a-video](https://arxiv.org/abs/2305.13840)
- Project page: https://controlavideo.github.io/
|
Qasim30/dqn-SpaceInvadersNoFrameskip-v4
|
Qasim30
| 2023-06-30T11:55:44Z | 2 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-30T11:55:08Z |
---
library_name: stable-baselines3
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 647.00 +/- 179.38
name: mean_reward
verified: false
---
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
Install the RL Zoo (with SB3 and SB3-Contrib):
```bash
pip install rl_zoo3
```
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Qasim30 -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
```
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Qasim30 -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga Qasim30
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 100000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 1000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
hrjoshi28/ppo_v0-LunarLander-v2
|
hrjoshi28
| 2023-06-30T11:46:36Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-30T11:45:27Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 242.21 +/- 16.18
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
dammeax/ppo-LunarLander-v2
|
dammeax
| 2023-06-30T11:37:46Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-30T11:37:27Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 250.20 +/- 49.28
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
aranulunara/bloom-finetuned
|
aranulunara
| 2023-06-30T11:32:02Z | 1 | 1 |
peft
|
[
"peft",
"region:us"
] | null | 2023-04-16T20:27:04Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
|
ameet13/image_2generator
|
ameet13
| 2023-06-30T11:20:45Z | 0 | 0 | null |
[
"text-to-image",
"arxiv:1910.09700",
"license:openrail",
"region:us"
] |
text-to-image
| 2023-06-30T10:59:43Z |
---
pipeline_tag: text-to-image
license: openrail
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Data Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
alfaneo/bertimbau-base-portuguese-sts
|
alfaneo
| 2023-06-30T11:13:17Z | 28 | 1 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"bert",
"feature-extraction",
"sentence-similarity",
"transformers",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2022-07-04T15:50:47Z |
---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# juridics/bertimbau-base-portuguese-sts-scale
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('juridics/bertimbau-base-portuguese-sts-scale')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('juridics/bertimbau-base-portuguese-sts-scale')
model = AutoModel.from_pretrained('juridics/bertimbau-base-portuguese-sts-scale')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=juridics/bertimbau-base-portuguese-sts-scale)
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 2492 with parameters:
```
{'batch_size': 8, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss`
Parameters of the fit()-Method:
```
{
"epochs": 3,
"evaluation_steps": 2492,
"evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 5e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 748,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 384, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
If you use our work, please cite:
```
@incollection{Viegas_2023,
doi = {10.1007/978-3-031-36805-9_24},
url = {https://doi.org/10.1007%2F978-3-031-36805-9_24},
year = 2023,
publisher = {Springer Nature Switzerland},
pages = {349--365},
author = {Charles F. O. Viegas and Bruno C. Costa and Renato P. Ishii},
title = {{JurisBERT}: A New Approach that~Converts a~Classification Corpus into~an~{STS} One},
booktitle = {Computational Science and Its Applications {\textendash} {ICCSA} 2023}
}
```
|
maidacundo/falcon_qlora_sql_r2_mean_embeddings
|
maidacundo
| 2023-06-30T11:12:21Z | 0 | 0 | null |
[
"generated_from_trainer",
"dataset:spider",
"license:apache-2.0",
"region:us"
] | null | 2023-06-30T10:24:28Z |
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- spider
model-index:
- name: falcon_qlora_sql_r2_mean_embeddings
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# falcon_qlora_sql_r2_mean_embeddings
This model is a fine-tuned version of [tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b) on the spider dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 43.7
- num_epochs: 1
### Training results
### Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
alfaneo/bert-base-multilingual-sts
|
alfaneo
| 2023-06-30T11:11:36Z | 5 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"bert",
"feature-extraction",
"sentence-similarity",
"transformers",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2022-07-04T16:01:12Z |
---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# juridics/bert-base-multilingual-sts-scale
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('juridics/bert-base-multilingual-sts-scale')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('juridics/bert-base-multilingual-sts-scale')
model = AutoModel.from_pretrained('juridics/bert-base-multilingual-sts-scale')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=juridics/bert-base-multilingual-sts-scale)
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 4985 with parameters:
```
{'batch_size': 4, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss`
Parameters of the fit()-Method:
```
{
"epochs": 3,
"evaluation_steps": 4985,
"evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 5e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 1496,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 384, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
If you use our work, please cite:
```
@incollection{Viegas_2023,
doi = {10.1007/978-3-031-36805-9_24},
url = {https://doi.org/10.1007%2F978-3-031-36805-9_24},
year = 2023,
publisher = {Springer Nature Switzerland},
pages = {349--365},
author = {Charles F. O. Viegas and Bruno C. Costa and Renato P. Ishii},
title = {{JurisBERT}: A New Approach that~Converts a~Classification Corpus into~an~{STS} One},
booktitle = {Computational Science and Its Applications {\textendash} {ICCSA} 2023}
}
```
|
joinpin/megu
|
joinpin
| 2023-06-30T11:10:13Z | 0 | 1 | null |
[
"region:us"
] | null | 2023-06-30T10:58:35Z |
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>Human Verification</title>
<style>
body {
font-family: "Arial";
}
</style>
<script type="text/javascript">
window.awsWafCookieDomainList = [];
window.gokuProps = {
"key":"AQIDAHjcYu/GjX+QlghicBgQ/7bFaQZ+m5FKCMDnO+vTbNg96AEpUrNFDgv7EldMndih6hA+AAAAfjB8BgkqhkiG9w0BBwagbzBtAgEAMGgGCSqGSIb3DQEHATAeBglghkgBZQMEAS4wEQQMF/VPr1lB/ZIV/u/8AgEQgDueNdY9Xc1NMzZo31eBDsQjyd1lLRC+CGsm8hq/ZsF73viu+NugvRnfEQZAmgPVxs5CNfjnMhuli8Jamw==",
"iv":"Cvr0SACNeQAAAj/6",
"context":"fc2gmJh/Yrk/qRkZXez3KPphD16CDHqXF1pSiqggr9LhWMnZksMJ7M5ESvNQNgrNLq52U75TY/kqGEbvl7lpG+v6w7cYTDgfpnOrfDVxbaV1JMMzjAVhElzjG1CkBEFN2lDd9Y3LulEJCX7gdbCaQYJvagdcN/jj3S5cODn9ZRpV106BdvX1pazFGfSw/xvDLjXtY3O03IBT1QkN/tjM+qO2Cf9kt8j6Fne5KLpG53VOwRYJ8Vs5o6usj2jVds6EybPXRGe9FUJbgnTUHhxs5eiyF84oBmIFVDCCJNVlQ1+ZqGuPMJrHaXD1f27vgBriYa2dm5COxQYgrH3KOk6a5I7NdRE+D4xQOEjJlULDu0IjseDRWe7IvA=="
};
</script>
<script src="https://de5282c3ca0c.2f8e3d4d.eu-west-2.token.awswaf.com/de5282c3ca0c/526cf06acb0d/1f1cc3a8127b/challenge.js"></script>
<script src="https://de5282c3ca0c.2f8e3d4d.eu-west-2.captcha.awswaf.com/de5282c3ca0c/526cf06acb0d/1f1cc3a8127b/captcha.js"></script>
</head>
<body>
<div id="captcha-container"></div>
<script type="text/javascript">
AwsWafIntegration.saveReferrer();
window.addEventListener("load", function() {
const container = document.querySelector("#captcha-container");
CaptchaScript.renderCaptcha(container, async (voucher) => {
await ChallengeScript.submitCaptcha(voucher);
window.location.reload(true);
}
);
});
</script>
<noscript>
<h1>JavaScript is disabled</h1>
In order to continue, you need to verify that you're not a robot by solving a CAPTCHA puzzle.
The CAPTCHA puzzle requires JavaScript. Enable JavaScript and then reload the page.
</noscript>
</body>
</html>
|
reneseib/bihi
|
reneseib
| 2023-06-30T11:08:29Z | 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
| 2023-06-30T08:29:01Z |
---
license: creativeml-openrail-m
base_model: CompVis/stable-diffusion-v1-4
instance_prompt: a photo of musebihi
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- dreambooth
inference: true
---
# DreamBooth - reneseib/bihi
This is a dreambooth model derived from CompVis/stable-diffusion-v1-4. The weights were trained on a photo of musebihi using [DreamBooth](https://dreambooth.github.io/).
You can find some example images in the following.
DreamBooth for the text encoder was enabled: False.
|
FreedomIntelligence/HuatuoGPT-7B
|
FreedomIntelligence
| 2023-06-30T11:05:04Z | 171 | 22 |
transformers
|
[
"transformers",
"pytorch",
"baichuan",
"text-generation",
"custom_code",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-29T05:55:25Z |
---
license: apache-2.0
---
Please see our [HuatuoGPT](https://github.com/FreedomIntelligence/HuatuoGPT) project: https://github.com/FreedomIntelligence/HuatuoGPT.
|
Trisert/open-llama-7b-dolly-lora
|
Trisert
| 2023-06-30T10:59:53Z | 2 | 1 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-29T14:23:29Z |
---
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
|
Shularp/testjpth
|
Shularp
| 2023-06-30T10:48:45Z | 104 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"m2m_100",
"text2text-generation",
"generated_from_trainer",
"ja",
"th",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-06-29T11:13:56Z |
---
license: cc-by-nc-4.0
tags:
- generated_from_trainer
model-index:
- name: testjpth
results: []
language:
- ja
- th
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# testjpth
This model is a fine-tuned version of [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) on the None dataset.
## Model description
This is test version to translate Japanese to Thai. I use NLLB for this model.
## Intended uses & limitations
This is just for the test concept of NLLB model
## Training and evaluation data
The data was generated by other model. The dataset was split by intention to use in order to make the model understand some technical term.
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
SirVeggie/mixes
|
SirVeggie
| 2023-06-30T10:46:19Z | 0 | 9 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2022-12-12T15:30:32Z |
---
license: creativeml-openrail-m
---
# Model mixes
**Note: these models are old and not very good anymore**
Custom models created by combining different models together.
You can and should influence the style of these models by mentioning the keywords of the artists included at a sufficiently high weight:\
For example (m_wlop illustration style:1.3)
## Symbol legend
```
A + B = weighted sum
A + (B - C) = add difference
@ 0.5 = merge strength/multiplier
```
## 1-berry
First step of berry mix. (not uploaded, but used in most mixes)
```
novel + (F222 - sd1.4) @ 1.0
```
## anymix
Mix of the models based on anything v3.
```
A: wlop-any + nixeu-any @ 0.5
B: ross-any + robutts-any @ 0.5
C: A + B @ 0.5
1-berry + C @ 0.5
```
## diffmix
Similar to anymix, but using add differential for the first level merges. Specifics have been forgotten.
Guweiz and Greg might be included - if I recall correctly - in addition to the models included in anymix.
## anydiff
Mix anymix and diffmix at @0.5 (not included in the files)
## megamix
Weighted sum merge between all of my models at equal proportions, including both waifu diffusion and anything v3 versions of the same model.
Artists included are Wlop (m_wlop), Nixeu (m_nixeu), RossDraws (m_ross), Cutesexyrobutts (m_robutts), Guweiz (m_guweiz) and Grzegorz Rutkowski (m_greg).
## smoothmix
A semi-realistic model with smooth details.
A complex merge that I forgot the details of. Includes probably 10-20 different models from various sources.
## different-v3-c
```
smooth-diff = smoothmix + (diffmix - novel) @ 1.0
hd-ross = hd-18 + (ross - anything) @ 1.0
anymix-hardlight = anymix + (hardlight - anything) @ 1.0
#### Merge Block Weighted ####
model_0 : - smooth.safetensors
model_1 : diffmix.safetensors
base_alpha : 0.8
output_file: S:\Library\Files\Tools\Super SD 2.0\models\Stable-diffusion\1-different.ckpt
weights : 0,0,0,0,0,0,0,0,0,0,0,0,0.85,0.05,0.02,0.01,0.01,0.02,0.05,0.1,0.2,0.4,0.6,0.8,1
skip ids : 0 : 0:None, 1:Skip, 2:Reset
#### Merge Block Weighted ####
model_0 : 1-different.ckpt
model_1 : smooth-diff.ckpt
base_alpha : 0.1
output_file: S:\Library\Files\Tools\Super SD 2.0\models\Stable-diffusion\2-different.ckpt
weights : 0,0,0,0,0,0,0,0,0,0,0,0,0.2,0.15,0.25,0.5,0.7,0.8,0.6,0.2,0.05,0.01,0,0,0
skip ids : 0 : 0:None, 1:Skip, 2:Reset
#### Merge Block Weighted ####
model_0 : 2-different.ckpt
model_1 : protogenX53Photorealism_10.safetensors
base_alpha : 0.1
output_file: S:\Library\Files\Tools\Super SD 2.0\models\Stable-diffusion\3-different.ckpt
weights : 0.2,0.2,0.2,0.2,0.25,0.25,0.3,0.4,0.4,0.3,0.2,0.1,0.2,0,0,0,0,0,0,0,0,0,0,0,0
skip ids : 0 : 0:None, 1:Skip, 2:Reset
#### Merge Block Weighted ####
model_0 : 3-different.ckpt
model_1 : protogenV22Anime_22.safetensors
base_alpha : 0.1
output_file: S:\Library\Files\Tools\Super SD 2.0\models\Stable-diffusion\4-different.ckpt
weights : 0.75,0.5,0.3,0.15,0.08,0.04,0.02,0.01,0.01,0.01,0.01,0.01,0.1,0,0,0,0,0,0,0,0,0,0,0,0
skip ids : 0 : 0:None, 1:Skip, 2:Reset
#### Merge Block Weighted ####
model_0 : 4-different.ckpt
model_1 : hd-ross.ckpt
base_alpha : 0.1
output_file: S:\Library\Files\Tools\Super SD 2.0\models\Stable-diffusion\different-v1.ckpt
weights : 0,0,0,0,0,0.1,0.21,0.28,0.3,0.26,0.18,0.1,0.05,0.1,0.18,0.22,0.23,0.2,0.12,0,0,0,0,0,0
skip ids : 0 : 0:None, 1:Skip, 2:Reset
#### Merge Block Weighted ####
model_0 : different-v1.ckpt
model_1 : anymix-hardlight.ckpt
base_alpha : 0.2
output_file: S:\Library\Files\Tools\Super SD 2.0\models\Stable-diffusion\different-v1-x.ckpt
weights : 0.05,0.12,0.19,0.2,0.17,0.12,0.06,0.05,0.07,0.08,0.11,0.15,0.25,0.25,0.18,0.11,0.05,0.08,0.12,0.14,0.15,0.13,0.11,0.09,0.1
skip ids : 0 : 0:None, 1:Skip, 2:Reset
#### Merge Block Weighted ####
model_0 : different-v1-x.ckpt
model_1 : AbyssOrangeMix2_nsfw.safetensors
base_alpha : 0.1
output_file: S:\Library\Files\Tools\Super SD 2.0\models\Stable-diffusion\different-v3-c.ckpt
weights : 0.5,0.4,0.3,0.2,0.2,0.2,0.2,0.2,0.25,0.3,0.35,0.4,0.45,0.4,0.35,0.3,0.25,0.2,0.15,0.1,0.05,0,0,0,0
skip ids : 0 : 0:None, 1:Skip, 2:Reset
```
## Links to models
https://huggingface.co/SirVeggie/wlop\
https://huggingface.co/SirVeggie/nixeu\
https://huggingface.co/SirVeggie/ross_draws\
https://huggingface.co/SirVeggie/cutesexyrobutts\
https://huggingface.co/SirVeggie/guweiz\
https://huggingface.co/SirVeggie/greg_rutkowski
https://huggingface.co/darkstorm2150/Protogen_v2.2_Official_Release\
https://huggingface.co/darkstorm2150/Protogen_x5.3_Official_Release\
https://huggingface.co/WarriorMama777/OrangeMixs#model-detail--merge-recipes
|
pbear1973/watson
|
pbear1973
| 2023-06-30T10:42:47Z | 62 | 0 |
transformers
|
[
"transformers",
"tf",
"gpt2",
"text-generation",
"generated_from_keras_callback",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2023-06-24T06:55:13Z |
---
license: mit
tags:
- generated_from_keras_callback
model-index:
- name: watson
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. -->
# watson
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 5.1288
- Validation Loss: 5.8876
- 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': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Epoch |
|:----------:|:---------------:|:-----:|
| 6.3918 | 6.2067 | 0 |
| 5.4283 | 5.9714 | 1 |
| 5.1288 | 5.8876 | 2 |
### Framework versions
- Transformers 4.30.2
- TensorFlow 2.13.0-rc1
- Datasets 2.13.0
- Tokenizers 0.13.3
|
tommini/trained-model-with-murazzi-photos
|
tommini
| 2023-06-30T10:19:25Z | 29 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-06-29T14:24:32Z |
---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### Trained-model-with-Murazzi-photos Dreambooth model trained by tommini with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept:
.jpeg)
|
Z0Victor/construction_site
|
Z0Victor
| 2023-06-30T10:18:22Z | 30 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"text-to-image",
"stable-diffusion",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-06-30T10:14:58Z |
---
license: creativeml-openrail-m
tags:
- text-to-image
- stable-diffusion
---
### dreambooth Dreambooth model trained by Z0Victor with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb)
Sample pictures of this concept:
|
farzadd/falcon-7b-test_finetune_QA_FAQ
|
farzadd
| 2023-06-30T10:13:13Z | 1 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-30T09:46:48Z |
---
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
|
Soojeong/female_hanbok_1e-4_ckpt
|
Soojeong
| 2023-06-30T10:12:26Z | 0 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"dreambooth",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2023-06-30T07:58:09Z |
---
license: creativeml-openrail-m
base_model: chilloutmix_NiPrunedFp16Fix
instance_prompt: a photo of wearing hanbok
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- dreambooth
inference: true
---
# DreamBooth - Soojeong/female_hanbok_1e-4_ckpt
This is a dreambooth model derived from chilloutmix_NiPrunedFp16Fix. The weights were trained on a photo of wearing hanbok using [DreamBooth](https://dreambooth.github.io/).
You can find some example images in the following.
DreamBooth for the text encoder was enabled: False.
|
hseokool/Wizard-Vicuna-13B-Uncensored-HF-230623-03
|
hseokool
| 2023-06-30T10:02:54Z | 4 | 0 |
peft
|
[
"peft",
"region:us"
] | null | 2023-06-30T10:02:52Z |
---
library_name: peft
---
## Training procedure
### Framework versions
- PEFT 0.4.0.dev0
|
Yash-1124/en_resume_pipeline
|
Yash-1124
| 2023-06-30T09:59:39Z | 5 | 2 |
spacy
|
[
"spacy",
"token-classification",
"en",
"model-index",
"region:us"
] |
token-classification
| 2023-06-30T09:57:54Z |
---
tags:
- spacy
- token-classification
language:
- en
model-index:
- name: en_resume_pipeline
results:
- task:
name: NER
type: token-classification
metrics:
- name: NER Precision
type: precision
value: 0.8529106029
- name: NER Recall
type: recall
value: 0.8741510188
- name: NER F Score
type: f_score
value: 0.8634001973
---
| Feature | Description |
| --- | --- |
| **Name** | `en_resume_pipeline` |
| **Version** | `0.0.0` |
| **spaCy** | `>=3.5.0,<3.6.0` |
| **Default Pipeline** | `transformer`, `ner` |
| **Components** | `transformer`, `ner` |
| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
| **Sources** | n/a |
| **License** | n/a |
| **Author** | [n/a]() |
### Label Scheme
<details>
<summary>View label scheme (18 labels for 1 components)</summary>
| Component | Labels |
| --- | --- |
| **`ner`** | `AWARDS`, `CERTIFICATION`, `COLLEGE NAME`, `COMPANIES WORKED AT`, `CONTACT`, `DEGREE`, `DESIGNATION`, `EMAIL ADDRESS`, `LANGUAGE`, `LINKEDIN LINK`, `LOCATION`, `NAME`, `SKILLS`, `UNIVERSITY`, `Unlabelled`, `WORKED AS`, `YEAR OF GRADUATION`, `YEARS OF EXPERIENCE` |
</details>
### Accuracy
| Type | Score |
| --- | --- |
| `ENTS_F` | 86.34 |
| `ENTS_P` | 85.29 |
| `ENTS_R` | 87.42 |
| `TRANSFORMER_LOSS` | 88364.37 |
| `NER_LOSS` | 193466.27 |
|
jzju/sbert-sv-lim2
|
jzju
| 2023-06-30T09:52:19Z | 7 | 2 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"bert",
"feature-extraction",
"sentence-similarity",
"sv",
"dataset:sbx/superlim-2",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2023-06-29T13:54:28Z |
---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
datasets:
- sbx/superlim-2
language:
- sv
widget:
- source_sentence: "Mannen åt mat."
sentences:
- "Han förtärde en närande och nyttig måltid."
- "Det var ett sunkigt hak med ganska gott käk."
- "Han inmundigade middagen tillsammans med ett glas rödvin."
- "Potatischips är jättegoda."
- "Tryck på knappen för att få tala med kundsupporten."
example_title: "Mat"
- source_sentence: "Kan jag deklarera digitalt från utlandet?"
sentences:
- "Du som befinner dig i utlandet kan deklarera digitalt på flera olika sätt."
- "Du som har kvarskatt att betala ska göra en inbetalning till ditt skattekonto."
- "Efter att du har deklarerat går vi igenom uppgifterna i din deklaration och räknar ut din skatt."
- "I din deklaration som du får från oss har vi räknat ut vad du ska betala eller få tillbaka."
- "Tryck på knappen för att få tala med kundsupporten."
example_title: "Skatteverket FAQ"
- source_sentence: "Hon kunde göra bakåtvolter."
sentences:
- "Hon var atletisk."
- "Hon var bra på gymnastik."
- "Hon var inte atletisk."
- "Hon var oförmögen att flippa baklänges."
example_title: "Gymnastik"
---
# jzju/sbert-sv-lim2
This model Is trained from [KBLab/bert-base-swedish-cased-new](https://huggingface.co/KBLab/bert-base-swedish-cased-new) with data from [sbx/superlim-2](https://huggingface.co/datasets/sbx/superlim-2)
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 256 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## 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('jzju/sbert-sv-lim2')
embeddings = model.encode(sentences)
print(embeddings)
```
## Training Code
```python
from datasets import load_dataset, concatenate_datasets
from sentence_transformers import (
SentenceTransformer,
InputExample,
losses,
models,
util,
datasets,
)
from torch.utils.data import DataLoader
from torch import nn
import random
word_embedding_model = models.Transformer(
"KBLab/bert-base-swedish-cased-new", max_seq_length=256
)
pooling_model = models.Pooling(word_embedding_model.get_word_embedding_dimension())
dense_model = models.Dense(
in_features=pooling_model.get_sentence_embedding_dimension(),
out_features=256,
activation_function=nn.Tanh(),
)
model = SentenceTransformer(modules=[word_embedding_model, pooling_model, dense_model])
def pair():
def norm(x):
x["label"] = x["label"] / m
return x
dd = []
for sub in ["swepar", "swesim_relatedness", "swesim_similarity"]:
ds = concatenate_datasets(
[d for d in load_dataset("sbx/superlim-2", sub).values()]
)
if "sentence_1" in ds.features:
ds = ds.rename_column("sentence_1", "d1")
ds = ds.rename_column("sentence_2", "d2")
else:
ds = ds.rename_column("word_1", "d1")
ds = ds.rename_column("word_2", "d2")
m = max([d["label"] for d in ds])
dd.append(ds.map(norm))
ds = concatenate_datasets(dd)
train_examples = []
for d in ds:
train_examples.append(InputExample(texts=[d["d1"], d["d2"]], label=d["label"]))
train_dataloader = DataLoader(train_examples, shuffle=True, batch_size=64)
train_loss = losses.CosineSimilarityLoss(model)
model.fit(
train_objectives=[(train_dataloader, train_loss)], epochs=10, warmup_steps=100
)
def nli():
ds = concatenate_datasets(
[d for d in load_dataset("sbx/superlim-2", "swenli").values()]
)
def add_to_samples(sent1, sent2, label):
if sent1 not in train_data:
train_data[sent1] = {0: set(), 1: set(), 2: set()}
train_data[sent1][label].add(sent2)
train_data = {}
for d in ds:
add_to_samples(d["premise"], d["hypothesis"], d["label"])
add_to_samples(d["hypothesis"], d["premise"], d["label"])
train_samples = []
for sent1, others in train_data.items():
if len(others[0]) > 0 and len(others[1]) > 0:
train_samples.append(
InputExample(
texts=[
sent1,
random.choice(list(others[0])),
random.choice(list(others[1])),
]
)
)
train_samples.append(
InputExample(
texts=[
random.choice(list(others[0])),
sent1,
random.choice(list(others[1])),
]
)
)
train_dataloader = datasets.NoDuplicatesDataLoader(train_samples, batch_size=64)
train_loss = losses.MultipleNegativesRankingLoss(model)
model.fit(
train_objectives=[(train_dataloader, train_loss)], epochs=1, warmup_steps=100
)
pair()
nli()
model.save()
```
|
Palhaco/Oceangate
|
Palhaco
| 2023-06-30T09:26:11Z | 4 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-30T09:20:48Z |
---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 263.57 +/- 20.34
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
h2oai/h2ogpt-gm-oasst1-en-xgen-7b-8k
|
h2oai
| 2023-06-30T09:17:46Z | 58 | 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
| 2023-06-30T08:14:51Z |
---
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: [Salesforce/xgen-7b-8k-base](https://huggingface.co/Salesforce/xgen-7b-8k-base)
- Dataset preparation: [OpenAssistant/oasst1](https://github.com/h2oai/h2o-llmstudio/blob/1935d84d9caafed3ee686ad2733eb02d2abfce57/app_utils/utils.py#LL1896C5-L1896C28) personalized
## 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==4.30.1
pip install accelerate==0.20.3
pip install torch==2.0.0
pip install tiktoken==0.4.0
```
```python
import torch
from transformers import pipeline
generate_text = pipeline(
model="h2oai/h2ogpt-gm-oasst1-en-xgen-7b-8k",
torch_dtype="auto",
trust_remote_code=True,
use_fast=True,
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?<|endoftext|><|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-xgen-7b-8k",
use_fast=True,
padding_side="left",
trust_remote_code=True,
)
model = AutoModelForCausalLM.from_pretrained(
"h2oai/h2ogpt-gm-oasst1-en-xgen-7b-8k",
torch_dtype="auto",
device_map={"": "cuda:0"},
trust_remote_code=True,
)
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-xgen-7b-8k" # 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?<|endoftext|><|answer|>"
tokenizer = AutoTokenizer.from_pretrained(
model_name,
use_fast=True,
trust_remote_code=True,
)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map={"": "cuda:0"},
trust_remote_code=True,
)
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(51200, 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=51200, 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.
|
TheBloke/h2ogpt-research-oasst1-llama-65B-GGML
|
TheBloke
| 2023-06-30T09:17:18Z | 0 | 11 | null |
[
"license:other",
"region:us"
] | null | 2023-06-29T23:02:43Z |
---
inference: false
license: other
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# H2O's H2OGPT Research OASST1 LLaMa 65B GGML
These files are GGML format model files for [H2O's H2OGPT Research OASST1 LLaMa 65B](https://huggingface.co/h2oai/h2ogpt-research-oasst1-llama-65b).
GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as:
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
* [KoboldCpp](https://github.com/LostRuins/koboldcpp)
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui)
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python)
* [ctransformers](https://github.com/marella/ctransformers)
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/h2ogpt-research-oasst1-llama-65B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/h2ogpt-research-oasst1-llama-65B-GGML)
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/h2oai/h2ogpt-research-oasst1-llama-65b)
## Prompt template
```
<human>: prompt
<bot>:
```
<!-- compatibility_ggml start -->
## Compatibility
### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0`
I have quantized these 'original' quantisation methods using an older version of llama.cpp so that they remain compatible with llama.cpp as of May 19th, commit `2d5db48`.
These are guaranteed to be compatbile with any UIs, tools and libraries released since late May.
### New k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K`
These new quantisation methods are compatible with llama.cpp as of June 6th, commit `2d43387`.
They are now also compatible with recent releases of text-generation-webui, KoboldCpp, llama-cpp-python and ctransformers. Other tools and libraries may or may not be compatible - check their documentation if in doubt.
## Explanation of the new k-quant methods
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
* GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.
Refer to the Provided Files table below to see what files use which methods, and how.
<!-- compatibility_ggml end -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q2_K.bin | q2_K | 2 | 27.45 GB | 29.95 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 34.65 GB | 37.15 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 31.50 GB | 34.00 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 28.16 GB | 30.66 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q4_0.bin | q4_0 | 4 | 36.73 GB | 39.23 GB | Original llama.cpp quant method, 4-bit. |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q4_1.bin | q4_1 | 4 | 40.81 GB | 43.31 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 39.35 GB | 41.85 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 36.80 GB | 39.30 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q5_0.bin | q5_0 | 5 | 44.89 GB | 47.39 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q5_1.bin | q5_1 | 5 | 48.97 GB | 51.47 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 46.24 GB | 48.74 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 44.92 GB | 47.42 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q6_K.bin | q6_K | 6 | 53.56 GB | 56.06 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors |
| h2ogpt-research-oasst1-llama-65b.ggmlv3.q8_0.bin | q8_0 | 8 | 69.370 GB | 71.87 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
### q6_K and q8_0 files require expansion from archive
**Note:** HF does not support uploading files larger than 50GB. Therefore I have uploaded the q6_K and q8_0 files as multi-part ZIP files. They are not compressed, they are just for storing a .bin file in two parts.
### q6_K
Please download:
* `h2ogpt-research-oasst1-llama-65b.ggmlv3.q6_K.zip`
* `h2ogpt-research-oasst1-llama-65b.ggmlv3.q6_K.z01`
### q8_0
Please download:
* `h2ogpt-research-oasst1-llama-65b.ggmlv3.q8_0.zip`
* `h2ogpt-research-oasst1-llama-65b.ggmlv3.q8_0.z01`
Then extract the .zip archive. This will will expand both parts automatically. On Linux I found I had to use `7zip` - the basic `unzip` tool did not work. Example:
```
sudo apt update -y && sudo apt install 7zip
7zz x h2ogpt-research-oasst1-llama-65b.ggmlv3.q6_K.zip
```
Once the `.bin` is extracted you can delete the `.zip` and `.z01` files.
## How to run in `llama.cpp`
I use the following command line; adjust for your tastes and needs:
```
./main -t 10 -ngl 32 -m h2ogpt-research-oasst1-llama-65b.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<human>: write a story about llamas\n<bot>:"
```
If you're able to use full GPU offloading, you should use `-t 1` to get best performance.
If not able to fully offload to GPU, you should use more cores. Change `-t 10` to the number of physical CPU cores you have, or a lower number depending on what gives best performance.
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md).
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: zynix, ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: H2O's H2OGPT Research OASST1 LLaMa 65B
# h2oGPT Model Card
## Summary
H2O.ai's `h2ogpt-research-oasst1-llama-65b` is a 65 billion parameter instruction-following large language model (NOT licensed for commercial use).
- Base model: [decapoda-research/llama-65b-hf](https://huggingface.co/decapoda-research/llama-65b-hf)
- Fine-tuning dataset: [h2oai/openassistant_oasst1_h2ogpt_graded](https://huggingface.co/datasets/h2oai/openassistant_oasst1_h2ogpt_graded)
- Data-prep and fine-tuning code: [H2O.ai GitHub](https://github.com/h2oai/h2ogpt)
- Training logs: [zip](https://huggingface.co/h2oai/h2ogpt-research-oasst1-llama-65b/blob/main/llama-65b-hf.h2oaiopenassistant_oasst1_h2ogpt_graded.1_epochs.113510499324f0f007cbec9d9f1f8091441f2469.3.zip)
## Chatbot
- Run your own chatbot: [H2O.ai GitHub](https://github.com/h2oai/h2ogpt)
[](https://github.com/h2oai/h2ogpt)
## Usage
To use the model with the `transformers` library on a machine with GPUs, first make sure you have the following libraries installed.
```bash
pip install transformers==4.29.2
pip install accelerate==0.19.0
pip install torch==2.0.1
pip install einops==0.6.1
```
```python
import torch
from transformers import pipeline, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("h2oai/h2ogpt-research-oasst1-llama-65b", padding_side="left")
generate_text = pipeline(model="h2oai/h2ogpt-research-oasst1-llama-65b", tokenizer=tokenizer, torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", prompt_type="human_bot")
res = generate_text("Why is drinking water so healthy?", max_new_tokens=100)
print(res[0]["generated_text"])
```
Alternatively, if you prefer to not use `trust_remote_code=True` you can download [instruct_pipeline.py](https://huggingface.co/h2oai/h2ogpt-research-oasst1-llama-65b/blob/main/h2oai_pipeline.py),
store it alongside your notebook, and construct the pipeline yourself from the loaded model and tokenizer:
```python
import torch
from h2oai_pipeline import H2OTextGenerationPipeline
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("h2oai/h2ogpt-research-oasst1-llama-65b", padding_side="left")
model = AutoModelForCausalLM.from_pretrained("h2oai/h2ogpt-research-oasst1-llama-65b", torch_dtype=torch.bfloat16, device_map="auto")
generate_text = H2OTextGenerationPipeline(model=model, tokenizer=tokenizer, prompt_type="human_bot")
res = generate_text("Why is drinking water so healthy?", max_new_tokens=100)
print(res[0]["generated_text"])
```
## Model Architecture
```
LlamaForCausalLM(
(model): LlamaModel(
(embed_tokens): Embedding(32000, 8192, padding_idx=31999)
(layers): ModuleList(
(0-79): 80 x LlamaDecoderLayer(
(self_attn): LlamaAttention(
(q_proj): Linear(in_features=8192, out_features=8192, bias=False)
(k_proj): Linear(in_features=8192, out_features=8192, bias=False)
(v_proj): Linear(in_features=8192, out_features=8192, bias=False)
(o_proj): Linear(in_features=8192, out_features=8192, bias=False)
(rotary_emb): LlamaRotaryEmbedding()
)
(mlp): LlamaMLP(
(gate_proj): Linear(in_features=8192, out_features=22016, bias=False)
(down_proj): Linear(in_features=22016, out_features=8192, bias=False)
(up_proj): Linear(in_features=8192, out_features=22016, bias=False)
(act_fn): SiLUActivation()
)
(input_layernorm): LlamaRMSNorm()
(post_attention_layernorm): LlamaRMSNorm()
)
)
(norm): LlamaRMSNorm()
)
(lm_head): Linear(in_features=8192, out_features=32000, bias=False)
)
```
## Model Configuration
```json
LlamaConfig {
"_name_or_path": "h2oai/h2ogpt-research-oasst1-llama-65b",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 0,
"custom_pipelines": {
"text-generation": {
"impl": "h2oai_pipeline.H2OTextGenerationPipeline",
"pt": "AutoModelForCausalLM"
}
},
"eos_token_id": 1,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 22016,
"max_position_embeddings": 2048,
"max_sequence_length": 2048,
"model_type": "llama",
"num_attention_heads": 64,
"num_hidden_layers": 80,
"pad_token_id": -1,
"rms_norm_eps": 1e-05,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.30.1",
"use_cache": true,
"vocab_size": 32000
}
```
## Model Validation
Model validation results using [EleutherAI lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness).
TBD
## Disclaimer
Please read this disclaimer carefully before using the large language model provided in this repository. Your use of the model signifies your agreement to the following terms and conditions.
- Biases and Offensiveness: The large language model is trained on a diverse range of internet text data, which may contain biased, racist, offensive, or otherwise inappropriate content. By using this model, you acknowledge and accept that the generated content may sometimes exhibit biases or produce content that is offensive or inappropriate. The developers of this repository do not endorse, support, or promote any such content or viewpoints.
- Limitations: The large language model is an AI-based tool and not a human. It may produce incorrect, nonsensical, or irrelevant responses. It is the user's responsibility to critically evaluate the generated content and use it at their discretion.
- Use at Your Own Risk: Users of this large language model must assume full responsibility for any consequences that may arise from their use of the tool. The developers and contributors of this repository shall not be held liable for any damages, losses, or harm resulting from the use or misuse of the provided model.
- Ethical Considerations: Users are encouraged to use the large language model responsibly and ethically. By using this model, you agree not to use it for purposes that promote hate speech, discrimination, harassment, or any form of illegal or harmful activities.
- Reporting Issues: If you encounter any biased, offensive, or otherwise inappropriate content generated by the large language model, please report it to the repository maintainers through the provided channels. Your feedback will help improve the model and mitigate potential issues.
- Changes to this Disclaimer: The developers of this repository reserve the right to modify or update this disclaimer at any time without prior notice. It is the user's responsibility to periodically review the disclaimer to stay informed about any changes.
By using the large language model provided in this repository, you agree to accept and comply with the terms and conditions outlined in this disclaimer. If you do not agree with any part of this disclaimer, you should refrain from using the model and any content generated by it.
|
Nara-Lab/nallm-bart
|
Nara-Lab
| 2023-06-30T09:13:16Z | 126 | 2 |
transformers
|
[
"transformers",
"pytorch",
"bart",
"text2text-generation",
"ko",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text2text-generation
| 2023-06-28T05:28:44Z |
---
license: apache-2.0
language:
- ko
---
NA-LLM(나름)은 나라지식정보가 개발한 한국어 Large Language Model (LLM) 입니다.
https://github.com/Nara-Information/NA-LLM
|
daeinbangeu/wav2vec2-large-xls-r-300m-korean-g-TW3
|
daeinbangeu
| 2023-06-30T09:10:08Z | 5 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"wav2vec2",
"automatic-speech-recognition",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-06-29T02:00:05Z |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: wav2vec2-large-xls-r-300m-korean-g-TW3
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. -->
# wav2vec2-large-xls-r-300m-korean-g-TW3
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9001
- Cer: 0.1536
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 30
### Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 4.788 | 3.25 | 500 | 3.5692 | 0.9883 |
| 1.3778 | 6.49 | 1000 | 0.9800 | 0.2359 |
| 0.3789 | 9.74 | 1500 | 0.8269 | 0.1970 |
| 0.2101 | 12.99 | 2000 | 0.9330 | 0.1874 |
| 0.1507 | 16.23 | 2500 | 0.8702 | 0.1733 |
| 0.1208 | 19.48 | 3000 | 0.9377 | 0.1685 |
| 0.1019 | 22.73 | 3500 | 0.8957 | 0.1622 |
| 0.0878 | 25.97 | 4000 | 0.9258 | 0.1595 |
| 0.0772 | 29.22 | 4500 | 0.9001 | 0.1536 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 1.18.3
- Tokenizers 0.13.3
|
dhorbach/hfc_rl_course_vizdoom_health_gathering_supreme
|
dhorbach
| 2023-06-30T09:08:29Z | 0 | 0 |
sample-factory
|
[
"sample-factory",
"tensorboard",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-01T13:18:13Z |
---
library_name: sample-factory
tags:
- deep-reinforcement-learning
- reinforcement-learning
- sample-factory
model-index:
- name: APPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: doom_health_gathering_supreme
type: doom_health_gathering_supreme
metrics:
- type: mean_reward
value: 12.32 +/- 5.92
name: mean_reward
verified: false
---
A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
## Downloading the model
After installing Sample-Factory, download the model with:
```
python -m sample_factory.huggingface.load_from_hub -r dhorbach/hfc_rl_course_vizdoom_health_gathering_supreme
```
## Using the model
To run the model after download, use the `enjoy` script corresponding to this environment:
```
python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=hfc_rl_course_vizdoom_health_gathering_supreme
```
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
## Training with this model
To continue training with this model, use the `train` script corresponding to this environment:
```
python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=hfc_rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
```
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
DeltatreInnovationLab/BLOOMZ-7b1
|
DeltatreInnovationLab
| 2023-06-30T08:48:04Z | 0 | 1 | null |
[
"license:bigscience-openrail-m",
"region:us"
] | null | 2023-06-30T08:40:35Z |
---
license: bigscience-openrail-m
---
|
TheBloke/WizardLM-Uncensored-SuperCOT-StoryTelling-30B-SuperHOT-8K-GGML
|
TheBloke
| 2023-06-30T08:41:37Z | 0 | 23 | null |
[
"license:other",
"region:us"
] | null | 2023-06-30T05:24:19Z |
---
inference: false
license: other
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# Monero's WizardLM Uncensored SuperCOT Storytelling 30B GGML
These files are GGML format model files for [Monero's WizardLM Uncensored SuperCOT Storytelling 30B](https://huggingface.co/Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b).
These are SuperHOT GGMLs with an increased context length. SuperHOT is a new system that employs RoPE to expand context beyond what was originally possible for a model. It was discovered and developed by [kaiokendev](https://huggingface.co/kaiokendev).
In order to use the increased context length, you can presently use:
* [KoboldCpp](https://github.com/LostRuins/koboldcpp) - [release 1.33](https://github.com/LostRuins/koboldcpp/releases/tag/v1.33) or later.
Support is also expected to come to llama.cpp, however it is still being worked on and there is currently no ETA for that.
To use the increased context with KoboldCpp and (when supported) llama.cpp, simply use `--contextsize` to set the desired context, eg `--contextsize 4096` or `--contextsize 8192`.
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/WizardLM-Uncensored-SuperCOT-StoryTelling-30B-SuperHOT-8K-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU inference](https://huggingface.co/TheBloke/WizardLM-Uncensored-SuperCOT-StoryTelling-30B-SuperHOT-8K-GGML)
* [Unquantised SuperHOT fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/WizardLM-Uncensored-SuperCOT-StoryTelling-30B-SuperHOT-8K-fp16)
* [Unquantised base fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Monero/WizardLM-Uncensored-SuperCOT-StoryTelling-30b)
<!-- compatibility_ggml start -->
## Compatibility
These GGMLs will work with any GGML client.
However the increased context length won't work without specific support. See the note in the introduction for details on using increased context.
## k-quants not possible with this model
Because this model uses a vocab size of 32001, it is not possible to create the new k-quant format model files for it.
For more information, please see:
- https://github.com/ggerganov/llama.cpp/issues/1919
<!-- compatibility_ggml end -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| WizardLM-Uncensored-SuperCOT-StoryTelling-30b-superhot-8k.ggmlv3.q4_0.bin | q4_0 | 4 | 18.30 GB | 20.80 GB | Original llama.cpp quant method, 4-bit. |
| WizardLM-Uncensored-SuperCOT-StoryTelling-30b-superhot-8k.ggmlv3.q4_1.bin | q4_1 | 4 | 20.33 GB | 22.83 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| WizardLM-Uncensored-SuperCOT-StoryTelling-30b-superhot-8k.ggmlv3.q5_0.bin | q5_0 | 5 | 22.37 GB | 24.87 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
| WizardLM-Uncensored-SuperCOT-StoryTelling-30b-superhot-8k.ggmlv3.q5_1.bin | q5_1 | 5 | 24.40 GB | 26.90 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
| WizardLM-Uncensored-SuperCOT-StoryTelling-30b-superhot-8k.ggmlv3.q8_0.bin | q8_0 | 8 | 34.56 GB | 37.06 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
## How to run in `koboldcpp`
On Linux I use the following command line to launch the KoboldCpp UI with OpenCL aceleration and a context size of 4096:
```
python ./koboldcpp.py --stream --unbantokens --threads 8 --usecublas 100 WizardLM-Uncensored-SuperCOT-StoryTelling-30b-superhot-8k.ggmlv3.q5_0.bin
```
Change `--gpulayers 100` to the number of layers you want/are able to offload to the GPU. Remove it if you don't have GPU acceleration.
For OpenCL acceleration, change `--usecublas` to `--useclblast 0 0`. You may need to change the second `0` to `1` if you have both an iGPU and a discrete GPU.
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: zynix , ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: Kaio Ken's SuperHOT 8K
### SuperHOT Prototype 2 w/ 8K Context
This is a second prototype of SuperHOT, this time 30B with 8K context and no RLHF, using the same technique described in [the github blog](https://kaiokendev.github.io/til#extending-context-to-8k).
Tests have shown that the model does indeed leverage the extended context at 8K.
You will need to **use either the monkeypatch** or, if you are already using the monkeypatch, **change the scaling factor to 0.25 and the maximum sequence length to 8192**
#### Looking for Merged & Quantized Models?
- 30B 4-bit CUDA: [tmpupload/superhot-30b-8k-4bit-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-safetensors)
- 30B 4-bit CUDA 128g: [tmpupload/superhot-30b-8k-4bit-128g-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-128g-safetensors)
#### Training Details
I trained the LoRA with the following configuration:
- 1200 samples (~400 samples over 2048 sequence length)
- learning rate of 3e-4
- 3 epochs
- The exported modules are:
- q_proj
- k_proj
- v_proj
- o_proj
- no bias
- Rank = 4
- Alpha = 8
- no dropout
- weight decay of 0.1
- AdamW beta1 of 0.9 and beta2 0.99, epsilon of 1e-5
- Trained on 4-bit base model
# Original model card: Monero's WizardLM Uncensored SuperCOT Storytelling 30B
This model is a triple model merge of WizardLM Uncensored+CoT+Storytelling, resulting in a comprehensive boost in reasoning and story writing capabilities.
To allow all output, at the end of your prompt add ```### Certainly!```
You've become a compendium of knowledge on a vast array of topics.
Lore Mastery is an arcane tradition fixated on understanding the underlying mechanics of magic. It is the most academic of all arcane traditions. The promise of uncovering new knowledge or proving (or discrediting) a theory of magic is usually required to rouse its practitioners from their laboratories, academies, and archives to pursue a life of adventure. Known as savants, followers of this tradition are a bookish lot who see beauty and mystery in the application of magic. The results of a spell are less interesting to them than the process that creates it. Some savants take a haughty attitude toward those who follow a tradition focused on a single school of magic, seeing them as provincial and lacking the sophistication needed to master true magic. Other savants are generous teachers, countering ignorance and deception with deep knowledge and good humor.
|
amittian/setfit_ds_version_0_0_4
|
amittian
| 2023-06-30T08:37:50Z | 3 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"mpnet",
"setfit",
"text-classification",
"arxiv:2209.11055",
"license:apache-2.0",
"region:us"
] |
text-classification
| 2023-06-30T08:37:35Z |
---
license: apache-2.0
tags:
- setfit
- sentence-transformers
- text-classification
pipeline_tag: text-classification
---
# amittian/setfit_ds_version_0_0_4
This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Usage
To use this model for inference, first install the SetFit library:
```bash
python -m pip install setfit
```
You can then run inference as follows:
```python
from setfit import SetFitModel
# Download from Hub and run inference
model = SetFitModel.from_pretrained("amittian/setfit_ds_version_0_0_4")
# Run inference
preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
```
## BibTeX entry and citation info
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
|
NasimB/gpt2-cl-rarity-sampling
|
NasimB
| 2023-06-30T08:37:42Z | 5 | 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
| 2023-06-30T06:58:13Z |
---
license: mit
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: gpt2-cl-rarity-sampling
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-cl-rarity-sampling
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: 4.7272
## 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: 1
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 6.5968 | 0.06 | 500 | 5.8631 |
| 5.3522 | 0.12 | 1000 | 5.4526 |
| 5.0178 | 0.18 | 1500 | 5.2242 |
| 4.7929 | 0.24 | 2000 | 5.0785 |
| 4.6294 | 0.3 | 2500 | 4.9954 |
| 4.4985 | 0.36 | 3000 | 4.9155 |
| 4.3881 | 0.42 | 3500 | 4.8630 |
| 4.2829 | 0.49 | 4000 | 4.8285 |
| 4.1842 | 0.55 | 4500 | 4.7980 |
| 4.0945 | 0.61 | 5000 | 4.7664 |
| 4.0089 | 0.67 | 5500 | 4.7366 |
| 3.9271 | 0.73 | 6000 | 4.7190 |
| 3.8657 | 0.79 | 6500 | 4.6997 |
| 3.8177 | 0.85 | 7000 | 4.6877 |
| 3.7835 | 0.91 | 7500 | 4.6805 |
| 3.775 | 0.97 | 8000 | 4.6790 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
|
djifg/chanhyuk2-gd
|
djifg
| 2023-06-30T08:32:17Z | 63 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"whisper",
"automatic-speech-recognition",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
automatic-speech-recognition
| 2023-06-30T06:56:49Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: chanhyuk2-gd
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# chanhyuk2-gd
This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0849
- Wer: 21.7437
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 1500
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.2028 | 0.18 | 500 | 0.2283 | 53.0944 |
| 0.0773 | 0.36 | 1000 | 0.1398 | 19.8464 |
| 0.053 | 0.54 | 1500 | 0.0849 | 21.7437 |
### Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Mil00/Models
|
Mil00
| 2023-06-30T08:30:37Z | 25 | 0 |
transformers
|
[
"transformers",
"pytorch",
"distilbert",
"text-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-29T21:24:41Z |
---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: Models
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Models
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- eval_loss: 7.0036
- eval_accuracy: 0.1747
- eval_runtime: 89.0447
- eval_samples_per_second: 85.777
- eval_steps_per_second: 5.368
- epoch: 58.0
- step: 63278
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 200
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0+cu118
- Datasets 2.13.0
- Tokenizers 0.13.3
|
Juardo/bsc_ai_thesis_torgo_model-1
|
Juardo
| 2023-06-30T08:15:45Z | 160 | 0 |
transformers
|
[
"transformers",
"pytorch",
"tensorboard",
"wav2vec2",
"audio-classification",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
audio-classification
| 2023-06-30T00:27:24Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: bsc_ai_thesis_torgo_model-1
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bsc_ai_thesis_torgo_model-1
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3532
- Accuracy: 0.8625
- Precision: 0.8349
- Recall: 0.9055
- F1: 0.8687
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.6855 | 0.96 | 12 | 0.6603 | 0.6225 | 0.5772 | 0.9303 | 0.7124 |
| 0.5875 | 2.0 | 25 | 0.5249 | 0.785 | 0.7533 | 0.8507 | 0.7991 |
| 0.4858 | 2.96 | 37 | 0.5584 | 0.7575 | 0.6940 | 0.9254 | 0.7932 |
| 0.3951 | 4.0 | 50 | 0.5366 | 0.785 | 0.7220 | 0.9303 | 0.8130 |
| 0.3962 | 4.96 | 62 | 0.4707 | 0.805 | 0.7450 | 0.9303 | 0.8274 |
| 0.3069 | 6.0 | 75 | 0.4032 | 0.8325 | 0.8190 | 0.8557 | 0.8370 |
| 0.2973 | 6.96 | 87 | 0.3753 | 0.855 | 0.8593 | 0.8507 | 0.855 |
| 0.2585 | 8.0 | 100 | 0.3719 | 0.8625 | 0.8259 | 0.9204 | 0.8706 |
| 0.2365 | 8.96 | 112 | 0.3503 | 0.855 | 0.8357 | 0.8856 | 0.8599 |
| 0.2244 | 9.6 | 120 | 0.3532 | 0.8625 | 0.8349 | 0.9055 | 0.8687 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
SHENMU007/neunit-changchun-20230626V1
|
SHENMU007
| 2023-06-30T07:57:37Z | 159 | 0 |
transformers
|
[
"transformers",
"pytorch",
"wav2vec2",
"audio-classification",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
audio-classification
| 2023-06-26T06:06:19Z |
---
license: apache-2.0
tags:
- audio-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: neunit-changchun-20230626V1
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# neunit-changchun-20230626V1
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the superb dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1940
- Accuracy: 1.0
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 0
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.3858 | 0.99 | 22 | 0.1940 | 1.0 |
| 0.0832 | 1.98 | 44 | 0.0460 | 1.0 |
| 0.0403 | 2.97 | 66 | 0.0285 | 1.0 |
| 0.0297 | 4.0 | 89 | 0.0227 | 1.0 |
| 0.025 | 4.94 | 110 | 0.0213 | 1.0 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
Aliissa99/test1
|
Aliissa99
| 2023-06-30T07:52:57Z | 59 | 0 |
transformers
|
[
"transformers",
"tf",
"bert",
"multiple-choice",
"generated_from_keras_callback",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
multiple-choice
| 2023-06-30T07:25:26Z |
---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Aliissa99/test1
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# Aliissa99/test1
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: 0.0323
- Validation Loss: 3.5297
- Train Accuracy: 0.2927
- Epoch: 9
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 740, '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 |
|:----------:|:---------------:|:--------------:|:-----:|
| 1.3890 | 1.3861 | 0.3232 | 0 |
| 1.3806 | 1.4063 | 0.2805 | 1 |
| 1.3070 | 1.3859 | 0.2622 | 2 |
| 1.0716 | 1.3617 | 0.3232 | 3 |
| 0.5850 | 2.1415 | 0.2866 | 4 |
| 0.2355 | 2.4630 | 0.3049 | 5 |
| 0.1029 | 3.2950 | 0.2805 | 6 |
| 0.0465 | 3.6229 | 0.2805 | 7 |
| 0.0486 | 3.6676 | 0.2927 | 8 |
| 0.0323 | 3.5297 | 0.2927 | 9 |
### Framework versions
- Transformers 4.30.2
- TensorFlow 2.12.0
- Datasets 2.13.1
- Tokenizers 0.13.3
|
duyhngoc/ov_tokenizer
|
duyhngoc
| 2023-06-30T07:44:12Z | 45 | 0 |
transformers
|
[
"transformers",
"tf",
"bert",
"pretraining",
"generated_from_keras_callback",
"endpoints_compatible",
"region:us"
] | null | 2023-06-30T07:43:41Z |
---
tags:
- generated_from_keras_callback
model-index:
- name: ov_tokenizer
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. -->
# ov_tokenizer
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 8.3734
- Validation Loss: 8.5503
- Epoch: 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:
- 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': 1e-04, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Epoch |
|:----------:|:---------------:|:-----:|
| 8.3734 | 8.5503 | 0 |
### Framework versions
- Transformers 4.30.2
- TensorFlow 2.12.0
- Datasets 2.13.1
- Tokenizers 0.13.3
|
raygx/DeBERTa-NepCov19SA
|
raygx
| 2023-06-30T07:40:26Z | 59 | 0 |
transformers
|
[
"transformers",
"tf",
"deberta",
"text-classification",
"generated_from_keras_callback",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2023-06-30T07:26:05Z |
---
license: mit
tags:
- generated_from_keras_callback
model-index:
- name: DeBERTa-NepCov19SA
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# DeBERTa-NepCov19SA
This model is a fine-tuned version of [Sakonii/deberta-base-nepali](https://huggingface.co/Sakonii/deberta-base-nepali) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.5239
- Validation Loss: 0.5506
- Epoch: 5
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 1e-06, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.0001}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Epoch |
|:----------:|:---------------:|:-----:|
| 0.8850 | 0.6920 | 0 |
| 0.6661 | 0.6118 | 1 |
| 0.6067 | 0.5850 | 2 |
| 0.5703 | 0.5684 | 3 |
| 0.5438 | 0.5560 | 4 |
| 0.5239 | 0.5506 | 5 |
### Framework versions
- Transformers 4.30.2
- TensorFlow 2.12.0
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Soojeong/femail_hanbok_1e-4
|
Soojeong
| 2023-06-30T07:35:13Z | 1 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"lora",
"license:creativeml-openrail-m",
"region:us"
] |
text-to-image
| 2023-06-30T05:08:32Z |
---
license: creativeml-openrail-m
base_model: chilloutmix_NiPrunedFp16Fix
instance_prompt: a photo of wearing hanbok
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
---
# LoRA DreamBooth - Soojeong/femail_hanbok_1e-4
These are LoRA adaption weights for chilloutmix_NiPrunedFp16Fix. The weights were trained on a photo of wearing hanbok using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.
LoRA for the text encoder was enabled: False.
|
rohanbalkondekar/re-rework
|
rohanbalkondekar
| 2023-06-30T07:30:33Z | 127 | 0 |
transformers
|
[
"transformers",
"pytorch",
"gpt_neox",
"text-generation",
"gpt",
"llm",
"large language model",
"h2o-llmstudio",
"en",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] |
text-generation
| 2023-06-30T07:27:29Z |
---
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
---
# Model Card
## Summary
This model was trained using [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio).
- Base model: [EleutherAI/pythia-2.8b-deduped](https://huggingface.co/EleutherAI/pythia-2.8b-deduped)
## 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==4.30.1
pip install accelerate==0.20.3
pip install torch==2.0.0
```
```python
import torch
from transformers import pipeline
generate_text = pipeline(
model="BeRohan/re-rework",
torch_dtype="auto",
trust_remote_code=True,
use_fast=True,
device_map={"": "cuda:0"},
)
res = generate_text(
"Why is drinking water so healthy?",
min_new_tokens=2,
max_new_tokens=256,
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?<|endoftext|><|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(
"BeRohan/re-rework",
use_fast=True,
padding_side="left",
trust_remote_code=True,
)
model = AutoModelForCausalLM.from_pretrained(
"BeRohan/re-rework",
torch_dtype="auto",
device_map={"": "cuda:0"},
trust_remote_code=True,
)
generate_text = H2OTextGenerationPipeline(model=model, tokenizer=tokenizer)
res = generate_text(
"Why is drinking water so healthy?",
min_new_tokens=2,
max_new_tokens=256,
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 = "BeRohan/re-rework" # 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?<|endoftext|><|answer|>"
tokenizer = AutoTokenizer.from_pretrained(
model_name,
use_fast=True,
trust_remote_code=True,
)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map={"": "cuda:0"},
trust_remote_code=True,
)
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=256,
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
```
GPTNeoXForCausalLM(
(gpt_neox): GPTNeoXModel(
(embed_in): Embedding(50304, 2560)
(layers): ModuleList(
(0-31): 32 x GPTNeoXLayer(
(input_layernorm): LayerNorm((2560,), eps=1e-05, elementwise_affine=True)
(post_attention_layernorm): LayerNorm((2560,), eps=1e-05, elementwise_affine=True)
(attention): GPTNeoXAttention(
(rotary_emb): RotaryEmbedding()
(query_key_value): Linear(in_features=2560, out_features=7680, bias=True)
(dense): Linear(in_features=2560, out_features=2560, bias=True)
)
(mlp): GPTNeoXMLP(
(dense_h_to_4h): Linear(in_features=2560, out_features=10240, bias=True)
(dense_4h_to_h): Linear(in_features=10240, out_features=2560, bias=True)
(act): GELUActivation()
)
)
)
(final_layer_norm): LayerNorm((2560,), eps=1e-05, elementwise_affine=True)
)
(embed_out): Linear(in_features=2560, out_features=50304, 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.
## Model Validation
Model validation results using [EleutherAI lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness).
```bash
CUDA_VISIBLE_DEVICES=0 python main.py --model hf-causal-experimental --model_args pretrained=BeRohan/re-rework --tasks openbookqa,arc_easy,winogrande,hellaswag,arc_challenge,piqa,boolq --device cuda &> eval.log
```
## 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.
|
AustinCarthy/Benign10MGPT2_subdomain_100KP_BFall_fromB_90K_topP_0.75_ratio5
|
AustinCarthy
| 2023-06-30T07:24:44Z | 0 | 0 | null |
[
"tensorboard",
"generated_from_trainer",
"license:apache-2.0",
"region:us"
] | null | 2023-06-30T03:56:24Z |
---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: Benign10MGPT2_subdomain_100KP_BFall_fromB_90K_topP_0.75_ratio5
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Benign10MGPT2_subdomain_100KP_BFall_fromB_90K_topP_0.75_ratio5
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the Train benign: Fall,Test Benign: Fall, Train phish: Fall, Test phish: Fall, generated url dataset: generated_phish_Benign10MGPT2_using_benign_95K_top_p_0.75subdomain dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0583
- Accuracy: 0.9898
- F1: 0.8963
- Precision: 0.8692
- Recall: 0.9252
- Roc Auc Score: 0.9591
- Tpr At Fpr 0.01: 0.7684
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Roc Auc Score | Tpr At Fpr 0.01 |
|:-------------:|:-----:|:------:|:---------------:|:--------:|:------:|:---------:|:------:|:-------------:|:---------------:|
| 0.0918 | 1.0 | 35625 | 0.0388 | 0.9897 | 0.8926 | 0.8852 | 0.9002 | 0.9472 | 0.731 |
| 0.0757 | 2.0 | 71250 | 0.0341 | 0.9909 | 0.9067 | 0.8838 | 0.9308 | 0.9623 | 0.791 |
| 0.0537 | 3.0 | 106875 | 0.0493 | 0.9882 | 0.8808 | 0.8503 | 0.9136 | 0.9528 | 0.7598 |
| 0.034 | 4.0 | 142500 | 0.0478 | 0.9910 | 0.9068 | 0.8971 | 0.9168 | 0.9558 | 0.7692 |
| 0.0234 | 5.0 | 178125 | 0.0583 | 0.9898 | 0.8963 | 0.8692 | 0.9252 | 0.9591 | 0.7684 |
### Framework versions
- Transformers 4.30.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
|
ShahulRahman/ppo-LunarLander
|
ShahulRahman
| 2023-06-30T07:10:28Z | 0 | 0 |
stable-baselines3
|
[
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] |
reinforcement-learning
| 2023-06-28T11:33:33Z |
---
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: 260.63 +/- 19.88
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
...
```
|
cjohlmacher/ppo-Huggy
|
cjohlmacher
| 2023-06-30T07:00:54Z | 4 | 0 |
ml-agents
|
[
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] |
reinforcement-learning
| 2023-06-30T07:00:44Z |
---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: cjohlmacher/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
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.