Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

https://github.com/bigscience-workshop/petals

๐ŸŒธ Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
https://github.com/bigscience-workshop/petals

bloom chatbot deep-learning distributed-systems falcon gpt guanaco language-models large-language-models llama llama2 machine-learning neural-networks nlp pipeline-parallelism pretrained-models pytorch tensor-parallelism transformer volunteer-computing

Last synced: about 1 month ago
JSON representation

๐ŸŒธ Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

Lists

README 

        


    


    Run large language models at home, BitTorrent-style.


    Fine-tuning and inference up to 10x faster than offloading

    



    

    

    





Generate text with distributed **Llama 2** (70B), **Falcon** (40B+), **BLOOM** (176B) (or their derivatives), and fineโ€‘tune them for your own tasks โ€” right from your desktop computer or Google Colab:



```python

from transformers import AutoTokenizer

from petals import AutoDistributedModelForCausalLM



# Choose any model available at https://health.petals.dev

model_name = "petals-team/StableBeluga2"  # This one is fine-tuned Llama 2 (70B)



# Connect to a distributed network hosting model layers

tokenizer = AutoTokenizer.from_pretrained(model_name)

model = AutoDistributedModelForCausalLM.from_pretrained(model_name)



# Run the model as if it were on your computer

inputs = tokenizer("A cat sat", return_tensors="pt")["input_ids"]

outputs = model.generate(inputs, max_new_tokens=5)

print(tokenizer.decode(outputs[0]))  # A cat sat on a mat...

```





    ๐Ÿš€ ย Try now in Colab




๐Ÿ” **Privacy.** Your data will be processed with the help of other people in the public swarm. Learn more about privacy [here](https://github.com/bigscience-workshop/petals/wiki/Security,-privacy,-and-AI-safety). For sensitive data, you can set up a [private swarm](https://github.com/bigscience-workshop/petals/wiki/Launch-your-own-swarm) among people you trust.



๐Ÿฆ™ **Want to run Llama 2?** Request access to its weights at the โ™พ๏ธ [Meta AI website](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) and ๐Ÿค— [Model Hub](https://huggingface.co/meta-llama/Llama-2-70b-hf), then run `huggingface-cli login` in the terminal before loading the model. Or just try it in our [chatbot app](https://chat.petals.dev).



๐Ÿ’ฌ **Any questions?** Ping us in [our Discord](https://discord.gg/KdThf2bWVU)!



## Connect your GPU and increase Petals capacity



Petals is a community-run system โ€” we rely on people sharing their GPUs. You can check out [available models](https://health.petals.dev) and help serving one of them! As an example, here is how to host a part of [Stable Beluga 2](https://huggingface.co/stabilityai/StableBeluga2) on your GPU:



๐Ÿง **Linux + Anaconda.** Run these commands for NVIDIA GPUs (or follow [this](https://github.com/bigscience-workshop/petals/wiki/Running-on-AMD-GPU) for AMD):



```bash

conda install pytorch pytorch-cuda=11.7 -c pytorch -c nvidia

pip install git+https://github.com/bigscience-workshop/petals

python -m petals.cli.run_server petals-team/StableBeluga2

```



๐ŸชŸ **Windows + WSL.** Follow [this guide](https://github.com/bigscience-workshop/petals/wiki/Run-Petals-server-on-Windows) on our Wiki.



๐Ÿ‹ **Docker.** Run our [Docker](https://www.docker.com) image for NVIDIA GPUs (or follow [this](https://github.com/bigscience-workshop/petals/wiki/Running-on-AMD-GPU) for AMD):



```bash

sudo docker run -p 31330:31330 --ipc host --gpus all --volume petals-cache:/cache --rm \

    learningathome/petals:main \

    python -m petals.cli.run_server --port 31330 petals-team/StableBeluga2

```



๐Ÿ **macOS + Apple M1/M2 GPU.** Install [Homebrew](https://brew.sh/), then run these commands:



```bash

brew install python

python3 -m pip install git+https://github.com/bigscience-workshop/petals

python3 -m petals.cli.run_server petals-team/StableBeluga2

```





    ๐Ÿ“š ย Learn more (how to use multiple GPUs, start the server on boot, etc.)




๐Ÿ’ฌ **Any questions?** Ping us in [our Discord](https://discord.gg/X7DgtxgMhc)!



๐Ÿฆ™ **Want to host Llama 2?** Request access to its weights at the โ™พ๏ธ [Meta AI website](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) and ๐Ÿค— [Model Hub](https://huggingface.co/meta-llama/Llama-2-70b-hf), generate an ๐Ÿ”‘ [access token](https://huggingface.co/settings/tokens), then add `--token YOUR_TOKEN_HERE` to the `python -m petals.cli.run_server` command.



๐Ÿ”’ **Security.** Hosting a server does not allow others to run custom code on your computer. Learn more [here](https://github.com/bigscience-workshop/petals/wiki/Security,-privacy,-and-AI-safety).



๐Ÿ† **Thank you!** Once you load and host 10+ blocks, we can show your name or link on the [swarm monitor](https://health.petals.dev) as a way to say thanks. You can specify them with `--public_name YOUR_NAME`.



## How does it work?



- You load a small part of the model, then join a [network](https://health.petals.dev) of people serving the other parts. Singleโ€‘batch inference runs at up to **6 tokens/sec** for **Llama 2** (70B) and up to **4 tokens/sec** for **Falcon** (180B) โ€” enough for [chatbots](https://chat.petals.dev) and interactive apps.

- You can employ any fine-tuning and sampling methods, execute custom paths through the model, or see its hidden states. You get the comforts of an API with the flexibility of **PyTorch** and **๐Ÿค— Transformers**.





    






    ๐Ÿ“œ ย Read paper

    ย ย ย ย ย ย ย ย ย ย 

    ๐Ÿ“š ย See FAQ




## ๐Ÿ“š Tutorials, examples, and more



Basic tutorials:



- Getting started: [tutorial](https://colab.research.google.com/drive/1uCphNY7gfAUkdDrTx21dZZwCOUDCMPw8?usp=sharing)

- Prompt-tune Llama-65B for text semantic classification: [tutorial](https://colab.research.google.com/github/bigscience-workshop/petals/blob/main/examples/prompt-tuning-sst2.ipynb)

- Prompt-tune BLOOM to create a personified chatbot: [tutorial](https://colab.research.google.com/github/bigscience-workshop/petals/blob/main/examples/prompt-tuning-personachat.ipynb)



Useful tools:



- [Chatbot web app](https://chat.petals.dev) (connects to Petals via an HTTP/WebSocket endpoint): [source code](https://github.com/petals-infra/chat.petals.dev)

- [Monitor](https://health.petals.dev) for the public swarm: [source code](https://github.com/petals-infra/health.petals.dev)



Advanced guides:



- Launch a private swarm: [guide](https://github.com/bigscience-workshop/petals/wiki/Launch-your-own-swarm)

- Run a custom model: [guide](https://github.com/bigscience-workshop/petals/wiki/Run-a-custom-model-with-Petals)



### Benchmarks



Please see **Section 3.3** of our [paper](https://arxiv.org/pdf/2209.01188.pdf).



### ๐Ÿ› ๏ธ Contributing



Please see our [FAQ](https://github.com/bigscience-workshop/petals/wiki/FAQ:-Frequently-asked-questions#contributing) on contributing.



### ๐Ÿ“œ Citation



Alexander Borzunov, Dmitry Baranchuk, Tim Dettmers, Max Ryabinin, Younes Belkada, Artem Chumachenko, Pavel Samygin, and Colin Raffel.

[Petals: Collaborative Inference and Fine-tuning of Large Models.](https://arxiv.org/abs/2209.01188)

_arXiv preprint arXiv:2209.01188,_ 2022.



```bibtex

@article{borzunov2022petals,

  title = {Petals: Collaborative Inference and Fine-tuning of Large Models},

  author = {Borzunov, Alexander and Baranchuk, Dmitry and Dettmers, Tim and Ryabinin, Max and Belkada, Younes and Chumachenko, Artem and Samygin, Pavel and Raffel, Colin},

  journal = {arXiv preprint arXiv:2209.01188},

  year = {2022},

  url = {https://arxiv.org/abs/2209.01188}

}

```



--------------------------------------------------------------------------------





    This project is a part of the BigScience research workshop.