Run large language models at home, BitTorrent-style.
Fine-tuning and inference up to 10x faster than offloading
π Try now in Colab
π Make sure you follow the model's terms of use (see [LLaMA 2](https://bit.ly/llama2-license), [LLaMA](https://bit.ly/llama-license) and [BLOOM](https://bit.ly/bloom-license) licenses). π Your data will be processed by 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. ### Connect your GPU and increase Petals capacity Run these commands in an [Anaconda](https://www.anaconda.com) env (requires Linux and Python 3.8+): ```bash conda install pytorch pytorch-cuda=11.7 -c pytorch -c nvidia pip install --upgrade petals python -m petals.cli.run_server enoch/llama-65b-hf --adapters timdettmers/guanaco-65b ``` Or run our [Docker](https://www.docker.com) image (works on Linux, macOS, and Windows with [WSL2](https://learn.microsoft.com/en-us/windows/ai/directml/gpu-cuda-in-wsl)): ```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 enoch/llama-65b-hf --adapters timdettmers/guanaco-65b ``` This will host a part of LLaMA-65B with optional [Guanaco](https://huggingface.co/timdettmers/guanaco-65b) adapters on your machine. You can also host `meta-llama/Llama-2-70b-hf`, `meta-llama/Llama-2-70b-chat-hf`, `bigscience/bloom`, `bigscience/bloomz`, and other compatible models from π€ [Model Hub](https://huggingface.co/models), or [add support](https://github.com/bigscience-workshop/petals/wiki/Run-a-custom-model-with-Petals) for new model architectures. π Hosting a server does not allow others to run custom code on your computer. Learn more about security [here](https://github.com/bigscience-workshop/petals/wiki/Security,-privacy,-and-AI-safety). π¬ See [FAQ](https://github.com/bigscience-workshop/petals/wiki/FAQ:-Frequently-asked-questions#running-a-server) to learn how to use multple GPUs, restart the server on reboot, etc. If you have any issues or feedback, ping us in [our Discord](https://discord.gg/D9MwApKgWa)! ### Check out 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 and advanced guides: - [Chatbot web app](https://chat.petals.dev) (connects to Petals via an HTTP/WebSocket endpoint): [source code](https://github.com/borzunov/chat.petals.dev) - [Monitor](https://health.petals.dev) for the public swarm: [source code](https://github.com/borzunov/health.petals.dev) - Launch your own swarm: [guide](https://github.com/bigscience-workshop/petals/wiki/Launch-your-own-swarm) - Run a custom foundation model: [guide](https://github.com/bigscience-workshop/petals/wiki/Run-a-custom-model-with-Petals) Learning more: - Frequently asked questions: [FAQ](https://github.com/bigscience-workshop/petals/wiki/FAQ:-Frequently-asked-questions) - In-depth system description: [paper](https://arxiv.org/abs/2209.01188) ## How does it work? - Petals runs large language models like [LLaMA](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) and [BLOOM](https://huggingface.co/bigscience/bloom) **collaboratively** β you load a small part of the model, then team up with people serving the other parts to run inference or fine-tuning. - Single-batch inference runs at up to 6 steps/sec for LLaMA 2 (70B) and ≈ 1 step/sec for BLOOM-176B. This is [up to 10x faster](https://github.com/bigscience-workshop/petals#benchmarks) than offloading, enough for [chatbots](https://chat.petals.dev) and other interactive apps. Parallel inference reaches hundreds of tokens/sec. - Beyond classic language model APIs β 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.
π See FAQ π Read paper
## Installation Here's how to install Petals with [Anaconda](https://www.anaconda.com/products/distribution) on Linux: ```bash conda install pytorch pytorch-cuda=11.7 -c pytorch -c nvidia pip install --upgrade petals ``` If you don't use Anaconda, you can install PyTorch in [any other way](https://pytorch.org/get-started/locally/). If you want to run models with 8-bit weights, please install PyTorch with CUDA 11.x or newer for compatility with [bitsandbytes](https://github.com/timDettmers/bitsandbytes). See the instructions for macOS and Windows, the full requirements, and troubleshooting advice in our [FAQ](https://github.com/bigscience-workshop/petals/wiki/FAQ:-Frequently-asked-questions#running-a-client). ## Benchmarks The benchmarks below are for BLOOM-176B:Network | Single-batch inference (steps/s) |
Parallel forward (tokens/s) |
|||
---|---|---|---|---|---|
Bandwidth | Round-trip latency |
Sequence length | Batch size | ||
128 | 2048 | 1 | 64 | ||
Offloading, max. possible speed on 1x A100 1 | |||||
256 Gbit/s | 0.18 | 0.18 | 2.7 | 170.3 | |
128 Gbit/s | 0.09 | 0.09 | 2.4 | 152.8 | |
Petals on 14 heterogeneous servers across Europe and North America 2 | |||||
Real world | 0.83 | 0.79 | 32.6 | 179.4 | |
Petals on 3 servers, with one A100 each 3 | |||||
1 Gbit/s | < 5 ms | 1.71 | 1.54 | 70.0 | 253.6 |
100 Mbit/s | < 5 ms | 1.66 | 1.49 | 56.4 | 182.0 |
100 Mbit/s | 100 ms | 1.23 | 1.11 | 19.7 | 112.2 |
This project is a part of the BigScience research workshop.