Metadata-Version: 2.1
Name: petals
Version: 1.1.3
Summary: Easy way to efficiently run 100B+ language models without high-end GPUs
Home-page: https://github.com/bigscience-workshop/petals
Author: Petals Developers
Author-email: petals-dev@googlegroups.com
Project-URL: Bug Tracker, https://github.com/bigscience-workshop/petals/issues
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Topic :: Scientific/Engineering
Classifier: Topic :: Scientific/Engineering :: Mathematics
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development
Classifier: Topic :: Software Development :: Libraries
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.7
Description-Content-Type: text/markdown
Provides-Extra: dev
License-File: LICENSE

<p align="center">
    <img src="https://i.imgur.com/7eR7Pan.png" width="400"><br>
    Run 100B+ language models at home, BitTorrent-style.<br>
    Fine-tuning and inference up to 10x faster than offloading<br><br>
    <a href="https://pypi.org/project/petals/"><img src="https://img.shields.io/pypi/v/petals.svg?color=green"></a><br>
</p>

Generate text using distributed 176B-parameter [BLOOM](https://huggingface.co/bigscience/bloom) or [BLOOMZ](https://huggingface.co/bigscience/bloomz) and fine-tune them for your own tasks:

```python
from petals import DistributedBloomForCausalLM

model = DistributedBloomForCausalLM.from_pretrained("bigscience/bloom-petals", tuning_mode="ptune", pre_seq_len=16)
# Embeddings & prompts are on your device, BLOOM blocks are distributed across the Internet

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...

# Fine-tuning (updates only prompts or adapters hosted locally)
optimizer = torch.optim.AdamW(model.parameters())
for input_ids, labels in data_loader:
    outputs = model.forward(input_ids)
    loss = cross_entropy(outputs.logits, labels)
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
```

<p align="center">
    🚀 &nbsp;<b><a href="https://colab.research.google.com/drive/1Ervk6HPNS6AYVr3xVdQnY5a-TjjmLCdQ?usp=sharing">Try now in Colab</a></b>
</p>

🔏 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 this in an [Anaconda](https://www.anaconda.com) env (requires Linux and Python 3.7+):

```bash
conda install pytorch pytorch-cuda=11.7 -c pytorch -c nvidia
pip install -U petals
python -m petals.cli.run_server bigscience/bloom-petals
```

Or use 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 bigscience/bloom-petals --port 31330
```

📚 See [FAQ](https://github.com/bigscience-workshop/petals/wiki/FAQ:-Frequently-asked-questions#running-a-server) to learn how to configure the server to use multiple GPUs, address common issues, etc.

You can also host [BLOOMZ](https://huggingface.co/bigscience/bloomz), a version of BLOOM fine-tuned to follow human instructions in the zero-shot regime — just replace `bloom-petals` with `bloomz-petals`.

🔒 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).

💬 If you have any issues or feedback, let us know on [our Discord server](https://discord.gg/D9MwApKgWa)!

### Check out tutorials, examples, and more

Basic tutorials:

- Getting started: [tutorial](https://colab.research.google.com/drive/1Ervk6HPNS6AYVr3xVdQnY5a-TjjmLCdQ?usp=sharing)
- 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)
- Prompt-tune BLOOM for text semantic classification: [tutorial](https://colab.research.google.com/github/bigscience-workshop/petals/blob/main/examples/prompt-tuning-sst2.ipynb)

Useful tools and advanced guides:

- [Chatbot web app](http://chat.petals.ml) (connects to Petals via an HTTP endpoint): [source code](https://github.com/borzunov/chat.petals.ml)
- [Monitor](http://health.petals.ml) for the public swarm: [source code](https://github.com/borzunov/health.petals.ml)
- 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)

📋 If you build an app running BLOOM with Petals, make sure it follows the BLOOM's [terms of use](https://huggingface.co/bigscience/bloom).

## How does it work?

- Petals runs large language models like [BLOOM-176B](https://huggingface.co/bigscience/bloom) **collaboratively** — you load a small part of the model, then team up with people serving the other parts to run inference or fine-tuning.
- Inference runs at ≈ 1 sec per step (token) — 10x faster than possible with offloading, enough for chatbots and other interactive apps. Parallel inference reaches hundreds of tokens/sec.
- Beyond classic language model APIs — you can employ any fine-tuning and sampling methods by executing custom paths through the model or accessing its hidden states. You get the comforts of an API with the flexibility of PyTorch.

<p align="center">
    <img src="https://i.imgur.com/RTYF3yW.png" width="800">
</p>

<p align="center">
    📚 &nbsp;<b><a href="https://github.com/bigscience-workshop/petals/wiki/FAQ:-Frequently-asked-questions">See FAQ</a></b>
    &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
    📜 &nbsp;<b><a href="https://arxiv.org/pdf/2209.01188.pdf">Read paper</a></b>
</p>

## Installation

Here's how to install Petals with conda:

```bash
conda install pytorch pytorch-cuda=11.7 -c pytorch -c nvidia
pip install -U petals
```

This script uses Anaconda to install CUDA-enabled PyTorch.
If you don't have anaconda, you can get it from [here](https://www.anaconda.com/products/distribution).
If you don't want anaconda, you can install PyTorch [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** or newer for compatility with [bitsandbytes](https://github.com/timDettmers/bitsandbytes).

__System requirements:__ Petals only supports Linux for now. If you don't have a Linux machine, consider running Petals in Docker (see our [image](https://hub.docker.com/r/learningathome/petals)) or, in case of Windows, in WSL2 ([read more](https://learn.microsoft.com/en-us/windows/ai/directml/gpu-cuda-in-wsl)). CPU is enough to run a client, but you probably need a GPU to run a server efficiently.

## 🛠️ Development

Petals uses pytest with a few plugins. To install them, run:

```bash
conda install pytorch pytorch-cuda=11.7 -c pytorch -c nvidia
git clone https://github.com/bigscience-workshop/petals.git && cd petals
pip install -e .[dev]
```

To run minimalistic tests, you need to make a local swarm with a small model and some servers. You may find more information about how local swarms work and how to run them in [this tutorial](https://github.com/bigscience-workshop/petals/wiki/Launch-your-own-swarm).

```bash
export MODEL_NAME=bloom-testing/test-bloomd-560m-main

python -m petals.cli.run_server $MODEL_NAME --block_indices 0:12 \
  --identity tests/test.id --host_maddrs /ip4/127.0.0.1/tcp/31337 --new_swarm  &> server1.log &
sleep 5  # wait for the first server to initialize DHT

python -m petals.cli.run_server $MODEL_NAME --block_indices 12:24 \
  --initial_peers SEE_THE_OUTPUT_OF_THE_1ST_PEER &> server2.log &

tail -f server1.log server2.log  # view logs for both servers
```

Then launch pytest:

```bash
export MODEL_NAME=bloom-testing/test-bloomd-560m-main REF_NAME=bigscience/bloom-560m
export INITIAL_PEERS=/ip4/127.0.0.1/tcp/31337/p2p/QmS9KwZptnVdB9FFV7uGgaTq4sEKBwcYeKZDfSpyKDUd1g
PYTHONPATH=. pytest tests --durations=0 --durations-min=1.0 -v
```

After you're done, you can terminate the servers and ensure that no zombie processes are left with `pkill -f petals.cli.run_server && pkill -f p2p`.

The automated tests use a more complex server configuration that can be found [here](https://github.com/bigscience-workshop/petals/blob/main/.github/workflows/run-tests.yaml).

### Code style

We use [black](https://black.readthedocs.io/en/stable/the_black_code_style/current_style.html) and [isort](https://pycqa.github.io/isort/) for all pull requests.
Before committing your code, simply run `black . && isort .` and you will be fine.

## 📜 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}
}
```

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

<p align="center">
    This project is a part of the <a href="https://bigscience.huggingface.co/">BigScience</a> research workshop.
</p>
<p align="center">
    <img src="https://petals.ml/bigscience.png" width="150">
</p>
