- Run inference or fine-tune [BLOOM-176B](https://huggingface.co/bigscience/bloom) by joining compute resources with people all over the Internet. No need to have high-end GPUs.
- One inference step takes ≈ 1 sec — much faster than possible with offloading. Enough for chatbots and other interactive apps.
- Employ any fine-tuning and sampling methods by accessing model's hidden states and changing its control flow — something you can't do in proprietary APIs.
- Run inference or fine-tune large language models like [BLOOM-176B](https://huggingface.co/bigscience/bloom) by joining compute resources with people all over the Internet. No need to have high-end GPUs.
- It's difficult to fit the whole BLOOM-176B into GPU memory [unless](https://twitter.com/Tim_Dettmers/status/1559892918395031552) you have multiple high-end GPUs. Instead, **Petals** allows to load and serve a small part of the model, then team up with people serving all the other parts to run inference or fine-tuning.
- This way, one inference step takes ≈ 1 sec — much faster than possible with offloading. Enough for chatbots and other interactive apps.
- Beyond traditional language model APIs — you can employ any fine-tuning and sampling methods by executing custom paths through the model or accessing its hidden states. This allows for the comforts of an API with the flexibility of PyTorch.
Be careful: some features may not work, interfaces may change, and we have no detailed docs yet (see [roadmap](https://github.com/bigscience-workshop/petals/issues/12)).
Petals integrates seamlessly with PyTorch and the Hugging Face [Transformers](https://github.com/huggingface/transformers) library.
A stable version of the code and a public swarm open to everyone will be released in November 2022. You can [subscribe](https://petals.ml/) to be emailed when it happens or fill in [this form](https://forms.gle/TV3wtRPeHewjZ1vH9) to help the public launch by donating GPU time. In the meantime, you can launch and use your own private swarm.
This snippet shows how to **(a)** generate text with BLOOM and **(b)** solve a sequence classification task via soft prompt tuning:
## Code examples
```python
# Initialize distributed BLOOM and connect to the swarm
model = DistributedBloomForCausalLM.from_pretrained(
# Training (updates only local prompts / adapters)
optimizer = torch.optim.AdamW(model.parameters())
for input_ids, labels in data_loader:
# Forward pass with local and remote layers
outputs = model.forward(input_ids)
loss = cross_entropy(outputs.logits, labels)
# Distributed backward w.r.t. local params
loss.backward() # Compute model.prompts.grad
optimizer.step() # Update local params only
optimizer.zero_grad()
loss.backward()
optimizer.step()
```
### 🚧 This project is in active development
Be careful: some features may not work, interfaces may change, and we have no detailed docs yet (see [roadmap](https://github.com/bigscience-workshop/petals/issues/12)).
A stable version of the code and a public swarm open to everyone will be released in November 2022. You can [subscribe](https://petals.ml/) to be emailed when it happens or fill in [this form](https://forms.gle/TV3wtRPeHewjZ1vH9) to help the public launch by donating GPU time. In the meantime, you can launch and use your own private swarm.
### 🔒 Privacy and security
If you work with sensitive data, you should only use a private swarm (or a subset of servers in the public swarm) hosted by people and institutions you trust, who are authorized to process this data.
This is important because it's technically possible for peers serving model layers to recover input data or model outputs. Also, if there are malicious peers, they may alter their outputs to influence the model outputs. See a more detailed discussion in Section 4 of our [paper](https://arxiv.org/pdf/2209.01188.pdf).
## FAQ
1. **What's the motivation for people to host model layers in the public swarm?**
People who run inference and fine-tuning themselves get a certain speedup if they host a part of the model locally. Some may be also motivated to "give back" to the community helping them to run the model (similarly to how [BitTorrent](https://en.wikipedia.org/wiki/BitTorrent) users help others by sharing data they have already downloaded).
Since it may be not enough for everyone, we are also working on introducing explicit __incentives__ ("bloom points") for people donating their GPU time to the public swarm. Once this system is ready, people who earned these points will be able to spend them on inference/fine-tuning with higher priority or increased security guarantees, or (maybe) exchange them for other rewards.
2. **Why is the platform named "Petals"?**
"Petals" is a metaphor for people serving different parts of the model. Together, they host the entire language model — [BLOOM](https://huggingface.co/bigscience/bloom).
While our platform focuses on BLOOM now, we aim to support more [foundation models](https://arxiv.org/abs/2108.07258) in future.
## Installation
🚧 **Note:** These are short instructions for running a private swarm with a test 6B version of BLOOM. We will replace them with instructions involving the full 176B BLOOM and more detailed explanations soon (in a day or two).