Skip to content

[doc] add Quick Preview #2706

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Feb 14, 2023
Merged

[doc] add Quick Preview #2706

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 23 additions & 2 deletions applications/ChatGPT/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
# RLHF - ColossalAI
# RLHF - Colossal-AI

Implementation of RLHF (Reinforcement Learning with Human Feedback) powered by ColossalAI. It supports distributed training and offloading, which can fit extremly large models.
Implementation of RLHF (Reinforcement Learning with Human Feedback) powered by Colossal-AI. It supports distributed training and offloading, which can fit extremly large models. More details can be found in the [blog](https://www.hpc-ai.tech/blog/colossal-ai-chatgpt).

<p align="center">
<img src="https://raw.githubusercontent.com/hpcaitech/public_assets/main/applications/chatgpt/chatgpt.png" width=700/>
Expand Down Expand Up @@ -60,6 +60,27 @@ We also support training reward model with true-world data. See `examples/train_
- [ ] integrate with Ray
- [ ] support more RL paradigms, like Implicit Language Q-Learning (ILQL)

## Quick Preview
<p id="ChatGPT_scaling" align="center">
<img src="https://raw.githubusercontent.com/hpcaitech/public_assets/main/applications/chatgpt/ChatGPT%20scaling.png" width=800/>
</p>

- Up to 7.73 times faster for single server training and 1.42 times faster for single-GPU inference

<p id="ChatGPT-1GPU" align="center">
<img src="https://raw.githubusercontent.com/hpcaitech/public_assets/main/applications/chatgpt/ChatGPT-1GPU.jpg" width=450/>
</p>

- Up to 10.3x growth in model capacity on one GPU
- A mini demo training process requires only 1.62GB of GPU memory (any consumer-grade GPU)

<p id="inference" align="center">
<img src="https://raw.githubusercontent.com/hpcaitech/public_assets/main/applications/chatgpt/LoRA%20data.jpg" width=600/>
</p>

- Increase the capacity of the fine-tuning model by up to 3.7 times on a single GPU
- Keep in a sufficiently high running speed

## Citations

```bibtex
Expand Down