iicd/ddpo-pytorch
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md to include a note about the trl integration

Browse Source
This commit is contained in:
Sayak Paul 2023-09-30 15:07:48 +02:00 committed by GitHub
parent b590ec0a7c
commit bfcba5e28e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
README.md
View File

@ -53,3 +53,8 @@ If you want to run the LLaVA prompt-image alignment experiments, you need to ded
<img src="https://github.com/kvablack/ddpo-pytorch/assets/12429600/669076d5-2826-4b77-835b-d82e0c18a2a6" width="49%">
<img src="https://github.com/kvablack/ddpo-pytorch/assets/12429600/393a929e-36af-46f2-8022-33384bdae1c8" width="49%">
## Training using 🤗 `trl`
🤗 `trl` provides a [`DDPOTrainer` class](https://huggingface.co/docs/trl/ddpo_trainer) which lets you fine-tune Stable Diffusion on different reward functions using DDPO. The integration supports LoRA, too. You can check out the [supplementary blog post](https://huggingface.co/blog/trl-ddpo) for additional guidance. The DDPO integration was contributed by @metric-space to `trl`.