Skip to content
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

Add QLoRA + FSDP Docs #1403

Merged
merged 2 commits into from
Mar 14, 2024
Merged

Add QLoRA + FSDP Docs #1403

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4aa168f
pre commit
hamelsmu Mar 14, 2024
fd833af
Update fsdp_qlora.md
hamelsmu Mar 14, 2024
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
4 changes: 4 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1080,6 +1080,10 @@ fsdp_config:
fsdp_transformer_layer_cls_to_wrap: LlamaDecoderLayer
```

##### FSDP + QLoRA
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It may be good to add this to Table of Contents


Axolotl supports training with FSDP and QLoRA, see [these docs](docs/fsdp_qlora.md) for more information.

##### Weights & Biases Logging

Make sure your `WANDB_API_KEY` environment variable is set (recommended) or you login to wandb with `wandb login`.
Expand Down
37 changes: 37 additions & 0 deletions docs/fsdp_qlora.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,37 @@
# FDSP + QLoRA

## Background

Using FSDP with QLoRA is essential for **fine-tuning larger (70b+ parameter) LLMs on consumer GPUs.** For example, you can use FSDP + QLoRA to train a 70b model on two 24GB GPUs[^1].

Below, we describe how to use this feature in Axolotl.

## Usage

To enable `QLoRA` with `FSDP`, you need to perform the following steps:

> ![Tip]
> See the [example config](#example-config) file in addition to reading these instructions.

1. Set `adapter: qlora` in your axolotl config file.
2. Enable FSDP in your axolotl config, as [described here](https://github.com/OpenAccess-AI-Collective/axolotl?tab=readme-ov-file#fsdp).
3. Use one of the supported model types: `llama`, `mistral` or `mixtral`.

## Example Config

[examples/llama-2/qlora-fsdp.yml](../examples/llama-2/qlora-fsdp.yml) contains an example of how to enable QLoRA + FSDP in axolotl.

## References

- [PR #1378](https://github.com/OpenAccess-AI-Collective/axolotl/pull/1378) enabling QLoRA in FSDP in Axolotl.
- [Blog Post](https://www.answer.ai/posts/2024-03-06-fsdp-qlora.html) from the [Answer.AI](https://www.answer.ai/) team describing the work that enabled QLoRA in FSDP.
- Related HuggingFace PRs Enabling FDSP + QLoRA:
- Accelerate [PR#2544](https://github.com/huggingface/accelerate/pull/2544 )
- Transformers [PR#29587](https://github.com/huggingface/transformers/pull/29587)
- TRL [PR#1416](https://github.com/huggingface/trl/pull/1416)
- PEFT [PR#1550](https://github.com/huggingface/peft/pull/1550)




[^1]: This was enabled by [this work](https://www.answer.ai/posts/2024-03-06-fsdp-qlora.html) from the Answer.AI team.
Loading