📘 SFT doc rewrite #3619
📘 SFT doc rewrite #3619
Conversation
# What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflects the extent of your awesome contribution. Then, please replace this with a description of the change and which issue is fixed (if applicable). Please also include relevant motivation and context. List any dependencies (if any) that are required for this change. Once you're done, someone will review your PR shortly. They may suggest changes to make the code even better. --> <!-- Remove if not applicable --> Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/trl/blob/main/CONTRIBUTING.md#create-a-pull-request), Pull Request section? - [ ] Was this discussed/approved via a GitHub issue? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR.
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
…into sft-doc-refactor
Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
…n SFTTrainer documentation
| Unsloth library that is fully compatible with [`SFTTrainer`]. Some benchmarks on 1x A100 listed below: | ||
|
|
||
| | 1 A100 40GB | Dataset | 🤗 | 🤗 + Flash Attention 2 | 🦥 Unsloth | 🦥 VRAM saved | |
There was a problem hiding this comment.
Is the VRAM saved relative to the 🤗 + FA2 combination or the vanilla 🤗 one? Might be good to specify for clarity
Co-authored-by: lewtun <lewis.c.tunstall@gmail.com>
Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>
Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com> Co-authored-by: lewtun <lewis.c.tunstall@gmail.com>
| ) | ||
|
|
||
| trainer.train() | ||
| ``` | ||
|
|
||
| > [!WARNING] |
There was a problem hiding this comment.
Hi @qgallouedec
I am just wondering why this warning was removed? Is this something that has been resolved?
There was a problem hiding this comment.
Now it's handled automatically if you use clone_chat_template (or chat_template_path from SFTConfig)
There was a problem hiding this comment.
Thanks for the quick reply @qgallouedec but based on my reading of the documentation, it does not handle the modules_to_save issue that was described in this warning.
The user still needs to explicitly add modules_to_save in case new tokens are being added.
Is this the correct interpretation or am I missing something?
There was a problem hiding this comment.
@qgallouedec Sorry for pinging again - But hoping I could understand this. Can you please point me to the correct implementation?
No description provided.