peft
https://github.com/huggingface/peft
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
not yet supported1 Subscribers
Add a CodeTriage badge to peft
Help out
- Issues
- Forward hooks leak when the `_enable_peft_forward_hooks` block raises, poisoning the model
- FEAT Add function to create 'detached' copies of models
- FIX Issue with key matching when dealing with disk offloading
- DOC Fix duplicate tuner navigation entries
- Fix bias="lora_only"/"boft_only" dropping the trained bias on save
- TST Fix some multi GPU tests
- [Coordination] Add Super-Tuning tuner class (arXiv:2607.09287) — checking fit before PR
- FIX add_weighted_adapter creates an overscaled adapter when the source uses rslora
- modules_to_save module whose name contains the LoRA prefix ("lora_") is silently not restored on load
- FIX Accept layers_to_transform=0 together with layers_pattern
- Docs
- not yet supported