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
- FIX Model attribute error in get_model_conversion_mapping
- fix(tuners): guard child.weight access in _replace_module for non-linear modules
- fix(pvera): use _cast_input_dtype in forward instead of raw .to()
- fix(gralora): use _cast_input_dtype in forward instead of raw .to()
- Proposal: FIM-guided adaptive LoRA rank allocation (FimConfig + initialize_lora_fim_ranks)
- feat(lora): Add FIM-guided adaptive LoRA rank allocation (FimConfig + initialize_lora_fim_ranks)
- CHORE: Upgrade ruff 0.15.12
- Proposal: support ShadowPEFT method in PEFT
- ENH Optimize HRA forward for better memory efficiency
- RFC: Improve code to resolve LoRA variants
- Docs
- not yet supported