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
- [RFC, I can do a PR] Make `lora_alpha` a float
- FEAT Add MoE-to-Dense adapter
- hotswap_adapter: silent no-op when adapter is merged; KeyError on modules_to_save checkpoints; stale peft_config breaks save/load after swapping different rank/alpha
- save_pretrained writes an empty/truncated adapter checkpoint (silently) when another adapter name equals a base-model module path component
- LN Tuning: KeyError on forward/merge when the active adapter does not target all adapted layers
- ENH Add option to use Khatri-Rao to LoHa
- PeftModel.disable_adapter is not reentrant for prompt-specific adapters
- Implementation for Multi Token Prediction (2507.11851)
- Fix PeftMixedModel.disable_adapter to restore prior adapter state
- ENH Improve BOFT forward pass, remove CUDA kernel
- Docs
- not yet supported