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
- Loading an adapter from a repo subfolder fails with HF_HUB_OFFLINE=1
- RoAd mixed-adapter batches fail for float16/bfloat16 models
- [Proposal] Add Cortex-Structural: parameter-efficient FFN expansion for dense and MoE models
- [New method] Bayesian-LoRA: Probabilistic Low-Rank Adaptation (ICML 2026)
- n_frequency_pattern, block_size_pattern and lambda_pattern lose their key order on save
- OFT Conv2d: unmerged and merged outputs differ for kernels larger than 1x1
- Revalidate Transformer Engine GPU CI support
- docs: clarify AdaLoRA importance measurement and training phases
- Mixed adapter batch raises KeyError when only one adapter has modules_to_save
- Prompt-learning methods crash on transformers 4.43/4.44: the pre-get_text_config fallback uses `in` on a PretrainedConfig
- Docs
- not yet supported