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
- TST Add tests for hotswapping targeted LoRA parameters
- Created tutorial detailing how to do differentially private PEFT fine-tuning of huggingface transformer models using FastDP
- ENH Add KaSA (Knowledge-aware Singular-value Adaptation) as a LoRA variant
- Bump the third-party-actions group with 3 updates
- Proposal: add FineGates structured-sparsity PEFT method
- fix(utils): call empty_cache() after fp16→fp32 casts in prepare_model_for_kbit_training
- Add default target_modules for nemotron_h hybrid Mamba-MoE models
- FIX: inject_adapter incorrectly propagates inference_mode to active adapters
- Proposal: Content-addressed adapter recipes for cross-platform LoRA distribution
- FIX Remove duplicate VBLoRAConfig entry from peft.__all__
- Docs
- not yet supported