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
- `modules_to_save` raises TypeError when a name is a suffix of a LoRA sub-module (e.g. "out", "A")
- docs: document Riemannian-preconditioned LoRA optimizer
- `get_peft_model` and `add_adapter` do not preserve eval mode for newly injected adapter modules
- PiSSA / MiCA / CorDA init bypasses quantized-layer guard on 4-bit float-storage layers
- bnb LoRA merge with lora_bias=True drops scaling factor on bias
- FEAT Add helper function to create a dummy LoRA config to hotswap
- DOC Fix target_parameters example and regex claim in LoRA docs
- add_weighted_adapter with rank_pattern produces adapters that cannot be reloaded (linear, ties, dare, magnitude_prune)
- CI: workflows that need repo secrets fail on every fork sync (tests-main, build_documentation, deploy_*)
- FIX MoE weight conversion issue with ambiguous name
- Docs
- not yet supported