-
Notifications
You must be signed in to change notification settings - Fork 2.1k
Pull requests: huggingface/peft
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
FIX Load quantized weights with PEFT mixed model
#2915
opened Nov 18, 2025 by
BenjaminBossan
Loading 1�7
TST FIX: Issue with pickle models and caching
#2913
opened Nov 17, 2025 by
BenjaminBossan
Loading 1�7
Fix caching for LoRA parametrizations on nn.Parameter
#2912
opened Nov 16, 2025 by
jonnyli1125
Loading 1�7
Add Intruder Dimension Mitigation for LoRA Adapters
#2911
opened Nov 15, 2025 by
ved1beta
Loading 1�7
ENH: Improve torch.compile support in MetaMath
#2900
opened Nov 6, 2025 by
BenjaminBossan
Loading 1�7
Fix autocast_adapter_dtype=False for quantized models
#2891
opened Nov 4, 2025 by
Aznix07
Loading 1�7
ENH: Tie weights for target_modules in Lora (#2864)
#2879
opened Oct 29, 2025 by
romitjain
Loading 1�7
Implement ensure_weight_tying for trainable_token_indices (#2864)
#2870
opened Oct 26, 2025 by
sambhavnoobcoder
Loading 1�7
7 tasks done
Add LoRA-MPO integration for enhanced parameter efficiency
#2868
opened Oct 24, 2025 by
lpyhdzx
Loading 1�7
Add conv2d support for fourierft and other improvements
#2794
opened Sep 21, 2025 by
frutiemax92
Loading 1�7
Pull Request: Adding HiRA integration into PEFT library
#2668
opened Jul 24, 2025 by
hqsiswiliam
Loading 1�7
ENH Cache DoRA weight norm for inference
wip
#2661
opened Jul 21, 2025 by
BenjaminBossan
Loading 1�7
Previous Next
ProTip!
Type g i on any issue or pull request to go back to the issue listing page.

