-
Notifications
You must be signed in to change notification settings - Fork 2.4k
Pull requests: huggingface/peft
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Add UniLoraConfig to ALL_CONFIG_CLASSES test matrix
#3383
opened Jul 1, 2026 by
DaoyuanLi2816
Contributor
Loading…
1 task done
FIX MiSS with bat init error with some quantization backends
#3381
opened Jul 1, 2026 by
BenjaminBossan
Member
Loading…
fix: store miss_fn per-adapter in MiSS layer
#3379
opened Jul 1, 2026 by
peft-jambot
Contributor
•
Draft
FIX Register per-adapter containers so delete_adapter removes them (unilora, fourierft, psoft)
#3376
opened Jul 1, 2026 by
DaoyuanLi2816
Contributor
Loading…
CI: Bump the third-party-actions group across 1 directory with 7 updates
dependencies
Pull requests that update a dependency file
github_actions
Pull requests that update GitHub Actions code
#3375
opened Jul 1, 2026 by
dependabot
Bot
Loading…
Add Relation Extraction LoRA script and notebook tutorial
#3368
opened Jun 28, 2026 by
GauravPatil2515
Loading…
FIX AdaMSS: register adamss_newB in other_param_names (delete_adapter leak)
#3367
opened Jun 28, 2026 by
DaoyuanLi2816
Contributor
Loading…
feat: support LoRA conversion for multiplicative PEFT methods (OFT, BOFT)
#3360
opened Jun 25, 2026 by
peft-jambot
Contributor
•
Draft
Proposal: alternative ShadowPEFT implementation
#3357
opened Jun 24, 2026 by
BenjaminBossan
Member
•
Draft
Add P-Tuning LSTM experiment with 50 virtual tokens to MetaMathQA benchmark
#3356
opened Jun 23, 2026 by
Akashsinghbhadoriya
Loading…
refactor: move OFT to generic quantization framework
#3355
opened Jun 23, 2026 by
peft-jambot
Contributor
Loading…
ENH Add PEFT method papers in a structured way
#3323
opened Jun 12, 2026 by
BenjaminBossan
Member
•
Draft
fix: respect layer-specific LoRA-FA scaling in optimizer
#3315
opened Jun 10, 2026 by
eSVeeF
Contributor
Loading…
fix(save_and_load): save base_layer.bias for bias="lora_only"
#3307
opened Jun 7, 2026 by
Anai-Guo
Loading…
ENH Add KaSA (Knowledge-aware Singular-value Adaptation) as a LoRA variant
#3298
opened Jun 2, 2026 by
robbiebusinessacc
•
Draft
Created tutorial detailing how to do differentially private PEFT fine-tuning of huggingface transformer models using FastDP
#3297
opened Jun 2, 2026 by
lmarchyok
Loading…
fix(utils): call empty_cache() after fp16→fp32 casts in prepare_model_for_kbit_training
#3293
opened May 31, 2026 by
umutonuryasar
Loading…
FIX: inject_adapter incorrectly propagates inference_mode to active adapters
#3290
opened May 30, 2026 by
kiritozc
Loading…
Add default target_modules for nemotron_h hybrid Mamba-MoE models
#3289
opened May 29, 2026 by
A1c0r-Z
Loading…
Previous Next
ProTip!
What’s not been updated in a month: updated:<2026-06-02.