Skip to content

Pull requests: huggingface/peft

New pull request New
33 Open 1,549 Closed
33 Open 1,549 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[WIP] Changes for transformers 5 weight conversion
#3083 opened Mar 5, 2026 by BenjaminBossan • Draft
[WIP] Image generation benchmark
#3082 opened Mar 4, 2026 by BenjaminBossan • Draft
14
Ensure that te.pytorch exists
#3081 opened Mar 4, 2026 by githubnemo Loading…
1
LoRA and Transformers TP
#3079 opened Mar 3, 2026 by michaelbenayoun • Draft
1
[method_comparison] RL training based method comparison for lora adapters
#3078 opened Mar 3, 2026 by kashif • Draft
5
WIP: Support tranformers weight conversion
#3071 opened Feb 27, 2026 by githubnemo • Draft
1
DOC: Section on weight tying with LoRA
#3066 opened Feb 25, 2026 by BenjaminBossan Loading…
5
docs: replace deprecated financial_phrasebank dataset in IA3 tutorial
#3058 opened Feb 23, 2026 by dhruvildarji Loading…
3 tasks done
1
4
ENH Support models with low precision float dtypes
#3055 opened Feb 20, 2026 by BenjaminBossan Loading…
1
Refactor layer initialization: PR 2960 continued
#3047 opened Feb 17, 2026 by BenjaminBossan • Draft
3
FIX Add guard when detecting the optimum version
#3042 opened Feb 13, 2026 by BenjaminBossan Loading…
2
fix: layers_to_transform now correctly matches layer index on MoE models
#3028 opened Feb 7, 2026 by Mr-Neutr0n Loading…
1
8
[TinyLoRA]tinylora implementation
#3024 opened Feb 6, 2026 by kashif Loading…
37
Add tooling to bump action version
#3022 opened Feb 4, 2026 by githubnemo Loading…
5
update get_error_factor to cache up with the latest transformers change
#3021 opened Feb 4, 2026 by jiqing-feng Loading…
9
Fix moe layers to transform
#3017 opened Feb 1, 2026 by MichalMraz Loading…
1
4
fix: eliminate cross-terms bug when combining adapters with different weights
#3013 opened Jan 30, 2026 by wingding12 • Draft
1
2
[feature] Tiny modification to enable OFT for finetuning embedding layers
#3005 opened Jan 21, 2026 by zqiu24 Loading…
2
Add get base model state dict
#3000 opened Jan 16, 2026 by Isalia20 Loading…
1
16
Add AdaMSS tuner with Adaptive Subspace Allocation (ASA)
#2987 opened Jan 10, 2026 by LonglongaaaGo Loading…
208
fix: auto-untie word embeddings on merge_and_unload when both are adapted
#2972 opened Dec 31, 2025 by www-spam Loading…
5 tasks done
1
8
Implements EWoRA in PEFT
#2971 opened Dec 31, 2025 by HarshKohli Loading…
1
4
intorduce AdaDoRA implementation using both DoRA and AdaLoRa together
#2969 opened Dec 25, 2025 by OrMullerHahitti Loading…
64
Add UniLoRA tuner to PEFT
#2968 opened Dec 23, 2025 by KaiyangLi1992 Loading…
3 tasks done
41
[FEAT] Add FeRA (Frequency-Energy Constrained Routing Adaptation) method
#2951 opened Dec 11, 2025 by YinBo0927 Loading…
28
ProTip! Type g i on any issue or pull request to go back to the issue listing page.