Skip to content

Issues: huggingface/peft

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

27 Open 1,137 Closed
27 Open 1,137 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
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

PEFT LoRA forwarding latency mismatch
#2426 opened Mar 12, 2025 by leexcape
2 of 4 tasks
[Feature Request] LoRA-Null: Low-Rank Adaptation via Null Space for Large Language Models
#2425 opened Mar 12, 2025 by sailfish009
2
UserWarning: MatMul8bitLt: inputs will be cast from torch.float32 to float16 during quantization
#2424 opened Mar 12, 2025 by suhyun01150
1
load_adapter Fails When modules_to_save Are Different for Each Adapter
#2422 opened Mar 11, 2025 by saeid93
2 of 4 tasks
1
Adapters saved in float16 are loaded in float32
#2421 opened Mar 11, 2025 by BenjVig
2 of 4 tasks
1
size mismatch for lm_head when fintune QWEN2.5
#2415 opened Mar 10, 2025 by minmie
2 of 4 tasks
3
LoraConfig multiple properties should be unified
#2413 opened Mar 7, 2025 by Qubitium
11
running forward loop using get_peft_model disables requires_grad on output
#2410 opened Mar 6, 2025 by Hamidreza3252
3
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cuda:3! (when checking argument for argument mat2 in method wrapper_CUDA_mm)
#2407 opened Mar 4, 2025 by maxliang114514
6
SafetensorError when Merging LoRA Weights
#2405 opened Mar 3, 2025 by Nothern-ai
2 of 4 tasks
1
TP + DP training error
#2394 opened Feb 24, 2025 by iMountTai
2 of 4 tasks
7
ValueError: Target module Qwen2_5_VisionTransformerPretrainedModel is not supported.
#2388 opened Feb 19, 2025 by samuellimabraz
3
Bug when deleting adapters of a model with modules_to_save bug Something isn't working
#2381 opened Feb 17, 2025 by BenjaminBossan
4 tasks
prompt_tuning_peft tutorial raises cache layer error
#2379 opened Feb 15, 2025 by jakerobers
1 of 4 tasks
3
Contributing new model merging method to PEFT
#2377 opened Feb 14, 2025 by SpeeeedLee
1
Inconsistent documentation
#2359 opened Feb 4, 2025 by makelinux
5
CI: Add gptqmodel to the CI wip
#2342 opened Jan 23, 2025 by BenjaminBossan
4
Request to intergrate Structure Sparsity-based PEFT (S2FT)
#2329 opened Jan 14, 2025 by Hanyuezhuohua
4
[Warning] Merge lora module to 4-bit linear may get different generations
#2321 opened Jan 11, 2025 by steveepreston
1 of 4 tasks
15
Issue merging a Lora model to a SANA transformer
#2318 opened Jan 10, 2025 by frutiemax92
4 tasks
13
Comparison of Different Fine-Tuning Techniques for Conversational AI contributions-welcome good first issue Good for newcomers help wanted Extra attention is needed
#2310 opened Jan 7, 2025 by ImamaDev
14
Is it possible to add LoRA on specific head?
#2293 opened Dec 22, 2024 by SpeeeedLee
11
Incompatibility of X-LoRA and MistralForSequenceClassification
#2281 opened Dec 13, 2024 by cyx96
2 of 4 tasks
6
Integration of merge-kit into PEFT
#2179 opened Oct 25, 2024 by ParagEkbote
@ParagEkbote
21
Support optimum-quanto contributions-welcome wip
#1997 opened Aug 9, 2024 by BenjaminBossan
1
15
ProTip! Exclude everything labeled bug with -label:bug.