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

29 Open 1,052 Closed
29 Open 1,052 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

How to specify the coefficients of loading lora during inference?
#2216 opened Nov 14, 2024 by laolongboy
训练时使用的QLoRA 4rank，进行cuda模型合并导出时出现，KeyError: 'base_model.model.model.model.layers.14.mlp.down_proj'
#2213 opened Nov 14, 2024 by xiaoheiyue
4 tasks
4
Documentation for LoRAConfig.
#2212 opened Nov 12, 2024 by brynhayder
1
TypeError: LoraConfig.__init__() got an unexpected keyword argument 'exclude_modules'
#2208 opened Nov 9, 2024 by imrankh46
4 tasks done
25
modules_to_save Incorrect Overlap in Multiple LoRA Adapters
#2206 opened Nov 8, 2024 by saeid93
2 of 4 tasks
2
KeyError: Parameter containing
#2205 opened Nov 8, 2024 by Amerehei
5
KeyError: 'messages'
#2204 opened Nov 8, 2024 by rickeyhhh
4 tasks
7
Add Assertions for task_type in LoraConfig
#2203 opened Nov 8, 2024 by d-kleine
1
1
RuntimeError: element 0 of tensors.. OpenCLIP model
#2200 opened Nov 5, 2024 by EngEmmanuel
2 of 4 tasks
4
[BUG] Issue with using rank_pattern and alpha_pattern together in LoraConfig
#2194 opened Nov 1, 2024 by sirluk
2 of 4 tasks
2
How to change 'modules_to_save' setting when reloading a lora finetuned model
#2188 opened Oct 30, 2024 by dengchengxifrank
2 of 4 tasks
1
Xlora cannot reload model from last checkpoint by using trainer.train(resume_from_checkpoint="checkpp")
#2185 opened Oct 29, 2024 by SongHanKen
3 of 4 tasks
Evaluation of peft models using lm-eval-harness
#2182 opened Oct 27, 2024 by JINO-ROHIT
4
Integration of merge-kit into PEFT
#2179 opened Oct 25, 2024 by ParagEkbote
@ParagEkbote
11
Invalid none check for loftq_config attribute in LoraConfig contributions-welcome
#2170 opened Oct 22, 2024 by sirluk
2 of 4 tasks
5
Prompt Tuning Crash with Llama-3.2 in torch.embedding
#2161 opened Oct 18, 2024 by hrsmanian
2 of 4 tasks
4
LoraConfig conflict when using layers_to_transform in LlamaModel
#2155 opened Oct 17, 2024 by Evan02580
2 of 4 tasks
3
about run_unsloth_peft.sh
#2152 opened Oct 16, 2024 by opentld
4
When I use peft to finetune llama2, the gpu memory keeps growing
#2141 opened Oct 10, 2024 by xuanzhangyang
2 of 4 tasks
7
support for heterogeneous types for modules_to_save
#2136 opened Oct 7, 2024 by saeid93
5
Key mismatch when trying to load a LORA adapter into an XLORA model
#2132 opened Oct 5, 2024 by p4arth
2 of 4 tasks
4
merge_and_unload docs do not clarify behaviour for quantized base models
#2105 opened Sep 26, 2024 by RonanKMcGovern
2 of 4 tasks
7
XLoRA: training issues, Gradients will be None
#2015 opened Aug 18, 2024 by benjamin-marie
10
Support optimum-quanto contributions-welcome wip
#1997 opened Aug 9, 2024 by BenjaminBossan
1
15
Deprecation: Transformers will no longer support past_key_values to be tuples contributions-welcome help wanted Extra attention is needed wip
#1962 opened Jul 26, 2024 by BenjaminBossan
15
ProTip! Exclude everything labeled bug with -label:bug.