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

22 Open 956 Closed
22 Open 956 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

Deprecation: Transformers will no longer support past_key_values to be tuples contributions-welcome help wanted Extra attention is needed
#1962 opened Jul 26, 2024 by BenjaminBossan
Inference with different LoRA adapters in the same batch does not use the correct module_to_save classifier contributions-welcome
#1960 opened Jul 26, 2024 by saeid93
2 of 4 tasks
4
Incorrect target modules does not error
#1959 opened Jul 26, 2024 by irenedea
4 tasks
1
Optimal hyperparameter for fine tuning LLM
#1948 opened Jul 24, 2024 by BigDataMLexplorer
2 of 4 tasks
7
AttributeError: 'LlamaForCausalLM' object has no attribute 'add_weighted_adapter'
#1943 opened Jul 22, 2024 by mingkangz
2 of 4 tasks
3
Improving generalization of LoRA with wise-ft contributions-welcome good-second-pr PRs welcome to address this contributions are welcome from community members on this issue
#1940 opened Jul 22, 2024 by SimJeg
8
Memory usage spike when using merge_and_unload
#1939 opened Jul 22, 2024 by snarayan21
4 tasks
6
[Call for contributions] help us improve LoKr, LoHa, and other LyCORIS contributions-welcome good-second-pr
#1935 opened Jul 18, 2024 by sayakpaul
6 tasks
2
load a model with unmerged lora adapters
#1934 opened Jul 18, 2024 by Ledzy
3
load_adapter seems to require the base model to be identical
#1932 opened Jul 17, 2024 by zyzhang1130
4 tasks
2
PEFT implementations of adapters are outdated and languishing
#1931 opened Jul 16, 2024 by bghira
2 of 4 tasks
7
Example semantic_segmentation_peft_lora - better results
#1927 opened Jul 15, 2024 by ibayer
2 of 4 tasks
14
VeRA not working with Quantization contributions-welcome
#1921 opened Jul 10, 2024 by Sharan1712
2 of 4 tasks
5
A bug caused by endswith when using modules_to_save.
#1917 opened Jul 9, 2024 by gary-young
2 of 4 tasks
3
Error using SFTTrainer with Dora & FSDP
#1910 opened Jul 6, 2024 by qZhang88
4 tasks
1
How to use multiple GPUs
#1903 opened Jul 3, 2024 by Lihwnlp
1 of 4 tasks
6
Model encapsulation
#1902 opened Jul 2, 2024 by tomekrut
2 of 4 tasks
1
After fine-tuning, the model inference is abnormal
#1883 opened Jun 24, 2024 by mumu029
2 of 4 tasks
2
eval_loss missing when using peft model with STFTrainer
#1881 opened Jun 21, 2024 by J4Q8
1 of 4 tasks
8
Model with LoRA adapter errors when saving with safe_serialization=True
#1876 opened Jun 20, 2024 by mliu-aqtc
4 tasks
4
DoRA support for Embedding contributions-welcome
#1677 opened Apr 24, 2024 by ShayekhBinIslam
3
Implementation of adapter? wip
#244 opened Mar 31, 2023 by jzhang38
5
ProTip! no:milestone will show everything without a milestone.