[go: nahoru, domu]
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

Clear current search query, filters, and sorts
22 Open 923 Closed
22 Open 923 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

[BugReport] init_lora_weights with pissa is not compatible with deepspeed stage3
#1826 opened Jun 5, 2024 by wsp317 updated Jun 5, 2024
1
Implementation of adapter? wip
#244 opened Mar 31, 2023 by jzhang38 updated Jun 5, 2024
5
question about bits_pattern feature
#1839 opened Jun 10, 2024 by harrysyz99 updated Jun 10, 2024
1
Tutorial notebook for applying PEFT with DNA Language models
#1837 opened Jun 9, 2024 by rahulbshrestha updated Jun 10, 2024
1
Lora Training Tab
#1814 opened Jun 2, 2024 by ClericerQ updated Jun 10, 2024
4
LoRA adaptation shape mismatch
#1746 opened May 19, 2024 by manlenzzz updated Jun 10, 2024
9
Fail to use zero_init to construct llama2 with deepspeed zero3 and qlora!
#1844 opened Jun 11, 2024 by CHNRyan updated Jun 11, 2024
2 of 4 tasks
6
Issues when switching between multiple adapters LoRAs
#1802 opened May 26, 2024 by JhonDan1999 updated Jun 11, 2024
7
Geometric Parametrization (GmP) [CLIP] - is it compatible with PEFT?
#1863 opened Jun 16, 2024 by zer0int updated Jun 17, 2024
1
Do we have to delete the PiSSA adapter after save_pissa_as_lora
#1860 opened Jun 15, 2024 by hiyouga updated Jun 17, 2024
2 of 4 tasks
4
Does PEFT support CodeBERT?
#1865 opened Jun 16, 2024 by MabelQi updated Jun 18, 2024
2 of 4 tasks
5
Using PEFT causes model to not predict EOS
#1672 opened Apr 23, 2024 by Km3888 updated Jun 23, 2024
2 of 4 tasks
13
After fine-tuning, the model inference is abnormal
#1883 opened Jun 24, 2024 by mumu029 updated Jun 24, 2024
2 of 4 tasks
1
Model with LoRA adapter errors when saving with safe_serialization=True
#1876 opened Jun 20, 2024 by mliu-aqtc updated Jun 24, 2024
4 tasks
3
eval_loss missing when using peft model with STFTrainer
#1881 opened Jun 21, 2024 by J4Q8 updated Jun 24, 2024
1 of 4 tasks
1
AdaLora: rank remains constant (to init_r value) across training
#1801 opened May 24, 2024 by geoffvdr updated Jun 24, 2024
2 of 4 tasks
4
FSDP Dora/QDora Broken
#1737 opened May 17, 2024 by mallorbc updated Jun 24, 2024
2 of 4 tasks
5
Add Special Optimizer for LoRA training
#1803 opened May 27, 2024 by fangzhaozhang updated Jun 26, 2024
3
local pytest run puts torch.allclose() out of range in test_4bit_lora_mixed_adapter_batches_lora
#1889 opened Jun 27, 2024 by kallewoof updated Jun 27, 2024
4 tasks
1
6
Correctly Uploading PEFT/QLoRA model to HuggingFace
#1812 opened May 30, 2024 by taoofstefan updated Jun 30, 2024
9
PeftModel.from_pretrained not load modules_to_save in config file
#1894 opened Jun 28, 2024 by double-fire-0 updated Jul 1, 2024
4 tasks
3
ValueError: Trying to set a tensor of shape torch.Size([43176, 8192]) in "weight" (which has shape torch.Size([0])), this look incorrect.
#1890 opened Jun 27, 2024 by KarasZhang updated Jul 1, 2024
2 of 4 tasks
14
ProTip! Adding no:label will show everything without a label.