[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
0 Open 926 Closed
0 Open 926 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

PeftModel.from_pretrained not load modules_to_save in config file
#1894 by double-fire-0 was closed Jul 2, 2024
4 tasks
4
LORA finetuning gradients are scaled by a unknown constant factor
#1893 by goliaro was closed Jun 29, 2024
2 of 4 tasks
2
ValueError: Trying to set a tensor of shape torch.Size([43176, 8192]) in "weight" (which has shape torch.Size([0])), this look incorrect.
#1890 by KarasZhang was closed Jul 2, 2024
2 of 4 tasks
15
local pytest run puts torch.allclose() out of range in test_4bit_lora_mixed_adapter_batches_lora
#1889 by kallewoof was closed Jul 2, 2024
4 tasks
1
6
you cannot fine-tune quantized model with torch.compile
#1886 by fengyunflya was closed Jun 25, 2024
2
Add MoSLoRA
#1878 by wutaiqiang was closed Jun 24, 2024
4
just import of peft leads to cuda context initialization
#1877 by PhyscalX was closed Jun 26, 2024
1
1
VeRA doesn't work with lower-precision models
#1872 by 51616 was closed Jun 19, 2024
2 of 4 tasks
1
4
FEAT: LoRA: Possibility to dynamically register layers to dispatch
#1867 by BenjaminBossan was closed Jun 25, 2024
1
Is merge_and_unload() an awq model and its peft qlora adapter available now?
#1853 by cywuuuu was closed Jun 14, 2024
2 of 4 tasks
3
Conv1D not supported using AdaLora
#1846 by bukun46 was closed Jun 14, 2024
2 of 4 tasks
5
device_map not work
#1840 by bxrjmfh was closed Jun 10, 2024
2 of 4 tasks
2
Different results when merging LORA weights into the base model vs. when not
#1836 by ankur6ue was closed Jun 25, 2024
1 of 4 tasks
9
A Question about new PEFT methods on FSDP
#1834 by Abhrant was closed Jun 7, 2024
4
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument mat2 in method wrapper_CUDA_mm)
#1831 by kevalshah90 was closed Jun 11, 2024
4 tasks
9
How to change to PEFT model dynamically?
#1829 by whr819987540 was closed Jun 6, 2024
4
Some issues with attributes on custom models
#1827 by BenjaminBossan was closed Jun 7, 2024
4 tasks
1
I met a problem when I use torch=2.0.0, I can't use loftq config in loraConfig
#1825 by LiManyuan663 was closed Jun 10, 2024
13
Fix PeftMixedModel example
#1824 by ringohoffman was closed Jun 12, 2024
1
2
Support for different layer shapes for VeRA
#1816 by dkopi was closed Jun 10, 2024
QLoRA perfomance degradation after loading with PeftModel.from_pretrained
#1815 by vanerk03 was closed Jun 3, 2024
4
AdaLora: rank remains constant (to init_r value) across training
#1801 by geoffvdr was closed Jul 3, 2024
2 of 4 tasks
4
LoRA Adapter from local model are leading to error
#1800 by philschmid was closed May 24, 2024
2 of 4 tasks
1
High loss when init with AdaLora
#1798 by zwhe99 was closed Jun 25, 2024
2 of 4 tasks
1
4
ImportError with pkg_resources and packaging in PEFT when using setuptools >= 70.0.0
#1795 by juancopi81 was closed May 23, 2024
4 tasks
2
ProTip! Type g i on any issue or pull request to go back to the issue listing page.