[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 932 Closed
0 Open 932 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

Confusion about model.save_pretrained("output_dir")
#452 by Air-Spring was closed Jun 27, 2023
3
can peft be compatible with pytorch1.12?
#454 by hjc3613 was closed Jun 24, 2023
1
LLaMA Adapter Fails during the inference due to mixed precision weights.
#455 by HamidShojanazeri was closed Jun 1, 2023
1
4
is accelerate integrated into peft model inference?
#469 by Emerald01 was closed Jun 26, 2023
1
AutoTokenizer bug when using LlamaTokenizer
#714 by sidnb13 was closed Aug 25, 2023
1 of 2 tasks
1
Bug when pass subfolder parameter in peftmodel.load_adapter method!
#718 by ShayDuane was closed Jul 19, 2023
2 of 4 tasks
1
1
The loss of prefix-tuning cannot decrease
#710 by shuaizhao95 was closed Aug 23, 2023
4 tasks
1
Inference on multiple GPUs with LoRA weights raises device-side assert triggered CUDA error
#709 by changyeli was closed Aug 31, 2023
2 of 4 tasks
2
doing qlora finetune with deepspeed
#671 by Nisoka was closed Aug 14, 2023
2
Export finetuned PEFT / LoRA model to ONNX
#670 by ingo-m was closed Jul 9, 2023
2 of 4 tasks
4
Prototype LoRA/Adapter/Prefix-tuning support - Arxiv PRs welcome to address this contributions are welcome from community members on this issue
#648 by he20010515 was closed Aug 9, 2023
2
High memory consumption during LORA training
#658 by DanielRoeder1 was closed Aug 9, 2023
2 of 4 tasks
7
whisper-peft model to onnx
#660 by marziye-A was closed Aug 9, 2023
2
Is it necessary to provide target_modules in LoraConfig?
#659 by siddhsql was closed Aug 2, 2023
2
Add ability to save only selected adapters
#699 by crowsonkb was closed Jul 14, 2023
1
@younesbelkada
1
Calling merge_and_unload then save_pretrained uploads weights twice
#692 by fozziethebeat was closed Aug 20, 2023
1 of 4 tasks
7
Question about lora_A weight when using GPT2
#706 by jungwhank was closed Aug 21, 2023
1
failed in saving offload PeftModel
#704 by iumyx2612 was closed Aug 21, 2023
2 of 4 tasks
1
LoRA + gradient_accumulation_steps > 1 does not work
#619 by dardodel was closed Aug 16, 2023
3
P-tuning (GPT Understands, too) solved solved
#627 by MichelleHS777 was closed Aug 4, 2023
2 of 4 tasks
2
tuning “shallow encoder and deep decoder” model
#689 by Zz-dong was closed Aug 20, 2023
2 of 4 tasks
1
Matrix mistmatch when trying to adapt Falcon with QLoRA, how to fix?
#685 by brando90 was closed Jul 22, 2023
2 of 4 tasks
7
Add dense layers to TRANSFORMERS_MODELS_TO_LORA_TARGET_MODULES_MAPPING
#735 by BramVanroy was closed Aug 27, 2023
2
AdaLoRa doesn't work with Embedding layer
#529 by avostryakov was closed Jul 11, 2023
1
model does not appear to have a file named config.json
#523 by banank1989 was closed Oct 13, 2023
14
ProTip! Updated in the last three days: updated:>2024-07-06.