Skip to content

Issues: yxli2123/LoftQ

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

18 Open 19 Closed
18 Open 19 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
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 change rank when training glue？
#38 opened Aug 20, 2024 by Rain-yj
When running the train_clm code, there is an explosion in learning rate in the third epoch
#37 opened Aug 20, 2024 by Rain-yj
Identical GPU memory usage and Fine-Tuning time for 2-bit and 4-bit quantized Llama-2-7b-hf model
#36 opened Aug 17, 2024 by zhuzhuxia1221
Number of iterations seems always set to 1 based on latest code
#34 opened Jul 4, 2024 by au-revoir
About the test result on gsm8k
#33 opened Jun 7, 2024 by lucasliunju
Embedding layer
#31 opened May 26, 2024 by ShayekhBinIslam
1
Method fails on Gemma-7B model
#30 opened May 15, 2024 by Ther-nullptr
1
Error with shape
#27 opened Apr 21, 2024 by manlenzzz
2
Why are base weights on HF LoftQ models in 16-bit?
#26 opened Apr 17, 2024 by RonanKMcGovern
2
Performance worsens versus QLoRA with TinyLlama
#25 opened Apr 15, 2024 by RonanKMcGovern
Failing to converge when using some random seeds
#24 opened Apr 13, 2024 by Car-pe
2
Is there any way for using LoftQ to GPTQ or AWQ model?
#18 opened Mar 7, 2024 by LameloBally
2
loftQ can not use multi gpu to train
#17 opened Feb 4, 2024 by WanBenLe
9
Does it support Mixtral 8x7B？
#15 opened Jan 14, 2024 by iMountTai
1
Can we use LoftQ to optimize vision foundation models like OWL-ViT v2 and Grounding Dino?
#13 opened Dec 26, 2023 by solomonmanuelraj
1
How to execute uniform quantization instead of NF4 quantization?
#12 opened Dec 26, 2023 by LuletterSoul
4
how to train with 2bit quantization model?
#10 opened Dec 15, 2023 by duany049
6
try to run quantize.py but get error CUDA out of memory
#2 opened Nov 13, 2023 by ysanimals
6
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.