Skip to content

Issues: horseee/LLM-Pruner

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

35 Open 22 Closed
35 Open 22 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

No random seed Settings found in post_training.py
#59 opened May 12, 2024 by JunKong5
Evaluation：UnicodeDecodeError: 'utf-8' codec can't decode byte 0x8b in position 1: invalid start byte
#58 opened Apr 28, 2024 by manlenzzz
Pruning llama3
#57 opened Apr 21, 2024 by yinwangsong
I tired Mistral 7b model, but I got this issue
#56 opened Apr 11, 2024 by TejasLidhure
How to prune the embedding and lm_head?
#55 opened Mar 26, 2024 by L-hongbin
Is this method implementable on multi-GPUs?
#54 opened Mar 14, 2024 by LeonCheng0129
RecursionError: maximum recursion depth exceeded
#53 opened Mar 13, 2024 by Zhenyu001225
1
Unable to reproduce the results for param_first and param_second in the paper after finetuning.
#52 opened Feb 12, 2024 by danyal97
The quantization of the compressed models
#49 opened Jan 14, 2024 by lihuang258
Cannot use huggface to load
#46 opened Dec 27, 2023 by coderchem
401 Client Error: Unauthorized for url: https://huggingface.co/decapoda-research/llama-7b-hf/resolve/main/tokenizer_config.json
#43 opened Dec 19, 2023 by azuryl
1
Adding a tutorial for adapting new models?
#42 opened Dec 1, 2023 by zhichaoxu-shufe
在将部分层进行剪枝之后，不能直接通过tgi加载模型
#41 opened Dec 1, 2023 by coderchem
Pruning MQA?
#40 opened Nov 30, 2023 by jianyuheng
Question related to the model tuning
#39 opened Nov 29, 2023 by shawnricecake
2
为什么num_examples默认是10？
#38 opened Nov 27, 2023 by coderchem
2
the new pytorch.bin is bigger than original model issue
#37 opened Nov 18, 2023 by lb553024300
4
Supporting device_map = 'auto' similar to the one in .from_pretrained method from Huggingface
#36 opened Nov 16, 2023 by Ahmed-Roushdy
3
a post-training issue
#35 opened Nov 16, 2023 by cmnfriend
2
Reproducing paper results
#34 opened Nov 13, 2023 by grigorn
6
Examples on the Huggingface Hub
#31 opened Oct 20, 2023 by vgoklani
When will you support ChatGLM?
#30 opened Oct 12, 2023 by AboveParadise
Force even pruning across layers
#29 opened Oct 5, 2023 by thedarkzeno
1
param_first and param_mix result the same ppl
#23 opened Sep 1, 2023 by Kausal-Lei
1
I encountered the following error message when I assign iterative_steps = 2 during baichuan-7B pruning bug Something isn't working
#21 opened Aug 18, 2023 by yangd85
1
ProTip! Updated in the last three days: updated:>2024-05-08.