Skip to content

Issues: luogen1996/LaVIN

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

29 Open 12 Closed
29 Open 12 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

COCO Caption
#43 opened Jun 3, 2024 by liangyi-qianwan
Any suggestions to reduce the training epochs? like tuning lr or something else?
#42 opened Apr 27, 2024 by baiyuting
Where to get 15-eph-pretrain.pth to run the demo?
#41 opened Jan 20, 2024 by YatingPan
1
lavin-7B结果达不到，两次结果差别很大，一样的代码
#40 opened Jan 7, 2024 by yanghu819
8
License
#39 opened Jan 2, 2024 by RobertBiehl
提供一个用于 mme 评估的 shell 脚本？
#38 opened Dec 17, 2023 by baiyuting
3090 24G
#37 opened Dec 12, 2023 by hsb1995
Regarding the tokenizer.model in /data/weights dir
#36 opened Nov 22, 2023 by wanboyang
1
I would like to execute "gradio_client" reference
#35 opened Nov 15, 2023 by choibigo
why starting the "input" in base_prompt.py with two "\n"
#34 opened Nov 14, 2023 by moured
1
when eval the same checkpoint, different batch size get different result, how to handle this problem?
#33 opened Nov 13, 2023 by baiyuting
Gradient Is Not Accumulated?
#32 opened Oct 31, 2023 by HenryPengZou
1
vicuna 7b 版本怎么选择？
#31 opened Oct 31, 2023 by baiyuting
Do you support llama2 now？
#30 opened Oct 14, 2023 by hangzeli05
2
About the 4bit quantification
#29 opened Sep 26, 2023 by Pefect96
1
关于repAdapter_Router 代码的疑问
#28 opened Sep 25, 2023 by verigle
2
Beginner cuestion
#27 opened Sep 15, 2023 by mauridev777
1
目前7B单卡精度略低于论文值，请问可能的原因
#25 opened Sep 6, 2023 by verigle
2
A sample docker and update for requirments.txt
#23 opened Aug 28, 2023 by yzbx
How to continue fine-tuning training on the basis of your pre training fine-tuning nodes【LaVIN-7B】or 【LaVIN-13B】
#22 opened Aug 27, 2023 by hangzeli08
2
Questions about training related to NCCL
#21 opened Aug 23, 2023 by air-tea
3
Figure 2 questions about Adapter
#19 opened Aug 1, 2023 by HYUNMIN-HWANG
[BUG] when NaN loss encountered->zeroDivisionError: float division by zero
#18 opened Jul 24, 2023 by verigle
1
Incorrect path used to load tokenizer in eval.py
#17 opened Jul 19, 2023 by angelala3252
Demo可以在24G的显卡上运行吗，爆显存了
#14 opened Jul 9, 2023 by wooozihui
1
ProTip! Exclude everything labeled bug with -label:bug.