Skip to content
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.

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

Instruction follow ability is weak #68

Open
lmx760581375 opened this issue Jun 21, 2024 · 7 comments
Open

Instruction follow ability is weak #68

lmx760581375 opened this issue Jun 21, 2024 · 7 comments

Comments

@lmx760581375
Copy link

I deployed playground on 8 v100's and I found that even with 34b models, there were issues with not following instructions, duplicate generation, etc.
微信截图_72e3b4f5-c34b-4c7c-abcb-b821715d100e

@1028686314
Copy link

hello 我也遇到了类似的问题 请问你解决了吗

@lmx760581375
Copy link
Author

hello 我也遇到了类似的问题 请问你解决了吗

貌似使用其他版本的chat template 能改善,但我还是很疑惑,目前这些问题貌似是训练得有问题导致的。

据我使用下来,整体的能力还是偏弱的,甚至可能模型的大部分能力还是来自 llava

@1028686314
Copy link

你有测下来比较强的视频理解模型嘛 感觉开源的效果测下来都比较一般啊 我现在想选个架构自己再训一训 大佬有没有什么建议 我们可以交流下

@lmx760581375
Copy link
Author

你有测下来比较强的视频理解模型嘛 感觉开源的效果测下来都比较一般啊 我现在想选个架构自己再训一训 大佬有没有什么建议 我们可以交流下

效果都挺一般的,可以交流下,我也主要在关注视频这块

@1028686314
Copy link

我应该怎么联系你 留个wx吧~

@lmx760581375
Copy link
Author

我应该怎么联系你 留个wx吧~

邮箱:lmingxiao3@gmail.com

@1028686314
Copy link

1028686314 commented Jul 1, 2024

1

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants