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

<sft>llama3上下文支持好像有点问题 #422

Open
ghtwf01 opened this issue Apr 27, 2024 · 3 comments
Open

<sft>llama3上下文支持好像有点问题 #422

ghtwf01 opened this issue Apr 27, 2024 · 3 comments
Assignees
Labels

Comments

@ghtwf01
Copy link

ghtwf01 commented Apr 27, 2024

Description

上下文1
上下文2
上下文3

Link

No response

@zzhangpurdue
Copy link
Collaborator

你用的llama3么?是dashscope还是通过openaiapi的?
具体llama3的8b还是70b?

@ghtwf01
Copy link
Author

ghtwf01 commented Apr 28, 2024

你用的llama3么?是dashscope还是通过openaiapi的? 具体llama3的8b还是70b?

我用的modelscope社区微信公众号文章(https://mp.weixin.qq.com/s/IuagQ-S_spbQRyVsJuFIkQ)里面训练好了的llama3-8B-Instruct-Agent模型,用的openaiapi

@zzhangpurdue
Copy link
Collaborator

之前训练的时候遇到过这个问题,我们也有过复现,8b上确实会存在这个问题,是模型能力的问题,我们接下来还会训练一个V2的版本,尽可能的在小模型上去掉这个问题。

@zzhangpurdue zzhangpurdue self-assigned this Apr 29, 2024
@zzhangpurdue zzhangpurdue changed the title 上下文支持好像有点问题 llama3上下文支持好像有点问题 Apr 29, 2024
@zzhangpurdue zzhangpurdue changed the title llama3上下文支持好像有点问题 <sft>llama3上下文支持好像有点问题 Apr 29, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

2 participants