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

Qwen2和Qwen2.5的代码为什么在output之后加的是pad_token_id而不是eos_token_id,这有什么影响吗? #326

Open
zihao-ai opened this issue Jan 7, 2025 · 4 comments

Comments

@zihao-ai
Copy link

zihao-ai commented Jan 7, 2025

PixPin_2025-01-07_21-49-18

@KMnO4-zx
Copy link
Contributor

KMnO4-zx commented Jan 7, 2025

没有影响,Qwen2.5 的 pad_token_id 和 eos_token_id 是一样的

@HarryTMa
Copy link

没有影响,Qwen2.5 的 pad_token_id 和 eos_token_id 是一样的

您好!经查看发现,Qwen2.5的带instruct的模型的tokenizer的pad_token和eos_token不一样,前者是<|endoftext|>(id为151643),后者是<|im_end|>(id为151645);不带instruct的模型的pad_token和eos_token是一样的,都是<|endoftext|>

@KMnO4-zx
Copy link
Contributor

感谢您的提醒!我们会抓紧修改一下!

@Guncuke
Copy link

Guncuke commented Jan 13, 2025

没有影响,Qwen2.5 的 pad_token_id 和 eos_token_id 是一样的

您好!经查看发现,Qwen2.5的带instruct的模型的tokenizer的pad_token和eos_token不一样,前者是<|endoftext|>(id为151643),后者是<|im_end|>(id为151645);不带instruct的模型的pad_token和eos_token是一样的,都是<|endoftext|>

我觉得应该补一个<|im_end|> 然后后面接<|endoftext|>,不然最后一句用户的im没有闭合

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

4 participants