Junnan Liu

icon company NWPU / BUAA / PJLab / Monash icon location Melbourne icon location Focus on NLP, LLM, Reasoning, Agentic | NWPU / BUAA / PJLab / Monash

Results 3 comments of Junnan Liu

指定gpu运行失败：using GPU 0 to perform barrier as devices used by this process are currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect.

你好，请问解决了吗

[Bug]: 您好，使用vllm部署的Qwen2.5-Math-72B-Instruct和Qwen2.5-Math-7B-Instruct数学模型，为什么评测时模型怎么回答了很多其他乱七八糟的内容，直到达到限制token数才停止？

请问这个有发现这个问题是因为什么吗

[Bug]: 您好，使用vllm部署的Qwen2.5-Math-72B-Instruct和Qwen2.5-Math-7B-Instruct数学模型，为什么评测时模型怎么回答了很多其他乱七八糟的内容，直到达到限制token数才停止？

> 是的，我也有这个问题，7B的模型有时候会在输出回答后再输出一些无关紧要的内容，有时候也只是无限重复原问题，直到token数量上限。 Yes, I have this question either. The 7B model sometimes appends some unrelated content after giving an answer, or it will endlessly repeat the original question until it...