关于Qwen2.5-coder模型的一点问题

[jsuper]

请问下，能用qwen2.5-coder-32b-instruct模型做对话问答和FIM代码智能补全的两种功能吗？还是说FIM智能补全模式情况下只能使用qwen2.5-coder-32b-base模型呢？

另外，我看官方只发布了qwen2.5-coder-32b-instruct的量化模型，是否有32b-base的官方量化模型呢？

[cyente]

Hi, you can use Qwen2.5-Coder-32B-Instruct in either chat or FIM format.

However, Qwen2.5-Coder-32B-Instruct may perform slightly worse than the base model.

We have not released a quantized version of the 32B base model.

[jsuper]

Hi, you can use Qwen2.5-Coder-32B-Instruct in either chat or FIM format.

However, Qwen2.5-Coder-32B-Instruct may perform slightly worse than the base model.

We have not released a quantized version of the 32B base model.

是的，instruct模型能够做一些补全，但是在FIM上补全上效果没有base模型好，如果不加<|repo_name|>这种说明，只是一个注释的话，会输出一些自然语言的回答结果

[cyente]

may be you can try to use the instruct model while maintaining the same fim structure as the base model, rather than converting to ChatML format.