QwenLM/Qwen2.5-Coder

the chat template `qwen2_5` corresponding to the model `qwen2_5-coder-32b-instruct-awq` is in chat format. Please use the `chat.completions` API.

Closed this issue · 2 comments

gitYuZui commented

部署方式

ms-swift + vllm 方式部署

错误说明：

我从/v1/chat/completions的方式调用进来是正常的。但是从 /v1/completions方式调用，接口会报错：the chat template qwen2_5 corresponding to the model qwen2_5-coder-32b-instruct-awq is in chat format. Please use the chat.completions API.
image
image

问题：

1、这是因为这个模型不支持completions方式调用吗？
2、如何解决？
3、有没有更好的方式去适配 continue插件？

cyente commented

please give us some time to check it out

cyente commented

Hi, the completions format is still under development. Please check back in a few days and stay tuned for MS-swift announcement