qwen1.5-7b-chat是不是推理起来比qwen1.5-7b快很多

#9
by endNone - opened

跑fastchat/mtbench的时候,我发现qwen1.5-7b-chat花费的时间是qwen1.5-7b不到一半,是官方对qwen1.5-7b-chat做了什么加速处理吗

Qwen org

There are no difference in code. But since MTBench is for evaluating chat models, my guess it that the base model qwen1.5-7b generated overly long responses and thus cost more time.

I have compared the length of the generated dialogues, and the chat model produces longer ones.

This comment has been hidden
JustinLin610 changed discussion status to closed

Sign up or log in to comment