humbleyll

Results 3 comments of humbleyll

@hiyouga 哈喽作者大人,可以关注一下这个问题吗?

I encountered the same problem. The root cause is that the chat_template of Qwen2-VL and Qwen2-VL-Instruct is different, which causes the input_ids to be empty before inference. So the solution...

> > I encountered the same problem. The root cause is that the chat_template of Qwen2-VL and Qwen2-VL-Instruct is different, which causes the input_ids to be empty before inference. So...