Ziao Wang
Ziao Wang
Same issue encountered!
Same question, how the model make sure that the attention layers capture the global information and the CNN layers capture local information with only one NLL loss? Have you figure...
同样异常 登录不了了
https://github.com/Zy143L/jd_cookie/releases/tag/1.0 用这个本地获取,亲测可用
I also use vllm_server_host for training qwen-vl model, however, it give such error: and the vllm server shows have you met this problem? seems the vllm does not support image...