majijia505

Results 5 issues of majijia505

![image](https://github.com/THUDM/VisualGLM-6B/assets/14145007/8b43d370-1b24-4a7a-829d-1ec0f5ac4cf6)

使用Qwen1.5-14B-int8-Chat进行微调,完成后不释放显存 需要kill train_web才可以 使用加载模型功能,卸载模型后,也不释放显存 LLama_factory版本0.5.0和0.5.3都存在该问题 ![image](https://github.com/hiyouga/LLaMA-Factory/assets/14145007/e61abe42-af42-41c8-8c8d-d7653a499fb9) ![image](https://github.com/hiyouga/LLaMA-Factory/assets/14145007/440446b4-99cb-4360-b65c-0ac3683fbb7f) 但是使用chatglm3或者Qwen-7b就没这个问题

pending

### 是否已有关于该错误的issue或讨论? | Is there an existing issue / discussion for this? - [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions ### 该问题是否在FAQ中有解答? | Is there an...

Notice: In order to resolve issues more efficiently, please raise issue following the template. (注意:为了更加高效率解决您遇到的问题,请按照模板提问,补充细节) ## ❓ Questions and Help 使用容器镜像启动funASR服务后使用客户端无法调用成功,提示vad_handle is null 后台服务启动日志如下: root@ea758f46b6b5:/workspace/FunASR/runtime# bash run_server_2pass.sh \ > --download-model-dir...

question

Notice: In order to resolve issues more efficiently, please raise issue following the template. (注意:为了更加高效率解决您遇到的问题,请按照模板提问,补充细节) ## ❓ Questions and Help ### Before asking: 1. search the issues. 2. search the...

question