陈小浩同学

> just a helpful hint. if you paste in an image instead of text it makes it hard for people with this bug to find the solution if it ever...

command: **python -m fastchat.serve.cli --model-path ./model_weights/lmsys/vicuna-7b-delta-v1.1 --load-8bit** error info: OutOfMemoryError: CUDA out of memory. Tried to allocate 86.00 MiB (GPU 0; 6.00 GiB total capacity; 4.01 GiB already allocated; 84.00...

I have re read the document content and it seems that my model needs to be converted, and there is also a problem with my command. I am currently working...

hello, have you resolved the issue? I also have the same problem as you. command：python -m fastchat.serve.model_worker --model-path eachadea/vicuna-13b-1.1 --num-gpus 4 

I have already solved this problem. The problem comes from the model file, please update it;the current state is GPU insufficient to start this;

> > 我已经解决了这个问题。模型文件问题，请更新；当前状态为GPU不足，无法启动； > > @ch930410 > > 你是怎么解决这个问题的？模型文件中应该更改什么？ the model file is original

I also have the same problem and look forward to solving it

hello, you can try node: 16.17.0. My initial version was 18.16.0, but it also reported an error after running. Changing to this one will be successful.

> this is a resource that was not found. Please find this introduction in the code and comment on it.

https://github.com/alphacep/vosk-server/blob/master/client-samples/vue/src/assets/scss/_base.scss#L4 https://github.com/alphacep/vosk-server/blob/master/client-samples/vue/src/assets/scss/_base.scss#L10 Introduction of annotation font files