Open RayLam2022 opened 1 year ago
This issue may be useful to you 😃
Thanks,I have modified several modules related to AutoTokenizer based on this method, such as model_worker.py and so on. It is much faster to read the model and display in the gradio interface, but it seems my problem is not solved yet. I am going to show the figure as below. It keeps failed to be entered.
Who can help me solve the above problem?When I entered the gradio interface.It's always in the loading state, as shown in the screenshot above,and I can't type anything
The Chatbot and Parameters in the gradio interface are not displayed. After changing the web_server.py, the relevant vision setting in script must be set to True before it can be displayed. However, after being displayed, the inputs of chatbot, parameters, and prompt remain in a loading state for a long time. As a result, the gradio interface cannot be used. How can this be solved?