qftie
qftie
 您好,从代码看好像不能同时设定emotion_prediction='True' 和speaker_task='True',实际使用时也会报错找不到data目录。
I would like to ask if your ERC model would use the dialogue information after the target utterance when recognizing the emotion of a utterance.
I am currently deploying the model and exposing a callable OpenAI API. I am modifying model.ts to fit my own model, but I'm experiencing instability when using mpt-30b-chat and mpt-30b-instruct....
During the streaming output process, does FastChat consider stopping the token output after the frontend disconnects using `AbortController` ? If so, could you please let me know where the code...