Closed code-ex0 closed 1 year ago
It seems you forgot about this part:
Replace /path/to/weights below with the a real path to a local model such as Vicuna. It can also be a Hugging Face repo id such as lmsys/fastchat-t5-3b-v1.0.
i use this python -m fastchat.serve.model_worker --model-names "gpt-3.5-turbo,text-davinci-003,text-embedding-ada-002" --model-path lmsys/fastchat-t5-3b-v1.0
i dont forgot the model path
mybe you should check your FastChat/fastchat/serve/model_worker.py
file. serch "--model-names" in this file?
the parameter is called --model-name
. this is a small bug in the example. you can check the parameters with python3 -m fastchat.serve.model_worker --help
Ok I find error if I install fschat 0.2.13 he solves the problems of the doc.
pip install fschat==0.2.13
I want to self how open ai API with fastchat and I see this example but i see a error.
I can use the seconde command
python3 -m fastchat.serve.model_worker --model-names "gpt-3.5-turbo,text-davinci-003,text-embedding-ada-002" --model-path /path/to/weights
the parameter --model-names doesn't exist and I don't know how to replace it.
do you have an idea ??