Skip to content

Update openai_api.py #484

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Update openai_api.py #484

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions openai_api.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -135,7 +135,7 @@ async def predict(query: str, history: List[List[str]], model_id: str):
finish_reason=None
)
chunk = ChatCompletionResponse(model=model_id, choices=[choice_data], object="chat.completion.chunk")
yield "{}".format(chunk.json(exclude_unset=True, ensure_ascii=False))
yield "{}".format(chunk.model_dump_json(exclude_unset=True,exclude_none=True))

current_length = 0

Expand All @@ -152,7 +152,7 @@ async def predict(query: str, history: List[List[str]], model_id: str):
finish_reason=None
)
chunk = ChatCompletionResponse(model=model_id, choices=[choice_data], object="chat.completion.chunk")
yield "{}".format(chunk.json(exclude_unset=True, ensure_ascii=False))
yield "{}".format(chunk.model_dump_json(exclude_unset=True,exclude_none=True))


choice_data = ChatCompletionResponseStreamChoice(
Expand All @@ -161,14 +161,14 @@ async def predict(query: str, history: List[List[str]], model_id: str):
finish_reason="stop"
)
chunk = ChatCompletionResponse(model=model_id, choices=[choice_data], object="chat.completion.chunk")
yield "{}".format(chunk.json(exclude_unset=True, ensure_ascii=False))
yield "{}".format(chunk.model_dump_json(exclude_unset=True,exclude_none=True))
yield '[DONE]'



if __name__ == "__main__":
tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True)
model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).cuda()
tokenizer = AutoTokenizer.from_pretrained("chatglm2-6b", trust_remote_code=True)
model = AutoModel.from_pretrained("chatglm2-6b", trust_remote_code=True).cuda()
# 多显卡支持，使用下面两行代替上面一行，将num_gpus改为你实际的显卡数量
# from utils import load_model_on_gpus
# model = load_model_on_gpus("THUDM/chatglm2-6b", num_gpus=2)
Expand Down