423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-15 03:10:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

remove empty stream response

Browse Source
This commit is contained in:
hiyouga
2024-05-04 16:13:52 +08:00
parent 941924fdbd
commit e984ba3167
1 changed files with 4 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
src/llmtuner/api/chat.py
View File

@@ -156,9 +156,10 @@ async def create_stream_chat_completion_response(
top_p=request.top_p, top_p=request.top_p,
max_new_tokens=request.max_tokens, max_new_tokens=request.max_tokens,
): ):
yield _create_stream_chat_completion_chunk( if len(new_token) != 0:
completion_id=completion_id, model=request.model, delta=ChatCompletionMessage(content=new_token) yield _create_stream_chat_completion_chunk(
) completion_id=completion_id, model=request.model, delta=ChatCompletionMessage(content=new_token)
)
yield _create_stream_chat_completion_chunk( yield _create_stream_chat_completion_chunk(
completion_id=completion_id, model=request.model, delta=ChatCompletionMessage(), finish_reason=Finish.STOP completion_id=completion_id, model=request.model, delta=ChatCompletionMessage(), finish_reason=Finish.STOP