423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-23 22:32:54 +08:00
Code Issues Packages Projects Releases Wiki Activity

”add stop parameter in chat.py“

Browse Source 
Former-commit-id: 80645751bc4db20dbadb53950fe35af8b67eec41
This commit is contained in:
zhaonx96 2024-05-06 10:10:00 +08:00
parent 0c6c50f9b5
commit 189346188b
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/llmtuner/api/chat.py
View File

@ -103,6 +103,7 @@ async def create_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,
num_return_sequences=request.n, num_return_sequences=request.n,
stop=request.stop
) )
prompt_length, response_length = 0, 0 prompt_length, response_length = 0, 0
@ -155,6 +156,7 @@ async def create_stream_chat_completion_response(
temperature=request.temperature, temperature=request.temperature,
top_p=request.top_p, top_p=request.top_p,
max_new_tokens=request.max_tokens, max_new_tokens=request.max_tokens,
stop=request.stop
): ):
if len(new_token) != 0: if len(new_token) != 0:
yield _create_stream_chat_completion_chunk( yield _create_stream_chat_completion_chunk(