ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Optimize the handling of QWEN2 in scenarios involving multiple tool calls.

Browse Source 
Former-commit-id: 48f870edc96ada40360f7e6e67cbf58805295b33
This commit is contained in:
mMrBun
2024-06-10 02:00:14 +08:00
parent 44829df762
commit bc04ca464a
2 changed files with 28 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
src/llamafactory/api/chat.py
View File

@@ -150,11 +150,14 @@ async def create_chat_completion_response(
else:
result = response.response_text
if isinstance(result, tuple):
name, arguments = result
function = Function(name=name, arguments=arguments)
tool_call = FunctionCall(id="call_{}".format(uuid.uuid4().hex), function=function)
response_message = ChatCompletionMessage(role=Role.ASSISTANT, tool_calls=[tool_call])
if isinstance(result, list):
tool_calls = []
for tool in result:
name, arguments = tool
function = Function(name=name, arguments=arguments)
tool_call = FunctionCall(id="call_{}".format(uuid.uuid4().hex), function=function)
tool_calls.append(tool_call)
response_message = ChatCompletionMessage(role=Role.ASSISTANT, tool_calls=tool_calls)
finish_reason = Finish.TOOL
else:
response_message = ChatCompletionMessage(role=Role.ASSISTANT, content=result)