biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Misc][OpenAI] deprecate max_tokens in favor of new max_completion_tokens field for chat completion endpoint (#9837)

Browse Source
This commit is contained in:
Guillaume Calmettes
2024-10-31 02:15:56 +01:00
committed by GitHub
parent 64384bbcdf
commit abbfb6134d
14 changed files with 140 additions and 118 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tests/tool_use/test_parallel_tool_calls.py
View File

@@ -26,7 +26,7 @@ async def test_parallel_tool_calls(client: openai.AsyncOpenAI,
chat_completion = await client.chat.completions.create(
messages=MESSAGES_ASKING_FOR_PARALLEL_TOOLS,
temperature=0,
max_tokens=200,
max_completion_tokens=200,
model=model_name,
tools=[WEATHER_TOOL, SEARCH_TOOL],
logprobs=False)
@@ -63,7 +63,7 @@ async def test_parallel_tool_calls(client: openai.AsyncOpenAI,
model=model_name,
messages=MESSAGES_ASKING_FOR_PARALLEL_TOOLS,
temperature=0,
max_tokens=200,
max_completion_tokens=200,
tools=[WEATHER_TOOL, SEARCH_TOOL],
logprobs=False,
stream=True)
@@ -154,7 +154,7 @@ async def test_parallel_tool_calls_with_results(client: openai.AsyncOpenAI,
chat_completion = await client.chat.completions.create(
messages=MESSAGES_WITH_PARALLEL_TOOL_RESPONSE,
temperature=0,
max_tokens=200,
max_completion_tokens=200,
model=model_name,
tools=[WEATHER_TOOL, SEARCH_TOOL],
logprobs=False)
@@ -172,7 +172,7 @@ async def test_parallel_tool_calls_with_results(client: openai.AsyncOpenAI,
stream = await client.chat.completions.create(
messages=MESSAGES_WITH_PARALLEL_TOOL_RESPONSE,
temperature=0,
max_tokens=200,
max_completion_tokens=200,
model=model_name,
tools=[WEATHER_TOOL, SEARCH_TOOL],
logprobs=False,