phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-18 03:07:16 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

reduce the accuracy requirements to pass the chat completion structured output test

Browse source
This commit is contained in:
Matthew Farrellee 2024-11-25 10:22:33 -05:00
parent 34be07e0df
commit 107cd20e2b
1 changed files with 9 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/providers/tests/inference/test_text_inference.py
View file

@ -211,7 +211,15 @@ class TestInference:
response = await inference_impl.chat_completion( response = await inference_impl.chat_completion(
model_id=inference_model, model_id=inference_model,
messages=[ messages=[
SystemMessage(content="You are a helpful assistant."), # we include context about Michael Jordan in the prompt so that the test is
# focused on the funtionality of the model and not on the information embedded
# in the model. Llama 3.2 3B Instruct tends to think MJ played for 14 seasons.
SystemMessage(
content=(
"You are a helpful assistant.\n\n"
"Michael Jordan was born in 1963. He played basketball for the Chicago Bulls for 15 seasons."
)
),
UserMessage(content="Please give me information about Michael Jordan."), UserMessage(content="Please give me information about Michael Jordan."),
], ],
stream=False, stream=False,