phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-31 16:01:46 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

remove 8b_correctness scoring_fn from tests

Browse source
This commit is contained in:
Xi Yan 2024-11-11 15:55:09 -05:00
parent b1ebc837f8
commit f8f95dad1f
1 changed files with 0 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/tests/eval/test_eval.py
View file

@ -65,7 +65,6 @@ class Testeval:
assert len(rows.rows) == 3 assert len(rows.rows) == 3
scoring_functions = [ scoring_functions = [
"meta-reference::llm_as_judge_8b_correctness",
"meta-reference::equality", "meta-reference::equality",
] ]
task_id = "meta-reference::app_eval" task_id = "meta-reference::app_eval"
@ -88,7 +87,6 @@ class Testeval:
), ),
) )
assert len(response.generations) == 3 assert len(response.generations) == 3
assert "meta-reference::llm_as_judge_8b_correctness" in response.scores
assert "meta-reference::equality" in response.scores assert "meta-reference::equality" in response.scores
@pytest.mark.asyncio @pytest.mark.asyncio
@ -109,7 +107,6 @@ class Testeval:
) )
scoring_functions = [ scoring_functions = [
"meta-reference::llm_as_judge_8b_correctness",
"meta-reference::subset_of", "meta-reference::subset_of",
] ]
@ -138,7 +135,6 @@ class Testeval:
assert eval_response is not None assert eval_response is not None
assert len(eval_response.generations) == 5 assert len(eval_response.generations) == 5
assert "meta-reference::subset_of" in eval_response.scores assert "meta-reference::subset_of" in eval_response.scores
assert "meta-reference::llm_as_judge_8b_correctness" in eval_response.scores
@pytest.mark.asyncio @pytest.mark.asyncio
async def test_eval_run_benchmark_eval(self, eval_stack): async def test_eval_run_benchmark_eval(self, eval_stack):