phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-16 06:53:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor scoring

Browse source
This commit is contained in:
Xi Yan 2024-11-11 15:48:07 -05:00
parent aa66410f24
commit a6038ffee9
9 changed files with 50 additions and 51 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/tests/scoring/test_scoring.py
View file

@ -61,9 +61,9 @@ class TestScoring:
assert len(rows.rows) == 3
scoring_functions = {
"meta-reference::llm_as_judge_8b_correctness": None,
"meta-reference::equality": None,
}
response = await scoring_impl.score(
input_rows=rows.rows,
scoring_functions=scoring_functions,
@ -116,7 +116,7 @@ class TestScoring:
assert len(rows.rows) == 3
scoring_functions = {
"meta-reference::llm_as_judge_8b_correctness": LLMAsJudgeScoringFnParams(
"meta-reference::llm_as_judge_base": LLMAsJudgeScoringFnParams(
judge_model="Llama3.1-405B-Instruct",
prompt_template="Output a number response in the following format: Score: <number>, where <number> is the number between 0 and 9.",
judge_score_regexes=[r"Score: (\d+)"],