phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

Folder restructure for evals/datasets/scoring (#419)

Browse source 
* rename evals related stuff

* fix datasetio

* fix scoring test

* localfs -> LocalFS

* refactor scoring

* refactor scoring

* remove 8b_correctness scoring_fn from tests

* tests w/ eval params

* scoring fn braintrust fixture

* import
This commit is contained in:
Xi Yan 2024-11-11 17:35:40 -05:00 • committed by GitHub
parent 2b7d70ba86
commit b4416b72fd
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
37 changed files with 141 additions and 100 deletions
Download patch file Download diff file Expand all files Collapse all files

14
llama_stack/providers/tests/scoring/conftest.py
View file

@ -16,7 +16,7 @@ DEFAULT_PROVIDER_COMBINATIONS = [
pytest.param(
{
"scoring": "meta_reference",
"datasetio": "meta_reference",
"datasetio": "localfs",
"inference": "fireworks",
},
id="meta_reference_scoring_fireworks_inference",
@ -25,12 +25,21 @@ DEFAULT_PROVIDER_COMBINATIONS = [
pytest.param(
{
"scoring": "meta_reference",
"datasetio": "meta_reference",
"datasetio": "localfs",
"inference": "together",
},
id="meta_reference_scoring_together_inference",
marks=pytest.mark.meta_reference_scoring_together_inference,
),
pytest.param(
{
"scoring": "braintrust",
"datasetio": "localfs",
"inference": "together",
},
id="braintrust_scoring_together_inference",
marks=pytest.mark.braintrust_scoring_together_inference,
),
]
@ -38,6 +47,7 @@ def pytest_configure(config):
for fixture_name in [
"meta_reference_scoring_fireworks_inference",
"meta_reference_scoring_together_inference",
"braintrust_scoring_together_inference",
]:
config.addinivalue_line(
"markers",