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

mmlu loose

Browse source
This commit is contained in:
Xi Yan 2024-11-07 18:36:41 -08:00
parent 6ee02ca23b
commit edeb6dcf04
4 changed files with 46 additions and 59 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/inline/meta_reference/eval/eval.py
View file

@ -54,7 +54,7 @@ class MetaReferenceEvalImpl(Eval, EvalTasksProtocolPrivate):
benchmark_tasks = [
EvalTaskDef(
identifier="meta-reference-mmlu",
dataset_id="llamastack_mmlu",
dataset_id="llamastack_mmlu_loose",
scoring_functions=[
"meta-reference::regex_parser_multiple_choice_answer"
],