phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-06 03:52:17 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

regen pre-commit hooks

Browse source
This commit is contained in:
Yang Yang 2025-03-19 15:04:35 -07:00
parent d4df61e47a
commit 2a5374dbe3
2 changed files with 40 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

20
llama_stack/templates/open-benchmark/run.yaml
View file

@ -247,6 +247,16 @@ benchmarks:
- basic::regex_parser_multiple_choice_answer
metadata: {}
benchmark_id: meta-reference-gpqa-cot
- dataset_id: gpqa_cot_diamond
scoring_functions:
- basic::regex_parser_multiple_choice_answer
metadata: {}
benchmark_id: meta-reference-gpqa-cot-diamond
- dataset_id: gpqa
scoring_functions:
- basic::regex_parser_multiple_choice_answer
metadata: {}
benchmark_id: meta-reference-gpqa
- dataset_id: math_500
scoring_functions:
- basic::regex_parser_math_response
@ -262,6 +272,11 @@ benchmarks:
- basic::docvqa
metadata: {}
benchmark_id: meta-reference-docvqa
- dataset_id: MMMU
scoring_functions:
- basic::regex_parser_multiple_choice_answer
metadata: {}
benchmark_id: meta-reference-MMMU
- dataset_id: MMMU_Pro_standard
scoring_functions:
- basic::regex_parser_multiple_choice_answer
@ -272,6 +287,11 @@ benchmarks:
- basic::regex_parser_multiple_choice_answer
metadata: {}
benchmark_id: meta-reference-MMMU_Pro_vision
- dataset_id: ai2d
scoring_functions:
- basic::regex_parser_multiple_choice_answer
metadata: {}
benchmark_id: meta-reference-ai2d
tool_groups:
- toolgroup_id: builtin::websearch
provider_id: tavily-search