phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-03 20:12:16 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge remote-tracking branch 'origin/main' into if_eval

Browse source
This commit is contained in:
Botao Chen 2025-03-19 12:58:14 -07:00
commit 9068416bc4
18 changed files with 183 additions and 135 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/templates/open-benchmark/run.yaml
View file

@ -164,42 +164,36 @@ datasets:
uri: huggingface://datasets/llamastack/simpleqa?split=train
metadata: {}
dataset_id: simpleqa
provider_id: huggingface
- purpose: eval/messages-answer
source:
type: uri
uri: huggingface://datasets/llamastack/mmlu_cot?split=test&name=all
metadata: {}
dataset_id: mmlu_cot
provider_id: huggingface
- purpose: eval/messages-answer
source:
type: uri
uri: huggingface://datasets/llamastack/gpqa_0shot_cot?split=test&name=gpqa_main
metadata: {}
dataset_id: gpqa_cot
provider_id: huggingface
- purpose: eval/messages-answer
source:
type: uri
uri: huggingface://datasets/llamastack/math_500?split=test
metadata: {}
dataset_id: math_500
provider_id: huggingface
- purpose: eval/messages-answer
source:
type: uri
uri: huggingface://datasets/llamastack/bfcl_v3?split=train
metadata: {}
dataset_id: bfcl
provider_id: huggingface
- purpose: eval/messages-answer
source:
type: uri
uri: huggingface://datasets/llamastack/IfEval?split=train
metadata: {}
dataset_id: IfEval
provider_id: huggingface
scoring_fns: []
benchmarks:
- dataset_id: simpleqa