phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-03 09:02:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refine

Browse source
This commit is contained in:
Botao Chen 2025-03-19 14:38:14 -07:00
parent 9068416bc4
commit c4c56829ad
5 changed files with 15 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

9
llama_stack/templates/open-benchmark/open_benchmark.py
View file

@ -204,8 +204,7 @@ def get_distribution_template() -> DistributionTemplate:
),
),
DatasetInput(
dataset_id="IfEval",
provider_id="huggingface",
dataset_id="ifeval",
purpose=DatasetPurpose.eval_messages_answer,
source=URIDataSource(
uri="huggingface://datasets/llamastack/IfEval?split=train",
@ -240,9 +239,9 @@ def get_distribution_template() -> DistributionTemplate:
scoring_functions=["basic::bfcl"],
),
BenchmarkInput(
benchmark_id="meta-reference-IfEval",
dataset_id="IfEval",
scoring_functions=["basic::IfEval"],
benchmark_id="meta-reference-ifeval",
dataset_id="ifeval",
scoring_functions=["basic::ifeval"],
),
]
return DistributionTemplate(

8
llama_stack/templates/open-benchmark/run.yaml
View file

@ -193,7 +193,7 @@ datasets:
type: uri
uri: huggingface://datasets/llamastack/IfEval?split=train
metadata: {}
dataset_id: IfEval
dataset_id: ifeval
scoring_fns: []
benchmarks:
- dataset_id: simpleqa
@ -221,11 +221,11 @@ benchmarks:
- basic::bfcl
metadata: {}
benchmark_id: meta-reference-bfcl
- dataset_id: IfEval
- dataset_id: ifeval
scoring_functions:
- basic::IfEval
- basic::ifeval
metadata: {}
benchmark_id: meta-reference-IfEval
benchmark_id: meta-reference-ifeval
tool_groups:
- toolgroup_id: builtin::websearch
provider_id: tavily-search