phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-30 02:54:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into feat/litellm_sambanova_usage

Browse source
This commit is contained in:
Jorge Piedrahita Ortiz 2025-03-19 16:51:59 -05:00 • committed by GitHub
commit 02a4f9ac59
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
69 changed files with 1128 additions and 445 deletions
Download patch file Download diff file Expand all files Collapse all files

5
llama_stack/templates/open-benchmark/open_benchmark.py
View file

@ -170,7 +170,6 @@ def get_distribution_template() -> DistributionTemplate:
default_datasets = [
DatasetInput(
dataset_id="simpleqa",
provider_id="huggingface",
purpose=DatasetPurpose.eval_messages_answer,
source=URIDataSource(
uri="huggingface://datasets/llamastack/simpleqa?split=train",
@ -178,7 +177,6 @@ def get_distribution_template() -> DistributionTemplate:
),
DatasetInput(
dataset_id="mmlu_cot",
provider_id="huggingface",
purpose=DatasetPurpose.eval_messages_answer,
source=URIDataSource(
uri="huggingface://datasets/llamastack/mmlu_cot?split=test&name=all",
@ -186,7 +184,6 @@ def get_distribution_template() -> DistributionTemplate:
),
DatasetInput(
dataset_id="gpqa_cot",
provider_id="huggingface",
purpose=DatasetPurpose.eval_messages_answer,
source=URIDataSource(
uri="huggingface://datasets/llamastack/gpqa_0shot_cot?split=test&name=gpqa_main",
@ -194,7 +191,6 @@ def get_distribution_template() -> DistributionTemplate:
),
DatasetInput(
dataset_id="math_500",
provider_id="huggingface",
purpose=DatasetPurpose.eval_messages_answer,
source=URIDataSource(
uri="huggingface://datasets/llamastack/math_500?split=test",
@ -202,7 +198,6 @@ def get_distribution_template() -> DistributionTemplate:
),
DatasetInput(
dataset_id="bfcl",
provider_id="huggingface",
purpose=DatasetPurpose.eval_messages_answer,
source=URIDataSource(
uri="huggingface://datasets/llamastack/bfcl_v3?split=train",

5
llama_stack/templates/open-benchmark/run.yaml
View file

@ -164,35 +164,30 @@ 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
scoring_fns: []
benchmarks:
- dataset_id: simpleqa