forked from phoenix-oss/llama-stack-mirror
Merge branch 'main' into pr1573
This commit is contained in:
commit
cba4842a87
22 changed files with 1658 additions and 56 deletions
|
@ -200,6 +200,22 @@ def get_distribution_template() -> DistributionTemplate:
|
|||
uri="huggingface://llamastack/math_500?split=test",
|
||||
),
|
||||
),
|
||||
DatasetInput(
|
||||
dataset_id="bfcl",
|
||||
provider_id="huggingface",
|
||||
url=URL(uri="https://huggingface.co/datasets/llamastack/bfcl_v3"),
|
||||
metadata={
|
||||
"path": "llamastack/bfcl_v3",
|
||||
"split": "train",
|
||||
},
|
||||
dataset_schema={
|
||||
"function": {"type": "string"},
|
||||
"language": {"type": "string"},
|
||||
"ground_truth": {"type": "string"},
|
||||
"id": {"type": "string"},
|
||||
"chat_completion_input": {"type": "string"},
|
||||
},
|
||||
),
|
||||
]
|
||||
|
||||
default_benchmarks = [
|
||||
|
@ -223,6 +239,11 @@ def get_distribution_template() -> DistributionTemplate:
|
|||
dataset_id="math_500",
|
||||
scoring_functions=["basic::regex_parser_math_response"],
|
||||
),
|
||||
BenchmarkInput(
|
||||
benchmark_id="meta-reference-bfcl",
|
||||
dataset_id="bfcl",
|
||||
scoring_functions=["basic::bfcl"],
|
||||
),
|
||||
]
|
||||
return DistributionTemplate(
|
||||
name=name,
|
||||
|
|
|
@ -186,6 +186,24 @@ datasets:
|
|||
metadata: {}
|
||||
dataset_id: math_500
|
||||
provider_id: huggingface
|
||||
- dataset_schema:
|
||||
function:
|
||||
type: string
|
||||
language:
|
||||
type: string
|
||||
ground_truth:
|
||||
type: string
|
||||
id:
|
||||
type: string
|
||||
chat_completion_input:
|
||||
type: string
|
||||
url:
|
||||
uri: https://huggingface.co/datasets/llamastack/bfcl_v3
|
||||
metadata:
|
||||
path: llamastack/bfcl_v3
|
||||
split: train
|
||||
dataset_id: bfcl
|
||||
provider_id: huggingface
|
||||
scoring_fns: []
|
||||
benchmarks:
|
||||
- dataset_id: simpleqa
|
||||
|
@ -208,6 +226,11 @@ benchmarks:
|
|||
- basic::regex_parser_math_response
|
||||
metadata: {}
|
||||
benchmark_id: meta-reference-math-500
|
||||
- dataset_id: bfcl
|
||||
scoring_functions:
|
||||
- basic::bfcl
|
||||
metadata: {}
|
||||
benchmark_id: meta-reference-bfcl
|
||||
tool_groups:
|
||||
- toolgroup_id: builtin::websearch
|
||||
provider_id: tavily-search
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue