temp commit

llama_stack/templates/open-benchmark/open_benchmark.py

@@ -208,6 +208,14 @@ def get_distribution_template() -> DistributionTemplate:
                 uri="huggingface://datasets/llamastack/bfcl_v3?split=train",
             ),
         ),
+        DatasetInput(
+            dataset_id="IfEval",
+            provider_id="huggingface",
+            purpose=DatasetPurpose.eval_messages_answer,
+            source=URIDataSource(
+                uri="huggingface://datasets/llamastack/IfEval?split=train",
+            ),
+        ),
     ]
 
     default_benchmarks = [
@@ -236,6 +244,11 @@ def get_distribution_template() -> DistributionTemplate:
             dataset_id="bfcl",
             scoring_functions=["basic::bfcl"],
         ),
+        BenchmarkInput(
+            benchmark_id="meta-reference-IfEval",
+            dataset_id="IfEval",
+            scoring_functions=["basic::IfEval"],
+        ),
     ]
     return DistributionTemplate(
         name=name,

llama_stack/templates/open-benchmark/run.yaml

@@ -193,6 +193,13 @@ datasets:
   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
@@ -220,6 +227,11 @@ benchmarks:
   - basic::bfcl
   metadata: {}
   benchmark_id: meta-reference-bfcl
+- dataset_id: IfEval
+  scoring_functions:
+  - basic::IfEval
+  metadata: {}
+  benchmark_id: meta-reference-IfEval
 tool_groups:
 - toolgroup_id: builtin::websearch
   provider_id: tavily-search