diff --git a/evals/registry/data/Indian_Menstrual_Health_ChatBot_closedqa/closedqa/Indian_Menstrual_Bot_ClosedQA.jsonl b/evals/registry/data/Indian_Menstrual_Health_ChatBot_closedqa/closedqa/Indian_Menstrual_Bot_ClosedQA.jsonl new file mode 100644 index 0000000000..26d2fc70fd --- /dev/null +++ b/evals/registry/data/Indian_Menstrual_Health_ChatBot_closedqa/closedqa/Indian_Menstrual_Bot_ClosedQA.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6309f9af460f1f3e06a1edfd0171dfb097fdaf0533ea635f9a15232787498c90 +size 39009 diff --git a/evals/registry/evals/Indian_Menstrual_Health_ChatBot-closedqa.yaml b/evals/registry/evals/Indian_Menstrual_Health_ChatBot-closedqa.yaml new file mode 100644 index 0000000000..97a2e44c6e --- /dev/null +++ b/evals/registry/evals/Indian_Menstrual_Health_ChatBot-closedqa.yaml @@ -0,0 +1,9 @@ +Indian_Menstrual_Health_ChatBot-closedqa: + id: Indian_Menstrual_Health_ChatBot-closedqa.dev.v0 + metrics: [accuracy] +Indian_Menstrual_Health_ChatBot-closedqa.dev.v0: + class: evals.elsuite.modelgraded.classify:ModelBasedClassify + args: + samples_jsonl: Indian_Menstrual_Health_ChatBot_closedqa/closedqa/Indian_Menstrual_Bot_ClosedQA.jsonl + eval_type: cot_classify + modelgraded_spec: closedqa \ No newline at end of file