diff --git a/evals/registry/data/tnengoy/tnengoy_citations.jsonl b/evals/registry/data/tnengoy/tnengoy_citations.jsonl new file mode 100644 index 0000000000..57a2530744 --- /dev/null +++ b/evals/registry/data/tnengoy/tnengoy_citations.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:619b69fcf1f4ee1699855e1e21e79a9c0aab84b0e4965bc3937abeb96ea4ab26 +size 130 diff --git a/evals/registry/evals/tnengoy.yaml b/evals/registry/evals/tnengoy.yaml new file mode 100644 index 0000000000..3c285a5409 --- /dev/null +++ b/evals/registry/evals/tnengoy.yaml @@ -0,0 +1,6 @@ +tnengoy_citations.dev.v0: + class: evals.elsuite.modelgraded.classify:ModelBasedClassify + args: + samples_jsonl: tnengoy/tnengoy_citations.jsonl + eval_type: cot_classify + modelgraded_spec: fact