[Misc] Add network timeout to eval dataset downloads (#21873)

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-01 13:16:14 -07:00
parent a19ef3a615
commit 0138708576
6 changed files with 18 additions and 6 deletions
@@ -93,7 +93,10 @@ class MMLUEval(Eval):
    """MMLU benchmark evaluation."""

    def __init__(self, filename: str, num_examples: int | None, num_threads: int):
-        df = pandas.read_csv(filename)
+        if "://" in filename:
+            df = pandas.read_csv(filename, storage_options={"timeout": 30})
+        else:
+            df = pandas.read_csv(filename)
        examples = [row.to_dict() for _, row in df.iterrows()]
        if num_examples:
            examples = random.Random(0).sample(examples, num_examples)