From 7ce04b8ac64d68d28483af8f1988d5ccdaab494e Mon Sep 17 00:00:00 2001 From: sora Date: Thu, 27 Aug 2026 06:43:09 +0000 Subject: [PATCH] cmmlu few_shot_num 5->0 (es code default is 0-shot despite docstring claiming 5); 28-bench parity check all green --- evalharness/data/datasets/cmmlu.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/evalharness/data/datasets/cmmlu.py b/evalharness/data/datasets/cmmlu.py index 6312d99..7eb1cde 100644 --- a/evalharness/data/datasets/cmmlu.py +++ b/evalharness/data/datasets/cmmlu.py @@ -20,7 +20,7 @@ from ..spec import DatasetSpec subset='anatomy', # 67 subjects; override with --subset or 'all' split='test', few_shot_split='dev', - few_shot_num=5, + few_shot_num=0, # es default is 0-shot (docstring says 5 but code says 0) task_type='mcq', tags=['zh', 'knowledge'], description='Chinese multiple-choice QA (official content, ModelScope mirror).',