jiangzhs/OpenCompass
1
0
Fork 0
mirror of https://github.com/open-compass/opencompass.git synced 2025-05-30 16:03:24 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Update

Browse Source
This commit is contained in:
zhangsongyang 2025-02-27 04:47:50 +00:00
parent ff621ddb39
commit effddff840
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
opencompass/configs/datasets/livemathbench/livemathbench_hard_custom_llmverify_gen_9e7505.py → opencompass/configs/datasets/livemathbench/livemathbench_hard_custom_llmverify_gen_85d0ef.py
View File

@ -9,7 +9,7 @@ from itertools import product
# from opencompass.datasets.livemathbench import LiveMathBenchDataset, LiveMathBenchEvaluator
livemathbench_reader_cfg = dict(input_columns=['prompt'], output_column='answer')
livemathbench_reader_cfg = dict(input_columns=['question'], output_column='answer')
# Inference configuration
@ -20,7 +20,7 @@ livemathbench_infer_cfg = dict(
round=[
dict(
role='HUMAN',
prompt='{prompt}\nRemember to put your final answer within \\boxed{}.',
prompt='{question}\n',
),
]
),
@ -45,7 +45,7 @@ GRADER_TEMPLATE = """
B: INCORRECT
Just return the letters "A" or "B", with no text around it.
Here is your task. Simply reply with either CORRECT, INCORRECT. Don't apologize or correct yourself if there was a mistake; we are just trying to grade the answer.
<Original Question Begin>: \n{prompt}\n<Original Question End>\n\n
<Original Question Begin>: \n{question}\n<Original Question End>\n\n
<Gold Target Begin>: \n{answer}\n<Gold Target End>\n\n
<Predicted Answer Begin>: \n{prediction}\n<Predicted End>\n\n