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

fix bench

Browse Source
This commit is contained in:
bio-mlhui 2025-05-29 07:12:42 +00:00
parent 7687f8aa3c
commit 6aabba778d
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
opencompass/datasets/healthbench/healthbench.py
View File

@ -1,5 +1,6 @@
import hashlib import hashlib
import json import json
import os
import re import re
from collections import defaultdict from collections import defaultdict
from typing import Literal from typing import Literal
@ -260,7 +261,7 @@ class HealthBenchEvaluator(BaseEvaluator):
self.n_repeats = n_repeats self.n_repeats = n_repeats
self.n_threads = n_threads self.n_threads = n_threads
self.subset_name = subset_name self.subset_name = subset_name
self.grader_model = ChatCompletionSampler(model='gpt-4.1-2025-04-14', system_message=OPENAI_SYSTEM_MESSAGE_API, max_tokens=2048,) # noqa: E501 self.grader_model = ChatCompletionSampler(model=os.environ['OC_JUDGE_MODEL'], system_message=OPENAI_SYSTEM_MESSAGE_API, max_tokens=2048,) # noqa: E501
def grade_sample(self, prompt: list[dict[str, str]], response_text: str, example_tags: list[str], rubric_items: list[RubricItem], ) -> tuple[dict, str, list[dict]]: # noqa: E501 def grade_sample(self, prompt: list[dict[str, str]], response_text: str, example_tags: list[str], rubric_items: list[RubricItem], ) -> tuple[dict, str, list[dict]]: # noqa: E501
# construct and grade the sample # construct and grade the sample