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

[Feature] Support answer extraction of QwQ when evaluating HuProverbRea_OE (#31)

Browse Source
This commit is contained in:
Hoter Young 2025-02-14 10:16:05 +08:00 committed by GitHub
parent 0971777348
commit b6c8165ca3
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 34 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
examples/eval_OpenHuEval_HuProverbRea_OE.py
View File

@ -3,9 +3,9 @@ from mmengine.config import read_base
with read_base(): with read_base():
from opencompass.configs.datasets.OpenHuEval.HuProverbRea.HuProverbRea_OE import HuProverbRea_datasets from opencompass.configs.datasets.OpenHuEval.HuProverbRea.HuProverbRea_OE import HuProverbRea_datasets
# from opencompass.configs.models.openai.gpt_4o_mini_20240718 import models as gpt_4o_mini_20240718_model from opencompass.configs.models.openai.gpt_4o_mini_20240718 import models as gpt_4o_mini_20240718_model
# from opencompass.configs.models.openai.gpt_4o_2024_11_20 import models as gpt_4o_2024_11_20_model from opencompass.configs.models.openai.gpt_4o_2024_11_20 import models as gpt_4o_2024_11_20_model
# from opencompass.configs.models.deepseek.deepseek_v3_api_aliyun import models as deepseek_v3_api_aliyun_model from opencompass.configs.models.deepseek.deepseek_v3_api_aliyun import models as deepseek_v3_api_aliyun_model
from opencompass.configs.models.qwen2_5.lmdeploy_qwen2_5_7b_instruct import models as lmdeploy_qwen2_5_7b_instruct_model from opencompass.configs.models.qwen2_5.lmdeploy_qwen2_5_7b_instruct import models as lmdeploy_qwen2_5_7b_instruct_model
from opencompass.configs.models.qwen2_5.lmdeploy_qwen2_5_72b_instruct import models as lmdeploy_qwen2_5_72b_instruct_model from opencompass.configs.models.qwen2_5.lmdeploy_qwen2_5_72b_instruct import models as lmdeploy_qwen2_5_72b_instruct_model
@ -15,8 +15,8 @@ with read_base():
from opencompass.configs.models.hf_internlm.lmdeploy_internlm3_8b_instruct import models as lmdeploy_internlm3_8b_instruct_model from opencompass.configs.models.hf_internlm.lmdeploy_internlm3_8b_instruct import models as lmdeploy_internlm3_8b_instruct_model
from opencompass.configs.models.qwq.lmdeploy_qwq_32b_preview import models as lmdeploy_qwq_32b_preview_model from opencompass.configs.models.qwq.lmdeploy_qwq_32b_preview import models as lmdeploy_qwq_32b_preview_model
# from opencompass.configs.models.deepseek.deepseek_r1_api_aliyun import models as deepseek_r1_api_aliyun_model from opencompass.configs.models.deepseek.deepseek_r1_api_aliyun import models as deepseek_r1_api_aliyun_model
# from opencompass.configs.models.openai.o1_mini_2024_09_12 import models as o1_mini_2024_09_12_model from opencompass.configs.models.openai.o1_mini_2024_09_12 import models as o1_mini_2024_09_12_model
# from opencompass.configs.models.openai.o3_mini_2025_01_31 import models as o3_mini_2025_01_31_model # from opencompass.configs.models.openai.o3_mini_2025_01_31 import models as o3_mini_2025_01_31_model
datasets = HuProverbRea_datasets datasets = HuProverbRea_datasets
@ -30,6 +30,12 @@ for model in models:
'type': 'rm_<think>_before_eval' 'type': 'rm_<think>_before_eval'
} }
} }
if model['abbr'].startswith('QwQ'):
model['pred_postprocessor'] = {
'OpenHuEval_*': {
'type': 'extract_qwq_answer_before_eval'
}
}
del model del model
work_dir = './outputs/' + __file__.split('/')[-1].split('.')[0] + '/' # do NOT modify this line, yapf: disable, pylint: disable work_dir = './outputs/' + __file__.split('/')[-1].split('.')[0] + '/' # do NOT modify this line, yapf: disable, pylint: disable

23
opencompass/utils/text_postprocessors.py
View File

@ -241,3 +241,26 @@ def remove_reasoning_part_before_evaluation(text: str):
return text[reasoning_end + 8:] return text[reasoning_end + 8:]
else: else:
return text return text
@TEXT_POSTPROCESSORS.register_module('extract_qwq_answer_before_eval')
def extract_answer_before_evaluation(text: str):
"""Overall, there are three situations in responses of QWQ:
1. There is a **Final Answer** title in the whole context.
2. There is only one sentence in the context.
3. There are more than one sentences in the context, \
and the last one is the answer.
"""
if '**Final Answer**' in text:
answer = text.split('\n\n**Final Answer**\n\n')[-1]
else:
if '\n\nHuman' in text:
text = text.split('\n\nHuman')[0]
text_split = text.split('.')
if text_split[-1] == '':
answer = text_split[-2] + '.'
else:
answer = text_split[-1] + '.'
return answer