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 lint

Browse Source
This commit is contained in:
huihui 2025-05-08 06:07:08 +00:00
parent 26adccc20c
commit 862cf61f64
3 changed files with 14 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
opencompass/configs/datasets/SciKnowEval/SciKnowEval_gen_ebe47d.py
View File

@ -3,6 +3,7 @@ from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_prompt_template import PromptTemplate from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever from opencompass.openicl.icl_retriever import ZeroRetriever
ZERO_SHOT_PROMPT = '{q4}' ZERO_SHOT_PROMPT = '{q4}'
# Reader configuration # Reader configuration

1
opencompass/configs/datasets/SciKnowEval/SciKnowEval_llmjudge_gen_ebe47d.py
View File

@ -6,6 +6,7 @@ from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.evaluator import GenericLLMEvaluator from opencompass.evaluator import GenericLLMEvaluator
ZERO_SHOT_PROMPT = '{q4}' ZERO_SHOT_PROMPT = '{q4}'
GRADER_TEMPLATE = """ GRADER_TEMPLATE = """
Please as a grading expert, judge whether the final answers given by the candidates below are consistent with the standard answers, that is, whether the candidates answered correctly. Please as a grading expert, judge whether the final answers given by the candidates below are consistent with the standard answers, that is, whether the candidates answered correctly.

25
opencompass/datasets/SciKnowEval.py
View File

@ -1,23 +1,22 @@
import re import re
from datasets import Dataset, load_dataset from datasets import load_dataset
from opencompass.openicl import BaseEvaluator from opencompass.openicl import BaseEvaluator
from opencompass.registry import LOAD_DATASET, TEXT_POSTPROCESSORS from opencompass.registry import LOAD_DATASET, TEXT_POSTPROCESSORS
from opencompass.utils import get_logger
from .base import BaseDataset from .base import BaseDataset
def _parse(item, prompt_mode, discipline): def _parse(item, prompt_mode, discipline):
choices = item['choices'] choices = item['choices']
item['q4'] = f'You are an expert in {discipline}.\n' + item['prompt'][
'default'] + '\n' + item['question'] + '\n' + '\n'.join([ item['q4'] = f'You are an expert in {discipline}.\n'
f'{l}. {t}' for l, t in zip(choices['label'], choices['text']) item['q4'] += item['prompt']['default'] + '\n' + item['question'] + '\n'
]) # noqa: E501, E741, E741 label_texts = []
item['start'] = chr(65) for label_meta, text_meta in zip(choices['label'], choices['text']):
item['end'] = chr(65 + len(item.get('choices', {'label': []})['label']) - label_texts.append(f'{label_meta}. {text_meta}')
1) item['q4'] += '\n'.join(label_texts) # noqa: E501, E741, E741
item['prompt_mode'] = prompt_mode item['prompt_mode'] = prompt_mode
return item return item
@ -34,10 +33,10 @@ class SciKnowEvalDataset(BaseDataset):
return s[0].upper() + s[1:] return s[0].upper() + s[1:]
subset = kwargs['subset'] subset = kwargs['subset']
data_files = { data_files = {}
'test': test_file = f'data/{capitalize_first_letter(subset)}/'
f'data/{capitalize_first_letter(subset)}/sciknoweval_{subset}_test.jsonl' test_file += f'sciknoweval_{subset}_test.jsonl'
} data_files['test'] = test_file
dataset = load_dataset(path, data_files=data_files, split='test') dataset = load_dataset(path, data_files=data_files, split='test')
# dataset = dataset.select(range(20)) # dataset = dataset.select(range(20))
if prompt_mode == 'zero-shot': if prompt_mode == 'zero-shot':