mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
edab1c07ba
* add ceval, gsm8k modelscope surpport * update race, mmlu, arc, cmmlu, commonsenseqa, humaneval and unittest * update bbh, flores, obqa, siqa, storycloze, summedits, winogrande, xsum datasets * format file * format file * update dataset format * support ms_dataset * udpate dataset for modelscope support * merge myl_dev and update test_ms_dataset * udpate dataset for modelscope support * update readme * update eval_api_zhipu_v2 * remove unused code * add get_data_path function * update readme * remove tydiqa japanese subset * add ceval, gsm8k modelscope surpport * update race, mmlu, arc, cmmlu, commonsenseqa, humaneval and unittest * update bbh, flores, obqa, siqa, storycloze, summedits, winogrande, xsum datasets * format file * format file * update dataset format * support ms_dataset * udpate dataset for modelscope support * merge myl_dev and update test_ms_dataset * update readme * udpate dataset for modelscope support * update eval_api_zhipu_v2 * remove unused code * add get_data_path function * remove tydiqa japanese subset * update util * remove .DS_Store * fix md format * move util into package * update docs/get_started.md * restore eval_api_zhipu_v2.py, add environment setting * Update dataset * Update * Update * Update * Update --------- Co-authored-by: Yun lin <yunlin@U-Q9X2K4QV-1904.local> Co-authored-by: Yunnglin <mao.looper@qq.com> Co-authored-by: Yun lin <yunlin@laptop.local> Co-authored-by: Yunnglin <maoyl@smail.nju.edu.cn> Co-authored-by: zhangsongyang <zhangsongyang@pjlab.org.cn>
60 lines
1.9 KiB
Python
60 lines
1.9 KiB
Python
from mmengine.config import read_base
|
|
from opencompass.openicl.icl_prompt_template import PromptTemplate
|
|
from opencompass.openicl.icl_retriever import ZeroRetriever
|
|
from opencompass.openicl.icl_inferencer import GenInferencer
|
|
from opencompass.openicl.icl_evaluator import AccEvaluator
|
|
from opencompass.datasets import MMLUDataset
|
|
from opencompass.utils.text_postprocessors import match_answer_pattern
|
|
|
|
with read_base():
|
|
from .mmlu_all_sets import mmlu_all_sets
|
|
|
|
# None of the mmlu dataset in huggingface is correctly parsed, so we use our own dataset reader
|
|
# Please download the dataset from https://people.eecs.berkeley.edu/~hendrycks/data.tar
|
|
|
|
QUERY_TEMPLATE = """
|
|
Answer the following multiple choice question. The last line of your response should be of the following format: 'ANSWER: $LETTER' (without quotes) where LETTER is one of ABCD. Think step by step before answering.
|
|
|
|
{input}
|
|
|
|
A) {A}
|
|
B) {B}
|
|
C) {C}
|
|
D) {D}
|
|
""".strip()
|
|
|
|
mmlu_reader_cfg = dict(
|
|
input_columns=['input', 'A', 'B', 'C', 'D'],
|
|
output_column='target',
|
|
train_split='dev')
|
|
|
|
mmlu_datasets = []
|
|
for name in mmlu_all_sets:
|
|
mmlu_infer_cfg = dict(
|
|
prompt_template=dict(
|
|
type=PromptTemplate,
|
|
template=dict(
|
|
round=[
|
|
dict(role='HUMAN', prompt=QUERY_TEMPLATE),
|
|
],
|
|
),
|
|
),
|
|
retriever=dict(type=ZeroRetriever),
|
|
inferencer=dict(type=GenInferencer),
|
|
)
|
|
|
|
mmlu_eval_cfg = dict(
|
|
evaluator=dict(type=AccEvaluator),
|
|
pred_postprocessor=dict(type=match_answer_pattern, answer_pattern=r'(?i)ANSWER\s*:\s*([A-D])'))
|
|
|
|
mmlu_datasets.append(
|
|
dict(
|
|
abbr=f'lukaemon_mmlu_{name}',
|
|
type=MMLUDataset,
|
|
path='opencompass/mmlu',
|
|
name=name,
|
|
reader_cfg=mmlu_reader_cfg,
|
|
infer_cfg=mmlu_infer_cfg,
|
|
eval_cfg=mmlu_eval_cfg,
|
|
))
|