OpenCompass/configs/datasets/bbh/bbh_gen_2879b0.py

57 lines
2.1 KiB
Python
Raw Normal View History

import os
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.datasets import BBHDataset, bbh_mcq_postprocess, BBHEvaluator, BBHEvaluator_mcq
with read_base():
from .bbh_subset_settings import settings
bbh_datasets = []
for name, test_type in settings:
with open(os.path.join(os.path.dirname(__file__), 'lib_prompt', f'{name}.txt'), 'r') as f:
hint = f.read()
task_prompt, body = hint.split('\n\nQ:', 1)
sections = ('Q:' + body).split('\n\n')
prompt_rounds = []
for index, section in enumerate(sections):
question, answer = section.split('\nA:')
answer = 'A:' + answer
if index == 0:
desc = task_prompt.strip() + '\n'
else:
desc = ''
2024-05-14 15:35:58 +08:00
prompt_rounds.append(dict(role='HUMAN', prompt=f'{desc}{question.strip()}'))
prompt_rounds.append(dict(role='BOT', prompt=answer.strip()))
prompt_rounds.append(dict(role='HUMAN', prompt='Q: {input}'))
2024-05-14 15:35:58 +08:00
bbh_reader_cfg = dict(input_columns=['input'], output_column='target')
bbh_infer_cfg = dict(
prompt_template=dict(type=PromptTemplate, template=dict(round=prompt_rounds)),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer, max_out_len=512))
if test_type == 'mcq':
bbh_eval_cfg = dict(
evaluator=dict(type=BBHEvaluator_mcq),
2024-05-14 15:35:58 +08:00
pred_role='BOT',
pred_postprocessor=dict(type=bbh_mcq_postprocess),
dataset_postprocessor=dict(type=bbh_mcq_postprocess))
else:
bbh_eval_cfg = dict(
evaluator=dict(type=BBHEvaluator),
2024-05-14 15:35:58 +08:00
pred_role='BOT')
bbh_datasets.append(
dict(
type=BBHDataset,
[Feature] Support ModelScope datasets (#1289) * 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>
2024-07-29 13:48:32 +08:00
path='opencompass/bbh',
name=name,
abbr='bbh-' + name,
reader_cfg=bbh_reader_cfg.copy(),
infer_cfg=bbh_infer_cfg.copy(),
eval_cfg=bbh_eval_cfg.copy()))