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>
37 lines
1.3 KiB
Python
37 lines
1.3 KiB
Python
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 HumanevalDataset, HumanEvalEvaluator, humaneval_postprocess
|
|
|
|
humaneval_reader_cfg = dict(
|
|
input_columns=['prompt'], output_column='task_id', train_split='test')
|
|
|
|
# TODO: allow empty output-column
|
|
humaneval_infer_cfg = dict(
|
|
prompt_template=dict(
|
|
type=PromptTemplate,
|
|
template=dict(round=[
|
|
dict(
|
|
role='HUMAN',
|
|
prompt='Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\nCreate a Python script for this problem:\n{prompt}\n\n### Response:\n'),
|
|
])),
|
|
retriever=dict(type=ZeroRetriever),
|
|
inferencer=dict(type=GenInferencer, max_out_len=512))
|
|
|
|
humaneval_eval_cfg = dict(
|
|
evaluator=dict(type=HumanEvalEvaluator),
|
|
pred_role='BOT',
|
|
k=[1, 10, 100], # the parameter only for humaneval
|
|
pred_postprocessor=dict(type=humaneval_postprocess),
|
|
)
|
|
|
|
humaneval_datasets = [
|
|
dict(
|
|
abbr='openai_humaneval',
|
|
type=HumanevalDataset,
|
|
path='opencompass/humaneval',
|
|
reader_cfg=humaneval_reader_cfg,
|
|
infer_cfg=humaneval_infer_cfg,
|
|
eval_cfg=humaneval_eval_cfg)
|
|
]
|