mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
689ffe5b63
* update commonsenseqa * update drop * update flores_first100 * update gsm8k * update humaneval * update lambda * update obqa * update piqa * update race * update siqa * update story_cloze * update strategyqa * update tydiqa * update winogrande * update doc * update hellaswag * fix obqa * update collections * update .zip name
42 lines
1.4 KiB
Python
42 lines
1.4 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, HumanEvaluator, 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(
|
|
begin=[
|
|
dict(
|
|
role='SYSTEM',
|
|
fallback_role='HUMAN',
|
|
prompt='Complete the following python code:'),
|
|
],
|
|
round=[
|
|
dict(role='HUMAN', prompt='{prompt}'),
|
|
])),
|
|
retriever=dict(type=ZeroRetriever),
|
|
inferencer=dict(type=GenInferencer, max_out_len=512))
|
|
|
|
humaneval_eval_cfg = dict(
|
|
evaluator=dict(type=HumanEvaluator),
|
|
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='./data/humaneval/human-eval-v2-20210705.jsonl',
|
|
reader_cfg=humaneval_reader_cfg,
|
|
infer_cfg=humaneval_infer_cfg,
|
|
eval_cfg=humaneval_eval_cfg)
|
|
]
|