mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
fa54aa62f6
* fix pip version * fix pip version * update (#1522) Co-authored-by: zhulin1 <zhulin1@pjlab.org.cn> * [Feature] Update Models (#1518) * Update Models * Update * Update humanevalx * Update * Update * [Feature] Dataset prompts update for ARC, BoolQ, Race (#1527) add judgerbench and reorg sub add judgerbench and reorg subeval add judgerbench and reorg subeval * add judgerbench and reorg subeval * add judgerbench and reorg subeval * add judgerbench and reorg subeval * add judgerbench and reorg subeval --------- Co-authored-by: zhulinJulia24 <145004780+zhulinJulia24@users.noreply.github.com> Co-authored-by: zhulin1 <zhulin1@pjlab.org.cn> Co-authored-by: Songyang Zhang <tonysy@users.noreply.github.com> Co-authored-by: Linchen Xiao <xxllcc1993@gmail.com>
64 lines
2.0 KiB
Python
64 lines
2.0 KiB
Python
from opencompass.openicl.icl_prompt_template import PromptTemplate
|
|
from opencompass.openicl.icl_retriever import ZeroRetriever
|
|
from opencompass.openicl.icl_inferencer import ChatInferencer, GenInferencer
|
|
from opencompass.openicl.icl_evaluator import LMEvaluator
|
|
from opencompass.datasets import MTBench101Dataset, mtbench101_postprocess
|
|
|
|
subjective_reader_cfg = dict(
|
|
input_columns=['dialogue','task','multi_id','turn_id','system_prompt','prompt_template'],
|
|
output_column='judge',
|
|
)
|
|
|
|
subjective_all_sets = [
|
|
'mtbench101',
|
|
]
|
|
data_path ='data/subjective/'
|
|
|
|
mtbench101_datasets = []
|
|
|
|
for _name in subjective_all_sets:
|
|
subjective_infer_cfg = dict(
|
|
prompt_template=dict(
|
|
type=PromptTemplate,
|
|
template="""{dialogue}""",
|
|
),
|
|
retriever=dict(type=ZeroRetriever),
|
|
inferencer=dict(type=ChatInferencer, max_seq_len=4096, max_out_len=4096, infer_mode='last'),
|
|
)
|
|
|
|
subjective_eval_cfg = dict(
|
|
evaluator=dict(
|
|
type=LMEvaluator,
|
|
prompt_template=dict(
|
|
type=PromptTemplate,
|
|
template=dict(
|
|
begin=[
|
|
dict(
|
|
role='SYSTEM',
|
|
fallback_role='HUMAN',
|
|
prompt='{system_prompt}')
|
|
],
|
|
round=[
|
|
dict(
|
|
role='HUMAN',
|
|
prompt = '{prompt_template}'
|
|
),
|
|
]),
|
|
),
|
|
dict_postprocessor=dict(type=mtbench101_postprocess),
|
|
),
|
|
pred_role='BOT',
|
|
)
|
|
|
|
mtbench101_datasets.append(
|
|
dict(
|
|
abbr=f'{_name}',
|
|
type=MTBench101Dataset,
|
|
path=data_path,
|
|
name=_name,
|
|
reader_cfg=subjective_reader_cfg,
|
|
infer_cfg=subjective_infer_cfg,
|
|
eval_cfg=subjective_eval_cfg,
|
|
mode='singlescore',
|
|
))
|