mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
63 lines
1.8 KiB
Python
63 lines
1.8 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 MTBenchDataset
|
|
|
|
|
|
subjective_reader_cfg = dict(
|
|
input_columns=['dialogue', 'capability', 'system_prompt', 'prompt_template'],
|
|
output_column='judge',
|
|
)
|
|
|
|
subjective_all_sets = [
|
|
'mtbench',
|
|
]
|
|
data_path ='data/subjective/'
|
|
|
|
subjective_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=512, infer_mode='every'),
|
|
)
|
|
|
|
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}'
|
|
),
|
|
]),
|
|
),
|
|
),
|
|
pred_role='BOT',
|
|
)
|
|
|
|
subjective_datasets.append(
|
|
dict(
|
|
abbr=f'{_name}',
|
|
type=MTBenchDataset,
|
|
path=data_path,
|
|
name=_name,
|
|
reader_cfg=subjective_reader_cfg,
|
|
infer_cfg=subjective_infer_cfg,
|
|
eval_cfg=subjective_eval_cfg
|
|
))
|