mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
2ee8e8a1a1
* add mtbench * add mtbench * Update configs/datasets/subjective/multiround/mtbench_judgeby_gpt4.py Co-authored-by: Songyang Zhang <tonysy@users.noreply.github.com> * Update configs/datasets/subjective/multiround/mtbench_judgeby_gpt4.py Co-authored-by: Songyang Zhang <tonysy@users.noreply.github.com> * Update opencompass/datasets/subjective/__init__.py Co-authored-by: Songyang Zhang <tonysy@users.noreply.github.com> * Update opencompass/datasets/subjective/mtbench.py Co-authored-by: Songyang Zhang <tonysy@users.noreply.github.com> * fix mtbench --------- Co-authored-by: Songyang Zhang <tonysy@users.noreply.github.com>
65 lines
1.9 KiB
Python
65 lines
1.9 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,
|
|
infer_order='double',
|
|
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,
|
|
judge_type='pair',
|
|
reader_cfg=subjective_reader_cfg,
|
|
infer_cfg=subjective_infer_cfg,
|
|
eval_cfg=subjective_eval_cfg
|
|
))
|