mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
65fad8e2ac
* update crb * update crbbench * update crbbench * update crbbench * minor update wildbench * [Fix] Update doc of wildbench, and merge wildbench into subjective * [Fix] Update doc of wildbench, and merge wildbench into subjective, fix crbbench * Update crb.md * Update crb_pair_judge.py * Update crb_single_judge.py * Update subjective_evaluation.md * Update openai_api.py * [Update] update wildbench readme * [Update] update wildbench readme * [Update] update wildbench readme, remove crb * Delete configs/eval_subjective_wildbench_pair.py * Delete configs/eval_subjective_wildbench_single.py * Update __init__.py --------- Co-authored-by: bittersweet1999 <148421775+bittersweet1999@users.noreply.github.com>
48 lines
1.3 KiB
Python
48 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 ChatInferencer, GenInferencer
|
|
from opencompass.openicl.icl_evaluator import LMEvaluator
|
|
from opencompass.datasets import WildBenchDataset
|
|
|
|
|
|
subjective_reader_cfg = dict(
|
|
input_columns=['dialogue', 'prompt'],
|
|
output_column='judge',
|
|
)
|
|
|
|
data_path ='./data/WildBench/wildbench.jsonl'
|
|
|
|
wildbench_single_datasets = []
|
|
|
|
# the question is a list, how to process it
|
|
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='last'),
|
|
)
|
|
|
|
subjective_eval_cfg = dict(
|
|
evaluator=dict(
|
|
type=LMEvaluator,
|
|
prompt_template=dict(
|
|
type=PromptTemplate,
|
|
template="""{prompt}"""
|
|
),
|
|
),
|
|
pred_role='BOT',
|
|
)
|
|
|
|
wildbench_single_datasets.append(
|
|
dict(
|
|
abbr='wildbench',
|
|
type=WildBenchDataset,
|
|
path=data_path,
|
|
eval_mode='single',
|
|
reader_cfg=subjective_reader_cfg,
|
|
infer_cfg=subjective_infer_cfg,
|
|
eval_cfg=subjective_eval_cfg
|
|
))
|