mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
22a33d8759
* support G-Pass@k and livemathbench * fix bugs * fix comments of GPassKEvaluator * update saved details of GPassKEvaluator * update saved details of GPassKEvaluator * fix eval api configs & update openai_api for ease of debugging * update huggingface path * fix method name of G-Pass@k * fix default value of eval_model_name * refactor G-Pass@k evaluator * log generation params for each backend * fix evaluation resume * add notimplementerror * update livemathbench-hard configs * remove max_out_len from livemathbench_hard_greedy_gen_9befbf.py * remove max_out_len from livemathbench_hard_gen_9befbf.py * rename livemathbench_hard_gen_9befbf.py to livemathbench_hard_gen_353ae7.py * rename livemathbench_hard_greedy_gen_9befbf.py to livemathbench_hard_greedy_gen_353ae7.py * update livemathbench_gen_9befbf.py * remove whitespace * upload livemathbench hard configs
52 lines
1.4 KiB
Python
52 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.livemathbench import LiveMathBenchDataset, LiveMathBenchEvaluator
|
|
|
|
|
|
livemathbench_dataset = dict(
|
|
type=LiveMathBenchDataset,
|
|
path='',
|
|
k=16,
|
|
replication=3,
|
|
dataset_splits=['CNMO', 'CCEE', 'AMC', 'WLPMC'],
|
|
dataset_languages=['cn', 'en'],
|
|
cot=True,
|
|
version='202412',
|
|
abbr='LiveMathBench-v202412',
|
|
reader_cfg=dict(
|
|
input_columns=['prompt'],
|
|
output_column='answer'
|
|
),
|
|
infer_cfg=dict(
|
|
prompt_template=dict(
|
|
type=PromptTemplate,
|
|
template=dict(
|
|
round=[
|
|
dict(role='HUMAN', prompt='{prompt}'),
|
|
]
|
|
)
|
|
),
|
|
retriever=dict(type=ZeroRetriever),
|
|
inferencer=dict(
|
|
type=GenInferencer,
|
|
max_out_len=8192
|
|
),
|
|
),
|
|
eval_cfg=dict(
|
|
evaluator=dict(
|
|
type=LiveMathBenchEvaluator,
|
|
model_name='',
|
|
url=[],
|
|
use_extract_model=False,
|
|
extract_url=[],
|
|
extract_model_name='',
|
|
k=[4, 8, 16],
|
|
replication=3,
|
|
thresholds=[0.0, 0.25, 0.5, 0.75, 1.0]
|
|
)
|
|
)
|
|
)
|
|
livemathbench_datasets = [livemathbench_dataset]
|