511cbcf773
* init ceval benchmark test. * upload dataset. * add other tests. * add qwen evaluator. * fix qwen evaluator style. * fix qwen evaluator style. * update qwen evaluator. * add llama evaluator. * update eval * fix typo. * fix * fix typo. * fix llama evaluator. * fix bug. * fix style. * delete dataset. * fix style. * fix style. * add README.md and fix typo. * fix comments. * remove run scripts
31 lines
1,007 B
Python
31 lines
1,007 B
Python
#
|
|
# Copyright 2016 The BigDL Authors.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
#
|
|
|
|
class Evaluator:
|
|
def __init__(self, choices, model_path, device, qtype):
|
|
self.choices = choices
|
|
self.model_path = model_path
|
|
self.device = device
|
|
self.qtype = qtype
|
|
|
|
def format_example(self, line, **kwargs):
|
|
pass
|
|
|
|
def eval_subject(self, subject_name, test_df, eval_type, **kwargs):
|
|
pass
|
|
|
|
def extract_answer(self, response, row, **kwargs):
|
|
pass
|