wehub-resource-sync
75 lines
2.5 KiB
Python
75 lines
2.5 KiB
Python
# Copyright 2024 Bytedance Ltd. and/or its affiliates
|
|
#
|
|
# 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.
|
|
"""
|
|
Preprocess the GSM8k dataset to parquet format
|
|
"""
|
|
|
|
import argparse
|
|
import os
|
|
import re
|
|
|
|
import datasets
|
|
|
|
|
|
def extract_solution(solution_str):
|
|
solution = re.search("#### (\\-?[0-9\\.\\,]+)", solution_str)
|
|
assert solution is not None
|
|
final_solution = solution.group(0)
|
|
final_solution = final_solution.split("#### ")[1].replace(",", "")
|
|
return final_solution
|
|
|
|
|
|
if __name__ == "__main__":
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument("--local_dir", default="./gsm8k")
|
|
|
|
args = parser.parse_args()
|
|
|
|
data_source = "openai/gsm8k"
|
|
|
|
dataset = datasets.load_dataset(data_source, "main")
|
|
|
|
train_dataset = dataset["train"]
|
|
test_dataset = dataset["test"]
|
|
|
|
instruction_following = 'Let\'s think step by step and output the final answer after "####".'
|
|
|
|
# add a row to each data item that represents a unique id
|
|
def make_map_fn(split):
|
|
def process_fn(example, idx):
|
|
question_raw = "<|im_start|>user\n" + example.pop("question")
|
|
|
|
system_raw = (
|
|
"<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n"
|
|
)
|
|
question = system_raw + question_raw + " " + instruction_following + "<|im_end|>\n<|im_start|>assistant\n"
|
|
|
|
answer_raw = example.pop("answer")
|
|
solution = extract_solution(answer_raw)
|
|
data = {
|
|
"src": question,
|
|
"tgt": solution,
|
|
}
|
|
return data
|
|
|
|
return process_fn
|
|
|
|
train_dataset = train_dataset.map(function=make_map_fn("train"), with_indices=True)
|
|
test_dataset = test_dataset.map(function=make_map_fn("test"), with_indices=True)
|
|
|
|
local_dir = args.local_dir
|
|
|
|
train_dataset.to_json(os.path.join(local_dir, "train.jsonl"), orient="records", lines=True)
|
|
test_dataset.to_json(os.path.join(local_dir, "test.jsonl"), orient="records", lines=True)
|