Spaces:
Runtime error
Runtime error
File size: 2,018 Bytes
455a40f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 |
# coding=utf-8
# Copyright 2019-present, the HuggingFace Inc. team.
#
# 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.
"""
Preprocessing script before training the distilled model.
"""
import argparse
import logging
import pickle
from collections import Counter
logging.basicConfig(
format="%(asctime)s - %(levelname)s - %(name)s - %(message)s", datefmt="%m/%d/%Y %H:%M:%S", level=logging.INFO
)
logger = logging.getLogger(__name__)
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description="Token Counts for smoothing the masking probabilities in MLM (cf XLM/word2vec)"
)
parser.add_argument(
"--data_file", type=str, default="data/dump.bert-base-uncased.pickle", help="The binarized dataset."
)
parser.add_argument(
"--token_counts_dump", type=str, default="data/token_counts.bert-base-uncased.pickle", help="The dump file."
)
parser.add_argument("--vocab_size", default=30522, type=int)
args = parser.parse_args()
logger.info(f"Loading data from {args.data_file}")
with open(args.data_file, "rb") as fp:
data = pickle.load(fp)
logger.info("Counting occurrences for MLM.")
counter = Counter()
for tk_ids in data:
counter.update(tk_ids)
counts = [0] * args.vocab_size
for k, v in counter.items():
counts[k] = v
logger.info(f"Dump to {args.token_counts_dump}")
with open(args.token_counts_dump, "wb") as handle:
pickle.dump(counts, handle, protocol=pickle.HIGHEST_PROTOCOL)
|