File size: 1,862 Bytes
7934b29 |
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 |
# Copyright (c) 2022, NVIDIA CORPORATION. All rights reserved.
#
# 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.
"""
"""
from nemo.collections.nlp.modules.common.megatron.retrieval_services.bert_service import start_sentence_bert_server
from nemo.collections.nlp.modules.common.tokenizer_utils import get_nmt_tokenizer
from nemo.core.config import hydra_runner
def get_tokenizer(args):
tokenizer = get_nmt_tokenizer(
library=args.library,
model_name=args.type,
tokenizer_model=args.model,
vocab_file=args.vocab_file,
merges_file=args.merge_file,
delimiter=args.delimiter,
)
if not hasattr(tokenizer, "pad_id"):
tokenizer.add_special_tokens({'pad_token': '<pad>'})
elif hasattr(tokenizer, "pad_id") and (tokenizer.pad_id is None or tokenizer.pad_id < 0):
tokenizer.add_special_tokens({'pad_token': '<pad>'})
return tokenizer
@hydra_runner(config_path="conf", config_name="bert_service")
def main(cfg) -> None:
tokenizer = get_tokenizer(cfg.tokenizer)
start_sentence_bert_server(
cfg.name,
cfg.sentence_bert.devices,
tokenizer,
cfg.sentence_bert.sentence_bert,
cfg.sentence_bert.sentence_bert_batch,
port=cfg.sentence_bert.port,
)
if __name__ == "__main__":
main() # noqa pylint: disable=no-value-for-parameter
|