Name	Size	Mode	Actions
__pycache__/	-	0755	rm
configuration_lxmert.py	9226	0644	editdlrm
convert_lxmert_original_tf_checkpoint_to_pytorch.py	2120	0644	editdlrm
modeling_lxmert.py	64969	0644	editdlrm
modeling_tf_lxmert.py	62768	0644	editdlrm
tokenization_lxmert.py	1675	0644	editdlrm
tokenization_lxmert_fast.py	2037	0644	editdlrm
__init__.py	2766	0644	editdlrm

# coding=utf-8 # Copyright 2020 The Google AI Team, Stanford University and 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. from ..bert.tokenization_bert import BertTokenizer VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"} PRETRAINED_VOCAB_FILES_MAP = { "vocab_file": { "unc-nlp/lxmert-base-uncased": "https://huggingface.co/unc-nlp/lxmert-base-uncased/resolve/main/vocab.txt", } } PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { "unc-nlp/lxmert-base-uncased": 512, } PRETRAINED_INIT_CONFIGURATION = { "unc-nlp/lxmert-base-uncased": {"do_lower_case": True}, } class LxmertTokenizer(BertTokenizer): r""" Construct an LXMERT tokenizer. [`LxmertTokenizer`] is identical to [`BertTokenizer`] and runs end-to-end tokenization: punctuation splitting and wordpiece. Refer to superclass [`BertTokenizer`] for usage examples and documentation concerning parameters. """ vocab_files_names = VOCAB_FILES_NAMES pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION