Upload 15 files

.gitattributes

@@ -1,34 +1,9 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,20 @@
+# <a name="introduction"></a> PhoBERT: Pre-trained language models for Vietnamese 
+  
+Pre-trained PhoBERT models are the state-of-the-art language models for Vietnamese ([Pho](https://en.wikipedia.org/wiki/Pho), i.e. "Phở", is a popular food in Vietnam):
+
+ - Two PhoBERT versions of "base" and "large" are the first public large-scale monolingual language models pre-trained for Vietnamese. PhoBERT pre-training approach is based on [RoBERTa](https://github.com/pytorch/fairseq/blob/master/examples/roberta/README.md)  which optimizes the [BERT](https://github.com/google-research/bert) pre-training procedure for more robust performance.
+ - PhoBERT outperforms previous monolingual and multilingual approaches, obtaining new state-of-the-art performances on four downstream Vietnamese NLP tasks of Part-of-speech tagging, Dependency parsing, Named-entity recognition and Natural language inference.
+
+The general architecture and experimental results of PhoBERT can be found in our EMNLP-2020 Findings [paper](https://arxiv.org/abs/2003.00744):
+
+    @article{phobert,
+    title     = {{PhoBERT: Pre-trained language models for Vietnamese}},
+    author    = {Dat Quoc Nguyen and Anh Tuan Nguyen},
+    journal   = {Findings of EMNLP},
+    year      = {2020}
+    }
+
+**Please CITE** our paper when PhoBERT is used to help produce published results or is incorporated into other software.
+
+For further information or requests, please go to [PhoBERT's homepage](https://github.com/VinAIResearch/PhoBERT)!
+

config(1).json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "vinai/bartpho-word-base",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "MBartForQuestionAnswering"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_position_embeddings": 1024,
+  "model_type": "mbart",
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "tokenizer_class": "PhobertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.0.dev0",
+  "use_cache": true,
+  "vocab_size": 64001
+}

config.json

@@ -0,0 +1,23 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 258,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "tokenizer_class": "PhobertTokenizer",
+  "type_vocab_size": 1,
+  "vocab_size": 64001
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e2175c6ef2b2b841682ec586bc5d9d55a98f83e0b234d97d1054b633e14127b
+size 134

pytorch_model(1).bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70b592efd43bb30a4a8e606d3de69261b9e5a8142d043c397194e010cf9127cf
+size 599987121

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2804d836670fa8c026420788e2bcf5e5be453f54f988fac7321bf1fec49b834f
+size 134

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65375ff9d08688163a114495c37d7c6f2ddf3075e1bfda4015fa975b9a0303de
+size 134

tokenization_phobert.py

@@ -0,0 +1,383 @@
+# coding=utf-8
+# Copyright (c) 2020, VinAI Research and the HuggingFace Inc. team.
+# Copyright 2018 The Open AI Team Authors 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.
+""" Tokenization classes for PhoBERT"""
+
+
+import os
+import re
+from shutil import copyfile
+from typing import List, Optional, Tuple
+
+from transformers.tokenization_utils import PreTrainedTokenizer
+from transformers.utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+VOCAB_FILES_NAMES = {
+    "vocab_file": "vocab.txt",
+    "merges_file": "bpe.codes",
+}
+
+PRETRAINED_VOCAB_FILES_MAP = {
+    "vocab_file": {
+        "vinai/phobert-base": "https://huggingface.co/vinai/phobert-base/resolve/main/vocab.txt",
+        "vinai/phobert-large": "https://huggingface.co/vinai/phobert-large/resolve/main/vocab.txt",
+    },
+    "merges_file": {
+        "vinai/phobert-base": "https://huggingface.co/vinai/phobert-base/resolve/main/bpe.codes",
+        "vinai/phobert-large": "https://huggingface.co/vinai/phobert-large/resolve/main/bpe.codes",
+    },
+}
+
+PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
+    "vinai/phobert-base": 256,
+    "vinai/phobert-large": 256,
+}
+
+
+def get_pairs(word):
+    """
+    Return set of symbol pairs in a word.
+
+    Word is represented as tuple of symbols (symbols being variable-length strings).
+    """
+    pairs = set()
+    prev_char = word[0]
+    for char in word[1:]:
+        pairs.add((prev_char, char))
+        prev_char = char
+
+    pairs = set(pairs)
+    return pairs
+
+
+class PhobertTokenizer(PreTrainedTokenizer):
+    """
+    Construct a PhoBERT tokenizer. Based on Byte-Pair-Encoding.
+
+    This tokenizer inherits from [`PreTrainedTokenizer`] which contains most of the main methods. Users should refer to
+    this superclass for more information regarding those methods.
+
+    Args:
+        vocab_file (`str`):
+            Path to the vocabulary file.
+        merges_file (`str`):
+            Path to the merges file.
+        bos_token (`st`, *optional*, defaults to `"<s>"`):
+            The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.
+
+            <Tip>
+
+            When building a sequence using special tokens, this is not the token that is used for the beginning of
+            sequence. The token used is the `cls_token`.
+
+            </Tip>
+
+        eos_token (`str`, *optional*, defaults to `"</s>"`):
+            The end of sequence token.
+
+            <Tip>
+
+            When building a sequence using special tokens, this is not the token that is used for the end of sequence.
+            The token used is the `sep_token`.
+
+            </Tip>
+
+        sep_token (`str`, *optional*, defaults to `"</s>"`):
+            The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for
+            sequence classification or for a text and a question for question answering. It is also used as the last
+            token of a sequence built with special tokens.
+        cls_token (`str`, *optional*, defaults to `"<s>"`):
+            The classifier token which is used when doing sequence classification (classification of the whole sequence
+            instead of per-token classification). It is the first token of the sequence when built with special tokens.
+        unk_token (`str`, *optional*, defaults to `"<unk>"`):
+            The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
+            token instead.
+        pad_token (`str`, *optional*, defaults to `"<pad>"`):
+            The token used for padding, for example when batching sequences of different lengths.
+        mask_token (`str`, *optional*, defaults to `"<mask>"`):
+            The token used for masking values. This is the token used when training this model with masked language
+            modeling. This is the token which the model will try to predict.
+    """
+
+    vocab_files_names = VOCAB_FILES_NAMES
+    pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
+    max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
+    model_input_names = ["input_ids", "attention_mask"]
+
+    def __init__(
+        self,
+        vocab_file,
+        merges_file,
+        bos_token="<s>",
+        eos_token="</s>",
+        sep_token="</s>",
+        cls_token="<s>",
+        unk_token="<unk>",
+        pad_token="<pad>",
+        mask_token="<mask>",
+        **kwargs
+    ):
+        super().__init__(
+            bos_token=bos_token,
+            eos_token=eos_token,
+            unk_token=unk_token,
+            sep_token=sep_token,
+            cls_token=cls_token,
+            pad_token=pad_token,
+            mask_token=mask_token,
+            **kwargs,
+        )
+
+        self.vocab_file = vocab_file
+        self.merges_file = merges_file
+
+        self.encoder = {}
+        self.encoder[self.bos_token] = 0
+        self.encoder[self.pad_token] = 1
+        self.encoder[self.eos_token] = 2
+        self.encoder[self.unk_token] = 3
+
+        self.add_from_file(vocab_file)
+        self.encoder[self.mask_token] = len(self.encoder)
+
+        self.decoder = {v: k for k, v in self.encoder.items()}
+
+        with open(merges_file, encoding="utf-8") as merges_handle:
+            merges = merges_handle.read().split("\n")[:-1]
+        merges = [tuple(merge.split()[:-1]) for merge in merges]
+        self.bpe_ranks = dict(zip(merges, range(len(merges))))
+        self.cache = {}
+
+    def build_inputs_with_special_tokens(
+        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
+    ) -> List[int]:
+        """
+        Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
+        adding special tokens. A PhoBERT sequence has the following format:
+
+        - single sequence: `<s> X </s>`
+        - pair of sequences: `<s> A </s></s> B </s>`
+
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs to which the special tokens will be added.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+
+        Returns:
+            `List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
+        """
+
+        if token_ids_1 is None:
+            return [self.cls_token_id] + token_ids_0 + [self.sep_token_id]
+        cls = [self.cls_token_id]
+        sep = [self.sep_token_id]
+        return cls + token_ids_0 + sep + sep + token_ids_1 + sep
+
+    def get_special_tokens_mask(
+        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
+    ) -> List[int]:
+        """
+        Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
+        special tokens using the tokenizer `prepare_for_model` method.
+
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+            already_has_special_tokens (`bool`, *optional*, defaults to `False`):
+                Whether or not the token list is already formatted with special tokens for the model.
+
+        Returns:
+            `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
+        """
+
+        if already_has_special_tokens:
+            return super().get_special_tokens_mask(
+                token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
+            )
+
+        if token_ids_1 is None:
+            return [1] + ([0] * len(token_ids_0)) + [1]
+        return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]
+
+    def create_token_type_ids_from_sequences(
+        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
+    ) -> List[int]:
+        """
+        Create a mask from the two sequences passed to be used in a sequence-pair classification task. PhoBERT does not
+        make use of token type ids, therefore a list of zeros is returned.
+
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+
+        Returns:
+            `List[int]`: List of zeros.
+        """
+
+        sep = [self.sep_token_id]
+        cls = [self.cls_token_id]
+
+        if token_ids_1 is None:
+            return len(cls + token_ids_0 + sep) * [0]
+        return len(cls + token_ids_0 + sep + sep + token_ids_1 + sep) * [0]
+
+    @property
+    def vocab_size(self):
+        return len(self.encoder)
+
+    def get_vocab(self):
+        return dict(self.encoder, **self.added_tokens_encoder)
+
+    def bpe(self, token):
+        if token in self.cache:
+            return self.cache[token]
+        word = tuple(token)
+        word = tuple(list(word[:-1]) + [word[-1] + "</w>"])
+        pairs = get_pairs(word)
+
+        if not pairs:
+            return token
+
+        while True:
+            bigram = min(pairs, key=lambda pair: self.bpe_ranks.get(pair, float("inf")))
+            if bigram not in self.bpe_ranks:
+                break
+            first, second = bigram
+            new_word = []
+            i = 0
+            while i < len(word):
+                try:
+                    j = word.index(first, i)
+                except ValueError:
+                    new_word.extend(word[i:])
+                    break
+                else:
+                    new_word.extend(word[i:j])
+                    i = j
+
+                if word[i] == first and i < len(word) - 1 and word[i + 1] == second:
+                    new_word.append(first + second)
+                    i += 2
+                else:
+                    new_word.append(word[i])
+                    i += 1
+            new_word = tuple(new_word)
+            word = new_word
+            if len(word) == 1:
+                break
+            else:
+                pairs = get_pairs(word)
+        word = "@@ ".join(word)
+        word = word[:-4]
+        self.cache[token] = word
+        return word
+
+    def _tokenize(self, text):
+        """Tokenize a string."""
+        split_tokens = []
+
+        words = re.findall(r"\S+\n?", text)
+
+        for token in words:
+            split_tokens.extend([t for t in self.bpe(token).split(" ")])
+        return split_tokens
+
+    def _convert_token_to_id(self, token):
+        """Converts a token (str) in an id using the vocab."""
+        return self.encoder.get(token, self.encoder.get(self.unk_token))
+
+    def _convert_id_to_token(self, index):
+        """Converts an index (integer) in a token (str) using the vocab."""
+        return self.decoder.get(index, self.unk_token)
+
+    def convert_tokens_to_string(self, tokens):
+        """Converts a sequence of tokens (string) in a single string."""
+        out_string = " ".join(tokens).replace("@@ ", "").strip()
+        return out_string
+
+    def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
+        if not os.path.isdir(save_directory):
+            logger.error(f"Vocabulary path ({save_directory}) should be a directory.")
+            return
+
+        out_vocab_file = os.path.join(
+            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
+        )
+
+        if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
+            copyfile(self.vocab_file, out_vocab_file)
+        elif not os.path.isfile(self.vocab_file):
+            with open(out_vocab_file, "w", encoding="utf-8") as fp:
+                for token, value in self.encoder.items():
+                    if token not in self.all_special_tokens:
+                        fp.write(f"{str(token)} 1\n")
+
+        out_merges_file = os.path.join(
+            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["merges_file"]
+        )
+
+        if os.path.abspath(self.merges_file) != os.path.abspath(out_merges_file) and os.path.isfile(self.merges_file):
+            copyfile(self.merges_file, out_merges_file)
+        elif not os.path.isfile(self.merges_file):
+            index = 0
+            with open(out_merges_file, "w", encoding="utf-8") as writer:
+                for bpe_tokens, token_index in sorted(self.bpe_ranks.items(), key=lambda kv: kv[1]):
+                    if index != token_index:
+                        logger.warning(
+                            f"Saving vocabulary to {out_merges_file}: BPE merge indices are not consecutive."
+                            " Please check that the tokenizer is not corrupted!"
+                        )
+                        index = token_index
+                    writer.write(" ".join(bpe_tokens) + " 1\n")
+                    index += 1
+
+        return (out_vocab_file, out_merges_file)
+
+    # def decode(self, token_ids, skip_special_tokens=False, clean_up_tokenization_spaces=True):
+    #     filtered_tokens = ' '.join(self.convert_ids_to_tokens(token_ids, skip_special_tokens=skip_special_tokens))
+    #     tokens_generated_so_far = re.sub('(@@ )', '', string=filtered_tokens)
+    #     tokens_generated_so_far = re.sub('(@@ ?$)', '', string=tokens_generated_so_far)
+    #     return ''.join(tokens_generated_so_far)
+
+    def add_from_file(self, f):
+        """
+        Loads a pre-existing dictionary from a text file and adds its symbols to this instance.
+        """
+        if isinstance(f, str):
+            try:
+                with open(f, "r", encoding="utf-8") as fd:
+                    self.add_from_file(fd)
+            except FileNotFoundError as fnfe:
+                raise fnfe
+            except UnicodeError:
+                raise Exception(f"Incorrect encoding detected in {f}, please rebuild the dataset")
+            return
+
+        lines = f.readlines()
+        for lineTmp in lines:
+            line = lineTmp.strip()
+            idx = line.rfind(" ")
+            if idx == -1:
+                raise ValueError("Incorrect dictionary format, expected '<token> <cnt>'")
+            word = line[:idx]
+            self.encoder[word] = len(self.encoder)

tokenization_phobert_fast.py

@@ -0,0 +1,328 @@
+# coding=utf-8
+# Copyright (c) 2020, VinAI Research and the HuggingFace Inc. team.
+# Copyright 2018 The Open AI Team Authors 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.
+""" Tokenization classes for PhoBERT"""
+
+import os
+from collections import defaultdict
+from shutil import copyfile
+from typing import Any, Dict, List, Optional, Tuple, Union
+
+from transformers.tokenization_utils_base import EncodingFast
+
+from transformers.tokenization_utils_fast import PreTrainedTokenizerFast
+from transformers.utils import logging
+from .tokenization_phobert import PhobertTokenizer
+
+
+logger = logging.get_logger(__name__)
+
+VOCAB_FILES_NAMES = {
+    "vocab_file": "vocab.txt",
+    "merges_file": "bpe.codes",
+    "tokenizer_file": "tokenizer.json",
+}
+
+PRETRAINED_VOCAB_FILES_MAP = {
+    "vocab_file": {
+        "vinai/phobert-base": "https://huggingface.co/vinai/phobert-base/resolve/main/vocab.txt",
+        "vinai/phobert-large": "https://huggingface.co/vinai/phobert-large/resolve/main/vocab.txt",
+    },
+    "merges_file": {
+        "vinai/phobert-base": "https://huggingface.co/vinai/phobert-base/resolve/main/bpe.codes",
+        "vinai/phobert-large": "https://huggingface.co/vinai/phobert-large/resolve/main/bpe.codes",
+    },
+    "tokenizer_file": {
+        "vinai/phobert-base": "https://huggingface.co/vinai/phobert-base/resolve/main/tokenizer.json",
+        "vinai/phobert-large": "https://huggingface.co/vinai/phobert-large/resolve/main/tokenizer.json",
+    },
+}
+
+PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
+    "vinai/phobert-base": 256,
+    "vinai/phobert-large": 256,
+}
+
+
+class PhobertTokenizerFast(PreTrainedTokenizerFast):
+    """
+    Construct a "Fast" BPE tokenizer for PhoBERT (backed by HuggingFace's *tokenizers* library).
+
+    Peculiarities:
+
+    - uses BERT's pre-tokenizer: BertPreTokenizer splits tokens on spaces, and also on punctuation. Each occurrence of
+      a punctuation character will be treated separately.
+
+    This tokenizer inherits from [`PreTrainedTokenizer`] which contains most of the methods. Users should refer to the
+    superclass for more information regarding methods.
+
+    Args:
+        vocab_file (`str`):
+            Path to the vocabulary file.
+        merges_file (`str`):
+            Path to the merges file.
+    """
+
+    vocab_files_names = VOCAB_FILES_NAMES
+    pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
+    max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
+    model_input_names = ["input_ids", "attention_mask"]
+    slow_tokenizer_class = PhobertTokenizer
+
+    def __init__(
+        self,
+        vocab_file=None,
+        merges_file=None,
+        tokenizer_file=None,
+        bos_token="<s>",
+        eos_token="</s>",
+        sep_token="</s>",
+        cls_token="<s>",
+        unk_token="<unk>",
+        pad_token="<pad>",
+        mask_token="<mask>",
+        **kwargs
+    ):
+        super().__init__(
+            vocab_file,
+            merges_file,
+            tokenizer_file=tokenizer_file,
+            bos_token=bos_token,
+            eos_token=eos_token,
+            sep_token=sep_token,
+            cls_token=cls_token,
+            unk_token=unk_token,
+            pad_token=pad_token,
+            mask_token=mask_token,
+            **kwargs,
+        )
+
+        self.vocab_file = vocab_file
+        self.merges_file = merges_file
+        self.can_save_slow_tokenizer = False if not self.vocab_file else True
+
+    def get_added_vocab_hacking(self):
+        """
+        Returns the added tokens in the vocabulary as a dictionary of token to index.
+
+        Returns:
+            `Dict[str, int], Dict[int, int]`: The added tokens, and their original and new ids
+        """
+        base_vocab_size = self._tokenizer.get_vocab_size(with_added_tokens=False)
+        full_vocab_size = self._tokenizer.get_vocab_size(with_added_tokens=True)
+        if full_vocab_size == base_vocab_size:
+            return {}, {}
+
+        # Tokens in added_vocab should have ids that are equal to or larger than the size of base_vocab
+        added_vocab = dict(
+            (self._tokenizer.id_to_token(index), index + 1 - base_vocab_size + self.mask_token_id)
+            for index in range(base_vocab_size, full_vocab_size)
+        )
+
+        id_mapping = dict((index, self._tokenizer.token_to_id(tok)) for tok, index in added_vocab.items())
+
+        return added_vocab, id_mapping
+
+    def _decode(
+        self,
+        token_ids: Union[int, List[int]],
+        skip_special_tokens: bool = False,
+        clean_up_tokenization_spaces: bool = True,
+        **kwargs
+    ) -> str:
+        self._decode_use_source_tokenizer = kwargs.pop("use_source_tokenizer", False)
+
+        if isinstance(token_ids, int):
+            token_ids = [token_ids]
+
+        # Mapping ids into their original values
+        _, id_mapping = self.get_added_vocab_hacking()
+        if len(id_mapping) > 0:
+            token_ids = [id_mapping[id] if id in id_mapping else id for id in token_ids]
+
+        text = self._tokenizer.decode(token_ids, skip_special_tokens=skip_special_tokens)
+
+        if clean_up_tokenization_spaces:
+            clean_text = self.clean_up_tokenization(text)
+            return clean_text
+        else:
+            return text
+
+    def _convert_encoding(
+        self,
+        encoding: EncodingFast,
+        return_token_type_ids: Optional[bool] = None,
+        return_attention_mask: Optional[bool] = None,
+        return_overflowing_tokens: bool = False,
+        return_special_tokens_mask: bool = False,
+        return_offsets_mapping: bool = False,
+        return_length: bool = False,
+        verbose: bool = True,
+    ) -> Tuple[Dict[str, Any], List[EncodingFast]]:
+        """
+        Convert the encoding representation (from low-level HuggingFace tokenizer output) to a python Dict and a list
+        of encodings, take care of building a batch from overflowing tokens.
+
+        Overflowing tokens are converted to additional examples (like batches) so the output values of the dict are
+        lists (overflows) of lists (tokens).
+
+        Output shape: (overflows, sequence length)
+        """
+        if return_token_type_ids is None:
+            return_token_type_ids = "token_type_ids" in self.model_input_names
+        if return_attention_mask is None:
+            return_attention_mask = "attention_mask" in self.model_input_names
+
+        if return_overflowing_tokens and encoding.overflowing is not None:
+            encodings = [encoding] + encoding.overflowing
+        else:
+            encodings = [encoding]
+
+        encoding_dict = defaultdict(list)
+        added_vocab, _ = self.get_added_vocab_hacking()
+        for e in encodings:
+            # encoding_dict["input_ids"].append(e.ids)
+            # Reassign ids of tokens due to the hacking strategy
+            ids = []
+            for id, token in zip(e.ids, e.tokens):
+                if id <= self.mask_token_id:
+                    ids.append(id)
+                else:
+                    if token.strip() in added_vocab:
+                        ids.append(added_vocab[token.strip()])
+                    else:
+                        ids.append(self.unk_token_id)
+
+            encoding_dict["input_ids"].append(ids)
+
+            if return_token_type_ids:
+                encoding_dict["token_type_ids"].append(e.type_ids)
+            if return_attention_mask:
+                encoding_dict["attention_mask"].append(e.attention_mask)
+            if return_special_tokens_mask:
+                encoding_dict["special_tokens_mask"].append(e.special_tokens_mask)
+            if return_offsets_mapping:
+                encoding_dict["offset_mapping"].append(e.offsets)
+            if return_length:
+                # encoding_dict["length"].append(len(e.ids))
+                encoding_dict["length"].append(len(ids))
+
+        return encoding_dict, encodings
+
+    def build_inputs_with_special_tokens(
+        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
+    ) -> List[int]:
+        """
+        Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
+        adding special tokens. A PhoBERT sequence has the following format:
+
+        - single sequence: `<s> X </s>`
+        - pair of sequences: `<s> A </s></s> B </s>`
+
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs to which the special tokens will be added.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+
+        Returns:
+            `List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
+        """
+
+        if token_ids_1 is None:
+            return [self.cls_token_id] + token_ids_0 + [self.sep_token_id]
+        cls = [self.cls_token_id]
+        sep = [self.sep_token_id]
+        return cls + token_ids_0 + sep + sep + token_ids_1 + sep
+
+    def get_special_tokens_mask(
+        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
+    ) -> List[int]:
+        """
+        Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
+        special tokens using the tokenizer `prepare_for_model` method.
+
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+            already_has_special_tokens (`bool`, *optional*, defaults to `False`):
+                Whether or not the token list is already formatted with special tokens for the model.
+
+        Returns:
+            `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
+        """
+
+        if already_has_special_tokens:
+            return super().get_special_tokens_mask(
+                token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
+            )
+
+        if token_ids_1 is None:
+            return [1] + ([0] * len(token_ids_0)) + [1]
+        return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]
+
+    def create_token_type_ids_from_sequences(
+        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
+    ) -> List[int]:
+        """
+        Create a mask from the two sequences passed to be used in a sequence-pair classification task. PhoBERT does not
+        make use of token type ids, therefore a list of zeros is returned.
+
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+
+        Returns:
+            `List[int]`: List of zeros.
+
+        """
+
+        sep = [self.sep_token_id]
+        cls = [self.cls_token_id]
+
+        if token_ids_1 is None:
+            return len(cls + token_ids_0 + sep) * [0]
+        return len(cls + token_ids_0 + sep + sep + token_ids_1 + sep) * [0]
+
+    def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
+        if not self.can_save_slow_tokenizer:
+            raise ValueError(
+                "Your fast tokenizer does not have the necessary information to save the vocabulary for a slow "
+                "tokenizer."
+            )
+
+        if not os.path.isdir(save_directory):
+            logger.error(f"Vocabulary path ({save_directory}) should be a directory.")
+            return
+
+        out_vocab_file = os.path.join(
+            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
+        )
+
+        out_merges_file = os.path.join(
+            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["merges_file"]
+        )
+
+        if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file):
+            copyfile(self.vocab_file, out_vocab_file)
+
+        if os.path.abspath(self.merges_file) != os.path.abspath(out_merges_file):
+            copyfile(self.merges_file, out_merges_file)
+
+        return (out_vocab_file, out_merges_file)

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d811e9a47e2a1e14dc4b8144bced90f3376ed6ee01f1b8cb526f8e47c729919
+size 3451