File size: 9,839 Bytes
6fc683c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
# coding=utf-8
# Copyright 2019-present CNRS, Facebook Inc. 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.
""" Flaubert configuration, based on XLM. """


import logging

from .configuration_xlm import XLMConfig


logger = logging.getLogger(__name__)

FLAUBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
    "flaubert-small-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/flaubert/flaubert_small_cased/config.json",
    "flaubert-base-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/flaubert/flaubert_base_uncased/config.json",
    "flaubert-base-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/flaubert/flaubert_base_cased/config.json",
    "flaubert-large-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/flaubert/flaubert_large_cased/config.json",
}


class FlaubertConfig(XLMConfig):
    """
        Configuration class to store the configuration of a `FlaubertModel`.
        This is the configuration class to store the configuration of a :class:`~transformers.XLMModel`.
        It is used to instantiate an XLM model according to the specified arguments, defining the model
        architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of
        the `xlm-mlm-en-2048 <https://huggingface.co/xlm-mlm-en-2048>`__ architecture.

        Configuration objects inherit from  :class:`~transformers.PretrainedConfig` and can be used
        to control the model outputs. Read the documentation from  :class:`~transformers.PretrainedConfig`
        for more information.

        Args:
            pre_norm (:obj:`bool`, `optional`, defaults to :obj:`False`):
                Whether to apply the layer normalization before or after the feed forward layer following the
                attention in each layer (Vaswani et al., Tensor2Tensor for Neural Machine Translation. 2018)
            layerdrop (:obj:`float`, `optional`, defaults to 0.0):
                Probability to drop layers during training (Fan et al., Reducing Transformer Depth on Demand
                with Structured Dropout. ICLR 2020)
            vocab_size (:obj:`int`, optional, defaults to 30145):
                Vocabulary size of the Flaubert model. Defines the different tokens that
                can be represented by the `inputs_ids` passed to the forward method of :class:`~transformers.FlaubertModel`.
            emb_dim (:obj:`int`, optional, defaults to 2048):
                Dimensionality of the encoder layers and the pooler layer.
            n_layer (:obj:`int`, optional, defaults to 12):
                Number of hidden layers in the Transformer encoder.
            n_head (:obj:`int`, optional, defaults to 16):
                Number of attention heads for each attention layer in the Transformer encoder.
            dropout (:obj:`float`, optional, defaults to 0.1):
                The dropout probability for all fully connected
                layers in the embeddings, encoder, and pooler.
            attention_dropout (:obj:`float`, optional, defaults to 0.1):
                The dropout probability for the attention mechanism
            gelu_activation (:obj:`boolean`, optional, defaults to :obj:`True`):
                The non-linear activation function (function or string) in the
                encoder and pooler. If set to `True`, "gelu" will be used instead of "relu".
            sinusoidal_embeddings (:obj:`boolean`, optional, defaults to :obj:`False`):
                Whether to use sinusoidal positional embeddings instead of absolute positional embeddings.
            causal (:obj:`boolean`, optional, defaults to :obj:`False`):
                Set this to `True` for the model to behave in a causal manner.
                Causal models use a triangular attention mask in order to only attend to the left-side context instead
                if a bidirectional context.
            asm (:obj:`boolean`, optional, defaults to :obj:`False`):
                Whether to use an adaptive log softmax projection layer instead of a linear layer for the prediction
                layer.
            n_langs (:obj:`int`, optional, defaults to 1):
                The number of languages the model handles. Set to 1 for monolingual models.
            use_lang_emb (:obj:`boolean`, optional, defaults to :obj:`True`)
                Whether to use language embeddings. Some models use additional language embeddings, see
                `the multilingual models page <http://huggingface.co/transformers/multilingual.html#xlm-language-embeddings>`__
                for information on how to use them.
            max_position_embeddings (:obj:`int`, optional, defaults to 512):
                The maximum sequence length that this model might
                ever be used with. Typically set this to something large just in case
                (e.g., 512 or 1024 or 2048).
            embed_init_std (:obj:`float`, optional, defaults to 2048^-0.5):
                The standard deviation of the truncated_normal_initializer for
                initializing the embedding matrices.
            init_std (:obj:`int`, optional, defaults to 50257):
                The standard deviation of the truncated_normal_initializer for
                initializing all weight matrices except the embedding matrices.
            layer_norm_eps (:obj:`float`, optional, defaults to 1e-12):
                The epsilon used by the layer normalization layers.
            bos_index (:obj:`int`, optional, defaults to 0):
                The index of the beginning of sentence token in the vocabulary.
            eos_index (:obj:`int`, optional, defaults to 1):
                The index of the end of sentence token in the vocabulary.
            pad_index (:obj:`int`, optional, defaults to 2):
                The index of the padding token in the vocabulary.
            unk_index (:obj:`int`, optional, defaults to 3):
                The index of the unknown token in the vocabulary.
            mask_index (:obj:`int`, optional, defaults to 5):
                The index of the masking token in the vocabulary.
            is_encoder(:obj:`boolean`, optional, defaults to :obj:`True`):
                Whether the initialized model should be a transformer encoder or decoder as seen in Vaswani et al.
            summary_type (:obj:`string`, optional, defaults to "first"):
                Argument used when doing sequence summary. Used in for the multiple choice head in
                :class:`~transformers.XLMForSequenceClassification`.
                Is one of the following options:

                - 'last' => take the last token hidden state (like XLNet)
                - 'first' => take the first token hidden state (like Bert)
                - 'mean' => take the mean of all tokens hidden states
                - 'cls_index' => supply a Tensor of classification token position (GPT/GPT-2)
                - 'attn' => Not implemented now, use multi-head attention
            summary_use_proj (:obj:`boolean`, optional, defaults to :obj:`True`):
                Argument used when doing sequence summary. Used in for the multiple choice head in
                :class:`~transformers.XLMForSequenceClassification`.
                Add a projection after the vector extraction
            summary_activation (:obj:`string` or :obj:`None`, optional, defaults to :obj:`None`):
                Argument used when doing sequence summary. Used in for the multiple choice head in
                :class:`~transformers.XLMForSequenceClassification`.
                'tanh' => add a tanh activation to the output, Other => no activation.
            summary_proj_to_labels (:obj:`boolean`, optional, defaults to :obj:`True`):
                Argument used when doing sequence summary. Used in for the multiple choice head in
                :class:`~transformers.XLMForSequenceClassification`.
                If True, the projection outputs to config.num_labels classes (otherwise to hidden_size). Default: False.
            summary_first_dropout (:obj:`float`, optional, defaults to 0.1):
                Argument used when doing sequence summary. Used in for the multiple choice head in
                :class:`~transformers.XLMForSequenceClassification`.
                Add a dropout before the projection and activation
            start_n_top (:obj:`int`, optional, defaults to 5):
                Used in the SQuAD evaluation script for XLM and XLNet.
            end_n_top (:obj:`int`, optional, defaults to 5):
                Used in the SQuAD evaluation script for XLM and XLNet.
            mask_token_id (:obj:`int`, optional, defaults to 0):
                Model agnostic parameter to identify masked tokens when generating text in an MLM context.
            lang_id (:obj:`int`, optional, defaults to 1):
                The ID of the language used by the model. This parameter is used when generating
                text in a given language.
    """

    pretrained_config_archive_map = FLAUBERT_PRETRAINED_CONFIG_ARCHIVE_MAP
    model_type = "flaubert"

    def __init__(self, layerdrop=0.0, pre_norm=False, **kwargs):
        """Constructs FlaubertConfig.
        """
        super().__init__(**kwargs)
        self.layerdrop = layerdrop
        self.pre_norm = pre_norm