File size: 10,912 Bytes
37eaef1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
#           This file was automatically generated from src/transformers/models/modernbert/modular_modernbert.py.
#               Do NOT edit this file manually as any edits will be overwritten by the generation of
#             the file from the modular. If any change should be done, please apply the change to the
#                          modular_modernbert.py file directly. One of our CI enforces this.
#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# Copyright 2024 Answer.AI, LightOn, and contributors, and the HuggingFace Inc. team. 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 typing import Literal

from transformers.configuration_utils import PretrainedConfig


class ModernBertConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`ModernBertModel`]. It is used to instantiate an ModernBert
    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 ModernBERT-base.
    e.g. [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base)

    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
    documentation from [`PretrainedConfig`] for more information.

    Args:
        vocab_size (`int`, *optional*, defaults to 50368):
            Vocabulary size of the ModernBert model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`ModernBertModel`]
        hidden_size (`int`, *optional*, defaults to 768):
            Dimension of the hidden representations.
        intermediate_size (`int`, *optional*, defaults to 1152):
            Dimension of the MLP representations.
        num_hidden_layers (`int`, *optional*, defaults to 22):
            Number of hidden layers in the Transformer decoder.
        num_attention_heads (`int`, *optional*, defaults to 12):
            Number of attention heads for each attention layer in the Transformer decoder.
        hidden_activation (`str` or `function`, *optional*, defaults to `"gelu"`):
            The non-linear activation function (function or string) in the decoder. Will default to `"gelu"`
            if not specified.
        max_position_embeddings (`int`, *optional*, defaults to 8192):
            The maximum sequence length that this model might ever be used with.
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        initializer_cutoff_factor (`float`, *optional*, defaults to 2.0):
            The cutoff factor for the truncated_normal_initializer for initializing all weight matrices.
        norm_eps (`float`, *optional*, defaults to 1e-05):
            The epsilon used by the rms normalization layers.
        norm_bias (`bool`, *optional*, defaults to `False`):
            Whether to use bias in the normalization layers.
        pad_token_id (`int`, *optional*, defaults to 50283):
            Padding token id.
        eos_token_id (`int`, *optional*, defaults to 50282):
            End of stream token id.
        bos_token_id (`int`, *optional*, defaults to 50281):
            Beginning of stream token id.
        cls_token_id (`int`, *optional*, defaults to 50281):
            Classification token id.
        sep_token_id (`int`, *optional*, defaults to 50282):
            Separation token id.
        global_rope_theta (`float`, *optional*, defaults to 160000.0):
            The base period of the global RoPE embeddings.
        attention_bias (`bool`, *optional*, defaults to `False`):
            Whether to use a bias in the query, key, value and output projection layers during self-attention.
        attention_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for the attention probabilities.
        global_attn_every_n_layers (`int`, *optional*, defaults to 3):
            The number of layers between global attention layers.
        local_attention (`int`, *optional*, defaults to 128):
            The window size for local attention.
        local_rope_theta (`float`, *optional*, defaults to 10000.0):
            The base period of the local RoPE embeddings.
        embedding_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for the embeddings.
        mlp_bias (`bool`, *optional*, defaults to `False`):
            Whether to use bias in the MLP layers.
        mlp_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for the MLP layers.
        decoder_bias (`bool`, *optional*, defaults to `True`):
            Whether to use bias in the decoder layers.
        classifier_pooling (`str`, *optional*, defaults to `"cls"`):
            The pooling method for the classifier. Should be either `"cls"` or `"mean"`. In local attention layers, the
            CLS token doesn't attend to all tokens on long sequences.
        classifier_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for the classifier.
        classifier_bias (`bool`, *optional*, defaults to `False`):
            Whether to use bias in the classifier.
        classifier_activation (`str`, *optional*, defaults to `"gelu"`):
            The activation function for the classifier.
        deterministic_flash_attn (`bool`, *optional*, defaults to `False`):
            Whether to use deterministic flash attention. If `False`, inference will be faster but not deterministic.
        sparse_prediction (`bool`, *optional*, defaults to `False`):
            Whether to use sparse prediction for the masked language model instead of returning the full dense logits.
        sparse_pred_ignore_index (`int`, *optional*, defaults to -100):
            The index to ignore for the sparse prediction.
        reference_compile (`bool`, *optional*):
            Whether to compile the layers of the model which were compiled during pretraining. If `None`, then parts of
            the model will be compiled if 1) `triton` is installed, 2) the model is not on MPS, 3) the model is not
            shared between devices, and 4) the model is not resized after initialization. If `True`, then the model may
            be faster in some scenarios.

    Examples:

    ```python
    >>> from transformers import ModernBertModel, ModernBertConfig

    >>> # Initializing a ModernBert style configuration
    >>> configuration = ModernBertConfig()

    >>> # Initializing a model from the modernbert-base style configuration
    >>> model = ModernBertModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```"""

    model_type = "modernbert"
    keys_to_ignore_at_inference = ["past_key_values"]

    def __init__(
        self,
        vocab_size=50368,
        hidden_size=768,
        intermediate_size=1152,
        num_hidden_layers=22,
        num_attention_heads=12,
        hidden_activation="gelu",
        max_position_embeddings=8192,
        initializer_range=0.02,
        initializer_cutoff_factor=2.0,
        norm_eps=1e-5,
        norm_bias=False,
        pad_token_id=50283,
        eos_token_id=50282,
        bos_token_id=50281,
        cls_token_id=50281,
        sep_token_id=50282,
        global_rope_theta=160000.0,
        attention_bias=False,
        attention_dropout=0.0,
        global_attn_every_n_layers=3,
        local_attention=128,
        local_rope_theta=10000.0,
        embedding_dropout=0.0,
        mlp_bias=False,
        mlp_dropout=0.0,
        decoder_bias=True,
        classifier_pooling: Literal["cls", "mean"] = "cls",
        classifier_dropout=0.0,
        classifier_bias=False,
        classifier_activation="gelu",
        deterministic_flash_attn=False,
        sparse_prediction=False,
        sparse_pred_ignore_index=-100,
        reference_compile=None,
        **kwargs,
    ):
        super().__init__(
            pad_token_id=pad_token_id,
            bos_token_id=bos_token_id,
            eos_token_id=eos_token_id,
            cls_token_id=cls_token_id,
            sep_token_id=sep_token_id,
            **kwargs,
        )
        self.vocab_size = vocab_size
        self.max_position_embeddings = max_position_embeddings
        self.hidden_size = hidden_size
        self.intermediate_size = intermediate_size
        self.num_hidden_layers = num_hidden_layers
        self.num_attention_heads = num_attention_heads
        self.initializer_range = initializer_range
        self.initializer_cutoff_factor = initializer_cutoff_factor
        self.norm_eps = norm_eps
        self.norm_bias = norm_bias
        self.global_rope_theta = global_rope_theta
        self.attention_bias = attention_bias
        self.attention_dropout = attention_dropout
        self.hidden_activation = hidden_activation
        self.global_attn_every_n_layers = global_attn_every_n_layers
        self.local_attention = local_attention
        self.local_rope_theta = local_rope_theta
        self.embedding_dropout = embedding_dropout
        self.mlp_bias = mlp_bias
        self.mlp_dropout = mlp_dropout
        self.decoder_bias = decoder_bias
        self.classifier_pooling = classifier_pooling
        self.classifier_dropout = classifier_dropout
        self.classifier_bias = classifier_bias
        self.classifier_activation = classifier_activation
        self.deterministic_flash_attn = deterministic_flash_attn
        self.sparse_prediction = sparse_prediction
        self.sparse_pred_ignore_index = sparse_pred_ignore_index
        self.reference_compile = reference_compile

        if self.classifier_pooling not in ["cls", "mean"]:
            raise ValueError(
                f'Invalid value for `classifier_pooling`, should be either "cls" or "mean", but is {self.classifier_pooling}.'
            )


__all__ = ["ModernBertConfig"]