File size: 13,901 Bytes
9da5852
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
# coding=utf-8
# Copyright 2024 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.
""" Siglip model configuration"""

import os
from typing import Union

from transformers.configuration_utils import PretrainedConfig
from transformers.utils import logging


logger = logging.get_logger(__name__)

SIGLIP_PRETRAINED_CONFIG_ARCHIVE_MAP = {
    "google/siglip-base-patch16-224": "https://huggingface.co/google/siglip-base-patch16-224/resolve/main/config.json",
}


class SiglipTextConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`SiglipTextModel`]. It is used to instantiate a
    Siglip text encoder according to the specified arguments, defining the model architecture. Instantiating a
    configuration with the defaults will yield a similar configuration to that of the text encoder of the Siglip
    [google/siglip-base-patch16-224](https://huggingface.co/google/siglip-base-patch16-224) architecture.

    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 32000):
            Vocabulary size of the Siglip text model. Defines the number of different tokens that can be represented by
            the `inputs_ids` passed when calling [`SiglipModel`].
        hidden_size (`int`, *optional*, defaults to 768):
            Dimensionality of the encoder layers and the pooler layer.
        intermediate_size (`int`, *optional*, defaults to 3072):
            Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
        num_hidden_layers (`int`, *optional*, defaults to 12):
            Number of hidden layers in the Transformer encoder.
        num_attention_heads (`int`, *optional*, defaults to 12):
            Number of attention heads for each attention layer in the Transformer encoder.
        max_position_embeddings (`int`, *optional*, defaults to 64):
            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).
        hidden_act (`str` or `function`, *optional*, defaults to `"gelu_pytorch_tanh"`):
            The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
            `"relu"`, `"selu"` and `"gelu_new"` `"quick_gelu"` are supported.
        layer_norm_eps (`float`, *optional*, defaults to 1e-06):
            The epsilon used by the layer normalization layers.
        attention_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for the attention probabilities.
        pad_token_id (`int`, *optional*, defaults to 1):
            The id of the padding token in the vocabulary.
        bos_token_id (`int`, *optional*, defaults to 49406):
            The id of the beginning-of-sequence token in the vocabulary.
        eos_token_id (`int`, *optional*, defaults to 49407):
            The id of the end-of-sequence token in the vocabulary.

    Example:

    ```python
    >>> from transformers import SiglipTextConfig, SiglipTextModel

    >>> # Initializing a SiglipTextConfig with google/siglip-base-patch16-224 style configuration
    >>> configuration = SiglipTextConfig()

    >>> # Initializing a SiglipTextModel (with random weights) from the google/siglip-base-patch16-224 style configuration
    >>> model = SiglipTextModel(configuration)

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

    model_type = "siglip_text_model"

    def __init__(
        self,
        vocab_size=32000,
        hidden_size=768,
        intermediate_size=3072,
        num_hidden_layers=12,
        num_attention_heads=12,
        max_position_embeddings=64,
        hidden_act="gelu_pytorch_tanh",
        layer_norm_eps=1e-6,
        attention_dropout=0.0,
        # This differs from `CLIPTokenizer`'s default and from openai/siglip
        # See https://github.com/huggingface/transformers/pull/24773#issuecomment-1632287538
        pad_token_id=1,
        bos_token_id=49406,
        eos_token_id=49407,
        _flash_attn_2_enabled=True,
        **kwargs,
    ):
        super().__init__(pad_token_id=pad_token_id, bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)

        self.vocab_size = vocab_size
        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.max_position_embeddings = max_position_embeddings
        self.layer_norm_eps = layer_norm_eps
        self.hidden_act = hidden_act
        self.attention_dropout = attention_dropout
        self._flash_attn_2_enabled = _flash_attn_2_enabled

    @classmethod
    def from_pretrained(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs) -> "PretrainedConfig":
        cls._set_token_in_kwargs(kwargs)

        config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)

        # get the text config dict if we are loading from SiglipConfig
        if config_dict.get("model_type") == "siglip":
            config_dict = config_dict["text_config"]

        if "model_type" in config_dict and hasattr(cls, "model_type") and config_dict["model_type"] != cls.model_type:
            logger.warning(
                f"You are using a model of type {config_dict['model_type']} to instantiate a model of type "
                f"{cls.model_type}. This is not supported for all configurations of models and can yield errors."
            )

        return cls.from_dict(config_dict, **kwargs)


class SiglipVisionConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`SiglipVisionModel`]. It is used to instantiate a
    Siglip vision encoder according to the specified arguments, defining the model architecture. Instantiating a
    configuration with the defaults will yield a similar configuration to that of the vision encoder of the Siglip
    [google/siglip-base-patch16-224](https://huggingface.co/google/siglip-base-patch16-224) architecture.

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

    Args:
        hidden_size (`int`, *optional*, defaults to 768):
            Dimensionality of the encoder layers and the pooler layer.
        intermediate_size (`int`, *optional*, defaults to 3072):
            Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
        num_hidden_layers (`int`, *optional*, defaults to 12):
            Number of hidden layers in the Transformer encoder.
        num_attention_heads (`int`, *optional*, defaults to 12):
            Number of attention heads for each attention layer in the Transformer encoder.
        num_channels (`int`, *optional*, defaults to 3):
            Number of channels in the input images.
        image_size (`int`, *optional*, defaults to 224):
            The size (resolution) of each image.
        patch_size (`int`, *optional*, defaults to 16):
            The size (resolution) of each patch.
        hidden_act (`str` or `function`, *optional*, defaults to `"gelu_pytorch_tanh"`):
            The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
            `"relu"`, `"selu"` and `"gelu_new"` ``"quick_gelu"` are supported.
        layer_norm_eps (`float`, *optional*, defaults to 1e-06):
            The epsilon used by the layer normalization layers.
        attention_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for the attention probabilities.

    Example:

    ```python
    >>> from transformers import SiglipVisionConfig, SiglipVisionModel

    >>> # Initializing a SiglipVisionConfig with google/siglip-base-patch16-224 style configuration
    >>> configuration = SiglipVisionConfig()

    >>> # Initializing a SiglipVisionModel (with random weights) from the google/siglip-base-patch16-224 style configuration
    >>> model = SiglipVisionModel(configuration)

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

    model_type = "siglip_vision_model"

    def __init__(
        self,
        hidden_size=768,
        intermediate_size=3072,
        num_hidden_layers=12,
        num_attention_heads=12,
        num_channels=3,
        image_size=224,
        patch_size=16,
        hidden_act="gelu_pytorch_tanh",
        layer_norm_eps=1e-6,
        attention_dropout=0.0,
        _flash_attn_2_enabled=True,
        **kwargs,
    ):
        super().__init__(**kwargs)

        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.num_channels = num_channels
        self.patch_size = patch_size
        self.image_size = image_size
        self.attention_dropout = attention_dropout
        self.layer_norm_eps = layer_norm_eps
        self.hidden_act = hidden_act
        self._flash_attn_2_enabled = _flash_attn_2_enabled

    @classmethod
    def from_pretrained(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs) -> "PretrainedConfig":
        cls._set_token_in_kwargs(kwargs)

        config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)

        # get the vision config dict if we are loading from SiglipConfig
        if config_dict.get("model_type") == "siglip":
            config_dict = config_dict["vision_config"]

        if "model_type" in config_dict and hasattr(cls, "model_type") and config_dict["model_type"] != cls.model_type:
            logger.warning(
                f"You are using a model of type {config_dict['model_type']} to instantiate a model of type "
                f"{cls.model_type}. This is not supported for all configurations of models and can yield errors."
            )

        return cls.from_dict(config_dict, **kwargs)


class SiglipConfig(PretrainedConfig):
    r"""
    [`SiglipConfig`] is the configuration class to store the configuration of a [`SiglipModel`]. It is used to
    instantiate a Siglip model according to the specified arguments, defining the text model and vision model configs.
    Instantiating a configuration with the defaults will yield a similar configuration to that of the Siglip
    [google/siglip-base-patch16-224](https://huggingface.co/google/siglip-base-patch16-224) architecture.

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

    Args:
        text_config (`dict`, *optional*):
            Dictionary of configuration options used to initialize [`SiglipTextConfig`].
        vision_config (`dict`, *optional*):
            Dictionary of configuration options used to initialize [`SiglipVisionConfig`].
        kwargs (*optional*):
            Dictionary of keyword arguments.

    Example:

    ```python
    >>> from transformers import SiglipConfig, SiglipModel

    >>> # Initializing a SiglipConfig with google/siglip-base-patch16-224 style configuration
    >>> configuration = SiglipConfig()

    >>> # Initializing a SiglipModel (with random weights) from the google/siglip-base-patch16-224 style configuration
    >>> model = SiglipModel(configuration)

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

    >>> # We can also initialize a SiglipConfig from a SiglipTextConfig and a SiglipVisionConfig
    >>> from transformers import SiglipTextConfig, SiglipVisionConfig

    >>> # Initializing a SiglipText and SiglipVision configuration
    >>> config_text = SiglipTextConfig()
    >>> config_vision = SiglipVisionConfig()

    >>> config = SiglipConfig.from_text_vision_configs(config_text, config_vision)
    ```"""

    model_type = "siglip"

    def __init__(self, text_config=None, vision_config=None, **kwargs):
        super().__init__(**kwargs)

        if text_config is None:
            text_config = {}
            logger.info("`text_config` is `None`. Initializing the `SiglipTextConfig` with default values.")

        if vision_config is None:
            vision_config = {}
            logger.info("`vision_config` is `None`. initializing the `SiglipVisionConfig` with default values.")

        self.text_config = SiglipTextConfig(**text_config)
        self.vision_config = SiglipVisionConfig(**vision_config)

        self.initializer_factor = 1.0

    @classmethod
    def from_text_vision_configs(cls, text_config: SiglipTextConfig, vision_config: SiglipVisionConfig, **kwargs):
        r"""
        Instantiate a [`SiglipConfig`] (or a derived class) from siglip text model configuration and siglip vision
        model configuration.

        Returns:
            [`SiglipConfig`]: An instance of a configuration object
        """

        return cls(text_config=text_config.to_dict(), vision_config=vision_config.to_dict(), **kwargs)