File size: 8,342 Bytes
3a1fbb9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# coding=utf-8
# Copyright 2024 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 transformers.configuration_utils import PretrainedConfig
from transformers.utils import (
    logging,
)
from transformers.models.auto import CONFIG_MAPPING, AutoConfig


logger = logging.get_logger(__name__)


class LlavaOnevisionConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`LlavaOnevisionForConditionalGeneration`]. It is used to instantiate an
    Llava-NeXT 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 [llava-hf/llava-onevision-qwen2-7b-ov-hf](https://huggingface.co/llava-hf/llava-onevision-qwen2-7b-ov-hf)
    model.

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

    Args:
        vision_config (`Union[AutoConfig, dict]`,  *optional*, defaults to `SiglipVisionConfig`):
            The config object or dictionary of the vision backbone.
        text_config (`Union[AutoConfig, dict]`, *optional*, defaults to `Qwen2Config`):
            The config object or dictionary of the text backbone.
        image_token_index (`int`, *optional*, defaults to 151646):
            The image token index to encode the image prompt.
        video_token_index (`int`, *optional*, defaults to 151647):
            The video token index to encode the video prompt.
        projector_hidden_act (`str`, *optional*, defaults to `"gelu"`):
            The activation function used by the multimodal projector.
        vision_feature_select_strategy (`str`, *optional*, defaults to `"full"`):
            The feature selection strategy used to select the vision feature from the vision backbone.
            Can be one of `"default"` or `"full"`. If `"default"`, the CLS token is removed from the vision features.
            If `"full"`, the full vision features are used.
        vision_feature_layer (`Union[int, List[int]]`, *optional*, defaults to -1):
            The index of the layer to select the vision feature. If multiple indices are provided,
            the vision feature of the corresponding indices will be concatenated to form the
            vision features.
        vision_aspect_ratio (`str`, *optional*, defaults to `"anyres_max_9"`):
            Aspect ratio used when processong image features. The default value is "anyres_max_9".
        image_grid_pinpoints (`List`, *optional*):
            A list of possible resolutions to use for processing high resolution images. Each item in the list should be a tuple or list
            of the form `(height, width)`.
        tie_word_embeddings (`bool`, *optional*, defaults to `False`):
            Whether the model's input and output word embeddings should be tied.
        multimodal_projector_bias (`bool`, *optional*, defaults to `True`):
            Whether to use bias in the multimodal projector.

    Example:

    ```python
    >>> from transformers import LlavaOnevisionForConditionalGeneration, LlavaOnevisionConfig, SiglipVisionConfig, Qwen2Config

    >>> # Initializing a CLIP-vision config
    >>> vision_config = SiglipVisionConfig()

    >>> # Initializing a Llama config
    >>> text_config = Qwen2Config()

    >>> # Initializing a Llava-Next llava-hf/llava-onevision-qwen2-7b-ov-hf style configuration
    >>> configuration = LlavaOnevisionConfig(vision_config, text_config)

    >>> # Initializing a model from the llava-hf/llava-onevision-qwen2-7b-ov-hf style configuration
    >>> model = LlavaOnevisionForConditionalGeneration(configuration)

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

    model_type = "sdar_v"
    attribute_map = {
        "image_token_id": "image_token_index",
        "video_token_id": "video_token_index",
    }
    sub_configs = {"text_config": AutoConfig, "vision_config": AutoConfig}

    def __init__(
        self,
        vision_config=None,
        text_config=None,
        image_token_index=151646,
        video_token_index=151647,
        projector_hidden_act="gelu",
        vision_feature_select_strategy="full",
        vision_feature_layer=-1,
        vision_aspect_ratio="anyres_max_9",
        image_grid_pinpoints=None,
        tie_word_embeddings=False,
        multimodal_projector_bias=True,
        **kwargs,
    ):
        self.image_token_index = image_token_index
        self.video_token_index = video_token_index
        self.projector_hidden_act = projector_hidden_act
        self.multimodal_projector_bias = multimodal_projector_bias

        if vision_feature_select_strategy not in ["default", "full"]:
            raise ValueError(
                "vision_feature_select_strategy should be one of 'default', 'full'."
                f"Got: {vision_feature_select_strategy}"
            )

        self.vision_feature_select_strategy = vision_feature_select_strategy
        self.vision_feature_layer = vision_feature_layer
        self.vision_aspect_ratio = vision_aspect_ratio
        image_grid_pinpoints = (
            image_grid_pinpoints
            if image_grid_pinpoints is not None
            else [
                [384, 384],
                [384, 768],
                [384, 1152],
                [384, 1536],
                [384, 1920],
                [384, 2304],
                [768, 384],
                [768, 768],
                [768, 1152],
                [768, 1536],
                [768, 1920],
                [768, 2304],
                [1152, 384],
                [1152, 768],
                [1152, 1152],
                [1152, 1536],
                [1152, 1920],
                [1152, 2304],
                [1536, 384],
                [1536, 768],
                [1536, 1152],
                [1536, 1536],
                [1536, 1920],
                [1536, 2304],
                [1920, 384],
                [1920, 768],
                [1920, 1152],
                [1920, 1536],
                [1920, 1920],
                [1920, 2304],
                [2304, 384],
                [2304, 768],
                [2304, 1152],
                [2304, 1536],
                [2304, 1920],
                [2304, 2304],
            ]
        )
        self.image_grid_pinpoints = image_grid_pinpoints

        if isinstance(vision_config, dict):
            vision_config["model_type"] = (
                vision_config["model_type"] if "model_type" in vision_config else "siglip_vision_model"
            )
            vision_config = CONFIG_MAPPING[vision_config["model_type"]](**vision_config)
        elif vision_config is None:
            vision_config = CONFIG_MAPPING["siglip_vision_model"](
                hidden_size=1152,
                intermediate_size=4304,
                patch_size=14,
                image_size=384,
                num_hidden_layers=26,
                num_attention_heads=14,
                vision_use_head=False,
            )

        self.vision_config = vision_config

        if isinstance(text_config, dict):
            text_config["model_type"] = text_config["model_type"] if "model_type" in text_config else "qwen2"
            try:
                text_config = CONFIG_MAPPING[text_config["model_type"]](**text_config)
            except:
                from .configuration_sdar import SDARConfig
                text_config = SDARConfig(**text_config)
        elif text_config is None:
            text_config = CONFIG_MAPPING["qwen2"]()

        self.text_config = text_config

        super().__init__(tie_word_embeddings=tie_word_embeddings, **kwargs)


__all__ = ["LlavaOnevisionConfig"]