configuration_omchat.py

from transformers import LlamaConfig, PretrainedConfig
from transformers.utils import logging
from transformers import Qwen2Config, Qwen2Model, Qwen2ForCausalLM, AutoConfig, AutoModelForCausalLM


logger = logging.get_logger(__name__)

class InternVisionConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`InternVisionModel`]. It is used to
    instantiate a vision encoder according to the specified arguments, defining the model architecture.

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

    Args:
        num_channels (`int`, *optional*, defaults to 3):
            Number of color channels in the input images (e.g., 3 for RGB).
        patch_size (`int`, *optional*, defaults to 14):
            The size (resolution) of each patch.
        image_size (`int`, *optional*, defaults to 224):
            The size (resolution) of each image.
        qkv_bias (`bool`, *optional*, defaults to `False`):
            Whether to add a bias to the queries and values in the self-attention layers.
        hidden_size (`int`, *optional*, defaults to 3200):
            Dimensionality of the encoder layers and the pooler layer.
        num_attention_heads (`int`, *optional*, defaults to 25):
            Number of attention heads for each attention layer in the Transformer encoder.
        intermediate_size (`int`, *optional*, defaults to 12800):
            Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
        qk_normalization (`bool`, *optional*, defaults to `True`):
            Whether to normalize the queries and keys in the self-attention layers.
        num_hidden_layers (`int`, *optional*, defaults to 48):
            Number of hidden layers in the Transformer encoder.
        use_flash_attn (`bool`, *optional*, defaults to `True`):
            Whether to use flash attention mechanism.
        hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`):
            The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
            `"relu"`, `"selu"` and `"gelu_new"` ``"gelu"` are supported.
        layer_norm_eps (`float`, *optional*, defaults to 1e-6):
            The epsilon used by the layer normalization layers.
        dropout (`float`, *optional*, defaults to 0.0):
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        drop_path_rate (`float`, *optional*, defaults to 0.0):
            Dropout rate for stochastic depth.
        attention_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for the attention probabilities.
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        initializer_factor (`float`, *optional*, defaults to 0.1):
            A factor for layer scale.
    """

    model_type = 'intern_vit_6b'

    def __init__(
            self,
            num_channels=3,
            patch_size=14,
            image_size=448,
            qkv_bias=False,
            hidden_size=3200,
            num_attention_heads=25,
            intermediate_size=12800,
            qk_normalization=True,
            num_hidden_layers=45,
            use_flash_attn=True,
            hidden_act='gelu',
            layer_norm_eps=1e-6,
            dropout=0.0,
            drop_path_rate=0.0,
            attention_dropout=0.0,
            initializer_range=1e-10,
            initializer_factor=0.1,
            **kwargs,
    ):
        super().__init__(**kwargs)

        self.hidden_size = hidden_size
        self.intermediate_size = intermediate_size
        self.dropout = dropout
        self.drop_path_rate = drop_path_rate
        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.initializer_range = initializer_range
        self.initializer_factor = initializer_factor
        self.attention_dropout = attention_dropout
        self.layer_norm_eps = layer_norm_eps
        self.hidden_act = hidden_act
        self.qkv_bias = qkv_bias
        self.qk_normalization = qk_normalization
        self.use_flash_attn = use_flash_attn


class OmChatConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`OmChatForConditionalGeneration`]. 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-v1.6-mistral-7b-hf](https://huggingface.co/llava-hf/llava-v1.6-mistral-7b-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 `CLIPVisionConfig`):
            The config object or dictionary of the vision backbone.
        text_config (`Union[AutoConfig, dict]`, *optional*, defaults to `LlamaConfig`):
            The config object or dictionary of the text backbone.
        ignore_index (`int`, *optional*, defaults to -100):
            The ignore index for the loss function.
        image_token_index (`int`, *optional*, defaults to 32000):
            The image token index to encode the image 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 `"default"`):
            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 (`int`, *optional*, defaults to -2):
            The index of the layer to select the vision feature.
        image_grid_pinpoints (`List`, *optional*, defaults to `[[336, 672], [672, 336], [672, 672], [1008, 336], [336, 1008]]`):
            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.

    Example:

    ```python
    >>> from transformers import OmChatForConditionalGeneration, OmChatConfig, CLIPVisionConfig, LlamaConfig

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

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

    >>> # Initializing a Llava-Next llava-hf/llava-v1.6-mistral-7b-hf style configuration
    >>> configuration = OmChatConfig(vision_config, text_config)

    >>> # Initializing a model from the llava-hf/llava-v1.6-mistral-7b-hf style configuration
    >>> model = OmChatForConditionalGeneration(configuration)

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

    model_type = "omchat"
    is_composition = False

    def __init__(
        self,
        vision_config=None,
        text_config=None,
        ignore_index=-100,
        image_token_index=32000,
        projector_hidden_act="gelu",
        vision_feature_select_strategy="default",
        vision_feature_layer=-1,
        image_grid_pinpoints=None,
        tie_word_embeddings=False,
        **kwargs,
    ):
        self.ignore_index = ignore_index
        self.image_token_index = image_token_index
        self.projector_hidden_act = projector_hidden_act

        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
        image_grid_pinpoints = (
            image_grid_pinpoints
            if image_grid_pinpoints is not None
            else [[336, 672], [672, 336], [672, 672], [1008, 336], [336, 1008]]
        )
        self.image_grid_pinpoints = image_grid_pinpoints

        if isinstance(vision_config, dict):

            vision_config = InternVisionConfig(**vision_config)
        self.vision_config = vision_config

        if isinstance(text_config, dict):
            text_config = Qwen2Config(**text_config)

        self.text_config = text_config

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