
    sgB                         d dl mZ d dlmZ d dlmZ ddlmZmZ  ej                  e
      Z G d de      Z G d d	e      Z G d
 de      Zy)   )PretrainedConfig)!MODEL_FOR_CAUSAL_LM_MAPPING_NAMES)logging   )CONFIG_MAPPING
AutoConfigc                   B     e Zd ZdZdZdZ	 	 	 	 	 	 	 	 	 	 	 d fd	Z xZS )InstructBlipVideoVisionConfiga  
    This is the configuration class to store the configuration of a [`InstructBlipVideoVisionModel`]. It is used to
    instantiate a InstructBlipVideo vision encoder according to the specified arguments, defining the model architecture.
    Instantiating a configuration defaults will yield a similar configuration to that of the InstructBlipVideo
    [Salesforce/instruct-blip-flan-t5](https://huggingface.co/Salesforce/instruct-blip-flan-t5) 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 1408):
            Dimensionality of the encoder layers and the pooler layer.
        intermediate_size (`int`, *optional*, defaults to 6144):
            Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
        num_hidden_layers (`int`, *optional*, defaults to 39):
            Number of hidden layers in the Transformer encoder.
        num_attention_heads (`int`, *optional*, defaults to 16):
            Number of attention heads for each attention layer in the Transformer encoder.
        image_size (`int`, *optional*, defaults to 224):
            The size (resolution) of each image.
        patch_size (`int`, *optional*, defaults to 14):
            The size (resolution) of each patch.
        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. to 1e-5): The epsilon used by the layer
            normalization layers.
        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.
        initializer_range (`float`, *optional*, defaults to 1e-10):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        qkv_bias (`bool`, *optional*, defaults to `True`):
            Whether to add a bias to the queries and values in the self-attention layers.

    Example:

    ```python
    >>> from transformers import InstructBlipVideoVisionConfig, InstructBlipVideoVisionModel

    >>> # Initializing a InstructBlipVideoVisionConfig with Salesforce/instruct-blip-flan-t5 style configuration
    >>> configuration = InstructBlipVideoVisionConfig()

    >>> # Initializing a InstructBlipVideoVisionModel (with random weights) from the Salesforce/instruct-blip-flan-t5 style configuration
    >>> model = InstructBlipVideoVisionModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```instructblipvideo_vision_modelvision_configc                     t        |   di | || _        || _        || _        || _        || _        || _        |
| _        |	| _	        || _
        || _        || _        y )N )super__init__hidden_sizeintermediate_sizenum_hidden_layersnum_attention_heads
patch_size
image_sizeinitializer_rangeattention_dropoutlayer_norm_eps
hidden_actqkv_bias)selfr   r   r   r   r   r   r   r   r   r   r   kwargs	__class__s                x/var/www/html/venv/lib/python3.12/site-packages/transformers/models/instructblipvideo/configuration_instructblipvideo.pyr   z&InstructBlipVideoVisionConfig.__init__V   si     	"6"&!2!2#6 $$!2!2,$     )  i   '            gelugư>g        g|=T__name__
__module____qualname____doc__
model_typebase_config_keyr   __classcell__r   s   @r   r
   r
       sB    0d 2J%O ! !r    r
   c                   J     e Zd ZdZdZdZ	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 d fd	Z xZS )InstructBlipVideoQFormerConfiga  
    This is the configuration class to store the configuration of a [`InstructBlipVideoQFormerModel`]. It is used to
    instantiate a InstructBlipVideo Querying Transformer (Q-Former) 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 InstructBlipVideo [Salesforce/instruct-blip-flan-t5](https://huggingface.co/Salesforce/instruct-blip-flan-t5)
    architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs.
    Read the documentation from [`PretrainedConfig`] for more information.

    Note that [`InstructBlipVideoQFormerModel`] is very similar to [`BertLMHeadModel`] with interleaved cross-attention.

    Args:
        vocab_size (`int`, *optional*, defaults to 30522):
            Vocabulary size of the Q-Former model. Defines the number of different tokens that can be represented by
            the `inputs_ids` passed when calling the model.
        hidden_size (`int`, *optional*, defaults to 768):
            Dimensionality of the encoder layers and the pooler layer.
        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.
        intermediate_size (`int`, *optional*, defaults to 3072):
            Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder.
        hidden_act (`str` or `Callable`, *optional*, defaults to `"gelu"`):
            The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
            `"relu"`, `"silu"` and `"gelu_new"` are supported.
        hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
            The dropout ratio for the attention probabilities.
        max_position_embeddings (`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).
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        layer_norm_eps (`float`, *optional*, defaults to 1e-12):
            The epsilon used by the layer normalization layers.
        pad_token_id (`int`, *optional*, defaults to 0):
            Token id used for padding sequences.
        position_embedding_type (`str`, *optional*, defaults to `"absolute"`):
            Type of position embedding. Choose one of `"absolute"`, `"relative_key"`, `"relative_key_query"`. For
            positional embeddings use `"absolute"`. For more information on `"relative_key"`, please refer to
            [Self-Attention with Relative Position Representations (Shaw et al.)](https://arxiv.org/abs/1803.02155).
            For more information on `"relative_key_query"`, please refer to *Method 4* in [Improve Transformer Models
            with Better Relative Position Embeddings (Huang et al.)](https://arxiv.org/abs/2009.13658).
        cross_attention_frequency (`int`, *optional*, defaults to 2):
            The frequency of adding cross-attention to the Transformer layers.
        encoder_hidden_size (`int`, *optional*, defaults to 1408):
            The hidden size of the hidden states for cross-attention.

    Examples:

    ```python
    >>> from transformers import InstructBlipVideoQFormerConfig, InstructBlipVideoQFormerModel

    >>> # Initializing a InstructBlipVideo Salesforce/instruct-blip-flan-t5 style configuration
    >>> configuration = InstructBlipVideoQFormerConfig()

    >>> # Initializing a model (with random weights) from the Salesforce/instruct-blip-flan-t5 style configuration
    >>> model = InstructBlipVideoQFormerModel(configuration)
    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```instructblipvideo_qformerqformer_configc                     t        |   dd|i| || _        || _        || _        || _        || _        || _        || _        || _	        |	| _
        |
| _        || _        || _        || _        || _        y )Npad_token_idr   )r   r   
vocab_sizer   r   r   r   r   hidden_dropout_probattention_probs_dropout_probmax_position_embeddingsr   r   position_embedding_typecross_attention_frequencyencoder_hidden_size)r   r6   r   r   r   r   r   r7   r8   r9   r   r   r5   r:   r;   r<   r   r   s                    r   r   z'InstructBlipVideoQFormerConfig.__init__   s    & 	=l=f=$&!2#6 $!2#6 ,H)'>$!2,'>$)B&#6 r    )i:w  i      r=   i   r&   皙?r>   i   {Gz?g-q=    absoluter   r!   r'   r/   s   @r   r1   r1   t   sN    =~ -J&O %( # *"# !"7 "7r    r1   c                   \     e Zd ZdZdZeeedZ	 	 	 	 	 d	 fd	Z	e
dededefd       Z xZS )
InstructBlipVideoConfiga
  
    [`InstructBlipVideoConfig`] is the configuration class to store the configuration of a
    [`InstructBlipVideoForConditionalGeneration`]. It is used to instantiate a Instructblipvideo model according to the specified
    arguments, defining the vision model, Q-Former model and language model configs. Instantiating a configuration with
    the defaults will yield a similar configuration to that of the Instructblipvideo
    [Salesforce/instruct-blip-flan-t5](https://huggingface.co/Salesforce/instruct-blip-flan-t5) architecture.

    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 (`dict`, *optional*):
            Dictionary of configuration options used to initialize [`InstructBlipVideoVisionConfig`].
        qformer_config (`dict`, *optional*):
            Dictionary of configuration options used to initialize [`InstructBlipVideoQFormerConfig`].
        text_config (`dict`, *optional*):
            Dictionary of configuration options used to initialize any [`PretrainedConfig`].
        num_query_tokens (`int`, *optional*, defaults to 32):
            The number of query tokens passed through the Transformer.

        video_token_index (`int`, *optional*):
            Token index of special video token.
        kwargs (*optional*):
            Dictionary of keyword arguments.

    Example:

    ```python
    >>> from transformers import (
    ...     InstructBlipVideoVisionConfig,
    ...     InstructBlipVideoQFormerConfig,
    ...     OPTConfig,
    ...     InstructBlipVideoConfig,
    ...     InstructBlipVideoForConditionalGeneration,
    ... )

    >>> # Initializing a InstructBlipVideoConfig with Salesforce/instruct-blip-flan-t5 style configuration
    >>> configuration = InstructBlipVideoConfig()

    >>> # Initializing a InstructBlipVideoForConditionalGeneration (with random weights) from the Salesforce/instruct-blip-flan-t5 style configuration
    >>> model = InstructBlipVideoForConditionalGeneration(configuration)

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

    >>> # We can also initialize a InstructBlipVideoConfig from a InstructBlipVideoVisionConfig, InstructBlipVideoQFormerConfig and any PretrainedConfig

    >>> # Initializing Instructblipvideo vision, Instructblipvideo Q-Former and language model configurations
    >>> vision_config = InstructBlipVideoVisionConfig()
    >>> qformer_config = InstructBlipVideoQFormerConfig()
    >>> text_config = OPTConfig()

    >>> config = InstructBlipVideoConfig.from_text_vision_configs(vision_config, qformer_config, text_config)
    ```instructblipvideo)text_configr3   r   c                 f   t        |   di | |i }t        j                  d       |i }t        j                  d       |i }t        j                  d       t	        di || _        t        di || _        d|v r|d   nd}t        |   di || _	        | j                  j                  | _
        | j                  j                  | _        || _        || _        | j
                  j                  | j                  _        | j                  j                   t"        v | _        d| _        d| _        y )	NzZvision_config is None. initializing the InstructBlipVideoVisionConfig with default values.z\qformer_config is None. Initializing the InstructBlipVideoQFormerConfig with default values.zTtext_config is None. Initializing the text config with default values (`OPTConfig`).r,   optg      ?r?   r   )r   r   loggerinfor
   r   r1   r3   r   rE   tie_word_embeddingsis_encoder_decodernum_query_tokensvideo_token_indexr   r<   r,   r   use_decoder_only_language_modelinitializer_factorr   )	r   r   r3   rE   rL   rM   r   text_model_typer   s	           r   r   z InstructBlipVideoConfig.__init__  s"    	"6" MKKtu!NKKvwKKKno:K]K<N~N7C{7R+l3X])/:I[I#'#3#3#G#G "&"2"2"E"E 0!2262D2D2P2P//3/?/?/J/JNo/o,"%!%r    r   r3   rE   c                 n     | d|j                         |j                         |j                         d|S )a  
        Instantiate a [`InstructBlipVideoConfig`] (or a derived class) from a InstructBlipVideo vision model, Q-Former and
        language model configurations.

        Returns:
            [`InstructBlipVideoConfig`]: An instance of a configuration object
        )r   r3   rE   r   )to_dict)clsr   r3   rE   r   s        r    from_vision_qformer_text_configsz8InstructBlipVideoConfig.from_vision_qformer_text_configsA  sD       
'//1)113#++-
 	
 	
r    )NNN    N)r(   r)   r*   r+   r,   r   r1   r
   sub_configsr   classmethodr   rT   r.   r/   s   @r   rC   rC      sg    5n %J!86K $&L 
4
 7
 &	
 
r    rC   N)configuration_utilsr   models.auto.modeling_autor   utilsr   autor   r   
get_loggerr(   rH   r
   r1   rC   r   r    r   <module>r]      sV   . 4 J  - 
		H	%Q!$4 Q!he7%5 e7Pz
. z
r    