o
    	۷i
<                     @   sb   d Z ddlmZ ddlmZ eeZG dd deZG dd deZ	G dd	 d	eZ
g d
ZdS )zPix2Struct model configuration   )PretrainedConfig)loggingc                       sd   e Zd ZdZdZdgZddddddddZ				
															d fdd	Z  ZS )Pix2StructTextConfiga  
    This is the configuration class to store the configuration of a [`Pix2StructTextModel`]. It is used to instantiate
    a Pix2Struct text 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 Pix2Struct text decoder used by
    the [google/pix2struct-base](https://huggingface.co/google/pix2struct-base) 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 50244):
            Vocabulary size of the `Pix2Struct` text model. Defines the number of different tokens that can be
            represented by the `inputs_ids` passed when calling [`Pix2StructTextModel`].
        hidden_size (`int`, *optional*, defaults to 768):
            Dimensionality of the encoder layers and the pooler layer.
        d_kv (`int`, *optional*, defaults to 64):
            Dimensionality of the key, query, value projections in each attention head.
        d_ff (`int`, *optional*, defaults to 2048):
            Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
        num_layers (`int`, *optional*, defaults to 12):
            Number of hidden layers in the Transformer encoder.
        num_heads (`int`, *optional*, defaults to 12):
            Number of attention heads for each attention layer in the Transformer encoder.
        relative_attention_num_buckets (`int`, *optional*, defaults to 32):
            The number of buckets to use for each attention layer.
        relative_attention_max_distance (`int`, *optional*, defaults to 128):
            The maximum distance of the longer sequences for the bucket separation.
        dropout_rate (`float`, *optional*, defaults to 0.1):
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        layer_norm_epsilon (`float`, *optional*, defaults to 1e-6):
            The epsilon used by the layer normalization layers.
        initializer_factor (`float`, *optional*, defaults to 1.0):
            A factor for initializing all weight matrices (should be kept to 1, used internally for initialization
            testing).
        dense_act_fn (`Union[Callable, str]`, *optional*, defaults to `"gelu_new"`):
            The non-linear activation function (function or string).
        decoder_start_token_id (`int`, *optional*, defaults to 0):
            The id of the `decoder_start_token_id` token.
        use_cache (`bool`, *optional*, defaults to `False`):
            Whether or not the model should return the last key/values attentions (not used by all models).
        pad_token_id (`int`, *optional*, defaults to 0):
            The id of the `padding` token.
        eos_token_id (`int`, *optional*, defaults to 1):
            The id of the `end-of-sequence` token.

    Example:

    ```python
    >>> from transformers import Pix2StructTextConfig, Pix2StructTextModel

    >>> # Initializing a Pix2StructTextConfig with google/pix2struct-base style configuration
    >>> configuration = Pix2StructTextConfig()

    >>> # Initializing a Pix2StructTextModel (with random weights) from the google/pix2struct-base style configuration
    >>> model = Pix2StructTextModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```pix2struct_text_modelpast_key_valueshidden_size	num_heads
num_layers)r   num_attention_headsnum_hidden_layersdecoder_attention_headsencoder_attention_headsencoder_layersdecoder_layersD     @                皙?ư>      ?gelu_new    F   Tc                    s|   || _ || _|| _|| _|| _|| _|| _|| _|	| _|
| _	|| _
|| _|| _|| _|| _t jd|||||d| d S )N)pad_token_ideos_token_iddecoder_start_token_idtie_word_embeddings
is_decoder )
vocab_sizer   d_kvd_ffr	   r   relative_attention_num_bucketsrelative_attention_max_distancedropout_ratelayer_norm_epsiloninitializer_factor	use_cacher   r   dense_act_fnsuper__init__)selfr#   r   r$   r%   r	   r   r&   r'   r(   r)   r*   r,   r   r+   r   r   r    r!   kwargs	__class__r"   m/home/ubuntu/vllm_env/lib/python3.10/site-packages/transformers/models/pix2struct/configuration_pix2struct.pyr.   a   s0   
zPix2StructTextConfig.__init__)r   r   r   r   r   r   r   r   r   r   r   r   r   Fr   r   FT)	__name__
__module____qualname____doc__
model_typekeys_to_ignore_at_inferenceattribute_mapr.   __classcell__r"   r"   r1   r3   r      s>    <r   c                       sD   e Zd ZdZdZ													
				d fdd	Z  ZS )Pix2StructVisionConfiga  
    This is the configuration class to store the configuration of a [`Pix2StructVisionModel`]. It is used to
    instantiate a Pix2Struct vision model according to the specified arguments, defining the model architecture.
    Instantiating a configuration defaults will yield a similar configuration to that of the Pix2Struct-base
    [google/pix2struct-base](https://huggingface.co/google/pix2struct-base) 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.
        patch_embed_hidden_size (`int`, *optional*, defaults to 768):
            Dimensionality of the input patch_embedding layer in the Transformer encoder.
        d_ff (`int`, *optional*, defaults to 2048):
            Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
        d_kv (`int`, *optional*, defaults to 64):
            Dimensionality of the key, query, value projections per attention head.
        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.
        dense_act_fn (`str` or `function`, *optional*, defaults to `"gelu_new"`):
            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-06):
            The epsilon used by the layer normalization layers.
        dropout_rate (`float`, *optional*, defaults to 0.0):
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        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.
        initializer_factor (`float`, *optional*, defaults to 1.0):
            A factor for initializing all weight matrices (should be kept to 1, used internally for initialization
            testing).
        seq_len (`int`, *optional*, defaults to 4096):
            Maximum sequence length (here number of patches) supported by the model.
        relative_attention_num_buckets (`int`, *optional*, defaults to 32):
            The number of buckets to use for each attention layer.
        relative_attention_max_distance (`int`, *optional*, defaults to 128):
            The maximum distance (in tokens) to use for each attention layer.

    Example:

    ```python
    >>> from transformers import Pix2StructVisionConfig, Pix2StructVisionModel

    >>> # Initializing a Pix2StructVisionConfig with google/pix2struct-base style configuration
    >>> configuration = Pix2StructVisionConfig()

    >>> # Initializing a Pix2StructVisionModel (with random weights) from the google/pix2struct-base style configuration
    >>> model = Pix2StructVisionModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```pix2struct_vision_modelr   r   r   r   r   r           绽|=r      r   r   c                    sp   t  jdi | || _|| _|| _|	| _|| _|| _|| _|| _	|
| _
|| _|| _|| _|| _|| _|| _d S )Nr"   )r-   r.   r   patch_embed_hidden_sizer%   r(   r   r
   initializer_ranger*   attention_dropoutlayer_norm_epsr,   seq_lenr&   r'   r$   )r/   r   rA   r%   r$   r   r
   r,   rD   r(   rC   rB   r*   rE   r&   r'   r0   r1   r"   r3   r.      s    
zPix2StructVisionConfig.__init__)r   r   r   r   r   r   r   r   r>   r>   r?   r   r@   r   r   )r4   r5   r6   r7   r8   r.   r;   r"   r"   r1   r3   r<      s&    :r<   c                       s>   e Zd ZdZdZeedZ							d fd	d
	Z  Z	S )Pix2StructConfiga1	  
    [`Pix2StructConfig`] is the configuration class to store the configuration of a
    [`Pix2StructForConditionalGeneration`]. It is used to instantiate a Pix2Struct 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 Pix2Struct-base
    [google/pix2struct-base](https://huggingface.co/google/pix2struct-base) 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 [`Pix2StructTextConfig`].
        vision_config (`dict`, *optional*):
            Dictionary of configuration options used to initialize [`Pix2StructVisionConfig`].
        initializer_factor (`float`, *optional*, defaults to 1.0):
            Factor to multiply the initialization range with.
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        is_vqa (`bool`, *optional*, defaults to `False`):
            Whether the model has been fine-tuned for VQA or not.
        kwargs (*optional*):
            Dictionary of keyword arguments.

    Example:

    ```python
    >>> from transformers import Pix2StructConfig, Pix2StructForConditionalGeneration

    >>> # Initializing a Pix2StructConfig with google/pix2struct-base style configuration
    >>> configuration = Pix2StructConfig()

    >>> # Initializing a Pix2StructForConditionalGeneration (with random weights) from the google/pix2struct-base style configuration
    >>> model = Pix2StructForConditionalGeneration(configuration)

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

    >>> # We can also initialize a Pix2StructConfig from a Pix2StructTextConfig and a Pix2StructVisionConfig

    >>> # Initializing a Pix2Struct text and Pix2Struct vision configuration
    >>> config_text = Pix2StructTextConfig()
    >>> config_vision = Pix2StructVisionConfig()

    >>> config = Pix2StructConfig.from_text_vision_configs(config_text, config_vision)
    ```
pix2struct)text_configvision_configNr   {Gz?FTc           	         s   t  jd||d| |d u ri }td |d u r"i }td ||d< ||d< tdi || _tdi || _| jj| _| jj	| _	| jj
| _
|| _|| _| j| j_| j| j_|| _d S )N)r    is_encoder_decoderzOtext_config is None. Initializing the Pix2StructTextConfig with default values.zSvision_config is None. Initializing the Pix2StructVisionConfig with default values.rK   r    r"   )r-   r.   loggerinfor   rH   r<   rI   r   r   r   r*   rB   is_vqa)	r/   rH   rI   r*   rB   rN   r    rK   r0   r1   r"   r3   r.   *  s&   







zPix2StructConfig.__init__)NNr   rJ   FFT)
r4   r5   r6   r7   r8   r   r<   sub_configsr.   r;   r"   r"   r1   r3   rF      s    /
rF   )rF   r   r<   N)r7   configuration_utilsr   utilsr   
get_loggerr4   rL   r   r<   rF   __all__r"   r"   r"   r3   <module>   s   
|cZ