a
    ½Àhp.  ã                   @   s`   d Z ddlmZ ddlmZ e e¡ZG dd„ deƒZG dd„ deƒZ	G dd	„ d	eƒZ
d	gZd
S )zKOSMOS-2 model configurationé   )ÚPretrainedConfig)Úloggingc                       s<   e Zd ZdZdZdZdgZddddœZd‡ fdd„	Z‡  Z	S )ÚKosmos2TextConfiga±  
    This is the configuration class to store the configuration of a [`Kosmos2TextModel`]. It is used to instantiate a
    KOSMOS-2 text decoder 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 decoder of the KOSMOS-2
    [microsoft/kosmos-2-patch14-224](https://huggingface.co/microsoft/kosmos-2-patch14-224) 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 65037):
            Vocabulary size of the Kosmos2 model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`Kosmos2Model`].
        max_position_embeddings (`int`, *optional*, defaults to 2048):
            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).
        embed_dim (`int`, *optional*, defaults to 2048):
            Dimensionality of the layers and the pooler layer.
        layers (`int`, *optional*, defaults to 24):
            Number of hidden layers in the Transformer encoder.
        ffn_dim (`int`, *optional*, defaults to 8192):
            Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder.
        attention_heads (`int`, *optional*, defaults to 32):
            Number of attention heads for each attention layer in the Transformer encoder.
        activation_function (`str` or `function`, *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.
        dropout (`float`, *optional*, defaults to 0.1):
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        attention_dropout (`float`, *optional*, defaults to 0.1):
            The dropout ratio for the attention probabilities.
        activation_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for activations inside the fully connected layer.
        layerdrop (`float`, *optional*, defaults to 0.0):
            The LayerDrop probability for the decoder. See the [LayerDrop paper](see https://huggingface.co/papers/1909.11556)
            for more details.
        layer_norm_eps (`float`, *optional*, defaults to 1e-05):
            The epsilon used by the layer normalization layers.
        init_std (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        scale_embedding (`bool`, *optional*, defaults to `True`):
            Scale embeddings by diving by sqrt(embed_dim).
        use_cache (`bool`, *optional*, defaults to `True`):
            Whether or not the model should return the last key/values attentions (not used by all models).
        pad_token_id (`int`, *optional*, defaults to 1):
            Token id used for padding.
        bos_token_id (`int`, *optional*, defaults to 0):
            Token id used for beginning of string.
        eos_token_id (`int`, *optional*, defaults to 2):
            Token id used for end of string.
    ```Zkosmos_2_text_modelÚtext_configZpast_key_valuesÚattention_headsÚ	embed_dimÚlayers)Únum_attention_headsÚhidden_sizeÚnum_hidden_layerséþ  é   é   é    é    Úgeluçš™™™™™¹?ç        çñhãˆµøä>ç{®Gáz”?Té   é    é   c                    sx   t ƒ jf |||dœ|¤Ž || _|| _|| _|| _|| _|| _|| _|| _	|	| _
|
| _|| _|| _|| _|| _|| _d S )N)Úpad_token_idÚbos_token_idÚeos_token_id)ÚsuperÚ__init__Ú
vocab_sizeÚmax_position_embeddingsr   r   Úffn_dimr   Úactivation_functionÚdropoutÚattention_dropoutÚactivation_dropoutÚ	layerdropÚlayer_norm_epsÚinit_stdÚscale_embeddingÚ	use_cache)Úselfr   r   r   r   r    r   r!   r"   r#   r$   r%   r&   r'   r(   r)   r   r   r   Úkwargs©Ú	__class__© úm/var/www/html/assistant/venv/lib/python3.9/site-packages/transformers/models/kosmos2/configuration_kosmos2.pyr   V   s,    ýüzKosmos2TextConfig.__init__)r   r   r   r   r   r   r   r   r   r   r   r   r   TTr   r   r   )
Ú__name__Ú
__module__Ú__qualname__Ú__doc__Ú
model_typeÚbase_config_keyZkeys_to_ignore_at_inferenceZattribute_mapr   Ú__classcell__r.   r.   r,   r/   r      s6   4ý                  ír   c                       s*   e Zd ZdZdZdZd‡ fdd„	Z‡  ZS )ÚKosmos2VisionConfiga¡	  
    This is the configuration class to store the configuration of a [`Kosmos2VisionModel`]. It is used to instantiate a
    KOSMOS-2 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 KOSMOS-2
    [microsoft/kosmos-2-patch14-224](https://huggingface.co/microsoft/kosmos-2-patch14-224) 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 1024):
            Dimensionality of the encoder layers and the pooler layer.
        intermediate_size (`int`, *optional*, defaults to 4096):
            Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
        num_hidden_layers (`int`, *optional*, defaults to 24):
            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.
        num_channels (`int`, *optional*, defaults to 3):
            The number of input channels.
        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 `"quick_gelu"`):
            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-05):
            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 0.02):
            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).
    ```Zkosmos_2_vision_modelÚvision_configé   é   r   é   r   éà   é   Ú
quick_gelur   r   r   ç      ð?c                    s^   t ƒ jf i |¤Ž || _|| _|| _|| _|| _|| _|| _|| _	|| _
|
| _|	| _|| _d S )N)r   r   r
   Úintermediate_sizer   r	   Únum_channelsÚ
patch_sizeÚ
image_sizeÚinitializer_rangeÚinitializer_factorr#   r&   Ú
hidden_act)r*   r
   r@   r   r	   rA   rC   rB   rF   r&   r#   rD   rE   r+   r,   r.   r/   r   ®   s    zKosmos2VisionConfig.__init__)r9   r:   r   r;   r   r<   r=   r>   r   r   r   r?   )r0   r1   r2   r3   r4   r5   r   r6   r.   r.   r,   r/   r7   „   s    &            ór7   c                       s0   e Zd ZdZdZeedœZd‡ fdd„	Z‡  Z	S )	ÚKosmos2Configat  
    This is the configuration class to store the configuration of a [`Kosmos2Model`]. It is used to instantiate a
    KOSMOS-2 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 KOSMOS-2
    [microsoft/kosmos-2-patch14-224](https://huggingface.co/microsoft/kosmos-2-patch14-224) architecture.

    Args:
        text_config (`dict`, *optional*):
            Dictionary of configuration options used to initialize [`Kosmos2TextConfig`].
        vision_config (`dict`, *optional*):
            Dictionary of configuration options used to initialize [`Kosmos2VisionConfig`].
        latent_query_num (`int`, *optional*, defaults to 64):
            The number of latent query tokens that represent the image features used in the text decoder component.
        kwargs (*optional*):
            Dictionary of keyword arguments.

    Example:

    ```python
    >>> from transformers import Kosmos2Config, Kosmos2Model

    >>> # Initializing a Kosmos-2 kosmos-2-patch14-224 style configuration
    >>> configuration = Kosmos2Config()

    >>> # Initializing a model (with random weights) from the kosmos-2-patch14-224 style configuration
    >>> model = Kosmos2Model(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```zkosmos-2)r   r8   Né@   c                    sh   t ƒ jf i |¤Ž |d u r(i }t d¡ |d u r>i }t d¡ tf i |¤Ž| _tf i |¤Ž| _|| _d S )NzR`text_config` is `None`. Initializing the `Kosmos2TextConfig` with default values.zV`vision_config` is `None`. Initializing the `Kosmos2VisionConfig` with default values.)	r   r   ÚloggerÚinfor   r   r7   r8   Úlatent_query_num)r*   r   r8   rK   r+   r,   r.   r/   r   ñ   s    

zKosmos2Config.__init__)NNrH   )
r0   r1   r2   r3   r4   r   r7   Zsub_configsr   r6   r.   r.   r,   r/   rG   Î   s   
   ürG   N)r3   Zconfiguration_utilsr   Úutilsr   Z
get_loggerr0   rI   r   r7   rG   Ú__all__r.   r.   r.   r/   Ú<module>   s   
lJ: