
    gP"                         d Z ddlmZ ddlmZmZmZmZ ddlm	Z	m
Z
mZ ddlmZ ddlmZmZ ddlmZ  ej        e          Z G d	 d
e          Z G d de          ZdS )zGPT-J model configuration    )OrderedDict)AnyListMappingOptional   )PreTrainedTokenizer
TensorTypeis_torch_available)PretrainedConfig)OnnxConfigWithPastPatchingSpec)loggingc                   X     e Zd ZdZdZdddddZ	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 	 d fd	Z xZS )
GPTJConfiga=  
    This is the configuration class to store the configuration of a [`GPTJModel`]. It is used to instantiate a GPT-J
    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 GPT-J
    [EleutherAI/gpt-j-6B](https://huggingface.co/EleutherAI/gpt-j-6B) 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 50400):
            Vocabulary size of the GPT-J model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`GPTJModel`].
        n_positions (`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).
        n_embd (`int`, *optional*, defaults to 4096):
            Dimensionality of the embeddings and hidden states.
        n_layer (`int`, *optional*, defaults to 28):
            Number of hidden layers in the Transformer encoder.
        n_head (`int`, *optional*, defaults to 16):
            Number of attention heads for each attention layer in the Transformer encoder.
        rotary_dim (`int`, *optional*, defaults to 64):
            Number of dimensions in the embedding that Rotary Position Embedding is applied to.
        n_inner (`int`, *optional*, defaults to None):
            Dimensionality of the inner feed-forward layers. `None` will set it to 4 times n_embd
        activation_function (`str`, *optional*, defaults to `"gelu_new"`):
            Activation function, to be selected in the list `["relu", "silu", "gelu", "tanh", "gelu_new"]`.
        resid_pdrop (`float`, *optional*, defaults to 0.1):
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        embd_pdrop (`int`, *optional*, defaults to 0.1):
            The dropout ratio for the embeddings.
        attn_pdrop (`float`, *optional*, defaults to 0.1):
            The dropout ratio for the attention.
        layer_norm_epsilon (`float`, *optional*, defaults to 1e-5):
            The epsilon to use in the layer normalization layers.
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        use_cache (`bool`, *optional*, defaults to `True`):
            Whether or not the model should return the last key/values attentions (not used by all models).

    Example:

    ```python
    >>> from transformers import GPTJModel, GPTJConfig

    >>> # Initializing a GPT-J 6B configuration
    >>> configuration = GPTJConfig()

    >>> # Initializing a model from the configuration
    >>> model = GPTJModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```gptjn_positionsn_embdn_headn_layer)max_position_embeddingshidden_sizenum_attention_headsnum_hidden_layers              @   Ngelu_new        h㈵>{Gz?TP  Fc                 "   || _         || _        || _        || _        || _        || _        || _        || _        |	| _        |
| _	        || _
        || _        || _        || _        || _        || _         t!                      j        d|||d| d S )N)bos_token_ideos_token_idtie_word_embeddings )
vocab_sizer   r   r   r   n_inner
rotary_dimactivation_functionresid_pdrop
embd_pdrop
attn_pdroplayer_norm_epsiloninitializer_range	use_cacher'   r(   super__init__)selfr+   r   r   r   r   r-   r,   r.   r/   r0   r1   r2   r3   r4   r'   r(   r)   kwargs	__class__s                      g/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/gptj/configuration_gptj.pyr6   zGPTJConfig.__init__]   s    * %&$#6 &$$"4!2"(( 	
%LVi	
 	
ms	
 	
 	
 	
 	
    )r   r   r   r   r   r    Nr!   r"   r"   r"   r#   r$   Tr%   r%   F)__name__
__module____qualname____doc__
model_typeattribute_mapr6   __classcell__r9   s   @r:   r   r      s        5 5n J#0'&	 M &!%)
 )
 )
 )
 )
 )
 )
 )
 )
 )
r;   r   c                       e Zd Z	 	 	 ddededee         def fdZe	d	e
ee
eef         f         fd
            Ze	d	efd            Ze	d	efd            Z	 	 	 	 ddededededee         d	e
eef         f fdZe	d	efd            Z xZS )GPTJOnnxConfigdefaultNFconfigtaskpatching_specsuse_pastc                     t                                          ||||           t          | j        dd           sd| j        _        d S d S )N)rH   rI   rJ   pad_token_idr   )r5   r6   getattr_configrL   )r7   rG   rH   rI   rJ   r9   s        r:   r6   zGPTJOnnxConfig.__init__   sW     	d>T\]]]t|^T:: 	*()DL%%%	* 	*r;   returnc                     t          ddddi          }| j        r |                     |d           ddd|d<   nddd|d<   |S )	N	input_idsbatchsequence)r      inputs)	directionzpast_sequence + sequenceattention_mask)r   rJ   fill_with_past_key_values_)r7   common_inputss     r:   rU   zGPTJOnnxConfig.inputs   sp    #[g*2M2M$NOO= 	J++MX+NNN29>X.Y.YM*++29j.I.IM*+r;   c                     | j         j        S N)rN   r   r7   s    r:   
num_layerszGPTJOnnxConfig.num_layers   s    |##r;   c                     | j         j        S r[   )rN   r   r\   s    r:   r   z"GPTJOnnxConfig.num_attention_heads   s    |""r;   	tokenizer
batch_size
seq_lengthis_pair	frameworkc                 >   t          t          |                               |||||          }t          d|d         i          }| j        rwt                      st          d          dd l|d         j        \  }}	|	dz   }
|| j	        |
| j
        j        | j	        z  ffdt          | j                  D             |d<   |d         |d<   | j        rE|d         j        }                    |d                             ||
|	          gd
          |d<   |S )N)ra   rb   rc   rd   rQ   zACannot generate dummy past_keys inputs without PyTorch installed.r      c                 d    g | ],}                                                              f-S r*   )zeros).0_
past_shapetorchs     r:   
<listcomp>z8GPTJOnnxConfig.generate_dummy_inputs.<locals>.<listcomp>   sC     5 5 5KLU[[,,ekk*.E.EF5 5 5r;   past_key_valuesrW   )dtyperT   )dim)r5   r   generate_dummy_inputsr   rJ   r   
ValueErrorrl   shaper   rN   r   ranger]   ro   catones)r7   r`   ra   rb   rc   rd   rY   ordered_inputsrR   seqlenpast_key_values_length
mask_dtyperk   rl   r9   s               @@r:   rq   z$GPTJOnnxConfig.generate_dummy_inputs   sw    0$77MM*W`i N 
 

 %k=3M%NOO = 	%''  !deee -k : @v)/!&,*L,0HH	
5 5 5 5 5PUVZVePfPf5 5 501 ,99I+J'(= 	'(89?J/4yy 015::eE[cm:3n3nouv 09 0 0N+, r;   c                     dS )N   r*   r\   s    r:   default_onnx_opsetz!GPTJOnnxConfig.default_onnx_opset   s    rr;   )rF   NF)r_   r_   FN)r<   r=   r>   r   strr   r   boolr6   propertyr   intrU   r]   r   r	   r   r
   r   rq   r}   rB   rC   s   @r:   rE   rE      s        -1
* 
* 
* 
* \*	
*
 
* 
* 
* 
* 
* 
* WS#X%6 67    X $C $ $ $ X$ #S # # # X# *.* *&* * 	*
 * J'* 
c	* * * * * *X C    X    r;   rE   N)r?   collectionsr   typingr   r   r   r    r	   r
   r   configuration_utilsr   onnxr   r   utilsr   
get_loggerr<   loggerr   rE   r*   r;   r:   <module>r      s$      # # # # # # / / / / / / / / / / / / C C C C C C C C C C 3 3 3 3 3 3 4 4 4 4 4 4 4 4       
	H	%	%i
 i
 i
 i
 i
! i
 i
 i
ZN N N N N' N N N N Nr;   