
    9iu                     r    S r SSKJr  SSKJr  SSKJr  SSKJr  \" 5       r	 " S S\5      r
 " S S	\5      rg
)zT5 model configuration    )Mapping)PretrainedConfig)OnnxSeq2SeqConfigWithPast)
get_loggerc                   h   ^  \ rS rSrSrSrS/rSSSS.r                 SU 4S	 jjrS
r	U =r
$ )T5Config   a
  
This is the configuration class to store the configuration of a [`T5Model`] or a [`TFT5Model`]. It is used to
instantiate a T5 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 T5
[t5-small](https://huggingface.co/t5-small) architecture.

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

Arguments:
    vocab_size (`int`, *optional*, defaults to 32128):
        Vocabulary size of the T5 model. Defines the number of different tokens that can be represented by the
        `inputs_ids` passed when calling [`T5Model`] or [`TFT5Model`].
    d_model (`int`, *optional*, defaults to 512):
        Size of the encoder layers and the pooler layer.
    d_kv (`int`, *optional*, defaults to 64):
        Size of the key, query, value projections per attention head. `d_kv` has to be equal to `d_model //
        num_heads`.
    d_ff (`int`, *optional*, defaults to 2048):
        Size of the intermediate feed forward layer in each `T5Block`.
    num_layers (`int`, *optional*, defaults to 6):
        Number of hidden layers in the Transformer encoder.
    num_decoder_layers (`int`, *optional*):
        Number of hidden layers in the Transformer decoder. Will use the same value as `num_layers` if not set.
    num_heads (`int`, *optional*, defaults to 8):
        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 ratio for all dropout layers.
    layer_norm_eps (`float`, *optional*, defaults to 1e-6):
        The epsilon used by the layer normalization layers.
    initializer_factor (`float`, *optional*, defaults to 1):
        A factor for initializing all weight matrices (should be kept to 1, used internally for initialization
        testing).
    feed_forward_proj (`string`, *optional*, defaults to `"relu"`):
        Type of feed forward layer to be used. Should be one of `"relu"` or `"gated-gelu"`. T5v1.1 uses the
        `"gated-gelu"` feed forward projection. Original T5 uses `"relu"`.
    use_cache (`bool`, *optional*, defaults to `True`):
        Whether or not the model should return the last key/values attentions (not used by all models).
t5past_key_valuesd_model	num_heads
num_layers)hidden_sizenum_attention_headsnum_hidden_layersc                   > Xl         X l        X0l        X@l        XPl        U b  UOU R                  U l        Xpl        Xl        Xl        Xl	        Xl
        Xl        Xl        Xl        U R                  R                  S5      nUS   U l        US   S:H  U l        [#        U5      S:  a	  US   S:w  d  [#        U5      S:  a  [%        SU S35      eUS	:X  a  S
U l        [&        TU ]P  " SUUUS.UD6  g )N-r   gated      z`feed_forward_proj`: z is not a valid activation function of the dense layer.Please make sure `feed_forward_proj` is of the format `gated-{ACT_FN}` or `{ACT_FN}`, e.g. 'gated-gelu' or 'relu'z
gated-gelugelu_new)pad_token_ideos_token_idis_encoder_decoder )
vocab_sizer   d_kvd_ffr   num_decoder_layersr   relative_attention_num_bucketsrelative_attention_max_distancedropout_ratelayer_norm_epsiloninitializer_factorfeed_forward_proj	use_cachesplitdense_act_fnis_gated_actlen
ValueErrorsuper__init__)selfr   r   r   r   r   r    r   r!   r"   r#   r$   r%   r&   r   r'   r   r   kwargsact_info	__class__s                       f/var/www/html/land-doc-ocr/venv/lib/python3.13/site-packages/modelscope/models/nlp/T5/configuration.pyr.   T5Config.__init__N   s   & %		$9K*.:/#548OO 	 #.L+/N,("4"4!2"))//4$RL$QK72x=1!!73x=1;L'(9': ;) )* * , *D 	
%%1	
 		
    )r   r   r   r)   r#   r&   r%   r*   r$   r    r   r   r"   r!   r'   r   )i}  i   @   i      N          g?gư>g      ?reluTTr   r   )__name__
__module____qualname____firstlineno____doc__
model_typekeys_to_ignore_at_inferenceattribute_mapr.   __static_attributes____classcell__)r2   s   @r3   r   r      sh    *V J#4"5 *)M "$(0214!$($'#)$(#7
 7
r5   r   c                   X    \ rS rSr\S\\\\\4   4   4S j5       r\S\4S j5       r	Sr
g)T5OnnxConfig   returnc                     SSS.SSS.S.nU R                   (       a  SUS   S'   SS0US	'   SS
S.US'   OSSS.US	'   SSS.US'   U R                   (       a  U R                  USS9  U$ )Nbatchencoder_sequence)r   r   )	input_idsattention_maskz past_encoder_sequence + sequencerN   r   r   decoder_input_idsz past_decoder_sequence + sequencedecoder_attention_maskdecoder_sequenceinputs)	direction)use_pastfill_with_past_key_values_)r/   common_inputss     r3   rR   T5OnnxConfig.inputs   s     %
 %	
 ==7 *+23WM-.57M23 %2M-.
 %7M23
 ==++MX+Nr5   c                     g)N   r   )r/   s    r3   default_onnx_opsetT5OnnxConfig.default_onnx_opset   s    r5   r   N)r<   r=   r>   r?   propertyr   strintrR   rZ   rD   r   r5   r3   rG   rG      sJ     WS#X%6 67    D C  r5   rG   N)r@   typingr    transformers.configuration_utilsr   transformers.onnxr   modelscope.utils.loggerr   loggerr   rG   r   r5   r3   <module>rd      s:      = 7 .	k
 k
\', 'r5   