sgdZddlmZddlmZddlmZddlmZeje Z GddeZ Gd d eZ y ) zT5 model configuration)Mapping)PretrainedConfig)OnnxSeq2SeqConfigWithPast)loggingc`eZdZdZdZdgZdddddZ d fd ZxZS) T5Configa 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 [google-t5/t5-small](https://huggingface.co/google-t5/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. The `inner_dim` of the projection layer will be defined as `num_heads * d_kv`. 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. classifier_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for classifier. 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). t5past_key_valuesd_model num_heads num_layersd_kv) hidden_sizenum_attention_headsnum_hidden_layershead_dimc ||_||_||_||_||_||n |j|_||_||_| |_| |_ ||_ | |_ | |_ | |_ ||_|jjd}|d|_|ddk(|_t%|dkDr|ddk7st%|dkDrt'd| d| d k(rd |_t)|Td |||d |y) N-rgatedz`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-gelugelu_new) pad_token_id eos_token_idis_encoder_decoder) vocab_sizer rd_ffrnum_decoder_layersr relative_attention_num_bucketsrelative_attention_max_distance dropout_rateclassifier_dropoutlayer_norm_epsiloninitializer_factorfeed_forward_proj use_cachesplit dense_act_fn is_gated_actlen ValueErrorsuper__init__)selfrr rr rr!r r"r#r$r&r'r(rr)rrr%kwargsact_info __class__s Z/var/www/html/venv/lib/python3.12/site-packages/transformers/models/t5/configuration_t5.pyr0zT5Config.__init__Ss3,%   $"4"@ doo #.L+/N,("4"4"4!2"))//4$RL$QK72 x=1 !!73x=1;L'(9':;))   , *D   %%1   )i}i@iN g?gư>g?reluTTrrg) __name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inference attribute_mapr0 __classcell__)r4s@r5r r sn,\J#4"5 *) M  ')(+ '< < r6r cLeZdZedeeeeefffdZedefdZy) T5OnnxConfigreturncddddddd}|jrd|dd<ddi|d <dd d|d <ndd d|d <dd d|d <|jr|j|d |S)Nbatchencoder_sequence)rr) input_idsattention_maskz past_encoder_sequence + sequencerLrrdecoder_input_idsz past_decoder_sequence + sequencedecoder_attention_maskdecoder_sequenceinputs) direction)use_pastfill_with_past_key_values_)r1 common_inputss r5rPzT5OnnxConfig.inputss%);<").@A  ==1SM* +A .23WM- .:AFh6iM2 35r?propertyrstrintrPrWrr6r5rFrFsI WS#X%6 67$Cr6rFN)r@typingrconfiguration_utilsronnxrutilsr get_loggerr=loggerr rFrr6r5rasG3-   H %t t n,r6