o ei@s@dZddlmZddlmZeeZGdddeZdgZ dS)zT5 model configuration)PreTrainedConfig)loggingcsbeZdZdZdZdgZdddddZ               dfdd ZZS)T5Configa This is the configuration class to store the configuration of a [`T5Model`]. 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`]. 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_dim}@N 皙?ư>?reluTFc s ||_||_||_||_||_||_|dur|n|j|_||_||_| |_ | |_ ||_ | |_ | |_ | |_||_||_||_|jd}|d|_|ddk|_t|dkr[|ddksat|dkritd| d| d krpd |_|d u|_d |_tjd d |i|dS)N-rgatedrz`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_newTis_encoder_decoder) is_decoder vocab_sizerr d_ffr num_decoder_layersrrelative_attention_num_bucketsrelative_attention_max_distance dropout_rateclassifier_dropoutlayer_norm_epsiloninitializer_factorfeed_forward_proj use_cache pad_token_id eos_token_idsplit dense_act_fn is_gated_actlen ValueErrorscale_decoder_outputstie_word_embeddingssuper__init__)selfr&rr r'r r(rr)r*r+r-r.r/r#r0r1r2r,r9r%kwargsact_info __class__r$e/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/t5/configuration_t5.pyr;Os>  $  zT5Config.__init__)rrrrrNrrrrrrrTTrrrTF) __name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inference attribute_mapr; __classcell__r$r$r?rArs<. rN) rEconfiguration_utilsrutilsr get_loggerrBloggerr__all__r$r$r$rAs     ~