o ¾e¦i+ã@s@dZddlmZddlmZe e¡ZGdd„deƒZdgZ dS)zLED model configurationé)ÚPreTrainedConfig)Úloggingcs~eZdZdZdZdddddœZ                 ddeeeBdedBf‡fdd„ Z ‡Z S)Ú LEDConfigaý This is the configuration class to store the configuration of a [`LEDModel`]. It is used to instantiate an LED 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 LED [allenai/led-base-16384](https://huggingface.co/allenai/led-base-16384) 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 50265): Vocabulary size of the LED model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`LEDModel`]. d_model (`int`, *optional*, defaults to 1024): Dimensionality of the layers and the pooler layer. encoder_layers (`int`, *optional*, defaults to 12): Number of encoder layers. decoder_layers (`int`, *optional*, defaults to 12): Number of decoder layers. encoder_attention_heads (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the Transformer encoder. decoder_attention_heads (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the Transformer decoder. decoder_ffn_dim (`int`, *optional*, defaults to 4096): Dimensionality of the "intermediate" (often named feed-forward) layer in decoder. encoder_ffn_dim (`int`, *optional*, defaults to 4096): Dimensionality of the "intermediate" (often named feed-forward) layer in decoder. 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 0.0): 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. classifier_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for classifier. max_encoder_position_embeddings (`int`, *optional*, defaults to 16384): The maximum sequence length that the encoder might ever be used with. max_decoder_position_embeddings (`int`, *optional*, defaults to 16384): The maximum sequence length that the decoder might ever be used with. init_std (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. encoder_layerdrop (`float`, *optional*, defaults to 0.0): The LayerDrop probability for the encoder. See the [LayerDrop paper](see https://huggingface.co/papers/1909.11556) for more details. decoder_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. 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 LEDModel, LEDConfig >>> # Initializing a LED allenai/led-base-16384 style configuration >>> configuration = LEDConfig() >>> # Initializing a model from the allenai/led-base-16384 style configuration >>> model = LEDModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```ÚledÚencoder_attention_headsÚd_modelÚattention_dropoutÚinit_std)Únum_attention_headsÚ hidden_sizeÚattention_probs_dropout_probÚinitializer_rangeéYÄé@éé ééçTÚgeluçš™™™™™¹?ç{®Gáz”?ééééÚattention_windowÚtie_word_embeddingsNc s¶||_||_||_||_||_||_||_||_||_| |_ ||_ ||_ ||_ ||_ ||_| |_| |_||_| |_||_||_||_||_||_||_||_tƒjdd| i|¤ŽdS)NÚis_encoder_decoder©)Ú vocab_sizeÚmax_encoder_position_embeddingsÚmax_decoder_position_embeddingsrÚencoder_ffn_dimÚencoder_layersrÚdecoder_ffn_dimÚdecoder_layersÚdecoder_attention_headsÚdropoutrÚactivation_dropoutÚactivation_functionr Úencoder_layerdropÚdecoder_layerdropÚclassifier_dropoutÚ use_cacheÚnum_hidden_layersrÚ pad_token_idÚ bos_token_idÚ eos_token_idÚdecoder_start_token_idrÚsuperÚ__init__)Úselfr r!r"r$r#rr&r%r'r+r,r.rr*rr(rr)r r3r-r0r1r2rrÚkwargs©Ú __class__rúg/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/led/configuration_led.pyr5es6zLEDConfig.__init__)rrrrrrrrrrrTTrrrrrrrrrrrrT) Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typeÚ attribute_mapÚlistÚintÚboolr5Ú __classcell__rrr8r:rsNEü å æårN) r>Úconfiguration_utilsrÚutilsrÚ get_loggerr;ÚloggerrÚ__all__rrrr:Ús