U ,È-eÑã@sRdZddlmZmZddlmZddlmZe e ¡Z ddiZ Gdd „d eƒZ d S) z LED model configurationé)ÚListÚUnioné)ÚPretrainedConfig)Úloggingzallenai/led-base-16384zFhttps://huggingface.co/allenai/led-base-16384/resolve/main/config.jsoncsFeZdZdZdZdddddœZdeeeefdœ‡fdd„ Z ‡Z S)Ú LEDConfigaÿ 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`] or [`TFLEDModel`]. 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://arxiv.org/abs/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://arxiv.org/abs/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 ```ZledÚencoder_attention_headsÚd_modelÚattention_dropoutÚinit_std)Znum_attention_headsZ hidden_sizeZattention_probs_dropout_probZinitializer_rangeéYÄé@éé ééçTÚgeluçš™™™™™¹?ç{®Gáz”?ééré)Úattention_windowc s ||_||_||_||_||_||_||_||_||_| |_ ||_ ||_ ||_ ||_ ||_| |_| |_||_| |_||_||_tƒjf|||| |dœ|—ŽdS)N)Ú pad_token_idÚ bos_token_idÚ eos_token_idÚis_encoder_decoderÚdecoder_start_token_id)Ú vocab_sizeÚmax_encoder_position_embeddingsÚmax_decoder_position_embeddingsr Úencoder_ffn_dimÚencoder_layersrÚdecoder_ffn_dimÚdecoder_layersÚdecoder_attention_headsÚdropoutr Úactivation_dropoutÚactivation_functionr Úencoder_layerdropÚdecoder_layerdropÚclassifier_dropoutÚ use_cacheZnum_hidden_layersrÚsuperÚ__init__)Úselfrr r!r#r"rr%r$r&r*r+r-rr)r r'r r(r rr,rrrrÚkwargs©Ú __class__©új/var/www/html/Darija-Ai-Train/env/lib/python3.8/site-packages/transformers/models/led/configuration_led.pyr/ls<ûúzLEDConfig.__init__)r r rrrrrrrrrTTrrrrrrrrrrrr) Ú__name__Ú __module__Ú __qualname__Ú__doc__Z model_typeZ attribute_maprrÚintr/Ú __classcell__r4r4r2r5rsFDü æærN) r9ÚtypingrrZconfiguration_utilsrÚutilsrZ get_loggerr6ÚloggerZ!LED_PRETRAINED_CONFIG_ARCHIVE_MAPrr4r4r4r5Ús   ÿ