sgjdZddlmZmZddlmZddlmZeje Z GddeZ y) zLED model configuration)ListUnion)PretrainedConfig)loggingc~eZdZdZdZdddddZ d deeeefffd Z xZ S) LEDConfiga 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 ```ledencoder_attention_headsd_modelattention_dropoutinit_std)num_attention_heads hidden_sizeattention_probs_dropout_probinitializer_rangeattention_windowc V||_||_||_||_||_||_||_||_||_| |_ ||_ ||_ ||_ ||_ ||_| |_| |_||_| |_||_||_t+|Xd|||| |d|y)N) pad_token_id bos_token_id eos_token_idis_encoder_decoderdecoder_start_token_id) vocab_sizemax_encoder_position_embeddingsmax_decoder_position_embeddingsr encoder_ffn_dimencoder_layersr decoder_ffn_dimdecoder_layersdecoder_attention_headsdropoutr activation_dropoutactivation_functionrencoder_layerdropdecoder_layerdropclassifier_dropout use_cachenum_hidden_layersrsuper__init__)selfrrrrrr r!r r"r&r'r)rr%r r#r r$rrr(rrrrkwargs __class__s \/var/www/html/venv/lib/python3.12/site-packages/transformers/models/led/configuration_led.pyr,zLEDConfig.__init__hs:%/N,/N, .,'>$.,'>$ !2"4#6   !2!2"4"!/ 0  %%%1#9    )iYi@ r3r4r5r6TTgelur2g?r6r6g{Gz?r6rr8i) __name__ __module__ __qualname____doc__ model_type attribute_maprrintr, __classcell__)r/s@r0r r sC JJ8 (;' M(-(, " "" 255: 4 S 3/5: : r1r N) r=typingrrconfiguration_utilsrutilsr get_loggerr:loggerr rr1r0rGs63   H %H  H r1