o ZhM@s@dZddlmZddlmZeeZGdddeZdgZ dS)zPEGASUS model configuration)PretrainedConfig)loggingcseZdZdZdZdgZdddZ           dfdd Zede fddZ ede fddZ Z S) PegasusConfiga This is the configuration class to store the configuration of a [`PegasusModel`]. It is used to instantiate an PEGASUS 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 PEGASUS [google/pegasus-large](https://huggingface.co/google/pegasus-large) 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 PEGASUS model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`PegasusModel`] or [`TFPegasusModel`]. 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. max_position_embeddings (`int`, *optional*, defaults to 1024): The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048). 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. scale_embedding (`bool`, *optional*, defaults to `False`): Scale embeddings by diving by sqrt(d_model). use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models) forced_eos_token_id (`int`, *optional*, defaults to 1): The id of the token to force as the last generated token when `max_length` is reached. Usually set to `eos_token_id`. Example: ```python >>> from transformers import PegasusConfig, PegasusModel >>> # Initializing a PEGASUS google/pegasus-large style configuration >>> configuration = PegasusConfig() >>> # Initializing a model (with random weights) from the google/pegasus-large style configuration >>> model = PegasusModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```ZpegasusZpast_key_valuesencoder_attention_headsd_model)num_attention_heads hidden_sizeY Tgelu皙?{Gz?Fc s||_||_||_||_||_||_||_||_||_||_ ||_ ||_ | |_ ||_ | |_| |_| |_||_||_tjd||| ||d|dS)N) pad_token_id eos_token_idis_encoder_decoderdecoder_start_token_idforced_eos_token_id) vocab_sizemax_position_embeddingsrencoder_ffn_dimencoder_layersrdecoder_ffn_dimdecoder_layersdecoder_attention_headsdropoutattention_dropoutactivation_dropoutactivation_functioninit_stdencoder_layerdropdecoder_layerdrop use_cacheZnum_hidden_layersscale_embeddingsuper__init__)selfrrrrrrrr r&r'r(rr$rr!r"r#r%rr)rrrkwargs __class__r`/var/www/auris/lib/python3.10/site-packages/transformers/models/pegasus/configuration_pegasus.pyr+ds8 zPegasusConfig.__init__returncC|jSN)rr,rrr0rz!PegasusConfig.num_attention_headscCr2r3)rr4rrr0rr5zPegasusConfig.hidden_size)r r r r r r r r rrTTrr rrrrrFrrr) __name__ __module__ __qualname____doc__Z model_typeZkeys_to_ignore_at_inferenceZ attribute_mapr+propertyintrr __classcell__rrr.r0rsBG 7rN) r9Zconfiguration_utilsrutilsrZ get_loggerr6loggerr__all__rrrr0s