g/^dZddlmZddlmZejeZGddeZdS)zPEGASUS model configuration)PretrainedConfig)loggingceZdZdZdZdgZdddZ dfd Zede fdZ ede fdZ xZ 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 ```pegasuspast_key_valuesencoder_attention_headsd_model)num_attention_heads hidden_sizeY Tgelu皙?{Gz?Fc P||_||_||_||_||_||_||_||_||_||_ ||_ ||_ | |_ ||_ | |_| |_| |_||_||_t'jd||| ||d|dS)N) pad_token_id eos_token_idis_encoder_decoderdecoder_start_token_idforced_eos_token_id) vocab_sizemax_position_embeddingsr encoder_ffn_dimencoder_layersr decoder_ffn_dimdecoder_layersdecoder_attention_headsdropoutattention_dropoutactivation_dropoutactivation_functioninit_stdencoder_layerdropdecoder_layerdrop use_cachenum_hidden_layersscale_embeddingsuper__init__)selfrr r"r!r r$r#r%r+r,r-rr)r r&r'r(r*rr/rrrkwargs __class__s m/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/pegasus/configuration_pegasus.pyr1zPegasusConfig.__init__ds6%'>$ .,'>$.,'>$ !2"4#6   !2!2"!/. %%1#9 3         returnc|jSN)r r2s r5r z!PegasusConfig.num_attention_headss ++r6c|jSr9)r r:s r5r zPegasusConfig.hidden_sizes |r6)r rrrrrrrrrTTrrrrrrrFrrr) __name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inference attribute_mapr1propertyintr r __classcell__)r4s@r5rrsE E NJ#4"5,EV_``M $ " "" 15 5 5 5 5 5 n,S,,,X,SXr6rN) r?configuration_utilsrutilsr get_loggerr<loggerrrr6r5rJs"!333333  H % %IIIII$IIIIIr6