U ,È-e ã@sBdZddlmZddlmZe e¡ZddiZGdd„deƒZ dS) z PEGASUS model configurationé)ÚPretrainedConfig)Úloggingzgoogle/pegasus-largezDhttps://huggingface.co/google/pegasus-large/resolve/main/config.jsoncsZeZdZdZdZdgZdddœZd‡fdd„ Zee dœdd„ƒZ ee dœdd„ƒZ ‡Z S)Ú 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_valuesÚencoder_attention_headsÚd_model)Únum_attention_headsÚ hidden_sizeéYÄéé ééçTÚgeluçš™™™™™¹?ç{®Gáz”?éFéc s”||_||_||_||_||_||_||_||_||_||_ ||_ ||_ | |_ ||_ | |_| |_| |_||_||_tƒjf||| ||dœ|—ŽdS)N)Ú pad_token_idÚ eos_token_idÚis_encoder_decoderÚdecoder_start_token_idÚforced_eos_token_id)Ú vocab_sizeÚmax_position_embeddingsrÚencoder_ffn_dimÚencoder_layersrÚdecoder_ffn_dimÚdecoder_layersÚdecoder_attention_headsÚdropoutÚattention_dropoutÚactivation_dropoutÚactivation_functionÚinit_stdÚencoder_layerdropÚdecoder_layerdropÚ use_cacheZnum_hidden_layersÚscale_embeddingÚsuperÚ__init__)Úselfrrrrrrrrr%r&r'rr#rr r!r"r$rr(rrrÚkwargs©Ú __class__©úr/var/www/html/Darija-Ai-Train/env/lib/python3.8/site-packages/transformers/models/pegasus/configuration_pegasus.pyr*hs8ûúzPegasusConfig.__init__)ÚreturncCs|jS©N)r©r+r/r/r0rŸsz!PegasusConfig.num_attention_headscCs|jSr2)rr3r/r/r0r£szPegasusConfig.hidden_size)r r r r r r r r rrTTrr rrrrrFrrr) Ú__name__Ú __module__Ú __qualname__Ú__doc__Z model_typeZkeys_to_ignore_at_inferenceZ attribute_mapr*ÚpropertyÚintrrÚ __classcell__r/r/r-r0rs@F è7rN) r7Zconfiguration_utilsrÚutilsrZ get_loggerr4ÚloggerZ%PEGASUS_PRETRAINED_CONFIG_ARCHIVE_MAPrr/r/r/r0Ús   ÿ