o ¾e¦i=ã@s@dZddlmZddlmZe e¡ZGdd„deƒZdgZ dS)zMBART model configurationé)ÚPreTrainedConfig)ÚloggingcsleZdZdZdZdgZdddœZ              d‡fdd„ Z‡ZS)Ú MBartConfiga- This is the configuration class to store the configuration of a [`MBartModel`]. It is used to instantiate an MBART 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 MBART [facebook/mbart-large-cc25](https://huggingface.co/facebook/mbart-large-cc25) 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 MBART model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`MBartModel`]. 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_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://huggingface.co/papers/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://huggingface.co/papers/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 2): 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 MBartConfig, MBartModel >>> # Initializing a MBART facebook/mbart-large-cc25 style configuration >>> configuration = MBartConfig() >>> # Initializing a model (with random weights) from the facebook/mbart-large-cc25 style configuration >>> model = MBartModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```ÚmbartÚpast_key_valuesÚencoder_attention_headsÚd_model)Únum_attention_headsÚ hidden_sizeéYÄéé ééçTÚgeluçš™™™™™¹?ç{®Gáz”?FéééNc s¸||_||_||_||_||_||_||_||_||_||_ ||_ ||_ ||_ | |_ ||_| |_| |_||_| |_||_||_||_||_||_||_||_tƒjd| |dœ|¤ŽdS)N)Úis_encoder_decoderÚforced_eos_token_id©)Ú is_decoderÚ vocab_sizeÚmax_position_embeddingsrÚencoder_ffn_dimÚencoder_layersrÚdecoder_ffn_dimÚdecoder_layersÚdecoder_attention_headsÚdropoutÚattention_dropoutÚactivation_dropoutÚactivation_functionÚinit_stdÚencoder_layerdropÚdecoder_layerdropÚclassifier_dropoutÚ use_cacheÚnum_hidden_layersÚscale_embeddingÚ pad_token_idÚ bos_token_idÚ eos_token_idÚdecoder_start_token_idÚtie_word_embeddingsÚsuperÚ__init__)Úselfrrrrrr rr!r'r(r*rr%rr"r#r$r&r)r,r-r.r/r0rrr1Úkwargs©Ú __class__rúk/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/mbart/configuration_mbart.pyr3es@þ ýzMBartConfig.__init__)r r r rrr rrrrTTrr rrrrrFrrrNrFT) Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typeÚkeys_to_ignore_at_inferenceÚ attribute_mapr3Ú __classcell__rrr6r8rsBI ärN) r<Úconfiguration_utilsrÚutilsrÚ get_loggerr9ÚloggerrÚ__all__rrrr8Ús