o ¾e¦iÅã@s@dZddlmZddlmZe e¡ZGdd„deƒZdgZ dS)zBART model configurationé)ÚPreTrainedConfig)ÚloggingcsneZdZdZdZdgZdddœZ                d‡fdd„ Z‡ZS)Ú BartConfiga This is the configuration class to store the configuration of a [`BartModel`]. It is used to instantiate a BART 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 BART [facebook/bart-large](https://huggingface.co/facebook/bart-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 BART model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`BartModel`]. 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). num_labels (`int`, *optional*, defaults to 3): The number of labels to use in [`BartForSequenceClassification`]. Example: ```python >>> from transformers import BartConfig, BartModel >>> # Initializing a BART facebook/bart-large style configuration >>> configuration = BartConfig() >>> # Initializing a model (with random weights) from the facebook/bart-large style configuration >>> model = BartModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```ÚbartÚpast_key_valuesÚencoder_attention_headsÚd_model)Únum_attention_headsÚ hidden_sizeéYÄéé ééçÚgeluçš™™™™™¹?ç{®Gáz”?FTréééc s¸||_||_||_||_| |_||_||_||_||_||_ ||_ | |_ ||_ ||_ | |_||_| |_| |_||_||_||_||_||_||_||_||_tƒjd||dœ|¤ŽdS)N)Ú num_labelsÚis_encoder_decoder©)Ú is_decoderÚtie_word_embeddingsÚ 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_idÚsuperÚ__init__)Úselfrrrrrr!r r"r(r)r&rr#r$r%r'r*r-r+rr.r/r0rr1Úforced_eos_token_idrrÚkwargs©Ú __class__rúi/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/bart/configuration_bart.pyr3ds@ þ ýzBartConfig.__init__)r r r rrr rrrrrr rrrrrFTrrrrTrrFT) Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typeÚkeys_to_ignore_at_inferenceÚ attribute_mapr3Ú __classcell__rrr7r9rsDH ãrN) r=Úconfiguration_utilsrÚutilsrÚ get_loggerr:ÚloggerrÚ__all__rrrr9Ús