a ½ Àh­!ã@stdZddlmZddlmZddlmZddlmZddl m Z e   e ¡Z Gdd „d eƒZGd d „d eƒZd gZd S) zPLBART model configurationé©Ú OrderedDict)ÚMappingé)ÚPretrainedConfig)ÚOnnxConfigWithPast)Úloggingcs8eZdZdZdZdgZddddœZd‡fdd„ Z‡ZS)Ú PLBartConfiga This is the configuration class to store the configuration of a [`PLBartModel`]. It is used to instantiate an PLBART 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 PLBART [uclanlp/plbart-base](https://huggingface.co/uclanlp/plbart-base) 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 50005): Vocabulary size of the PLBART model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`PLBartModel`]. d_model (`int`, *optional*, defaults to 768): Dimensionality of the layers and the pooler layer. encoder_layers (`int`, *optional*, defaults to 6): Number of encoder layers. decoder_layers (`int`, *optional*, defaults to 6): Number of decoder layers. encoder_attention_heads (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. decoder_attention_heads (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer decoder. decoder_ffn_dim (`int`, *optional*, defaults to 3072): Dimensionality of the "intermediate" (often named feed-forward) layer in decoder. encoder_ffn_dim (`int`, *optional*, defaults to 3072): 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 0.1): 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 `True`): 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 PLBartConfig, PLBartModel >>> # Initializing a PLBART uclanlp/plbart-base style configuration >>> configuration = PLBartConfig() >>> # Initializing a model (with random weights) from the uclanlp/plbart-base style configuration >>> model = PLBartModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```ZplbartZpast_key_valuesÚencoder_attention_headsÚd_modelÚinit_std)Znum_attention_headsZ hidden_sizeZinitializer_rangeéUÃééé é çTÚgeluéçš™™™™™¹?ç{®Gáz”?éréc sš||_||_||_||_||_||_||_||_||_||_ ||_ ||_ | |_ ||_ | |_| |_||_| |_||_||_tƒjf|||| |dœ|¤ŽdS)N)Ú pad_token_idÚ bos_token_idÚ eos_token_idÚis_encoder_decoderÚforced_eos_token_id)Ú vocab_sizeÚmax_position_embeddingsr Úencoder_ffn_dimÚencoder_layersr Údecoder_ffn_dimÚdecoder_layersÚdecoder_attention_headsÚdropoutÚattention_dropoutÚactivation_dropoutÚactivation_functionr Úencoder_layerdropÚdecoder_layerdropÚclassifier_dropoutÚ use_cacheZnum_hidden_layersÚscale_embeddingÚsuperÚ__init__)Úselfrrr!r r r#r"r$r)r*r,rr(r r%r&r'r r+r-rrrrÚkwargs©Ú __class__©úk/var/www/html/assistant/venv/lib/python3.9/site-packages/transformers/models/plbart/configuration_plbart.pyr/ns:ûúzPLBartConfig.__init__)r rrrrrrrrrTTrrrrrrrTrrrr) Ú__name__Ú __module__Ú __qualname__Ú__doc__Z model_typeZkeys_to_ignore_at_inferenceZ attribute_mapr/Ú __classcell__r4r4r2r5r s@Iýçr c@sPeZdZeeeeeeffdœdd„ƒZeeeeeeffdœdd„ƒZdS)ÚPLBartOnnxConfig)ÚreturncCs tddddœfddddœfgƒS)NZ input_idsÚbatchÚsequence©rrZattention_maskr©r0r4r4r5Úinputs©s   þÿzPLBartOnnxConfig.inputscCsV|jr2tddddœfddddœfddddœfgƒStddddœfddddœfgƒSdS)NZlast_hidden_stater=r>r?Z past_keys)rrZencoder_last_hidden_state)Zuse_pastrr@r4r4r5Úoutputs²s   ýÿ  þÿzPLBartOnnxConfig.outputsN) r6r7r8ÚpropertyrÚstrÚintrArBr4r4r4r5r;¨s r;N)r9Ú collectionsrÚcollections.abcrZconfiguration_utilsrZonnxrÚutilsrZ get_loggerr6Úloggerr r;Ú__all__r4r4r4r5Ús