sg7!dZddlmZddlmZddlmZddlmZddl m Z e je Z Gdd eZGd d eZy ) zPLBART model configuration OrderedDict)Mapping)PretrainedConfig)OnnxConfigWithPast)loggingcheZdZdZdZdgZdddZ dfd ZxZS) 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://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 `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 ```plbartpast_key_valuesencoder_attention_headsd_model)num_attention_heads hidden_sizec H||_||_||_||_||_||_||_||_||_||_ ||_ ||_ | |_ ||_ | |_| |_||_| |_||_||_t)|Td|||| |d|y)N) pad_token_id bos_token_id eos_token_idis_encoder_decoderforced_eos_token_id) vocab_sizemax_position_embeddingsrencoder_ffn_dimencoder_layersrdecoder_ffn_dimdecoder_layersdecoder_attention_headsdropoutattention_dropoutactivation_dropoutactivation_functioninit_stdencoder_layerdropdecoder_layerdropclassifier_dropout use_cachenum_hidden_layersscale_embeddingsuper__init__)selfrrrrrrrrr%r&r(rr#rr r!r"r$r'r*rrrrkwargs __class__s b/var/www/html/venv/lib/python3.12/site-packages/transformers/models/plbart/configuration_plbart.pyr,zPLBartConfig.__init__js8%'>$ .,'>$.,'>$ !2"4#6   !2!2"4"!/.  %%%1 3    )iUi r2r3r4r5TTgelui皙?r7r5g{Gz?r5Trr9) __name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inference attribute_mapr, __classcell__)r/s@r0r r syG RJ#4"5,EV_`M $ " ""37 7 r1r c`eZdZedeeeeefffdZedeeeeefffdZy)PLBartOnnxConfigreturnc0tddddfddddfgS)N input_idsbatchsequencerr8attention_maskrr-s r0inputszPLBartOnnxConfig.inputss.'j9:!w:#>?   r1c|jrtddddfddddfddddfgStddddfddddfgS)Nlast_hidden_staterGrHrI past_keys)rr9encoder_last_hidden_state)use_pastrrKs r0outputszPLBartOnnxConfig.outputssp ==(g**EF g*"=>0g*2MN (g**EF0g*2MN r1N) r:r;r<propertyrstrintrLrRrr1r0rCrCs\  WS#X%6 67  gc3h&7!78r1rCN)r= collectionsrtypingrconfiguration_utilsronnxrutilsr get_loggerr:loggerr rCrr1r0r]sJ!#3&   H %E #E P)r1