o ei@s@dZddlmZddlmZeeZGdddeZdgZ dS)zMarian model configuration)PreTrainedConfig)loggingcsneZdZdZdZdgZdddZ                dfdd ZZS) MarianConfiga This is the configuration class to store the configuration of a [`MarianModel`]. It is used to instantiate an Marian 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 Marian [Helsinki-NLP/opus-mt-en-de](https://huggingface.co/Helsinki-NLP/opus-mt-en-de) 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 58101): Vocabulary size of the Marian model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`MarianModel`]. 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://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 0): The id of the token to force as the last generated token when `max_length` is reached. Usually set to `eos_token_id`. Examples: ```python >>> from transformers import MarianModel, MarianConfig >>> # Initializing a Marian Helsinki-NLP/opus-mt-en-de style configuration >>> configuration = MarianConfig() >>> # Initializing a model from the Helsinki-NLP/opus-mt-en-de style configuration >>> model = MarianModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```marianpast_key_valuesencoder_attention_headsd_model)num_attention_heads hidden_sizeN Tgelu皙?{Gz?Fc s||_||_||_|p ||_||_||_||_||_||_||_ ||_ | |_ ||_ ||_ ||_||_||_| |_| |_| |_||_||_||_||_||_||_||_||_tjd| |d|dS)N)is_encoder_decoderforced_eos_token_id) is_decodertie_word_embeddings vocab_sizedecoder_vocab_sizemax_position_embeddingsrencoder_ffn_dimencoder_layersrdecoder_ffn_dimdecoder_layersdecoder_attention_headsdropoutattention_dropoutactivation_dropoutactivation_functioninit_stdencoder_layerdropdecoder_layerdrop use_cachenum_hidden_layersscale_embedding share_encoder_decoder_embeddings pad_token_id eos_token_id bos_token_iddecoder_start_token_idsuper__init__)selfrrrrrrr!r r"r(r)r*rr&rr#r$r%r'r1r,r.r/r0rr-rrkwargs __class__rm/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/marian/configuration_marian.pyr3csD   zMarianConfig.__init__)r Nr r rrr rrrrTTrr rrrrrFrrNrTFT) __name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inference attribute_mapr3 __classcell__rrr6r8rsDG rN) r<configuration_utilsrutilsr get_loggerr9loggerr__all__rrrr8s