a ½ Àh½"ã@sTdZddlmZmZmZddlmZddlmZe  e ¡Z Gdd„deƒZ dgZ dS) zProphetNet model configurationé)ÚCallableÚOptionalÚUnioné)ÚPretrainedConfig)ÚloggingcsüeZdZdZdZdgZddiZdeeee e e fee ee ee ee ee ee ee ee eeeeee eeee ee ee ee ee ee ee eeee ee ee ee dœ‡fdd„ Zee dœdd„ƒZejdd„ƒZ‡ZS)ÚProphetNetConfigaŸ This is the configuration class to store the configuration of a [`ProphetNetModel`]. It is used to instantiate a ProphetNet 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 ProphetNet [microsoft/prophetnet-large-uncased](https://huggingface.co/microsoft/prophetnet-large-uncased) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: activation_dropout (`float`, *optional*, defaults to 0.1): The dropout ratio for activations inside the fully connected layer. 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. vocab_size (`int`, *optional*, defaults to 30522): Vocabulary size of the ProphetNET model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`ProphetNetModel`]. hidden_size (`int`, *optional*, defaults to 1024): Dimensionality of the layers and the pooler layer. encoder_ffn_dim (`int`, *optional*, defaults to 4096): Dimensionality of the "intermediate" (often named feed-forward) layer in decoder. num_encoder_layers (`int`, *optional*, defaults to 12): Number of encoder layers. num_encoder_attention_heads (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the Transformer encoder. decoder_ffn_dim (`int`, *optional*, defaults to 4096): Dimensionality of the `intermediate` (often named feed-forward) layer in decoder. num_decoder_layers (`int`, *optional*, defaults to 12): Number of decoder layers. num_decoder_attention_heads (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the Transformer decoder. attention_dropout (`float`, *optional*, defaults to 0.1): The dropout ratio for the attention probabilities. dropout (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. max_position_embeddings (`int`, *optional*, defaults to 512): 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. add_cross_attention (`bool`, *optional*, defaults to `True`): Whether cross-attention layers should be added to the model. is_encoder_decoder (`bool`, *optional*, defaults to `True`): Whether this is an encoder/decoder model. pad_token_id (`int`, *optional*, defaults to 1) Padding token id. bos_token_id (`int`, *optional*, defaults to 0) Beginning of stream token id. eos_token_id (`int`, *optional*, defaults to 2) End of stream token id. ngram (`int`, *optional*, defaults to 2) Number of future tokens to predict. Set to 1 to be same as traditional Language model to predict next first token. num_buckets (`int`, *optional*, defaults to 32) The number of buckets to use for each attention layer. This is for relative position calculation. See the [T5 paper](see https://huggingface.co/papers/1910.10683) for more details. relative_max_distance (`int`, *optional*, defaults to 128) Relative distances greater than this number will be put into the last same bucket. This is for relative position calculation. See the [T5 paper](see https://huggingface.co/papers/1910.10683) for more details. disable_ngram_loss (`bool`, *optional*, defaults to `False`): Whether be trained predicting only the next first token. eps (`float`, *optional*, defaults to 0.0): Controls the `epsilon` parameter value for label smoothing in the loss calculation. If set to 0, no label smoothing is performed. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). Z prophetnetZpast_key_valuesZnum_attention_headsÚnum_encoder_attention_headsçš™™™™™¹?Úgelué:wééé ééç{®Gáz”?Tréé é€Fçé)Úactivation_dropoutÚactivation_functionÚ vocab_sizeÚ hidden_sizeÚencoder_ffn_dimÚnum_encoder_layersr Údecoder_ffn_dimÚnum_decoder_layersÚnum_decoder_attention_headsÚattention_dropoutÚdropoutÚmax_position_embeddingsÚinit_stdÚis_encoder_decoderÚadd_cross_attentionÚdecoder_start_token_idÚngramÚ num_bucketsÚrelative_max_distanceÚdisable_ngram_lossÚepsÚ use_cacheÚ pad_token_idÚ bos_token_idÚ eos_token_idc sœ||_||_||_||_||_||_| |_| |_| |_||_ ||_ ||_ ||_ ||_ ||_||_| |_||_| |_||_tƒjf||||||dœ|¤ŽdS)N)r.r/r0r%r&r')rrrrr rrr r#r$rr(r)r*r+r,r!rr"r-ÚsuperÚ__init__)Úselfrrrrrrr rrr r!r"r#r$r%r&r'r(r)r*r+r,r-r.r/r0Úkwargs©Ú __class__©ús/var/www/html/assistant/venv/lib/python3.9/site-packages/transformers/models/prophetnet/configuration_prophetnet.pyr2fs<úùzProphetNetConfig.__init__)ÚreturncCs|jS)N)r)r3r7r7r8Únum_hidden_layers¨sz"ProphetNetConfig.num_hidden_layerscCs tdƒ‚dS)NzyThis model does not support the setting of `num_hidden_layers`. Please set `num_encoder_layers` and `num_decoder_layers`.)ÚNotImplementedError)r3Úvaluer7r7r8r:¬sÿ)r r r r rrrrrrr r rrTTrrrrFrTrrr)Ú__name__Ú __module__Ú __qualname__Ú__doc__Z model_typeZkeys_to_ignore_at_inferenceZ attribute_maprÚfloatrÚstrrÚintÚboolr2Úpropertyr:ÚsetterÚ __classcell__r7r7r5r8rs~EÿååBrN)r@ÚtypingrrrZconfiguration_utilsrÚutilsrZ get_loggerr=ÚloggerrÚ__all__r7r7r7r8Ús