U ,-ef#@sVdZddlmZmZmZddlmZddlmZe e Z ddiZ Gdd d eZ d S) z ProphetNet model configuration)CallableOptionalUnion)PretrainedConfig)loggingz"microsoft/prophetnet-large-uncasedzRhttps://huggingface.co/microsoft/prophetnet-large-uncased/resolve/main/config.jsoncseZdZdZdZdgZddiZdeeee e e fee ee ee ee ee ee ee ee eeeeee eeee ee ee ee ee ee ee eeee ee ee ee dfdd Zee dddZejddZZS)ProphetNetConfiga 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://arxiv.org/abs/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://arxiv.org/abs/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_headsnum_encoder_attention_heads皙?gelu:w {Gz?Tr F)activation_dropoutactivation_function vocab_size hidden_sizeencoder_ffn_dimnum_encoder_layersr decoder_ffn_dimnum_decoder_layersnum_decoder_attention_headsattention_dropoutdropoutmax_position_embeddingsinit_stdis_encoder_decoderadd_cross_attentiondecoder_start_token_idngram num_bucketsrelative_max_distancedisable_ngram_losseps use_cache pad_token_id bos_token_id eos_token_idc s||_||_||_||_||_||_| |_| |_| |_||_ ||_ ||_ ||_ ||_ ||_||_| |_||_| |_||_tjf||||||d|dS)N)r.r/r0r%r&r')rrrrr rrr r#r$rr(r)r*r+r,r!rr"r-super__init__)selfrrrrrrr rrr r!r"r#r$r%r&r'r(r)r*r+r,r-r.r/r0kwargs __class__x/var/www/html/Darija-Ai-Train/env/lib/python3.8/site-packages/transformers/models/prophetnet/configuration_prophetnet.pyr2ks<zProphetNetConfig.__init__)returncCs |j|jS)N)rr)r3r7r7r8num_hidden_layerssz"ProphetNetConfig.num_hidden_layerscCs tddS)NzyThis model does not support the setting of `num_hidden_layers`. Please set `num_encoder_layers` and `num_decoder_layers`.)NotImplementedError)r3valuer7r7r8r:s)r r r r rrrrrrr r rrTTrrrrFrTrrr)__name__ __module__ __qualname____doc__Z model_typeZkeys_to_ignore_at_inferenceZ attribute_maprfloatrstrrintboolr2propertyr:setter __classcell__r7r7r5r8r sDBrN)r@typingrrrZconfiguration_utilsrutilsrZ get_loggerr=loggerZ(PROPHETNET_PRETRAINED_CONFIG_ARCHIVE_MAPrr7r7r7r8s