U Ö9%eNã@sBdZddlmZddlmZe e¡ZddiZGdd„deƒZ dS) z CANINE model configurationé)ÚPretrainedConfig)Úloggingzgoogle/canine-sz?https://huggingface.co/google/canine-s/resolve/main/config.jsoncs&eZdZdZdZd‡fdd„ Z‡ZS)Ú CanineConfiga‰ This is the configuration class to store the configuration of a [`CanineModel`]. It is used to instantiate an CANINE 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 CANINE [google/canine-s](https://huggingface.co/google/canine-s) architecture. Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PretrainedConfig`] for more information. Args: hidden_size (`int`, *optional*, defaults to 768): Dimension of the encoder layers and the pooler layer. num_hidden_layers (`int`, *optional*, defaults to 12): Number of hidden layers in the deep Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer encoders. intermediate_size (`int`, *optional*, defaults to 3072): Dimension of the "intermediate" (i.e., feed-forward) layer in the Transformer encoders. hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported. hidden_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout probabilitiy for all fully connected layers in the embeddings, encoders, and pooler. attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout ratio for the attention probabilities. max_position_embeddings (`int`, *optional*, defaults to 16384): The maximum sequence length that this model might ever be used with. type_vocab_size (`int`, *optional*, defaults to 16): The vocabulary size of the `token_type_ids` passed when calling [`CanineModel`]. initializer_range (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. layer_norm_eps (`float`, *optional*, defaults to 1e-12): The epsilon used by the layer normalization layers. downsampling_rate (`int`, *optional*, defaults to 4): The rate at which to downsample the original character sequence length before applying the deep Transformer encoder. upsampling_kernel_size (`int`, *optional*, defaults to 4): The kernel size (i.e. the number of characters in each window) of the convolutional projection layer when projecting back from `hidden_size`*2 to `hidden_size`. num_hash_functions (`int`, *optional*, defaults to 8): The number of hash functions to use. Each hash function has its own embedding matrix. num_hash_buckets (`int`, *optional*, defaults to 16384): The number of hash buckets to use. local_transformer_stride (`int`, *optional*, defaults to 128): The stride of the local attention of the first shallow Transformer encoder. Defaults to 128 for good TPU/XLA memory alignment. Example: ```python >>> from transformers import CanineConfig, CanineModel >>> # Initializing a CANINE google/canine-s style configuration >>> configuration = CanineConfig() >>> # Initializing a model (with random weights) from the google/canine-s style configuration >>> model = CanineModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Zcanineéé é Úgeluçš™™™™™¹?é@éç{®Gáz”?çê-™—q=ééàéàééé€c s~tƒjf| | |dœ|—Ž||_||_||_||_||_||_||_||_ | |_ | |_ | |_ ||_ ||_||_||_||_dS)N)Ú pad_token_idÚ bos_token_idÚ eos_token_id)ÚsuperÚ__init__Úmax_position_embeddingsÚ hidden_sizeÚnum_hidden_layersÚnum_attention_headsÚintermediate_sizeÚ hidden_actÚhidden_dropout_probÚattention_probs_dropout_probÚinitializer_rangeÚtype_vocab_sizeÚlayer_norm_epsÚdownsampling_rateÚupsampling_kernel_sizeÚnum_hash_functionsÚnum_hash_bucketsÚlocal_transformer_stride)Úselfrrrrrrr rr"r!r#rrrr$r%r&r'r(Úkwargs©Ú __class__©ún/var/www/html/Darija-Ai-API/env/lib/python3.8/site-packages/transformers/models/canine/configuration_canine.pyr^s"zCanineConfig.__init__)rrrrrr r r r r r rrrrrrr r)Ú__name__Ú __module__Ú __qualname__Ú__doc__Z model_typerÚ __classcell__r-r-r+r.rs,>ìrN) r2Zconfiguration_utilsrÚutilsrZ get_loggerr/ÚloggerZ$CANINE_PRETRAINED_CONFIG_ARCHIVE_MAPrr-r-r-r.Ús   ÿ