U ,È-eã@sBdZddlmZddlmZe e¡ZddiZGdd„deƒZ dS) z MRA model configurationé)ÚPretrainedConfig)Úloggingzuw-madison/mra-base-512-4zIhttps://huggingface.co/uw-madison/mra-base-512-4/resolve/main/config.jsoncs&eZdZdZdZd‡fdd„ Z‡ZS)Ú MraConfigax This is the configuration class to store the configuration of a [`MraModel`]. It is used to instantiate an MRA 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 Mra [uw-madison/mra-base-512-4](https://huggingface.co/uw-madison/mra-base-512-4) 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 50265): Vocabulary size of the Mra model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`MraModel`]. 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 Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 12): Number of attention heads for each attention layer in the Transformer encoder. intermediate_size (`int`, *optional*, defaults to 3072): Dimension of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. 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, encoder, 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 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). type_vocab_size (`int`, *optional*, defaults to 1): The vocabulary size of the `token_type_ids` passed when calling [`MraModel`]. 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-5): The epsilon used by the layer normalization layers. position_embedding_type (`str`, *optional*, defaults to `"absolute"`): Type of position embedding. Choose one of `"absolute"`, `"relative_key"`, `"relative_key_query"`. block_per_row (`int`, *optional*, defaults to 4): Used to set the budget for the high resolution scale. approx_mode (`str`, *optional*, defaults to `"full"`): Controls whether both low and high resolution approximations are used. Set to `"full"` for both low and high resolution and `"sparse"` for only low resolution. initial_prior_first_n_blocks (`int`, *optional*, defaults to 0): The initial number of blocks for which high resolution is used. initial_prior_diagonal_n_blocks (`int`, *optional*, defaults to 0): The number of diagonal blocks for which high resolution is used. Example: ```python >>> from transformers import MraConfig, MraModel >>> # Initializing a Mra uw-madison/mra-base-512-4 style configuration >>> configuration = MraConfig() >>> # Initializing a model (with random weights) from the uw-madison/mra-base-512-4 style configuration >>> model = MraModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```ZmraéYÄéé é Úgeluçš™™™™™¹?ééç{®Gáz”?çñh㈵øä>ÚabsoluteéÚfullééc s„tƒjf|||dœ|—Ž||_| |_||_||_||_||_||_||_ ||_ | |_ | |_ | |_ | |_||_||_||_||_dS)N)Ú pad_token_idÚ bos_token_idÚ eos_token_id)ÚsuperÚ__init__Ú vocab_sizeÚmax_position_embeddingsÚ hidden_sizeÚnum_hidden_layersÚnum_attention_headsÚintermediate_sizeÚ hidden_actÚhidden_dropout_probÚattention_probs_dropout_probÚinitializer_rangeÚtype_vocab_sizeÚlayer_norm_epsÚposition_embedding_typeÚ block_per_rowÚ approx_modeÚinitial_prior_first_n_blocksÚinitial_prior_diagonal_n_blocks)Úselfrrrrrrr r!rr#r"r$r%r&r'r(r)rrrÚkwargs©Ú __class__©új/var/www/html/Darija-Ai-Train/env/lib/python3.8/site-packages/transformers/models/mra/configuration_mra.pyr_s$zMraConfig.__init__)rrrrrr r r r r r rrrrrrr rr)Ú__name__Ú __module__Ú __qualname__Ú__doc__Z model_typerÚ __classcell__r.r.r,r/rs.@ërN) r3Zconfiguration_utilsrÚutilsrZ get_loggerr0ÚloggerZ!MRA_PRETRAINED_CONFIG_ARCHIVE_MAPrr.r.r.r/Ús   ÿ