gn^dZddlmZddlmZejeZGddeZdS)zMRA model configuration)PretrainedConfig)loggingcPeZdZdZdZ dfd ZxZS) MraConfigaw 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 probability 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 ```mraY gelu皙?{Gz?h㈵>absolutefullc 0tjd|||d|||_| |_||_||_||_||_||_||_ ||_ | |_ | |_ | |_ | |_||_||_||_||_dS)N) pad_token_id bos_token_id eos_token_id)super__init__ vocab_sizemax_position_embeddings hidden_sizenum_hidden_layersnum_attention_headsintermediate_size hidden_acthidden_dropout_probattention_probs_dropout_probinitializer_rangetype_vocab_sizelayer_norm_epsposition_embedding_type block_per_row approx_modeinitial_prior_first_n_blocksinitial_prior_diagonal_n_blocks)selfrr r!r"r#r$r%r&rr(r'r)r*r+r,r-r.rrrkwargs __class__s e/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/mra/configuration_mra.pyrzMraConfig.__init__\s0 sl\hsslrsss$'>$&!2#6 !2$#6 ,H)!2.,'>$*&,H)/N,,,)rr r r r r r r rrrrrrrrrrrr)__name__ __module__ __qualname____doc__ model_typer __classcell__)r1s@r2rrs? ? BJ%( # *%&()+*O*O*O*O*O*O*O*O*O*Or3rN) r7configuration_utilsrutilsr get_loggerr4loggerrrr3r2r>s333333  H % %nOnOnOnOnO nOnOnOnOnOr3