o h@sBdZddlmZddlmZeeZddiZGdddeZ dS) z YOSO model configuration)PretrainedConfig)loggingzuw-madison/yoso-4096zDhttps://huggingface.co/uw-madison/yoso-4096/resolve/main/config.jsoncsReZdZdZdZ                dfdd ZZS) YosoConfiga This is the configuration class to store the configuration of a [`YosoModel`]. It is used to instantiate an YOSO 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 YOSO [uw-madison/yoso-4096](https://huggingface.co/uw-madison/yoso-4096) 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 YOSO model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`YosoModel`]. 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 2): The vocabulary size of the `token_type_ids` passed when calling [`YosoModel`]. 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. position_embedding_type (`str`, *optional*, defaults to `"absolute"`): Type of position embedding. Choose one of `"absolute"`, `"relative_key"`, `"relative_key_query"`. use_expectation (`bool`, *optional*, defaults to `True`): Whether or not to use YOSO Expectation. Overrides any effect of num_hash. hash_code_len (`int`, *optional*, defaults to 9): The length of hashes generated by the hash functions. num_hash (`int`, *optional*, defaults to 64): Number of hash functions used in [`YosoSelfAttention`]. conv_window (`int`, *optional*): Kernel size of depth-wise convolution. use_fast_hash (`bool`, *optional*, defaults to `False`): Whether or not to use custom cuda kernels which perform fast random projection via hadamard transform. lsh_backward (`bool`, *optional*, defaults to `True`): Whether or not to perform backpropagation using Locality Sensitive Hashing. Example: ```python >>> from transformers import YosoConfig, YosoModel >>> # Initializing a YOSO uw-madison/yoso-4096 style configuration >>> configuration = YosoConfig() >>> # Initializing a model (with random weights) from the uw-madison/yoso-4096 style configuration >>> model = YosoModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```yosoY gelu皙?{Gz?-q=absoluteT @Nc stjd|||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_typeuse_expectation hash_code_lennum_hash conv_window use_fast_hash lsh_backward)selfrrrrr r!r"r#rr%r$r&r'r(r)r*r+r,r-rrrkwargs __class__ra/var/www/html/ai/venv/lib/python3.10/site-packages/transformers/models/yoso/configuration_yoso.pyrds( zYosoConfig.__init__)rrrrr r r r r r rrrTrrNTTr rr)__name__ __module__ __qualname____doc__ model_typer __classcell__rrr0r2rs4DrN) r6configuration_utilsrutilsr get_loggerr3logger"YOSO_PRETRAINED_CONFIG_ARCHIVE_MAPrrrrr2s