o ¾e¦iKã@s@dZddlmZddlmZe e¡ZGdd„deƒZdgZ dS)zRemBERT model configurationé)ÚPreTrainedConfig)ÚloggingcsPeZdZdZdZ               d‡fdd„ Z‡ZS)Ú RemBertConfiga¶ This is the configuration class to store the configuration of a [`RemBertModel`]. It is used to instantiate an RemBERT 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 RemBERT [google/rembert](https://huggingface.co/google/rembert) 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 250300): Vocabulary size of the RemBERT model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`RemBertModel`]. Vocabulary size of the model. Defines the different tokens that can be represented by the *inputs_ids* passed to the forward method of [`RemBertModel`]. hidden_size (`int`, *optional*, defaults to 1152): Dimensionality of the encoder layers and the pooler layer. num_hidden_layers (`int`, *optional*, defaults to 32): Number of hidden layers in the Transformer encoder. num_attention_heads (`int`, *optional*, defaults to 18): Number of attention heads for each attention layer in the Transformer encoder. input_embedding_size (`int`, *optional*, defaults to 256): Dimensionality of the input embeddings. output_embedding_size (`int`, *optional*, defaults to 1664): Dimensionality of the output embeddings. intermediate_size (`int`, *optional*, defaults to 4608): Dimensionality 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): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_probs_dropout_prob (`float`, *optional*, defaults to 0): The dropout ratio for the attention probabilities. classifier_dropout_prob (`float`, *optional*, defaults to 0.1): The dropout ratio for the classifier layer when fine-tuning. 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 [`RemBertModel`]. 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. is_decoder (`bool`, *optional*, defaults to `False`): Whether the model is used as a decoder or not. If `False`, the model is used as an encoder. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if `config.is_decoder=True`. Example: ```python >>> from transformers import RemBertModel, RemBertConfig >>> # Initializing a RemBERT rembert style configuration >>> configuration = RemBertConfig() >>> # Initializing a model from the rembert style configuration >>> model = RemBertModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```Úremberté¼Ñé€é ééé€éÚgeluççš™™™™™¹?ééç{®Gáz”?çê-™—q=Téé8é9Fc sštƒjdi|¤Ž||_||_||_||_||_||_||_||_ | |_ ||_ ||_ ||_ ||_||_| |_| |_| |_||_| |_||_||_d|_dS)NF©)ÚsuperÚ__init__Ú pad_token_idÚ bos_token_idÚ eos_token_idÚ is_decoderÚadd_cross_attentionÚ vocab_sizeÚinput_embedding_sizeÚoutput_embedding_sizeÚmax_position_embeddingsÚ hidden_sizeÚnum_hidden_layersÚnum_attention_headsÚintermediate_sizeÚ hidden_actÚhidden_dropout_probÚattention_probs_dropout_probÚclassifier_dropout_probÚinitializer_rangeÚtype_vocab_sizeÚlayer_norm_epsÚ use_cacheÚtie_word_embeddings)Úselfrr#r$r%r r!r&r'r(r)r*r"r,r+r-r.rrrrrÚkwargs©Ú __class__rúo/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/rembert/configuration_rembert.pyr]s. zRemBertConfig.__init__)rrrr r r r r rrrrrrrTrrrFF)Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typerÚ __classcell__rrr2r4rs2CêrN) r8Úconfiguration_utilsrÚutilsrÚ get_loggerr5ÚloggerrÚ__all__rrrr4Ús     y