o ¾e¦i×ã@s@dZddlmZddlmZe e¡ZGdd„deƒZdgZ dS)zDeBERTa model configurationé)ÚPreTrainedConfig)ÚloggingcsTeZdZdZdZ                d‡fdd„ Z‡ZS)Ú DebertaConfiga This is the configuration class to store the configuration of a [`DebertaModel`]. It is used to instantiate a DeBERTa 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 DeBERTa [microsoft/deberta-base](https://huggingface.co/microsoft/deberta-base) architecture. Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the documentation from [`PreTrainedConfig`] for more information. Arguments: vocab_size (`int`, *optional*, defaults to 50265): Vocabulary size of the DeBERTa model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`DebertaModel`]. hidden_size (`int`, *optional*, defaults to 768): Dimensionality 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): Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder. hidden_act (`str` or `Callable`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, `"relu"`, `"silu"`, `"gelu"`, `"tanh"`, `"gelu_fast"`, `"mish"`, `"linear"`, `"sigmoid"` 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 0): The vocabulary size of the `token_type_ids` passed when calling [`DebertaModel`]. 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. relative_attention (`bool`, *optional*, defaults to `False`): Whether use relative position encoding. max_relative_positions (`int`, *optional*, defaults to 1): The range of relative positions `[-max_position_embeddings, max_position_embeddings]`. Use the same value as `max_position_embeddings`. pad_token_id (`int`, *optional*, defaults to 0): The value used to pad input_ids. position_biased_input (`bool`, *optional*, defaults to `True`): Whether add absolute position embedding to content embedding. pos_att_type (`list[str]`, *optional*): The type of relative position attention, it can be a combination of `["p2c", "c2p"]`, e.g. `["p2c"]`, `["p2c", "c2p"]`. layer_norm_eps (`float`, *optional*, defaults to 1e-12): The epsilon used by the layer normalization layers. legacy (`bool`, *optional*, defaults to `True`): Whether or not the model should use the legacy `LegacyDebertaOnlyMLMHead`, which does not work properly for mask infilling tasks. Example: ```python >>> from transformers import DebertaConfig, DebertaModel >>> # Initializing a DeBERTa microsoft/deberta-base style configuration >>> configuration = DebertaConfig() >>> # Initializing a model (with random weights) from the microsoft/deberta-base style configuration >>> model = DebertaModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```ÚdebertaéYÄéé é Úgeluçš™™™™™¹?ééç{®Gáz”?çH¯¼šò×z>FéÿÿÿÿNTc sÐtƒjdi|¤Ž||_||_||_||_||_||_||_| |_ | |_ | |_ | |_ ||_ ||_||_||_||_||_t|tƒrMdd„| ¡ d¡Dƒ}||_||_| |_| d|¡|_||_||_||_dS)NcSsg|]}| ¡‘qS©)Ústrip)Ú.0Úxrrúo/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/deberta/configuration_deberta.pyÚ ’sz*DebertaConfig.__init__..ú|Úpooler_hidden_sizer)ÚsuperÚ__init__Ú hidden_sizeÚnum_hidden_layersÚnum_attention_headsÚintermediate_sizeÚ hidden_actÚhidden_dropout_probÚattention_probs_dropout_probÚmax_position_embeddingsÚtype_vocab_sizeÚinitializer_rangeÚrelative_attentionÚmax_relative_positionsÚ pad_token_idÚ bos_token_idÚ eos_token_idÚtie_word_embeddingsÚposition_biased_inputÚ isinstanceÚstrÚlowerÚsplitÚ pos_att_typeÚ vocab_sizeÚlayer_norm_epsÚgetrÚpooler_dropoutÚpooler_hidden_actÚlegacy)Úselfr1rrrrrr r!r"r#r$r2r%r&r'r(r)r+r0r4r5r6r*Úkwargs©Ú __class__rrras6  zDebertaConfig.__init__)rrrrr r r r r r rrFrr NNTNr r TT)Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú model_typerÚ __classcell__rrr9rrs6GèrN) r>Úconfiguration_utilsrÚutilsrÚ get_loggerr;ÚloggerrÚ__all__rrrrÚs