a h@#@sdZddlmZddlmZddlmZmZmZm Z ddl m Z ddl m Z ddlmZerpdd lmZmZmZeeZGd d d e ZGd d d e Zd d gZdS)zDeBERTa model configuration) OrderedDict)Mapping) TYPE_CHECKINGAnyOptionalUnion)PretrainedConfig) OnnxConfig)logging)FeatureExtractionMixinPreTrainedTokenizerBase TensorTypecs&eZdZdZdZdfdd ZZS) DebertaConfigaL This is the configuration class to store the configuration of a [`DebertaModel`] or a [`TFDebertaModel`]. 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`] or [`TFDebertaModel`]. 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`] or [`TFDebertaModel`]. 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 ```ZdebertaY gelu皙?r{Gz?Hz>FTNc stjfi|||_||_||_||_||_||_||_| |_ | |_ | |_ | |_ ||_ ||_||_t|trdd|dD}||_||_| |_|d||_||_||_||_dS)NcSsg|] }|qS)strip).0xrrm/var/www/html/assistant/venv/lib/python3.9/site-packages/transformers/models/deberta/configuration_deberta.py z*DebertaConfig.__init__..|pooler_hidden_size)super__init__ hidden_sizenum_hidden_layersnum_attention_headsintermediate_size hidden_acthidden_dropout_probattention_probs_dropout_probmax_position_embeddingstype_vocab_sizeinitializer_rangerelative_attentionmax_relative_positions pad_token_idposition_biased_input isinstancestrlowersplit pos_att_type vocab_sizelayer_norm_epsgetr"pooler_dropoutpooler_hidden_actlegacy)selfr8r%r&r'r(r)r*r+r,r-r.r9r/r0r1r2r7r;r<r=kwargs __class__rrr$ks0 zDebertaConfig.__init__)rrrrrrrrrrrrFrrTNrrT)__name__ __module__ __qualname____doc__Z model_typer$ __classcell__rrr@rr!s.Grcs|eZdZeeeeeeffdddZeedddZde d eeee e d eeed eee fd fdd Z ZS)DebertaOnnxConfig)returncCs`|jdkrdddd}n ddd}|jjdkrHtd|fd |fd |fgStd|fd |fgSdS) Nzmultiple-choicebatchchoicesequence)r)rrLrZ input_idsZattention_masktoken_type_ids)task_configr-r)r>Z dynamic_axisrrrinputss   zDebertaOnnxConfig.inputscCsdS)Nrr)r>rrrdefault_onnx_opsetsz$DebertaOnnxConfig.default_onnx_opsetrFNr()r r rr ) preprocessor batch_size seq_length num_choicesis_pair framework num_channels image_width image_height tokenizerrHc s.tj||d} |jjdkr*d| vr*| d=| S)N)rTrYrrN)r#generate_dummy_inputsrPr-) r>rTrUrVrWrXrYrZr[r\r]Z dummy_inputsr@rrr^s z'DebertaOnnxConfig.generate_dummy_inputs) rrrFNrrSrSN)rBrCrDpropertyrr4intrQrRrboolrrr^rFrrr@rrGs4  rGN)rE collectionsrcollections.abcrtypingrrrrZconfiguration_utilsr Zonnxr utilsr r r rZ get_loggerrBloggerrrG__all__rrrrs      %