o h'@sdZddlmZddlmZddlmZddlmZddl m Z e e Z idd d d d d ddddddddddddddddddd d!d"d#d$d%d&d'd(d)d*d+d,d-d.d/ZGd0d1d1eZGd2d3d3eZd4S)5z BERT model configuration) OrderedDict)Mapping)PretrainedConfig) OnnxConfig)loggingzbert-base-uncasedzAhttps://huggingface.co/bert-base-uncased/resolve/main/config.jsonzbert-large-uncasedzBhttps://huggingface.co/bert-large-uncased/resolve/main/config.jsonzbert-base-casedz?https://huggingface.co/bert-base-cased/resolve/main/config.jsonzbert-large-casedz@https://huggingface.co/bert-large-cased/resolve/main/config.jsonzbert-base-multilingual-uncasedzNhttps://huggingface.co/bert-base-multilingual-uncased/resolve/main/config.jsonzbert-base-multilingual-casedzLhttps://huggingface.co/bert-base-multilingual-cased/resolve/main/config.jsonzbert-base-chinesezAhttps://huggingface.co/bert-base-chinese/resolve/main/config.jsonzbert-base-german-casedzFhttps://huggingface.co/bert-base-german-cased/resolve/main/config.jsonz%bert-large-uncased-whole-word-maskingzUhttps://huggingface.co/bert-large-uncased-whole-word-masking/resolve/main/config.jsonz#bert-large-cased-whole-word-maskingzShttps://huggingface.co/bert-large-cased-whole-word-masking/resolve/main/config.jsonz5bert-large-uncased-whole-word-masking-finetuned-squadzehttps://huggingface.co/bert-large-uncased-whole-word-masking-finetuned-squad/resolve/main/config.jsonz3bert-large-cased-whole-word-masking-finetuned-squadzchttps://huggingface.co/bert-large-cased-whole-word-masking-finetuned-squad/resolve/main/config.jsonzbert-base-cased-finetuned-mrpczNhttps://huggingface.co/bert-base-cased-finetuned-mrpc/resolve/main/config.jsonzbert-base-german-dbmdz-casedzLhttps://huggingface.co/bert-base-german-dbmdz-cased/resolve/main/config.jsonzbert-base-german-dbmdz-uncasedzNhttps://huggingface.co/bert-base-german-dbmdz-uncased/resolve/main/config.jsonzcl-tohoku/bert-base-japanesezLhttps://huggingface.co/cl-tohoku/bert-base-japanese/resolve/main/config.jsonz/cl-tohoku/bert-base-japanese-whole-word-maskingz_https://huggingface.co/cl-tohoku/bert-base-japanese-whole-word-masking/resolve/main/config.jsonzQhttps://huggingface.co/cl-tohoku/bert-base-japanese-char/resolve/main/config.jsonzdhttps://huggingface.co/cl-tohoku/bert-base-japanese-char-whole-word-masking/resolve/main/config.jsonzShttps://huggingface.co/TurkuNLP/bert-base-finnish-cased-v1/resolve/main/config.jsonzUhttps://huggingface.co/TurkuNLP/bert-base-finnish-uncased-v1/resolve/main/config.jsonzNhttps://huggingface.co/wietsedv/bert-base-dutch-cased/resolve/main/config.json)z!cl-tohoku/bert-base-japanese-charz4cl-tohoku/bert-base-japanese-char-whole-word-maskingz#TurkuNLP/bert-base-finnish-cased-v1z%TurkuNLP/bert-base-finnish-uncased-v1zwietsedv/bert-base-dutch-casedcsFeZdZdZdZ           dfdd ZZS) BertConfiga This is the configuration class to store the configuration of a [`BertModel`] or a [`TFBertModel`]. It is used to instantiate a BERT 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 BERT [bert-base-uncased](https://huggingface.co/bert-base-uncased) 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 30522): Vocabulary size of the BERT model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`BertModel`] or [`TFBertModel`]. 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"` 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 2): The vocabulary size of the `token_type_ids` passed when calling [`BertModel`] or [`TFBertModel`]. 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"`. For positional embeddings use `"absolute"`. For more information on `"relative_key"`, please refer to [Self-Attention with Relative Position Representations (Shaw et al.)](https://arxiv.org/abs/1803.02155). For more information on `"relative_key_query"`, please refer to *Method 4* in [Improve Transformer Models with Better Relative Position Embeddings (Huang et al.)](https://arxiv.org/abs/2009.13658). 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`. classifier_dropout (`float`, *optional*): The dropout ratio for the classification head. Examples: ```python >>> from transformers import BertConfig, BertModel >>> # Initializing a BERT bert-base-uncased style configuration >>> configuration = BertConfig() >>> # Initializing a model (with random weights) from the bert-base-uncased style configuration >>> model = BertModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```bert:w gelu皙?{Gz?-q=rabsoluteTNc sttjdd| i|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ ||_||_||_dS)N pad_token_id)super__init__ vocab_size hidden_sizenum_hidden_layersnum_attention_heads hidden_actintermediate_sizehidden_dropout_probattention_probs_dropout_probmax_position_embeddingstype_vocab_sizeinitializer_rangelayer_norm_epsposition_embedding_type use_cacheclassifier_dropout)selfrrrrrrrr r!r"r#r$rr%r&r'kwargs __class__ra/var/www/html/ai/venv/lib/python3.10/site-packages/transformers/models/bert/configuration_bert.pyrs  zBertConfig.__init__)r r r r r rrrrrrrrrTN)__name__ __module__ __qualname____doc__ model_typer __classcell__rrr*r,rHs(Crc@s.eZdZedeeeeefffddZdS)BertOnnxConfigreturncCs<|jdkr dddd}nddd}td|fd|fd |fgS) Nzmultiple-choicebatchchoicesequence)rr)rr8 input_idsattention_masktoken_type_ids)taskr)r( dynamic_axisrrr,inputss  zBertOnnxConfig.inputsN)r-r.r/propertyrstrintr>rrrr,r3s$r3N)r0 collectionsrtypingrconfiguration_utilsronnxrutilsr get_loggerr-logger"BERT_PRETRAINED_CONFIG_ARCHIVE_MAPrr3rrrr,sn        -m