T^(h#dZddlmZddlmZmZmZmZddlm Z m Z ddl m Z m Z ddlmZmZmZej$eZGdd e ZGd d e Zd d gZy ) zLayoutLM model configuration OrderedDict)AnyListMappingOptional)PretrainedConfigPreTrainedTokenizer) OnnxConfig PatchingSpec) TensorTypeis_torch_availableloggingcHeZdZdZdZ dfd ZxZS)LayoutLMConfiga This is the configuration class to store the configuration of a [`LayoutLMModel`]. It is used to instantiate a LayoutLM 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 LayoutLM [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) architecture. Configuration objects inherit from [`BertConfig`] and can be used to control the model outputs. Read the documentation from [`BertConfig`] for more information. Args: vocab_size (`int`, *optional*, defaults to 30522): Vocabulary size of the LayoutLM model. Defines the different tokens that can be represented by the *inputs_ids* passed to the forward method of [`LayoutLMModel`]. 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" (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"`, `"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 into [`LayoutLMModel`]. 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. pad_token_id (`int`, *optional*, defaults to 0): The value used to pad input_ids. 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). 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`. max_2d_position_embeddings (`int`, *optional*, defaults to 1024): The maximum value that the 2D position embedding might ever used. Typically set this to something large just in case (e.g., 1024). Examples: ```python >>> from transformers import LayoutLMConfig, LayoutLMModel >>> # Initializing a LayoutLM configuration >>> configuration = LayoutLMConfig() >>> # Initializing a model (with random weights) from the configuration >>> model = LayoutLMModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```layoutlmc t|dd| i|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ ||_||_||_y)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_cachemax_2d_position_embeddings)selfrrrrrrrr r!r"r#r$rr%r&r'kwargs __class__s q/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/layoutlm/configuration_layoutlm.pyrzLayoutLMConfig.__init__cs( =l=f=$&!2#6 $!2#6 ,H)'>$.!2,'>$"*D')i:wi r-i gelu皙?r/ig{Gz?g-q=rabsoluteTi)__name__ __module__ __qualname____doc__ model_typer __classcell__r*s@r+rrsOB HJ%( # *#'##E#Er,rceZdZ d dededeeffd Zede ee e efffdZ dde de d e d e d eede eeff fd ZxZS)LayoutLMOnnxConfigconfigtaskpatching_specscRt|||||jdz |_y)N)r<r=)rrr'max_2d_positions)r(r;r<r=r*s r+rzLayoutLMOnnxConfig.__init__s, d>J & A AA Er,returnc HtddddfddddfddddfddddfgS)N input_idsbatchsequence)rr?bboxattention_masktoken_type_idsr)r(s r+inputszLayoutLMOnnxConfig.inputssH'j9:W45!w:#>?!w:#>?    r, tokenizer batch_size seq_lengthis_pair frameworkc t ||||||}gd}|tjk(s t dt s t dddl}|dj\}}|jg|g|zj|dd|d <|S) a Generate inputs to provide to the ONNX exporter for the specific framework Args: tokenizer: The tokenizer associated with this model configuration batch_size: The batch size (int) to export the model for (-1 means dynamic axis) seq_length: The sequence length (int) to export the model for (-1 means dynamic axis) is_pair: Indicate if the input is a pair (sentence 1, sentence 2) framework: The framework (optional) the tokenizer will generate tensor for Returns: Mapping[str, Tensor] holding the kwargs to provide to the model's forward function )rKrLrMrN)0TIzCExporting LayoutLM to ONNX is currently only supported for PyTorch.z7Cannot generate dummy inputs without PyTorch installed.rNrCr?rF) rgenerate_dummy_inputsrPYTORCHNotImplementedErrorr ValueErrortorchshapetensortile) r(rJrKrLrMrN input_dictboxrXr*s r+rTz(LayoutLMOnnxConfig.generate_dummy_inputss,W2 *W`i3  J...%&kl l!#VW W!+K!8!>!> J"\\*?SEJ,>*?@EEjRSUVW 6r,)defaultN)r_FN)r2r3r4r strrr rpropertyrintrIr boolrrrrTr7r8s@r+r:r:s-1 F FF\* F WS#X%6 67  *. &&&& &  & J' & c &&r,r:N)r5 collectionsrtypingrrrrr r onnxr r utilsrrr get_loggerr2loggerrr:__all__rr,r+rls_##//5,<<   H %jE%jEZ;;| 1 2r,