`i dZddlmZddlmZddlmZmZddlm Z m Z ddl m Z m Z ddlmZmZmZejeZGd d e ZGd d e Zd d gZd S)zLayoutLM model configuration OrderedDict)Mapping)AnyOptional)PretrainedConfigPreTrainedTokenizer) OnnxConfig PatchingSpec) TensorTypeis_torch_availableloggingcFeZdZdZdZ 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. 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 ```layoutlm:w gelu皙?{Gz?-q=rTc tjdd| 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_eps use_cachemax_2d_position_embeddings)selfr#r$r%r&r(r'r)r*r+r,r-r.rr/r0kwargs __class__s /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/layoutlm/configuration_layoutlm.pyr"zLayoutLMConfig.__init__^s& ==l=f===$&!2#6 $!2#6 ,H)'>$.!2,"*D''')rrrrrrrrrrrrrTr)__name__ __module__ __qualname____doc__ model_typer" __classcell__r3s@r4rrs< < |J%( ##'!!E!E!E!E!E!E!E!E!E!Er5rceZdZ ddededeeeffd Ze de ee e efffdZ dd e d e d e dedeede eeff fd ZxZS)LayoutLMOnnxConfigdefaultNconfigtaskpatching_specscnt||||jdz |_dS)N)rArB)r!r"r0max_2d_positions)r1r@rArBr3s r4r"zLayoutLMOnnxConfig.__init__s: d>JJJ & AA Er5returnc PtddddfddddfddddfddddfgS)N input_idsbatchsequence)rrDbboxattention_masktoken_type_idsr)r1s r4inputszLayoutLMOnnxConfig.inputssY'j99:W445!w:#>#>?!w:#>#>?     r5F tokenizer batch_size seq_lengthis_pair frameworkcbt|||||}gd}|tjkst dt st dddl}|dj\}}| g|g|z |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 )rQrRrSrT)0TIzCExporting LayoutLM to ONNX is currently only supported for PyTorch.z7Cannot generate dummy inputs without PyTorch installed.rNrHrDrK) r!generate_dummy_inputsr PYTORCHNotImplementedErrorr ValueErrortorchshapetensortile) r1rPrQrRrSrT input_dictboxr^r3s r4rZz(LayoutLMOnnxConfig.generate_dummy_inputss,WW22 *W`i3   J...%&kll l!## XVWW W !+K!8!> J"\\*?SEJ,>*?@@EEjRSUVWW 6r5)r?N)rOrOFN)r6r7r8r strrlistr r"propertyrintrNr boolr rrZr;r<s@r4r>r>s-7; FF FF!l!34 FFFFFF WS#X%6 67   X *. &&&&& &  & J' & c &&&&&&&&&&r5r>N)r9 collectionsrcollections.abcrtypingrrr r onnxr r utilsr rr get_loggerr6loggerrr>__all__r r5r4rrs##"############ 55555555,,,,,,,,<<<<<<<<<<  H % %bEbEbEbEbE%bEbEbEJ;;;;;;;;| 1 2r5