sgzZdZddlmZddlmZej eZGddeZy)zTrOCR model configuration)PretrainedConfig)loggingcbeZdZdZdZdgZddddZ d fd ZxZS) TrOCRConfiga This is the configuration class to store the configuration of a [`TrOCRForCausalLM`]. It is used to instantiate an TrOCR 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 TrOCR [microsoft/trocr-base-handwritten](https://huggingface.co/microsoft/trocr-base-handwritten) 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 50265): Vocabulary size of the TrOCR model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`TrOCRForCausalLM`]. d_model (`int`, *optional*, defaults to 1024): Dimensionality of the layers and the pooler layer. decoder_layers (`int`, *optional*, defaults to 12): Number of decoder layers. decoder_attention_heads (`int`, *optional*, defaults to 16): Number of attention heads for each attention layer in the Transformer decoder. decoder_ffn_dim (`int`, *optional*, defaults to 4096): Dimensionality of the "intermediate" (often named feed-forward) layer in decoder. activation_function (`str` or `function`, *optional*, defaults to `"gelu"`): The non-linear activation function (function or string) in the pooler. If string, `"gelu"`, `"relu"`, `"silu"` and `"gelu_new"` are supported. 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). dropout (`float`, *optional*, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, and pooler. attention_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for the attention probabilities. activation_dropout (`float`, *optional*, defaults to 0.0): The dropout ratio for activations inside the fully connected layer. init_std (`float`, *optional*, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. decoder_layerdrop (`float`, *optional*, defaults to 0.0): The LayerDrop probability for the decoder. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556) for more details. use_cache (`bool`, *optional*, defaults to `True`): Whether or not the model should return the last key/values attentions (not used by all models). scale_embedding (`bool`, *optional*, defaults to `False`): Whether or not to scale the word embeddings by sqrt(d_model). use_learned_position_embeddings (`bool`, *optional*, defaults to `True`): Whether or not to use learned position embeddings. If not, sinusoidal position embeddings will be used. layernorm_embedding (`bool`, *optional*, defaults to `True`): Whether or not to use a layernorm after the word + position embeddings. Example: ```python >>> from transformers import TrOCRConfig, TrOCRForCausalLM >>> # Initializing a TrOCR-base style configuration >>> configuration = TrOCRConfig() >>> # Initializing a model (with random weights) from the TrOCR-base style configuration >>> model = TrOCRForCausalLM(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```trocrpast_key_valuesdecoder_attention_headsd_modeldecoder_layers)num_attention_heads hidden_sizenum_hidden_layersc ||_||_||_||_||_||_||_||_| |_| |_ | |_ | |_ ||_ ||_ ||_||_t!|Dd|||| d|y)N) pad_token_id bos_token_id eos_token_iddecoder_start_token_id) vocab_sizer r r decoder_ffn_dimactivation_functionmax_position_embeddingsdropoutattention_dropoutactivation_dropoutinit_stddecoder_layerdrop use_cachescale_embeddinguse_learned_position_embeddingslayernorm_embeddingsuper__init__)selfrr r r rrrrrrrrrrrr r!rrrkwargs __class__s `/var/www/html/venv/lib/python3.12/site-packages/transformers/models/trocr/configuration_trocr.pyr#zTrOCRConfig.__init__`s0% ,'>$.#6 '>$ !2"4  !2"./N,#6   %%%#9    )iYi igeluig?r,g{Gz?r,TFTTr-) __name__ __module__ __qualname____doc__ model_typekeys_to_ignore_at_inference attribute_mapr# __classcell__)r&s@r'rrsq= ~J#4"58 -M "" # (, +/ / r(rN) r3configuration_utilsrutilsr get_loggerr0loggerrrr(r'r<s3 3   H %w "w r(