g\dZddlmZddlmZddlmZddlmZddl m Z e j e Z Gdd eZGd d eZd S) zRoBERTa configuration) OrderedDict)Mapping)PretrainedConfig) OnnxConfig)loggingcLeZdZdZdZ dfd ZxZS) RobertaConfiga This is the configuration class to store the configuration of a [`RobertaModel`] or a [`TFRobertaModel`]. It is used to instantiate a RoBERTa 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 RoBERTa [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) 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 RoBERTa model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`RobertaModel`] or [`TFRobertaModel`]. 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 [`RobertaModel`] or [`TFRobertaModel`]. 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 RobertaConfig, RobertaModel >>> # Initializing a RoBERTa configuration >>> configuration = RobertaConfig() >>> # Initializing a model (with random weights) from the configuration >>> model = RobertaModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ```robertaY gelu皙?{Gz?-q=rabsoluteTNc tjd| ||d|||_||_||_||_||_||_||_||_ | |_ | |_ | |_ | |_ ||_||_||_dS)N) pad_token_id bos_token_id eos_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)selfrr r!r"r$r#r%r&r'r(r)r*rrrr+r,r-kwargs __class__s m/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/roberta/configuration_roberta.pyrzRobertaConfig.__init__cs, sl\hsslrsss$&!2#6 $!2#6 ,H)'>$.!2,'>$""4)r r rrrrrrrrrrrrrrTN)__name__ __module__ __qualname____doc__ model_typer __classcell__)r0s@r1r r sA A FJ%( # *'&5&5&5&5&5&5&5&5&5&5r2r cJeZdZedeeeeefffdZdS)RobertaOnnxConfigreturncZ|jdkrdddd}nddd}td|fd|fgS) Nzmultiple-choicebatchchoicesequence)rrr)rr input_idsattention_mask)taskr)r. dynamic_axiss r1inputszRobertaOnnxConfig.inputssU 9) ) )&8 CCLL&:66Ll+!<0    r2N)r3r4r5propertyrstrintrDrr2r1r:r:sL   WS#X%6 67    X    r2r:N)r6 collectionsrtypingrconfiguration_utilsronnxrutilsr get_loggerr3loggerr r:rr2r1rOs ######333333  H % %l5l5l5l5l5$l5l5l5^           r2