Zj dSrSSKJr SSKJr SSKJr \"SS9\"SS \555rS /rg ) zDistilBERT model configuration)strict)PreTrainedConfig)auto_docstringzgoogle/distilbert-base-uncased) checkpointcN\rSrSr%SrSrSSSS.rSr\\ S 'S r \\ S 'S r \ \ S 'Sr \\ S'Sr\\ S'Sr\\ S'Sr\\ S'Sr\\-\ S'Sr\\-\ S'Sr\\ S'Sr\\ S'Sr\\-\ S'Sr\\-\ S'Sr\S-\ S'Sr\\\-S-\ S 'Sr\S-\ S!'S"r\ \ S#'S$rg)%DistilBertConfiga sinusoidal_pos_embds (`boolean`, *optional*, defaults to `False`): Whether to use sinusoidal positional embeddings. dim (`int`, *optional*, defaults to 768): Dimensionality of the encoder layers and the pooler layer. qa_dropout (`float`, *optional*, defaults to 0.1): The dropout probabilities used in the question answering model [`DistilBertForQuestionAnswering`]. seq_classif_dropout (`float`, *optional*, defaults to 0.2): The dropout probabilities used in the sequence classification and the multiple choice model [`DistilBertForSequenceClassification`]. Examples: ```python >>> from transformers import DistilBertConfig, DistilBertModel >>> # Initializing a DistilBERT configuration >>> configuration = DistilBertConfig() >>> # Initializing a model (with random weights) from the configuration >>> model = DistilBertModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config ``` distilbertdimn_headsn_layers) hidden_sizenum_attention_headsnum_hidden_layersi:w vocab_sizeimax_position_embeddingsFsinusoidal_pos_embds ii hidden_dimg?dropoutattention_dropoutgelu activationg{Gz?initializer_range qa_dropoutg?seq_classif_dropoutrN pad_token_id eos_token_id bos_token_idTtie_word_embeddings)__name__ __module__ __qualname____firstlineno____doc__ model_type attribute_maprint__annotations__rrboolrr r rrfloatrrstrrrrrr listr!r"__static_attributes__r#ڈ/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/models/distilbert/configuration_distilbert.pyr r s 4J('M J#&S&!&$&HcGSCNJGUS[%(us{(J#u#!J !'** L#* +/L#S /D(/#L#*# $$r2r N) r(huggingface_hub.dataclassesrconfiguration_utilsrutilsrr __all__r#r2r3r8sH%.3#;<2%'2%=2%j  r2