# Finetuned LayoutLMv2 with LayoutXLMTokenizer on standard_0.0.2_EasyOcrEngine

LayoutLMv2 with LayoutXLMTokenizer finetuned on all documents processed by standard_0.0.2_EasyOcrEngine, first-page only with no additional cleaning.

Base model: microsoft/layoutlmv2-base-uncased

Tokenizer: microsoft/layoutxlm-base

Dataset: fimu-docproc-research/standard_0.0.2_EasyOcrEngine