LayoutLM - a microsoft Collection

microsoft 's Collections

TAPEX

Table Transformer

Orca

UDOP

GIT

Phi-1

Phi-3

LayoutLM

updated Nov 27, 2023

The LayoutLM series are Transformer encoders useful for document AI tasks such as invoice parsing, document image classification and DocVQA.

microsoft/layoutlmv3-base

Updated 18 days ago • 8.37M • 267

Note Currently the best LayoutLM model.
microsoft/layoutxlm-base

Updated Sep 16, 2022 • 217k • 56

Note A multilingual variant trained on 100 languages.
microsoft/layoutlmv2-base-uncased

Updated Sep 16, 2022 • 2.58M • 48
impira/layoutlm-document-qa

Document Question Answering • Updated Mar 18, 2023 • 36k • 823

Note A LayoutLM (v1) model fine-tuned to perform question answering over documents (DocVQA).
nielsr/layoutlmv3-finetuned-funsd

Token Classification • Updated Sep 16, 2023 • 402 • 16

Note A LayoutLMv3 model fine-tuned on the FUNSD dataset, a benchmark for document parsing.