microsoft/layoutlmv3-base
0.1B
•
Updated
•
574k
•
468
LayoutLM
The LayoutLM series are Transformer encoders useful for document AI tasks such as invoice parsing, document image classification and DocVQA.
Note Currently the best LayoutLM model.
-
microsoft/layoutlmv2-base-uncased
Updated • 398k • 66 -
microsoft/layoutlm-base-uncased
0.1B • Updated • 92.5k • 61
microsoft/layoutxlm-base
Updated • 5.84k • 73Note A multilingual variant trained on 100 languages.
impira/layoutlm-document-qa
Document Question Answering • 0.1B • Updated • 7.35k • 1.15kNote A LayoutLM (v1) model fine-tuned to perform question answering over documents (DocVQA).
nielsr/layoutlmv3-finetuned-funsd
Token Classification • 0.1B • Updated • 1.79k • • 29Note A LayoutLMv3 model fine-tuned on the FUNSD dataset, a benchmark for document parsing.