Indian Flag
Government Of India
A-
A
A+
Home/Models/LayoutLMv3 - Multimodal Document AI

LayoutLMv3 - Multimodal Document AI

A pre-trained multimodal Transformer model for document AI, integrating unified text and image masking for tasks such as form understanding, receipt processing, and document layout analysis.

About Model

LayoutLMv3 is a pre-trained multimodal Transformer designed for document AI, utilizing unified text and image masking to enhance document understanding. Its unified architecture and training objectives make it a versatile, general-purpose model that can be fine-tuned for both text-centric and image-centric tasks. These include form and receipt understanding, document visual question answering, document layout analysis, and classification. Developed as an improvement over its predecessors, LayoutLMv3 is well-suited for applications in OCR, automated document processing, and AI-driven document workflows.

LayoutLMv3 - Multimodal Document AI

Metadata Metadata

Attribution-Non-Commercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)

Yiheng Xu, Minghao Li, Lei Cui, Shaohan Huang, Furu Wei, Ming Zhou

Transformers

Other

Open

Microsoft Corporation (India) Pvt. Ltd.

Sector Agnostic

20/08/25 11:44:40

Vikram Malhotra

0

Activity Overview Activity Overview

  • Downloads0
  • Redirect 15
  • File Size 0
  • Views 932

Tags Tags

  • PyTorch
  • Transformers
  • ONNX
  • English
  • safetensors
  • inference endpoints
  • tensorflow
  • layoutlmv3

License Control License Control

Attribution-Non-Commercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)

More Models from Microsoft Corporation (India) Pvt. Ltd. More Models from Microsoft Corporation (India) Pvt. Ltd.

TAPEX: Large SQL Execution Model (Table Pre-training via Learning a Neural SQL Executor)
A large-sized TAPEX model pre-trained to simulate neural SQL execution, enabling the execution of SQL queries on given tables.
DataRetrieval
Transformers
BART
TAPEX
PreTrainedModel
NeuralExecutor
SQLExecution
  • See Upvoters0
  • Downloads6
  • File Size0
  • Views214
Updated 10 month(s) ago
MICROSOFT CORPORATION (INDIA) PVT. LTD.
View Details
share
TAPEX: Large Model (Table Pre-training via Learning a Neural SQL Executor)
A large-sized pre-trained model designed to enhance table-based question answering and fact verification tasks.
FactVerification
BART
TableQuestionAnswering
PreTrainedModel
LargeModel
  • See Upvoters0
  • Downloads5
  • File Size0
  • Views169
Updated 10 month(s) ago
MICROSOFT CORPORATION (INDIA) PVT. LTD.
View Details
share
TAPEX: TabFact Data enabled Large Finetuned (Table Pre-training via Learning a Neural SQL Executor) Model
A large-sized TAPEX model fine-tuned on the TabFact dataset, designed to enhance performance in table-based fact verification tasks.
Transformers
TabFact
DataValidation
FactVerification
TAPEX
FineTunedModel
NaturalLanguageProcessing
BART
  • See Upvoters0
  • Downloads5
  • File Size0
  • Views131
Updated 10 month(s) ago
MICROSOFT CORPORATION (INDIA) PVT. LTD.
View Details
share
TAPEX (Table Pre-training via Learning a Neural SQL Executor) Large Finetuned Model
A large-sized TAPEX model fine-tuned on the WikiTableQuestions dataset, designed to enhance performance in table-based question answering tasks.
BART
Transformers
WikiTableQuestions
TableQuestionAnswering
DataExtraction
TAPEX
FineTunedModel
NaturalLanguageProcessing
  • See Upvoters0
  • Downloads2
  • File Size0
  • Views205
Updated 10 month(s) ago
MICROSOFT CORPORATION (INDIA) PVT. LTD.
View Details
share
TAPEX: Base Model (Table Pre-training via Learning a Neural SQL Executor)
A base-sized pre-trained model designed to enhance table-based question answering and fact verification tasks.
FactVerification
BART
TableQuestionAnswering
PreTrainedModel
TabularData
  • See Upvoters0
  • Downloads3
  • File Size0
  • Views122
Updated 10 month(s) ago
MICROSOFT CORPORATION (INDIA) PVT. LTD.
View Details
share
TAPEX: WikiTable Questions Data enabled Base Finetuned (Table Pre-training via Learning a Neural SQL Executor) Model
A base-sized TAPEX model fine-tuned on the WikiTableQuestions dataset, designed to enhance performance in table-based question answering tasks.
WikiTableQuestions
Transformers
BART
NaturalLanguageProcessing
FineTunedModel
TAPEX
DataExtraction
TableQuestionAnswering
  • See Upvoters0
  • Downloads3
  • File Size0
  • Views157
Updated 10 month(s) ago
MICROSOFT CORPORATION (INDIA) PVT. LTD.
View Details
share
TAPEX: WikiSQL Data enabled Base Finetuned (Table Pre-training via Learning a Neural SQL Executor) Model
A large-sized TAPEX model fine-tuned on the WikiSQL dataset, optimized for translating natural language questions into SQL queries for effective table-based question answering.
DataRetrieval
SQLQueryGeneration
Transformers
BART
NaturalLanguageProcessing
FineTunedModel
TAPEX
WikiSQL
  • See Upvoters0
  • Downloads5
  • File Size0
  • Views146
Updated 10 month(s) ago
MICROSOFT CORPORATION (INDIA) PVT. LTD.
View Details
share
TAPEX: TabFact Data enabled Base Finetuned (Table Pre-training via Learning a Neural SQL Executor) Model
A base-sized TAPEX model fine-tuned on the TabFact dataset, tailored for verifying the factual accuracy of textual statements against tabular data.
Transformers
BART
NaturalLanguageProcessing
FineTunedModel
TAPEX
FactVerification
DataValidation
TabFact
  • See Upvoters0
  • Downloads4
  • File Size0
  • Views122
Updated 10 month(s) ago
MICROSOFT CORPORATION (INDIA) PVT. LTD.
View Details
share
TAPEX: Base Finetuned (Table Pre-training via Learning a Neural SQL Executor) Model
A base-sized TAPEX model fine-tuned on the WikiSQL dataset, designed to enhance performance in table-based question answering tasks.
TAPEX
WikiSQL
TableQuestionAnswering
DataExtraction
Transformers
FineTunedModel
NaturalLanguageProcessing
BART
  • See Upvoters0
  • Downloads5
  • File Size0
  • Views174
Updated 10 month(s) ago
MICROSOFT CORPORATION (INDIA) PVT. LTD.
View Details
share
BiomedBERT - Domain-Specific Biomedical Language Model
A biomedical NLP model pre-trained from scratch on abstracts and full-text articles from PubMed and PubMed Central, achieving state-of-the-art performance on biomedical language understanding tasks.
Transformers
exbert
Fill-Mask
inference endpoints
Bert
English
JAX
PyTorch
  • See Upvoters0
  • Downloads91
  • File Size0
  • Views1,471
Updated 1 year(s) ago
MICROSOFT CORPORATION (INDIA) PVT. LTD.
View Details
share

© 2026 - Copyright AIKosh. All rights reserved.