Task
Other
L
microsoft/layoutlmv3-base
Other·microsoft· 830.1K· 501
transformers
cc-by-nc-sa-4.0
125.3M params
arxiv:2204.08387license:cc-by-nc-sa-4.0region:us
LayoutLMv3 is a pre-trained multimodal Transformer for Document AI with unified text and image masking. The simple unified architecture and training objectives make LayoutLMv3 a general-purpose pre-trained model. For example, LayoutLMv3 can be fine-tuned for both text-centric tasks, including form understanding, receipt understanding, and document visual question answering, and image-centric tasks
# pull & run locally
pip install mlforge-sdk && mlforge pull microsoft/layoutlmv3-base
pip install mlforge-sdk && mlforge pull microsoft/layoutlmv3-base
Model details
Provider
microsoft
Framework
transformers
Parameters
125.3M
Size
1.9 GB
License
cc-by-nc-sa-4.0
Downloads
830.1K
Likes
501
Paper
arXiv:2204.08387
Updated
2024-04-10
About microsoft/layoutlmv3-base
LayoutLMv3 is a pre-trained multimodal Transformer for Document AI with unified text and image masking. The simple unified architecture and training objectives make LayoutLMv3 a general-purpose pre-trained model. For example, LayoutLMv3 can be fine-tuned for both text-centric tasks, including form understanding, receipt understanding, and document visual question answering, and image-centric tasks such as document image classification and document layout analysis.