I have Fine tuned https://huggingface.co./facebook/sam-vit-base using Doclaynet-small dataset.

My focus was to detect structure from the documents like paragraph, header, tabel using SOTA model Segment Anything Model (SAM).

Downloads last month
10
Safetensors
Model size
93.7M params
Tensor type
F32
·
Inference API
Inference API (serverless) does not yet support transformers models for this pipeline type.

Dataset used to train Mit1208/sam-fine-tune-doclaynet