microsoft / object-detection Open weights updated 2 years ago

table-transformer-structure-recognition-v1.1-all

Name: table-transformer-structure-recognition-v1.1-all
Author: microsoft

Table Transformer (TATR) model trained on PubTables1M and FinTabNet.c. It was introduced in the paper Aligning benchmark datasets for table structure recognition by Smock et al. and first released in this repository.

Params

30 M

Context

—

Downloads 30d

200 K

Likes

Commercial use: allowed mit Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 106 days

▲ 37 K in the last 30 days (15.7%)

330 K200 K

Jul 28Sep 1Oct 6Nov 10

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f32	0.1 GB	0.6 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: TableTransformerForObjectDetection
Parameters: 30 M
Tensor type: F32
Licence: mit
First seen on the Hub: 2023-11-18
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with any object-detection model

Popular comparisons

rtdetr_r101vd_coco_o365 1.4 M table-transformer-structure-recognition 1.3 M PP-DocLayoutV3_safetensors 937 K yolos-small 751 K table-transformer-detection 270 K rtdetr_r50vd 234 K