hantian / token-classification updated 1 year ago

layoutreader

A reading order prediction model. Turn bboxes extracted from PDF or detected by OCR into readable order.

Params
360 M
Context
514
Downloads 30d
234 K
Likes
45
Commercial use: not allowed · cc-by-nc-sa-4.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days
424 K234 K
Jul 28Jul 31Aug 3Aug 6

Can you run it?

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

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors bf16 0.7 GB 1.3 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
LayoutLMv3ForTokenClassification
Parameters
360 M
Tensor type
BF16
Context length
514
Vocabulary
50,265
Layers / heads
24 / 16
Licence
cc-by-nc-sa-4.0
First seen on the Hub
2024-02-28
Training datasets
undisclosed
Added to our catalog
2026-07-28