Downloads · 30 days
27
8% of all-time downloads
PaddleOCR-VL-1.5-ONNX
lbm364dl/PaddleOCR-VL-1.5-ONNX
PaddleOCR-VL-1.5-ONNX is a image-to-text model from lbm364dl. Use it when you need a caption or text from an image. It is set up for transformers.js. The card lists the license as apache-2.0.
ONNX conversion of PaddlePaddle/PaddleOCR-VL-1.5 for browser deployment with Transformers.js.
All-time downloads
337
Public
Repo size
1 GB
Likes
5
Public
Repo makeup
Click a slice to open those files.
.onnx1 GB · 99%
At a glance
- Task
- Image-to-Text
- Library
- transformers.js
- License
- apache-2.0
- Model type
- paddleocr_vl
- Access
- Public
- Created
- Mar 27, 2026
- Updated
- Mar 27, 2026
- SHA
- 213c67b2
Base models
Model card
From the Hugging Face model README
PaddleOCR-VL-1.5 ONNX (Q4 Quantized)
ONNX conversion of PaddlePaddle/PaddleOCR-VL-1.5 for browser deployment with Transformers.js.
Model Details
- Base model: PaddleOCR-VL-1.5 (0.9B parameters)
- Quantization: INT4 (MatMulNBits, 32-block symmetric)
- Total size: ~991 MB (down from 3.4 GB FP32)
- License: Apache 2.0
- Table recognition accuracy: 92.76% TEDS on PubTabNet
Files
| File | Size | Description |
|---|---|---|
onnx/embed_tokens.onnx | 405 MB | Token embedding lookup |
onnx/vision_encoder.onnx | 369 MB | NaViT vision encoder + MLP projector |
onnx/decoder_model_merged.onnx | 217 MB | Ernie4.5 LLM decoder with KV cache |
Architecture
The model is split into 3 ONNX sub-models following the Florence-2 pattern:
- embed_tokens: Converts token IDs to embeddings
- vision_encoder: Processes image patches into visual tokens (NaViT + projector MLP)
- decoder_model_merged: Autoregressive text decoder with KV cache support
Key features:
- M-RoPE (3D multimodal rotary position embeddings)
- GQA (16 attention heads, 2 KV heads, head_dim=128)
- Merged decoder supporting both prefill and generation via
use_cache_branch
Validation
All components validated against PyTorch reference:
| Component | FP32 Cosine Sim | Q4 Cosine Sim |
|---|---|---|
| embed_tokens | 1.000000 | 1.000000 |
| vision_encoder | 1.000000 | 0.960662 |
| decoder (prefill) | 1.000000 | 0.970726 |
| decoder (with past) | 1.000000 | - |
Usage
Intended for browser-based OCR and table recognition via ONNX Runtime Web (WebGPU/WASM).
Credits
- Original model: PaddlePaddle/PaddleOCR-VL-1.5
- Conversion approach inspired by Xenova's Florence-2 ONNX export
- Task
- Image-to-Text
- Library
- transformers.js
- Type
- paddleocr_vl
- License
- apache-2.0
- Languages
- en, zh
- Created
- Mar 27, 2026
- Updated
- Mar 27, 2026