Instructions to use Reza2kn/surya-ocr-2-onnx-fp16-split-canary with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Reza2kn/surya-ocr-2-onnx-fp16-split-canary with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="Reza2kn/surya-ocr-2-onnx-fp16-split-canary")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Reza2kn/surya-ocr-2-onnx-fp16-split-canary", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Reza2kn/surya-ocr-2-onnx-fp16-split-canary with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Reza2kn/surya-ocr-2-onnx-fp16-split-canary"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Reza2kn/surya-ocr-2-onnx-fp16-split-canary",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Reza2kn/surya-ocr-2-onnx-fp16-split-canary

SGLang

How to use Reza2kn/surya-ocr-2-onnx-fp16-split-canary with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Reza2kn/surya-ocr-2-onnx-fp16-split-canary" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Reza2kn/surya-ocr-2-onnx-fp16-split-canary",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Reza2kn/surya-ocr-2-onnx-fp16-split-canary" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Reza2kn/surya-ocr-2-onnx-fp16-split-canary",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Reza2kn/surya-ocr-2-onnx-fp16-split-canary with Docker Model Runner:
```
docker model run hf.co/Reza2kn/surya-ocr-2-onnx-fp16-split-canary
```

Surya OCR 2 ONNX FP16 Split Canary

This repository contains a converted/quantized artifact derived from datalab-to/surya-ocr-2.

What is included

Source model: datalab-to/surya-ocr-2
Runtime/format: ONNX Runtime / WebGPU-oriented experimentation
Quantization: not quantized; FP16 split vision + language last-logits ONNX canary
Vision weights included: yes, included as surya_vision.onnx
Created for: local OCR/document-understanding experiments and parity testing

Validation status

Export canary diff vs full PyTorch forward: max_abs_diff = 0.0 for the traced sample.

Known caveats

This is a fixed-shape split export canary, not a complete browser OCR app. The full-graph ONNX benchmark runner stalled during ORT session/generation; a split decode harness is still required.

Files

surya_vision.onnx, surya_language_last_logits.onnx, processor assets, and export_config.json.

Usage

Use the vision ONNX and language last-logits ONNX together with a custom decode loop matching export_config.json shapes.

Provenance

This artifact was generated non-destructively from the original Hugging Face checkpoint. It is not a new fine-tune.

If you need production parity, compare against the original model on your own document distribution before deployment.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Reza2kn/surya-ocr-2-onnx-fp16-split-canary

Base model

datalab-to/surya-ocr-2

Quantized

(9)

this model