Instructions to use pszemraj/nougat-base-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pszemraj/nougat-base-onnx with Transformers:

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

pipe = pipeline("image-text-to-text", model="pszemraj/nougat-base-onnx")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("pszemraj/nougat-base-onnx")
model = AutoModelForMultimodalLM.from_pretrained("pszemraj/nougat-base-onnx", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pszemraj/nougat-base-onnx with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/pszemraj/nougat-base-onnx

SGLang

How to use pszemraj/nougat-base-onnx 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 "pszemraj/nougat-base-onnx" \
    --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": "pszemraj/nougat-base-onnx",
		"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 "pszemraj/nougat-base-onnx" \
        --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": "pszemraj/nougat-base-onnx",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pszemraj/nougat-base-onnx with Docker Model Runner:
```
docker model run hf.co/pszemraj/nougat-base-onnx
```

nougat-base onnx

https://huggingface.co/facebook/nougat-base but exported to onnx. This is not quantized.

from transformers import NougatProcessor
from optimum.onnxruntime import ORTModelForVision2Seq

model_name = 'pszemraj/nougat-base-onnx'
processor = NougatProcessor.from_pretrained(model_name)
model = ORTModelForVision2Seq.from_pretrained(
    model_name,
    provider="CPUExecutionProvider", # 'CUDAExecutionProvider' for gpu 
    use_merged=False,
    use_io_binding=True
)

on colab CPU-only (at time of writing) you may get CuPy errors, to solve this uninstall it:

pip uninstall cupy-cuda11x -y

how do da inference?

See here

Downloads last month: 10

Collection including pszemraj/nougat-base-onnx

Nougat ONNX

Collection

Faster Nougat in ONNX format (optimum onnxruntime) • 5 items • Updated Mar 2 • 1