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

Libraries

How to use genta-tech/nougat-base-onnx-quantized with Transformers:

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use genta-tech/nougat-base-onnx-quantized with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/genta-tech/nougat-base-onnx-quantized

SGLang

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

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

nougat-base-onnx-quantized / decoder_model.onnx

Rifky

Upload folder using huggingface_hub

a40c35f about 3 years ago

History Blame Contribute Delete

550 MB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: 60176b35bc6cc056805d989708497c701c59ee710beafd6c57fbc0dcfaa85502
Size of remote file:: 550 MB
SHA256:: f772f189f56c034a4564282c1a3a18843f15b890da0d82104c38ba2043dc5f36

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.