Instructions to use OralGPT/OralGPT-Omni-7B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OralGPT/OralGPT-Omni-7B-Instruct with Transformers:

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

pipe = pipeline("image-text-to-text", model="OralGPT/OralGPT-Omni-7B-Instruct")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("OralGPT/OralGPT-Omni-7B-Instruct")
model = AutoModelForMultimodalLM.from_pretrained("OralGPT/OralGPT-Omni-7B-Instruct")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OralGPT/OralGPT-Omni-7B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OralGPT/OralGPT-Omni-7B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OralGPT/OralGPT-Omni-7B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OralGPT/OralGPT-Omni-7B-Instruct

SGLang

How to use OralGPT/OralGPT-Omni-7B-Instruct 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 "OralGPT/OralGPT-Omni-7B-Instruct" \
    --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": "OralGPT/OralGPT-Omni-7B-Instruct",
		"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 "OralGPT/OralGPT-Omni-7B-Instruct" \
        --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": "OralGPT/OralGPT-Omni-7B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OralGPT/OralGPT-Omni-7B-Instruct with Docker Model Runner:
```
docker model run hf.co/OralGPT/OralGPT-Omni-7B-Instruct
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

OralGPT-Omni-7B-Instruct

📄 Paper: https://arxiv.org/abs/2511.22055

📦 Model configuration

model_name_or_path: OralGPT/OralGPT-Omni-7B-Instruct
template: qwen2_vl
infer_backend: huggingface  # choices: [huggingface, vllm, sglang]
trust_remote_code: true

🚀 Dtart inference API

API_PORT=8001 llamafactory-cli api LLaMA-Factory/examples/inference/qwen2_5vl.yaml

Citation

@article{hao2025oralgpt,
  title={OralGPT-Omni: A Versatile Dental Multimodal Large Language Model},
  author={Hao, Jing and Liang, Yuci and Lin, Lizhuo and Fan, Yuxuan and Zhou, Wenkai and Guo, Kaixin and Ye, Zanting and Sun, Yanpeng and Zhang, Xinyu and Yang, Yanqi and others},
  journal={arXiv preprint arXiv:2511.22055},
  year={2025}
}

Downloads last month: 4

Safetensors

Model size

8B params

Tensor type

F16

Inference Providers NEW

Image-Text-to-Text

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

Space using OralGPT/OralGPT-Omni-7B-Instruct 1

Paper for OralGPT/OralGPT-Omni-7B-Instruct

OralGPT-Omni: A Versatile Dental Multimodal Large Language Model

Paper • 2511.22055 • Published Nov 27, 2025 • 9