This repository contains code for deploying the
Qwen2.5-Omni-0.5B model to Hugging Face Inference Endpoints for use with the Indoor Scenes dataset.
The LLaVA-Onevision implementation with Qwen2.5-Omni provides multimodal capabilities for:
-
Setup your Hugging Face account:
- Ensure you have a Hugging Face account with a valid API token
- Use
huggingface-cli login to authenticate
-
Create and push to a Hugging Face repository:
1huggingface-cli repo create YOUR_USERNAME/my-qwen-omni-endpoint --type model
2git init
3git add .
4git commit -m "Initial commit"
5git remote add origin https://huggingface.co/YOUR_USERNAME/my-qwen-omni-endpoint
6git push -u origin main
-
Deploy to Inference Endpoints:
- Go to your repository on Hugging Face
- Navigate to "Settings" > "Inference Endpoints"
- Create a new endpoint
- Select appropriate hardware (recommend at least 16GB GPU)
- Deploy!
1{
2 "conversation": [
3 {"role": "user", "content": "Tell me about yourself."}
4 ]
5}
1{
2 "conversation": [
3 {
4 "role": "user",
5 "content": "What do you see in this image?",
6 "images": ["https://example.com/image.jpg"]
7 }
8 ]
9}
This endpoint is specifically designed to work with the MIT Indoor Scenes dataset from CVPR 2019. The model can be used to generate captions for indoor scene images to evaluate captioning performance.
The implementation supports test-time scaling through the standard inference interface, allowing for:
