Instructions to use Qwen/Qwen2.5-Omni-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Qwen/Qwen2.5-Omni-3B with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-Omni-3B") model = AutoModel.from_pretrained("Qwen/Qwen2.5-Omni-3B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add OmniCompass evaluation results
#17
by VCLab-PolyU - opened
Add the OmniCompass benchmark authors' published results for Qwen2.5-Omni-3B on omnicompass_av. Each value is Overall Cross-Specification Consistency Score on a 0-100 scale; higher is better.
Source: https://omnicompass.netlify.app/#leaderboard
Benchmark: https://huggingface.co/datasets/VCLab-PolyU/OmniCompass
The YAML preserves the published one-decimal scores and records frame counts and source attribution. It adds evaluation metadata only and makes no HF verified claim.