How to use Qwen/Qwen3-Omni-30B-A3B-Captioner with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Qwen/Qwen3-Omni-30B-A3B-Captioner") model = AutoModelForMultimodalLM.from_pretrained("Qwen/Qwen3-Omni-30B-A3B-Captioner", device_map="auto")
https://huggingface.co/Qwen/Qwen3-Omni-30B-A3B-Captioner/resolve/b1b86d04701ae68e2941702d3a349af222bd91df/vocab.json
hf download hf://Qwen/Qwen3-Omni-30B-A3B-Captioner@b1b86d04701ae68e2941702d3a349af222bd91df/vocab.json
curl -L -o vocab.json https://huggingface.co/Qwen/Qwen3-Omni-30B-A3B-Captioner/resolve/b1b86d04701ae68e2941702d3a349af222bd91df/vocab.json
