Instructions to use Qwen/Qwen3-Omni-30B-A3B-Captioner with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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") - Notebooks
- Google Colab
- Kaggle
Download generation_config.json from Qwen/Qwen3-Omni-30B-A3B-Captioner: direct link, hf CLI and curl.
- Browser
- Download file 133 Bytes
-
https://huggingface.co/Qwen/Qwen3-Omni-30B-A3B-Captioner/resolve/b1b86d04701ae68e2941702d3a349af222bd91df/generation_config.json
- Command line
-
hf download hf://Qwen/Qwen3-Omni-30B-A3B-Captioner@b1b86d04701ae68e2941702d3a349af222bd91df/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/Qwen/Qwen3-Omni-30B-A3B-Captioner/resolve/b1b86d04701ae68e2941702d3a349af222bd91df/generation_config.json
133 Bytes
| { | |
| "do_sample": true, | |
| "max_new_tokens": 32768, | |
| "repetition_penalty": 1.0, | |
| "temperature": 0.6, | |
| "top_k": 20, | |
| "top_p": 0.95 | |
| } |