Instructions to use Qwen/Qwen3-Omni-30B-A3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Qwen/Qwen3-Omni-30B-A3B-Instruct with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Qwen/Qwen3-Omni-30B-A3B-Instruct") model = AutoModelForMultimodalLM.from_pretrained("Qwen/Qwen3-Omni-30B-A3B-Instruct") - Notebooks
- Google Colab
- Kaggle
π Qwen3-Omni Fine-tuning support. (transformers & Megatron)
#8
by study-hjt - opened
Best practices & PR: https://github.com/modelscope/ms-swift/pull/5900
training shell: https://github.com/modelscope/ms-swift/blob/main/examples/megatron/multimodal/omni/moe.sh
raise ValueError(
[rank0]: ValueError: Unrecognized configuration class <class 'transformers.models.qwen3_omni_moe.configuration_qwen3_omni_moe.Qwen3OmniMoeConfig'> for this kind of AutoModel: AutoModelForCausalLM.
upgraded transformers but still facing this issue
Could you please help on which transformers version should work?
transformers version please?