Tencent releases Hy4 multimodal MoE model
Tencent Hy Team released Hy4 on Hugging Face as a 774B-class image-text-to-text model under the Tencent Hy License. The Mixture-of-Experts model supports text, image, and video understanding, activates 49B language parameters plus 1.23B vision parameters per token, and provides a 1,048,576-token context window. The release also includes deployment recipes for vLLM and SGLang, a 3.3B DFly2 drafter for speculative decoding, quantization resources, and finetuning documentation.
Tencent Hy Team's model card presents Hy4 as a large multimodal MoE model combining vision, long-context processing, tool use and production deployment resources.
tencent/Hy4 Image-Text-to-Text • 774B • Updated about 3 hours ago • 2 • • 30
license: other license_name: tencent-hy-license license_link: https://huggingface.co/tencent/Hy4/blob/main/LICENSE library_name: transformers pipeline_tag: image-text-to-text tags:
- hunyuan
- hy4
- moe
- multimodal
- instruct
中文 | English