腾讯发布WeMM-Video多模态模型权重
AI 总结
腾讯WeMM-Video模型卡称,WeMM-Video-35B-A3B是中英双语混合专家模型,总参数量为350亿、激活参数为30亿。该模型支持文本、图像、音频和视频输入,Hugging Face仓库已提供BF16权重及FP8、AWQ、GGUF和NVFP4量化版本,并采用Apache 2.0许可证。腾讯宣称其在开源全模态视频理解方面领先,但该基准结论属于厂商自述。
深度见解
此次发布提供了可下载的开放权重多模态模型,支持多种模态推理、量化格式和部署方案。
tencent/WeMM-Video-35BA3B Video-Text-to-Text • 36B • Updated about 4 hours ago • 5 • 21
license: apache-2.0 language:
- en
- zh pipeline_tag: video-text-to-text library_name: transformers tags:
- wemm
- multimodal
- video
- audio
- moe
WeMM-Video-35B-A3B
Overview
WeMM-Video-35B-A3B is the mixture-of-experts (35B total, 3B active) checkpoint in the WeMM-Video family. WeMM-Video is a Chinese–English bilingual family for joint audio-visual understanding and reasoning. It accepts text, images, audio, and video and generates text responses.
#Tencent#WeMM-Video-35B-A3B#WeMM-Video#Transformers#vLLM#SGLang