腾讯发布WeMM-Video AWQ量化版
AI 总结
腾讯发布了WeMM-Video-35B-A3B的AWQ W4A16 Safetensors检查点,权重文件为22.69 GiB,前馈权重采用INT4量化。该中英双语音视频模型支持文本、图像、音频和视频输入,文档还提供Transformers加载方法、修补版vLLM 0.18.0服务指南,以及NVIDIA L20和H20上的验证记录。
深度见解
此次发布以Apache-2.0许可开放检查点,并给出了以低精度权重部署大型多模态视频模型的具体方法,但相关能力描述仍来自厂商自述。
tencent/WeMM-Video-35BA3B-AWQ Video-Text-to-Text • 36B • Updated about 4 hours ago • 3 • 1
license: apache-2.0 language:
- en
- zh pipeline_tag: video-text-to-text library_name: transformers base_model: tencent/WeMM-Video-35BA3B base_model_relation: quantized tags:
- wemm
- multimodal
- video
- audio
- quantized
- awq
- moe
WeMM-Video-35B-A3B · AWQ W4A16
Overview
This repository contains the AWQ W4A16 Safetensors variant of WeMM-Video-35B-A3B. 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-35B-A3B AWQ#Transformers#vLLM#NVIDIA L20#NVIDIA H20