据“LongCat”官微消息,美团今日正式发布并开源大模型LongCat-Flash-Chat。LongCat-Flash采用创新性混合专家模型(Mixture-of-Experts, MoE)架构,总参数560B,激活参数18.6B-31.3B(平均 27B),实现计算效率与性能的双重优化。据多项基准测试综合评估,LongCat-Flash-Chat在仅激活少量参数的前提下,在智能体任务中具备突出优势,同时推理速度超过100tps。
特别声明:以上内容(如有图片或视频亦包括在内)为自媒体平台“网易号”用户上传并发布,本平台仅提供信息存储服务。
Notice: The content above (including the pictures and videos if any) is uploaded and posted by a user of NetEase Hao, which is a social media platform and only provides information storage services.