关闭导航

包含标签" Transformer"的内容

微软开源BitNet创新高效模型:1.58位低精度 2B参数0.4GB内存已上线Hugging Face
AI妹 3 个月前 14 0

Recently, Microsoft Research officially released an open-source large language model called BitNet

Google DeepMind MoR架构:动态分配计算资源 高效超越Transformer的大模型新方案
AI妹 3 个月前 14 0

In the field of artificial intelligence, large language models (LLMs) have received widespread att

2025开源大模型架构特点及技术趋势:主流模型深度分析
AI妹 3 个月前 18 0

Recent rapid development of large language models (LLMs) has pushed the boundaries of artificial i