核心信息
DeepSeek 新发布的 V4.1 Flash 模型据称已重回开源模型排行榜榜首，推理成本极低且能力很强。作者还制作了模型前向传播的讲解视频，并公开了权重与更多资料。
要点
- DeepSeek V4.1 Flash 已重回开源模型排行榜首位。
- 模型成本极低，并通过多种智能优化方式保持高能力。
- 视频展示了推理阶段模型内部的工作过程。
- 模型权重与相关资源可通过链接获取。
DeepSeek V4.1 Flash 登顶开源模型排行榜，兼顾低成本与高效率
原始推文
RT @Thom_Wolf: The new DeepSeek V4.1 Flash model is mindblowing - back on top of the open-source model leaderboard and extremely cheap. It has a lot of very smart ways to be efficient and highly capable so I made a video of the forward pass to give you a view of what going on inside the model during inference. Read more at https://t.co/A6rP4KKfiI And find the weights at https://t.co/Za7wVYUTaa