跳到正文
@Thom_Wolf· @Thom_Wolf · X·· 26 天前AI 评分34
AI 导读

一如 DeepSeek 的一贯风格,新模型 V4.1 Flash 有很多非常聪明的办法来实现高效且高能力 这里有一个详细的前向传播视频,让你了解模型在推理过程中内部发生了什么 https://t.co/4516HXUFAP

正文

As always with DeepSeek, the new model V4.1 Flash have a lot of very smart ways to be efficient and highly capable

Here is a detailed video of the forward pass to give you a view of what going on inside the model during inference https://t.co/4516HXUFAP

来源:@Thom_Wolf · x.com