➡️
继续阅读
-
Kimi K3 模型结构（6）：输入端与零件，MoonViT-V2、MTP、Per-Head Muon
Kimi K3模型采用从零训练的MoonViT-V2视觉编码器，27层、patch14结构，支持高分辨率图像token化；MTP层预训练后微调为EAGLE...
-
EP224：MCP与RAG及AI代理的对比
An AI agent is kind of an AI system where the agent performs the task autonom...
-
Kimi K3 模型结构（5）：宽度维度，Stable LatentMoE
Kimi K3模型采用Stable LatentMoE作为FFN，基于NVIDIA LatentMoE改进，将输入压缩至半宽latent空间，增加RMSN...
-
Claude Fable 5.1 对比 Fable 5：在实际工作中，我无法区分它们。
Anthropic launched Claude Fable 5.1 this week, calling it “our most advanced ...
-
在代理式RAG中建立信任始于证据
Basic retrieval-augmented generation (RAG) follows a straightforward pattern....
-
Fantasy Footballers’ Andy Holloway is a dedicated zero-inbox kinda guy
Andy Holloway cohosts the Fantasy Footballers podcast with his friends Jason ...
