[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-sebastian-raschka":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"12ed4ee4-4113-4c1a-a0e9-399d659fd792","Sebastian Raschka","sebastian-raschka",2,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"e7d8242f-edab-4282-8317-9a27fec3cb91","sebastian-raschka-llm-architecture-gallery-zh","Sebastian Raschka 的 LLM 架構圖鑑","Raschka 的 LLM Architecture Gallery 把 GPT-2、Llama 3、OLMo 2、DeepSeek、Qwen 等模型的層數、注意力與 KV cache 數字攤開來比，工程師一眼就能看出部署差異。","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775121663540-srg4.png","zh","2026-04-02T07:27:33.561537+00:00"]