DeepSeek-V4.1-Flash surprised ....
英文标题：DeepSeek-V4.1-Flash surprised ....
Hoping to see smartest medium size models soon & later with all available optimizations/architectures/etc.,. Thanks Deepseek! Ex 1: 30-50B MOE + 10-15B Engram + DeepSeek-V4.1-Flash type KVCache Ex 2: 15-30B Dense + 10-15B Engram + DeepSeek-V4.1-Flash type KVCache EDIT: Updated Engram to 10-15B
打开原文相关 2 · 机会 0
中文
Hoping to see smartest medium size models soon & later with all available optimizations/architectures/etc.,. Thanks Deepseek! Ex 1: 30-50B MOE + 10-15B Engram + DeepSeek-V4.1-Flash type KVCache Ex 2: 15-30B Dense + 10-15B Engram + DeepSeek-V4.1-Flash type KVCache EDIT: Updated Engram to 10-15B
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
Hoping to see smartest medium size models soon & later with all available optimizations/architectures/etc.,. Thanks Deepseek! Ex 1: 30-50B MOE + 10-15B Engram + DeepSeek-V4.1-Flash type KVCache Ex 2: 15-30B Dense + 10-15B Engram + DeepSeek-V4.1-Flash type KVCache EDIT: Updated Engram to 10-15B