view post Post 2,039 We're introducing KV1 1.2B.Its our first KV1 model using a 2 bit KV cache, based on LFM 2.5 1.2B.KV1 1.2B retains 75.8% of original intelligence.More details: klein-ml/blogModel klein-ml/KV1-1.2B See translation
pinned Running on Zero Agents 6 BananaMind Arena 🍌 Blind Elo battles between very small language models