Caleta: An Evidence-Oriented Trust Layer for Reproducible Local Large Language Model Inference Paper • 2611.10324 • Published 11 days ago • 1 • 1
view post Post 6,477 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 5 replies · 🔥 10 10 🚀 4 4 ➕ 1 1 + Reply
Caleta: An Evidence-Oriented Trust Layer for Reproducible Local Large Language Model Inference Paper • 2611.10324 • Published 11 days ago • 1