Lev1 is a System One decision model, in the line of Typesafe AI’s Jev: fast, intuitive calls on structured input. You send a state and typed questions, and Lev1 returns a probability for every option in one forward pass. It never generates text. — Fast. 28.8 ms median, 169.9 ms p95 per request on one RTX PRO 6000 Blackwell Server Edition. — Scored. 42.28 on Decision Index 0.2.1, from a complete run with the official harness. — Best in class on tools. 68.8 on Tools & Automation, above every model under 10B parameters on the board (as of 2026-09-28). — Small and open. A 3.7B model: a LoRA on IFM/K2-Horizon-3.7B, shipped as merged weights and as the adapter, under Apache-2.0. — Clean data. Training sources carry commercial-use licences and passed decontamination against the benchmark suite. The synthetic part is public as theaviv/lev1-decisions. I trained a LoRA (rank 32, alpha 64) on questions sampled from a 163,611-question mixture. Each short question also appears in a second option order, and a consistency loss pulls the two answers together. For 15,591 questions the target blends the gold label with Gemma-4-31B-it’s probabilities, on sources where Gemma matched gold at least 60%…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: theaviv
Теги: k2_horizon, decision-model, classification, lora, k2-horizon, decision-index, conversational, custom_code
Лайков: 3 | Загрузок: 338
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
