Post #1657 15 Oct 10, 2026, 16:23 UTC Unsloth сделали пакет для обучения своих decision моделей X (formerly Twitter) Unsloth AI (@UnslothAI) on X You can now train your own Decision model like Jev locally! We increased Qwen3.5 0.8B’s aggregate accuracy from 20.7% to 74.3% across 3 decision benchmarks - on just 4GB VRAM. Turn any LLM like …