24B (dense)
Apache 2.0
Premium adventure roleplay model for immersive stories with real consequences; trained on Mistral Small 3.1 Instruct using two-stage approach (SFT on multi-turn Wayfarer-style text adventures and general roleplay + DPO for narrative coherence); applies same DPO techniques as Muse to reduce clichés and repetitive patterns; focuses on enhancing instruction following, mid-sequence continuation, and long-sequence narrative coherence without user intervention; preserves Wayfarer's unforgiving essence with consistent character behaviors and smooth storytelling flows; trained exclusively on second-person present tense data; uses ChatML format; requires subscription on AI Dungeon; collaboration with Gryphe Padar.