12B (dense)
Apache 2.0
Adventure role-play model trained for challenging and dangerous text-based experiences; counters positivity bias in modern AI by embracing conflict, failure states, and character death; trained on Mistral Nemo Base using two-stage SFT (180K instruct data + 50/50 mix of synthetic 8K context text adventures and roleplay); data generated by simulating AI Dungeon scenario playthroughs with blind narrator-user interactions allowing genuine surprises; pessimistic emotional sentiment where failure is frequent and plot armor doesn't exist; trained exclusively on second-person present tense narrative style; uses ChatML format; designed for AI Dungeon interactive fiction; collaboration with Gryphe Padar.