Gryphe/Pantheon-Reasoning-27B · Hugging Face
A new open-source model, Gryphe/Pantheon-Reasoning-27B, has been released, aiming to enhance reasoning capabilities within roleplaying scenarios. This model is built upon Qwen 3.6 27B and incorporates a diverse dataset including Pantheon roleplay data, Claude Opus reasoning traces, and text adventure content. The training process emphasizes active thinking and reasoning traces across all assistant turns to improve narrative quality and character depth. AI
IMPACT Enhances roleplaying AI by integrating reasoning traces, potentially improving narrative depth and character interaction.