70B (dense)
Llama 3.3 License
Narrative-focused 70B roleplay model trained on Llama 3.3 70B Instruct; built with same techniques as Muse-12B emphasizing relationships and character development; trained on multiple datasets combining text adventures (Wayfarer-style), long emotional narratives, detailed worldbuilding, and general roleplay; all data rewritten to eliminate common AI clichés; small single-turn instruct dataset included; designed for character consistency across extended contexts and nuanced character work; suitable for cloak-and-dagger intrigue, personal drama, or epic quests; DPO explored but abandoned due to poor interaction with Llama 3.3's existing DPO training; trained exclusively on second-person present tense data; uses Llama 3 prompt format; collaboration with Gryphe Padar.