Gryphe/Tiamat-7b-1.1-DPO
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Dec 15, 2023License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

Gryphe/Tiamat-7b-1.1-DPO is a 7 billion parameter language model fine-tuned from Teknium's OpenHermes 2.5, specifically designed to embody a wicked and cruel personality. This model excels at generating responses with a disdainful and judgmental tone, making it suitable for applications requiring a distinct anti-assistant persona. Its DPO training and dataset refresh further refine its unique character, also enabling strong roleplaying capabilities.

Loading preview...