DogOnKeyboard/Mistral-7B-Heretic-V2
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kLicense:apache-2.0Architecture:Transformer0.0K Open Weights Cold

DogOnKeyboard/Mistral-7B-Heretic-V2 is a 7 billion parameter instruct-tuned causal language model, derived from mistralai/Mistral-7B-Instruct-v0.3. This model has been decensored using the Heretic v1.0.1 process, significantly reducing refusals from 86/100 to 2/100 while maintaining a low KL divergence of 0.08. It is optimized for use cases requiring less restrictive content generation and supports an extended vocabulary, v3 tokenizer, and function calling.

Loading preview...