DreamFast/gemma-3-12b-it-heretic

DreamFast/gemma-3-12b-it-heretic is a 12 billion parameter instruction-tuned Gemma 3 model, abliterated using Heretic to significantly reduce refusals while maintaining model quality. With a 32768 token context length, this model is primarily optimized as an uncensored text encoder for video generation models like LTX-2, offering more faithful prompt encoding by removing soft censorship. It achieves a low KL divergence of 0.0826, indicating minimal damage to the base model.

Warm
Public
Vision
12B
FP8
32768
License: gemma
Hugging Face