Ternary-Bonsai-2-4B-Uncensored-LoRA-GGUF
A 2.4 MB adapter, not a checkpoint. The 0.95 GB ternary pack stays byte-identical and the refusal direction...
A 2.4 MB adapter, not a checkpoint. The 0.95 GB ternary pack stays byte-identical and the refusal direction...
A 1.2 MB adapter, not a checkpoint. The 0.43 GB ternary pack stays byte-identical and the refusal direction...
This is an uncensored research model. Its built-in refusals were removed, so it answers prompts the base model...
> An abliterated variant of Qwen3-4B-Instruct-2507, produced using Heretic. Qwen3-4B-Instruct-2507-Abliterated is a modified variant of Qwen3-4B-Instruct-2507 created using...
Этот репозиторий содержит экспериментальное производное BF16 Qwen/Qwen3.8-27B. Производное использует абляцию в направлении отказа от OBLITERATUS. Он предназначен для...
This is a directionally-ablated («abliterated») version of Qwen/Qwen2.5-1.5B-Instruct, produced with ablate — an activation-engineering toolkit for mechanistic-interpretability and...
static quants of https://huggingface.co/DreamFast/Qwen3-VL-4b-Heretic For a convenient overview and download list, visit our model page for this model....
> Note: All credit to edwixx/diffusiongemma-26B-A4B-it-HERETIC-Uncensored, this repo only includes the processor_config.json 26.6B params · 4B active ·...
Vipera-V4NM is a dynamically uncensored and abliterated version of deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct. This model was created using the Heretic framework,...
static quants of https://huggingface.co/OBLITERATUS/Gemma-4-12B-OBLITERATED For a convenient overview and download list, visit our model page for this model....