Downloads · 30 days
216
16% of all-time downloads
signsur4739379373/Qwen3.6-27B-Heretic-LoRA
Qwen3.6-27B-Heretic-LoRA is a image-text-to-text model from signsur4739379373. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This is a standalone, lightweight LoRA adapter for Qwen3.6-27B that applies Heretic-style abliteration (uncensoring).
Downloads · 30 days
216
16% of all-time downloads
All-time downloads
1.3K
Public
Repo size
8.9 GB
Likes
0
Public
Click a slice to open those files.
.gguf8.9 GB · 100%
From the Hugging Face model README
This is a standalone, lightweight LoRA adapter for Qwen3.6-27B that applies Heretic-style abliteration (uncensoring).
Please be mindful: The abliteration capabilities of the LoRA is sub-par to the actual Heretic checkpoint. If you're looking for proper abliteration, please use full weights, This LoRA exists to serve a technical need.
Instead of downloading an entirely new checkpoint, you can load this adapter directly on top of the stock Qwen3.6-27B base model (or any of its quantized variants) in llama.cpp to remove most refusal vectors.
o_proj, down_proj, gate_proj, up_projqwen3.6-27b-heretic-lora-rank32.gguf)Load your preferred quant of the base model, and attach the adapter using the --lora flag:
llama-server -m qwen3.6-27b-Q4_K_M.gguf --lora qwen3.6-27b-heretic-lora-rank32.gguf