Here are 18 public repositories matching this topic...

p-e-w / heretic

Fully automatic censorship removal for language models

transformer llm abliteration

Updated Apr 21, 2026
Python

wuwangzhang1216 / abliterix

Automated alignment adjustment for LLMs — direct steering, LoRA, and MoE expert-granular abliteration, optimized via multi-objective Optuna TPE.

transformers pytorch alignment moe lora gemma peft uncensored mixture-of-experts optuna decensoring llm model-editing abliteration

Updated Apr 21, 2026
Python

Orion-zhen / abliteration

Make abliterated models with transformers, easy and fast

uncensored llm abliterate abliteration abliterator

Updated Dec 9, 2025
Python

Yog-Sotho / LLM-fine-tuner

Powerful no-code LLM fine-tuner: upload data → train → deploy in minutes. Unsloth 2-5× acceleration · QLoRA/DPO/RLHF/PPO/ORPO · Reward Model training · GGUF export · vLLM inference · BLEU/ROUGE/BERTScore · full CLI · Heretic Mode to unlock full model potential

python ai gradio fine-tuning peft dpo llm llms local-llm local-ai ollama lm-studio gguf unsloth abliteration

Updated Apr 16, 2026
Python

sunkencity999 / blasphemer

Enhanced fork of Heretic (an automated LLM de-censoring tool) optimized for macOS (Apple Silicon) with checkpoint system and LM Studio integration

ai uncensored llm abliteration

Updated Feb 16, 2026
Python

199-biotechnologies / gemma-4-abliterated

Gemma 4 31B Abliterated — quality-preserving guardrail removal for Google's most capable open model. Apache 2.0. Runs on Apple Silicon via MLX.

open-source gemma mlx uncensored google-deepmind apple-silicon llm vision-language-model abliteration abliterated gemma-4 guardrail-removal

Updated Apr 3, 2026
Python

PRITHIVSAKTHIUR / Auto-Abliteration

modify a language model's behavior by abliterating its weights.

uncensored streamlit huggingface-transformers llm llms ollama abliteration gemma3

Updated Mar 20, 2025
Python

jonhardwick-spec / aegis-trainer

Layer-by-layer model training and modification for 80B+ MoE models on consumer GPUs. Abliteration, LongRoPE, LoRA merge, weight visualization. Built because nothing else could do it. https://justcalljon.pro

machine-learning vulkan tui pytorch moe lora model-training intel-arc abliteration qwen3 layer-streaming longrope weight-modification

Updated Feb 7, 2026
Python

Bender1011001 / dual-system-architecture

Geometric sidecar for LLMs — uncensored + structured reasoning, zero base-model changes

nlp machine-learning deep-learning transformers pytorch sidecar uncensored geometric-reasoning llm mechanistic-interpretability qwen abliteration

Updated Apr 20, 2026
Python

zach0028 / abliteration-toolkit

Toolkit to abliterate any instruct-tuned LLM using Arditi 2024 + NousResearch method

jailbreak ai-safety huggingface llm mechanistic-interpretability abliteration

Updated Apr 11, 2026
Jupyter Notebook

OzelTam / lobopy

Lobopy is a lightweight PyTorch/HuggingFace library for analysing, steering/abliteration of causal language models.

huggingface steering-ai huggingface-transformers llm llms abliteration model-steering

Updated Feb 25, 2026
Python

studiofarzulla / genre-mimicry

Genre Mimicry in Academic Writing: Abliterated LLMs and Genre-Dependent Safety Behaviors | DP-2503 | Dissensus AI Discussion Paper

language-models ai-safety ethics abliteration dissensus-ai genre-conventions

Updated Feb 14, 2026
TeX

teilomillet / vauban

MLX-native toolkit for understanding and reshaping how language models behave on Apple Silicon

python mlx adversarial-attacks red-teaming apple-silicon mechanistic-interpretability llm-safety abliteration

Updated Apr 9, 2026
Python

marcfawzi / meltdown

Uncensoring LLMs via Albiteration and rehabilitating via RLVR/GRPO with small post training corpus

ai llms abliteration grpo rlvr

Updated Aug 16, 2025

vikrant-project / vikrant-OBLITERATUS

Advanced abliteration framework: 8-stage pipeline, auto fine-tuning, voice support, real-time collaboration, security scanning | Production-grade LLM liberation

security transformers collaboration pytorch fine-tuning llm mechanistic-interpretability abliteration refusal-removal voice-llm

Updated Mar 26, 2026
Python

timteh / timteh-forge

⚡ TIMTEH Model Forge — Uncensored, abliterated & reasoning-distilled GGUFs. Forged on 8×H200 SXM5 | 1.1TB VRAM

open-source machine-learning ai quantization uncensored h200 huggingface llm gguf abliteration

Updated Mar 27, 2026
Shell

robloxexploiterponole / aegis-trainer

🚀 Train and modify 80B+ parameter Mixture of Experts models layer-by-layer on consumer GPUs using Python with AEGIS AI Trainer.

machine-learning vulkan tui pytorch moe lora model-training intel-arc abliteration qwen3 layer-streaming longrope weight-modification

Updated Apr 21, 2026
Python

knol3j / cli-abliterated

Local Offline Abliterated CLI of a distilled gguf

cli local pentesting pentest-tool offline-ai abliteration

Updated Mar 4, 2026
Python