Fully automatic censorship removal for language models
-
Updated
Jun 5, 2026 - Python
相关标签
Here are 22 public repositories matching this topic...
Make abliterated models with transformers, easy and fast
-
Updated
Dec 9, 2025 - Python
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
Jun 4, 2026 - Python
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
Jun 6, 2026 - Python
Enhanced fork of Heretic (an automated LLM de-censoring tool) optimized for macOS (Apple Silicon) with checkpoint system and LM Studio integration
-
Updated
Feb 16, 2026 - Python
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
modify a language model's behavior by abliterating its weights.
-
Updated
Mar 20, 2025 - Python
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
🚀 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
Jun 6, 2026 - Python
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
May 2, 2026 - Python
Uncensoring LLMs via Albiteration and rehabilitating via RLVR/GRPO with small post training corpus
-
Updated
Aug 16, 2025
A reproducible audit of LLM institutional-skepticism framing — 36+ models, three force-escalation rungs (prompt → pipeline → weights), five judging methods cross-validated. The bias is in the systems, not the panel scoring them.
alignment reproducibility llm open-source-research rlhf ai-bias abliteration judgement-tool institutional-skepticism
-
Updated
May 31, 2026 - Python
Lobopy is a lightweight PyTorch/HuggingFace library for analysing, steering/abliteration of causal language models.
-
Updated
Feb 25, 2026 - Python
Local-first AI workstation. Run open-weight models, fine-tune, orchestrate multi-agent teams. No cloud required.
desktop-app privacy mcp multi-agent ai-agents fine-tuning tauri huggingface local-first llm llama-cpp local-llm agentic unsloth model-context-protocol abliteration
-
Updated
Jun 6, 2026
Can I run this LLM? Open-source deployment intelligence for local AI — VRAM estimation, quantization selection, hardware compatibility, speed prediction. Built with FastAPI + Next.js.
python open-source benchmark machine-learning typescript deployment nextjs quantization heretic model-comparison fine-tuning fastapi model-comparison-and-selection llm quantizations llama-cpp local-llm abliteration hardware-compatibility hardware-compatibility-detection
-
Updated
May 12, 2026 - TypeScript
Local Offline Abliterated CLI of a distilled gguf
-
Updated
Mar 4, 2026 - Python
Pharmakon-Eval: dual-use LLM evaluation via Pharmakon Separability Index (PSI) and Dose-Response Curve (DRC)
-
Updated
May 30, 2026 - Python
Toolkit to abliterate any instruct-tuned LLM using Arditi 2024 + NousResearch method
-
Updated
Apr 11, 2026 - Jupyter Notebook
⚡ TIMTEH Model Forge — Uncensored, abliterated & reasoning-distilled GGUFs. Forged on 8×H200 SXM5 | 1.1TB VRAM
-
Updated
Mar 27, 2026 - Shell
Local agent-driven mechanistic interpretability research platform for Apple Silicon
sparse-autoencoders ai-safety acdc interpretability apple-silicon mechanistic-interpretability activation-patching abliteration mech-interp transformer-lens
-
Updated
May 28, 2026 - Python