Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
-
Updated
Nov 3, 2026 - Python
#
abliteration
Here are 105 public repositories matching this topic...
Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.io/aeon-7/aeon-vllm-ultimate:latest container, tuned for long-context draft acceptance on DGX Spark. 6 HF variants (BF16/NVFP4/MTP/MTP-XS), docker-compose, and QuickStart.
quantization uncensored blackwell llm vllm qwen speculative-decoding abliteration qwen3 nvfp4 dgx-spark dflash
-
Updated
Oct 6, 2026 - 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
Nov 3, 2026 - Python
Refusal removal as a loadable KV-cache graft — zero weight modification, no refusal-direction projection, fully reversible.
-
Updated
Sep 21, 2026 - Python
Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Results are exportable.
visualization research ai transformers pytorch artificial-intelligence neural-networks interpretability steering huggingface large-language-models llm model-editing mechanistic-interpretability anthropic abliteration jacobian-lens j-wash
-
Updated
Sep 6, 2026 - Python
Make abliterated models with transformers, easy and fast
-
Updated
Nov 1, 2026 - Python
ReAlign models instantly, on demand. Per-request alignment for verified users and channels, or Always On. Use directly or with Hermes, OpenClaw and custom harnesses.
-
Updated
Nov 1, 2026 - Python
Reproducible refusal-subspace editing and TP=2 deployment of DeepSeek V4 Flash 0731 on two DGX Sparks
-
Updated
Aug 14, 2026 - Python
Ollama-compatible LLM server on a tuned llama.cpp fork. Beats vllm by 40% on single stream decode, and by 20% on multi stream decode, and beats ollama by much 2-4x. Made possible with custom CUDA kernels, MTP, speculation and its own 3-bit builds. Uncensors models in one command. Windows and Linux, NVIDIA. Optimized to not eat up ram.
windows cuda quantization mtp gemma inference-engine local-first llm llm-serving llama-cpp local-llm llm-inference ollama qwen gguf speculative-decoding ollama-api abliteration ollama-alternative nvfp4
-
Updated
Nov 3, 2026 - C++
No-code LLM fine-tuning: upload your data → click Train → get a model you can run anywhere. Gradio UI + CLI · SFT/DPO/ORPO/KTO/GRPO/reward models · distillation, vision & embedding models · Unsloth 2-5× · QLoRA · multi-GPU (FSDP/DeepSpeed) · GGUF/FP8 export · vLLM & llama.cpp serving · benchmarks & LLM-judge eval · Heretic Mode
python ai gradio fine-tuning peft dpo trl llm llms local-llm local-ai ollama lm-studio gguf unsloth abliteration
-
Updated
Oct 31, 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
Jul 22, 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
Nov 1, 2026 - Python
The world's top open-weight AI model workshop. Measure, uncensor and audit: refusal removal for transformer language models, with the instruments to measure what the edit cost.
python transformers pytorch model-evaluation ai-safety interpretability uncensored red-teaming large-language-models llm ai-assurance model-editing mechanistic-interpretability llm-evaluation uncensoring abliteration abliterated refusal-direction
-
Updated
Oct 26, 2026 - Python
The most complete abliteration handbook on the internet: every method, setup, bleeding-edge technique, and script for LLM refusal-direction surgery.
-
Updated
Oct 31, 2026 - Python
GLM-5.2, completely uncensored and fully local on 4 cards — the think-off recipe plus full serving + reproduction guide.
-
Updated
Jul 23, 2026 - Python
用 heretic 在 DGX Spark (GB10) 上做 abliteration：Qwen3.8-27B 去拒答版所用程式與設定
-
Updated
Oct 19, 2026 - Python
Automated, capability-preserving abliteration for open-weight LLMs — agent-native (MCP server). Clean-room MIT implementation.
-
Updated
Jun 19, 2026 - Python
Model-agnostic abliteration toolkit for HuggingFace causal LMs: compute and remove refusal directions via weight orthogonalization or runtime hooks, with KL-aware Optuna optimization, quantized-model bundles, and a local web UI.
nlp machine-learning transformers pytorch ai-safety interpretability ai-alignment huggingface llm abliteration refusal-direction
-
Updated
Nov 3, 2026 - Python
modify a language model's behavior by abliterating its weights.
-
Updated
Mar 20, 2025 - Python
Add this topic to your repo
To associate your repository with the abliteration topic, visit your repo's landing page and select "manage topics."