heretic
Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
- 43k
- Python
- AGPL-3.0
- 3 d ago
Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
Xolotl: run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 110 GB RAM): ~33 tok/s agent, ~41 fast, 512K context. Plus Inkling-2-Mini (Thinking Machines, own engine + MTP drafter), GLM-5.3-Flash, Qwen3.8, LFM3-Omni. MoE experts tiered across VRAM, RAM and NVMe (Xolotl Direct). OpenAI + Anthropic API.
One-click model liberation + chat playground
Runs in the browser on Hugging Face
Text generation model, used with gguf.
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.
Refusal removal as a loadable KV-cache graft — zero weight modification, no refusal-direction projection, fully reversible.
Automated alignment adjustment for LLMs — direct steering, LoRA, and MoE expert-granular abliteration, optimized via multi-objective Optuna TPE.
Ollama-compatible LLM server. 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.
Gemma 4 31B Abliterated — quality-preserving guardrail removal for Google's most capable open model. Apache 2.0. Runs on Apple Silicon via MLX.
What a fine-tune changed, measured from its weights
Runs in the browser on Hugging Face
MiniMax-H3 custom nodes: steering / cache / prompt director
One-click model liberation + chat playground
Runs in the browser on Hugging Face
One-click model liberation + chat playground
Runs in the browser on Hugging Face
Run GLM-5.3-Flash, DeepSeek-V4.1-Flash and MiniMax-M3.1-Flash locally on your own NVIDIA GPU with fast, private chat and OpenAI/Anthropic-compatible API.
One-click model liberation + chat playground
Runs in the browser on Hugging Face
Local agent-driven mechanistic interpretability research platform for Apple Silicon
One-click model liberation + chat playground
Runs in the browser on Hugging Face