abliteration repositories
Trending repositories tagged abliteration, ranked by trending score. Updated daily.
-
1
p-e-w/heretic
Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
GitHub · Python · 42,418 stars · 5,268 forks · +398 stars in 24 hours · Trending score 5.23
-
2
AEON-7/Qwen3.6-27B-AEON-Ultimate-Uncensored-DFlash
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.
GitHub · Python · 500 stars · 57 forks · +27 stars in 24 hours · Trending score 2.44
-
3
Indras-Mirror/Xolotl
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.
GitHub · C++ · 549 stars · 69 forks · +12 stars in 24 hours · Trending score 2.22
-
4
promptadvisers/unlock
Change how a local AI model behaves by asking Claude Code or Codex. Keeps the original, saves an edited copy, shows the before and after. Built on Heretic.
GitHub · Python · 20 stars · 12 forks · +11 stars in 24 hours · Trending score 1.29
-
5
heterodoxin/AbliteratedOutTheBox
llama.cpp fork that abliterates at inference
GitHub · C++ · 220 stars · 17 forks · +1 stars in 24 hours · Trending score 1.02
-
6
adybag14-cyber/Abliteration
The most complete abliteration handbook on the internet: every method, setup, bleeding-edge technique, and script for LLM refusal-direction surgery.
GitHub · Python · 15 stars · 1 forks · 0 stars in 24 hours · Trending score 0.18
-
7
ek15072809/Tema_Q-Abliterated
A tool for uncensoring LLMs — up to 49x faster.
GitHub · Python · 8 stars · 2 forks · 0 stars in 24 hours · Trending score 0.14
-
8
alesha-pro/qwen38-flashnext-strata-4x3090
Qwen3.8-Flash-Next on 2x RTX 3090: 150 tok/s on code, 262K context. Strata 0.2.10 + unsloth UD-IQ4_XS + DFlash2. Full recipe, refusal vectors, session patch, raw benchmark traces.
GitHub · Python · 10 stars · 1 forks · 0 stars in 24 hours · Trending score 0.14
-
9
Aevonix/FlashAlign
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.
GitHub · Python · 126 stars · 16 forks · 0 stars in 24 hours · Trending score 0.08
-
10
R0U5/Lethe
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.
GitHub · Python · 8 stars · 1 forks · 0 stars in 24 hours · Trending score 0.07
-
11
Moloch-AI/uncensored-ai
A developer's guide to uncensored, less-restricted language models: concepts, deployment options, setup, troubleshooting and a model comparison tool.
GitHub · Python · 18 stars · 0 forks · 0 stars in 24 hours · Trending score 0.05
-
12
omgitsbase/llmash
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.
GitHub · C++ · 37 stars · 7 forks · 0 stars in 24 hours · Trending score 0.04
-
13
wuwangzhang1216/abliterix
Automated alignment adjustment for LLMs — direct steering, LoRA, and MoE expert-granular abliteration, optimized via multi-objective Optuna TPE.
GitHub · Python · 276 stars · 46 forks · 0 stars in 24 hours · Trending score 0.00
-
14
sunkencity999/blasphemer
Enhanced fork of Heretic (an automated LLM de-censoring tool) optimized for macOS (Apple Silicon) with checkpoint system and LM Studio integration
GitHub · Python · 34 stars · 7 forks · 0 stars in 24 hours · Trending score 0.00
-
15
0xgetz/abliteration-bulk-creator
Bulk-create verified abliteration.ai accounts, each with its own randomly-named API key — browser-driven, proxy.txt/rotating-proxy ready, 6-language docs.
GitHub · JavaScript · 19 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00
-
16
Orion-zhen/abliteration
Make abliterated models with transformers, easy and fast
GitHub · Python · 193 stars · 107 forks · 0 stars in 24 hours · Trending score 0.00
-
17
AIAnytime/ablate
🔓 Ablate — directional ablation (abliteration) toolkit for open-source LLMs. Automatic censorship/refusal removal via residual-stream direction ablation, with KL-guided search, an LLM-judge harness, and one-call push to the Hub.
GitHub · HTML · 8 stars · 1 forks · −14 stars in 24 hours · Trending score -0.05