llama.cpp fork that abliterates at inference
☆219Oct 24, 2026Updated 3 weeks ago
Alternatives and similar repositories for AbliteratedOutTheBox
Users that are interested in AbliteratedOutTheBox are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Abliterates models quickly and efficently, Qwen2.5-7B: 95%→2% refusal at 0.095 KL☆46Nov 2, 2026Updated 2 weeks ago
- An atlas of all 1,290,240 neurons in Gemma-4-31B-it, a census of what they do when pushed, and the instrument to read them with.☆36Updated this week
- Refusal removal as a loadable KV-cache graft — zero weight modification, no refusal-direction projection, fully reversible.☆275Sep 21, 2026Updated last month
- Tensor-Core selector unlock for RTX 4070 Ti Super☆28Oct 20, 2026Updated 3 weeks ago
- Comparative forensic analysis of LLM abliteration techniques☆66Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- GLM-5.3-Flash with 152 of 288 experts per layer (RCO), for coding and agentic use on a home PC: recipe, mask, patches, evaluation harness☆15Oct 31, 2026Updated 2 weeks ago
- The most complete abliteration handbook on the internet: every method, setup, bleeding-edge technique, and script for LLM refusal-directi…☆15Updated this week
- Kotatsu — a desktop-first SillyTavern fork with a built-in Claude subscription bridge. Public release mirror; install with one file, upda…☆21Updated this week
- Multi-GPU (tensor-parallel) CUDA megakernel for Qwen3.8-27B GGUF (Q4_K_M, Q5_K_M, Q6_K, Q8_0) with on-device MTP speculative decoding. Fo…☆16Oct 23, 2026Updated 3 weeks ago
- See inside any GGUF: where two quantizations part ways, token by token, and what each sampler cuts. Live in your browser, powered by llam…☆92Updated this week
- Free online disassembler and binary analysis tool. Reverse engineer PE, ELF and Mach-O files in your browser. Nothing is uploaded.☆19Updated this week
- Self-host AI companion platform — characters with schedules, memory, and a life of their own (BSL 1.1)☆40Aug 28, 2026Updated 2 months ago
- A fast, polished, local Web UI for llama-server, vLLM, and OpenAI-compatible APIs - with charts, diagrams, and MCP tools.☆32Updated this week
- Pure-Rust inference engine for Qwen GGUF models (Qwen3 to Qwen3.8, dense and MoE up to 770B+). CUDA and Vulkan (NVIDIA, AMD), hybrid CPU+…☆267Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Run GLM-5.3 (744B), GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one das…☆2,986Updated this week
- ☆17Jun 26, 2026Updated 4 months ago
- A local-first web search agent☆29Jun 20, 2026Updated 4 months ago
- Indirect Prompt Injection Methodology (IPIM) - A structured process which security professionals can use to find Indirect Prompt Injectio…☆26Jul 28, 2025Updated last year
- Birds-eye view for web application coverage on a domain.☆12Apr 4, 2026Updated 7 months ago
- QEMU machine model and bare-metal emulator for Realtek RTD2841 / RTK284x SoCs (TCL RT41 chassis, tv030)☆17Updated this week
- Modern chat UI for local LLMs with streaming, user management, and web search. Self-hosted.☆13Feb 19, 2026Updated 8 months ago
- A markdown web renderer for AI agents — see the web without screenshots☆68Aug 28, 2026Updated 2 months ago
- A simpler self-hosted alternative to Open WebUI. Bring your own API keys or local models. Native Android and iOS clients.☆156Updated this week
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Lattice is a visual-node studio for shaping context, guiding scenes, and refining prose in SillyTavern.☆21Oct 29, 2026Updated 2 weeks ago
- Network for procedural editing of text with LLMs☆23Updated this week
- Hermes Agent context engine: the main model writes the compaction handoff on its cached prompt prefix☆75Updated this week
- Red-team your RAG pipeline for prompt injection, source-document leakage, and cross-document smuggling, in CI. The gap between RAG eval (…☆30Nov 3, 2026Updated 2 weeks ago
- A super minimal, pretty BASH shell prompt☆14Feb 12, 2024Updated 2 years ago
- ☆54Feb 19, 2026Updated 8 months ago
- ☆46Oct 14, 2026Updated last month
- Standalone mdBook source for the harness engineering workshop☆28Nov 4, 2026Updated 2 weeks ago
- Shodan.io for Hermes Agent. Host intel, search, DNS, CVE lookups, monitoring and on-demand scanning, with credit budgeting and response s…☆32Oct 17, 2026Updated last month
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- GLM-5.3-Flash EXL3 on 2x RTX PRO 6000☆31Updated this week
- A friendly Linux UI for local AI: chat, agent, models, backends, all in one☆22Updated this week
- Character Creation Through Strategic Ablation — Permanently ablating personality steering vectors into LLM weights using contrastive acti…☆46Nov 6, 2026Updated last week
- ☆41Aug 16, 2026Updated 3 months ago
- Evolutionary strategies finetuning library for LLMs☆26Sep 12, 2026Updated 2 months ago
- Bootstra AI Jailbreak for iOS: The World’s First AI-Powered Jailbreaking Tool☆38Jan 13, 2026Updated 10 months ago
- StatelessChatUI is a lightweight, single-file, OpenAI-compatible chat frontend. It’s built to be portable and privacy-friendly: no accoun…☆20Dec 18, 2025Updated 10 months ago
Are these results useful?