☆35Mar 24, 2026Updated 7 months ago
Alternatives and similar repositories for som-refusal-directions
Users that are interested in som-refusal-directions are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆17Nov 24, 2025Updated 11 months ago
- Foolbox implementation for NeurIPS 2021 Paper: "Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints".☆26Mar 16, 2022Updated 4 years ago
- Repository for the evaluation of the transferabiilty of adversarial examples.☆22Nov 25, 2025Updated 11 months ago
- Code to the paper: The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence☆38Jul 31, 2025Updated last year
- Attack benchmark repository☆25Nov 25, 2025Updated 11 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Official code for "Evaluations of Machine Learning Privacy Defenses are Misleading" (https://arxiv.org/abs/2404.17399)☆13Apr 29, 2024Updated 2 years ago
- Implementation of average- and worst-case robust flatness measures for adversarial training.☆15Nov 5, 2021Updated 4 years ago
- Materials for "Multi-property Steering of Large Language Models with Dynamic Activation Composition"☆14Nov 22, 2024Updated last year
- Code for the paper "Adversarial Neural Pruning with Latent Vulnerability Suppression"☆15Nov 23, 2022Updated 3 years ago
- minimal code to reproduce results from Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representati…☆14Sep 25, 2025Updated last year
- A collection of Italian benchmarks for LLM evaluation☆37Jun 9, 2026Updated 4 months ago
- ☆17Sep 11, 2026Updated last month
- A platform for running controlled experiments on teams of LLM agents: multi-agent simulations, an event-sourced run log, swap and fork in…☆27Updated this week
- ☆22Jan 9, 2026Updated 9 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆35Feb 6, 2026Updated 8 months ago
- ☆21Nov 6, 2025Updated 11 months ago
- Sharpness-Aware Minimization Leads to Low-Rank Features [NeurIPS 2023]☆29Sep 22, 2023Updated 3 years ago
- Dialog2Flow: convert your dialogs to flows. This repository accompanies the paper "Dialog2Flow: Pre-training Soft-Contrastive Sentence Em…☆20Jul 1, 2025Updated last year
- Make abliterated models with transformers, easy and fast☆198Mar 24, 2026Updated 7 months ago
- A Python package for analyzing and transforming neural latent spaces.☆54Mar 4, 2026Updated 7 months ago
- ☆12Mar 31, 2025Updated last year
- Code for Fast as CHITA: Neural Network Pruning with Combinatorial Optimization☆14Aug 2, 2023Updated 3 years ago
- ☆31Sep 21, 2026Updated last month
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ACL-2026] Official codebase for "Towards Identification and Intervention of Safety-Critical Parameters in Large Language Models". We int…☆17Aug 27, 2026Updated 2 months ago
- Github repository for paper: Think Before You Talk: Enhancing Meaningful Dialogue Generation in Full-Duplex Speech Language Models with P…☆14Jun 15, 2026Updated 4 months ago
- RLVR Testing and Training☆21Aug 28, 2025Updated last year
- ☆12Jan 19, 2024Updated 2 years ago
- DummyCore is an API for Minecraft Modmaking☆12Mar 8, 2016Updated 10 years ago
- Invasion from the Unknown, a Battle for Wesnoth add-on campaign.☆12Oct 22, 2026Updated last week
- FastAPI wrapper for LLM, a fork of (oobabooga / text-generation-webui)☆10Jun 1, 2023Updated 3 years ago
- 人机对话轮次检测模型，有效解决声学VAD等待过长的问题☆14Sep 17, 2025Updated last year
- Kandinsky 6.0 Video SR: Models for Video Super-Resolution☆22Oct 20, 2026Updated last week
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Runs the agents of a microblogging simulation (client side).☆11Oct 22, 2026Updated last week
- OpenAI API compatible Deployment for Neuphonic's Neutts☆17Oct 25, 2025Updated last year
- Colorizing Black & White images using GAN☆10Jan 13, 2023Updated 3 years ago
- Simple book management with qr codes☆11Aug 2, 2022Updated 4 years ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆11Nov 29, 2023Updated 2 years ago
- rasters and gexf network files for the not david power of friendship video☆17Jan 5, 2025Updated last year
- Docker container exposing a preconfigured python environment for Social Network Analysis☆15Feb 4, 2023Updated 3 years ago