Simple Python library/structure to ablate features in LLMs which are supported by TransformerLens
☆713Jun 11, 2024Updated 2 years ago
Alternatives and similar repositories for abliterator
Users that are interested in abliterator are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Evaling and unaligning Chinese LLM censorship☆97Apr 30, 2025Updated last year
- Implements harmful/harmless refusal removal using pure HF Transformers☆2,211Nov 27, 2025Updated 9 months ago
- Dead Simple LLM Abliteration☆280Mar 2, 2026Updated 6 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆446Jun 13, 2025Updated last year
- Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models☆270Apr 23, 2024Updated 2 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Tools for merging pretrained large language models.☆7,369Sep 12, 2026Updated last week
- This is our own implementation of 'Layer Selective Rank Reduction'☆240May 26, 2024Updated 2 years ago
- Make abliterated models with transformers, easy and fast☆171Dec 9, 2025Updated 9 months ago
- A library for mechanistic interpretability of GPT-style language models☆3,900Updated this week
- Simple Model Similarities Analysis☆21Feb 3, 2024Updated 2 years ago
- ☆146Aug 20, 2025Updated last year
- The official API server for Exllama. OAI compatible, lightweight, and fast.☆1,425Updated this week
- Go ahead and axolotl questions☆12,491Updated this week
- Training and data processing code for Saiga☆56Jan 2, 2026Updated 8 months ago
- 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.
- Low-Rank adapter extraction for fine-tuned transformers models☆181May 2, 2024Updated 2 years ago
- An Open Source Toolkit For LLM Distillation☆1,068May 12, 2026Updated 4 months ago
- Genertaes control vectors for use with llama.cpp in GGUF format.☆49Mar 19, 2025Updated last year
- A library for making RepE control vectors☆760Sep 24, 2025Updated last year
- A fast inference library for running LLMs locally on modern consumer-class GPUs☆4,626Mar 4, 2026Updated 6 months ago
- Make abliterated models with transformers, easy and fast☆193Mar 24, 2026Updated 6 months ago
- A benchmark for emotional intelligence in large language models☆461Jul 26, 2024Updated 2 years ago
- ☆21Oct 6, 2023Updated 2 years ago
- A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.☆2,946Sep 30, 2023Updated 2 years 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.
- Customizable implementation of the self-instruct paper.☆1,051Mar 7, 2024Updated 2 years ago
- Large-scale LLM inference engine☆1,865Sep 11, 2026Updated last week
- Decensoring Language Models Through Activation Tuning☆16Feb 21, 2025Updated last year
- Fully automatic censorship removal for language models☆32,237Updated this week
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆3,398Updated this week
- An unsupervised model merging algorithm for Transformers-based language models.☆107Apr 29, 2024Updated 2 years ago
- A bagel, with everything.☆326Apr 11, 2024Updated 2 years ago
- Training LLMs with QLoRA + FSDP☆1,553Nov 9, 2024Updated last year
- entropix style sampling + GUI☆27Oct 30, 2024Updated last year
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Glyphs, acting as collaboratively defined symbols linking related concepts, add a layer of multidimensional semantic richness to user-AI …☆57Feb 10, 2025Updated last year
- Universal and Transferable Attacks on Aligned Language Models☆4,800Aug 2, 2024Updated 2 years ago
- ☆17Sep 1, 2026Updated 3 weeks ago
- LLM Frontend in a single html file☆752Dec 27, 2025Updated 8 months ago
- Automatically evaluate your LLMs in Google Colab☆698May 7, 2024Updated 2 years ago
- Extract a single expert from a Mixture Of Experts model using slerp interpolation.☆19May 26, 2024Updated 2 years ago
- Distill thinking dataset more compactly and accurately!☆38Jun 6, 2025Updated last year