Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vectors

Training Sparse Autoencoders on Language Models

Large Concept Models: Language modeling in a sentence representation space

Unofficial implementation of "Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection"

Working Memory Attack on LLMs

Stop configuring your AI stack. Start using it. One command brings a complete pre-wired LLM stack with hundreds of services to explore.

Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization

Code for the EMNLP 2024 paper "Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps"

A curated list of safety-related papers, articles, and resources focused on Large Language Models (LLMs). This repository aims to provide researchers, practitioners, and enthusiasts with insights i…

RevLLM -- Reverse Engineering Tools for Large Language Models

🎨 ASCII art library for Python

Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".

visualizing attention for LLM users

Public repo for HF blog posts

Instruct-tune LLaMA on consumer hardware

The project is build on Google colaboratory using Python. The scripts extract the first five feeds from the website and convert them to audio file using GTTS.

Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".

LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces

Science Parse parses scientific papers (in PDF form) and returns them in structured form.

LLaMA 2 implemented from scratch in PyTorch

TaCo: Enhancing Cross-Lingual Transfer for Low-Resource Languages in LLMs through Translation-Assisted Chain-of-Thought Processes

a tool for calcualting character n-gram F score

A fast inference library for running LLMs locally on modern consumer-class GPUs

Inference Llama 2 in one file of pure C