Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Code, Dataset, and Pretrained Models for Audio and Speech Large Language Model "Listen, Think, and Understand".

Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives

The official implementation of our ICLR2024 paper "AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models".

This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.

Code for MIT 6.8610 project

Representation Engineering: A Top-Down Approach to AI Transparency

Data and Code for Program of Thoughts (TMLR 2023)

Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023

Code and data for "Lost in the Middle: How Language Models Use Long Contexts"