Automatic evals for LLMs

Exploring the Limitations of Large Language Models on Multi-Hop Queries

Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'

The official Meta Llama 3 GitHub site

[ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning

This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking".

Evaluating the Ripple Effects of Knowledge Editing in Language Models

A tiling window manager for macOS based on binary space partitioning

Oryx is a library for probabilistic programming and deep learning built on top of Jax.

Inference Llama 2 in one file of pure C

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

Mechanistic Interpretability Visualizations using React

A library for mechanistic interpretability of GPT-style language models

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform

ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.

This project is an attempt to create a common metric to test LLM's for progress in eliminating hallucinations which is the most serious current problem in widespread adoption of LLM's for many real…

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

PaL: Program-Aided Language Models (ICML 2023)

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…

A Multilingual Dataset for Parsing Realistic Task-Oriented Dialogs

The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

The Schema-Guided Dialogue Dataset

Code and documentation to train Stanford's Alpaca models, and generate the data.

[AAAI 2024] Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following

A playbook for systematically maximizing the performance of deep learning models.