[ICML2024 (Oral)] Official PyTorch implementation of DoRA: Weight-Decomposed Low-Rank Adaptation

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

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Scripts for fine-tuning Llama2 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization & question answering. S…

Official code for LLaGA: Large Language and Graph Assistant

Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

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

Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

This repository contains the source code for the LBR article "Towards Recommender Systems with Community Detection and Quantum Computing" soon to be published at RecSys 2022.

A framework for few-shot evaluation of autoregressive language models.

A fast MoE impl for PyTorch

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Models and examples built with TensorFlow

[NeurIPS 2020]auto_LiRPA: An Automatic Linear Relaxation based Perturbation Analysis Library for Neural Networks

Code for visualizing the loss landscape of neural nets

[CVPR 2021] "The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models" Tianlong Chen, Jonathan Frankle, Shiyu Chang, Sijia Liu, Yang Zhang, Michael C…

VOLO: Vision Outlooker for Visual Recognition

CV backbones including GhostNet, TinyNet and TNT.

Compositional Explanations of Neurons https://arxiv.org/abs/2006.14032

Official DeiT repository

A repository in preparation for open-sourcing lottery ticket hypothesis code.