RulinShao

AdversariallyRobustDistillation

Pytorch implementation of Adversarially Robust Distillation (ARD)

ALBEF

Code for ALBEF: a new vision-language pre-training method

Digital-Image-Processing

FastCkpt

Python package for rematerialization-aware gradient checkpointing

LightSeq

Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers

Llava-doremi

Automatic task-balancing for vision-language instruction tuning using group distributionally robust optimization (Group DRO, the technique used in Doremi)

on-the-adversarial-robustness-of-visual-transformer

Code for the paper "On the Adversarial Robustness of Visual Transformers"

RAG-evaluation-harnesses

An evaluation suite for Retrieval-Augmented Generation (RAG).

retrieval-scaling

Official repository for "Scaling Retrieval-Based Langauge Models with a Trillion-Token Datastore".

VL-Instruct

Codes for vision-language instruction tuning. Currently support BLIP2-t5 and BLIP2-vicuna.

RulinShao/LightSeq

Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers

RulinShao/retrieval-scaling

Official repository for "Scaling Retrieval-Based Langauge Models with a Trillion-Token Datastore".

RulinShao/on-the-adversarial-robustness-of-visual-transformer

Code for the paper "On the Adversarial Robustness of Visual Transformers"

RulinShao/FastCkpt

Python package for rematerialization-aware gradient checkpointing

RulinShao/RAG-evaluation-harnesses

An evaluation suite for Retrieval-Augmented Generation (RAG).

RulinShao/VL-Instruct

Codes for vision-language instruction tuning. Currently support BLIP2-t5 and BLIP2-vicuna.

RulinShao/Digital-Image-Processing

RulinShao/Llava-doremi

Automatic task-balancing for vision-language instruction tuning using group distributionally robust optimization (Group DRO, the technique used in Doremi)

RulinShao/AdversariallyRobustDistillation

Pytorch implementation of Adversarially Robust Distillation (ARD)

RulinShao/ALBEF

Code for ALBEF: a new vision-language pre-training method

RulinShao/bff

Large-scale deduplication & decontamination using bloom filters

RulinShao/denoised-smoothing

Provably defending pretrained classifiers including the Azure, Google, AWS, and Clarifai APIs

RulinShao/instruct-eval

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

RulinShao/NeMo

NeMo: a toolkit for conversational AI

RulinShao/Oscar

Oscar and VinVL

RulinShao/RepGAN

Code base from StyleGAN2-ADA

RulinShao/RulinShao.github.io

RulinShao/open_lm

A repository for research on medium sized language models.

RulinShao/UWrc.github.io

The best research computing website in all the land.