sbp354 Goto Github PK

datasciencecourse

This holds iPython notebooks and lecture slides for the Intro to Data Science Master's course I teach at NYU.

deep-learning-systems

Code for assignments and projects in NYU Courant's deep learning systems course. Most code is focused on training and evaluating deep learning models in various environments

deep_learning_systems

This repository contains assignments and projects I completed while I master's student at NYU that relate to training deep learning models on distributed systems

diva-eval

dotfiles

Easily deploy my zsh and tmux configuration on new machines. Includes local and remote aliases to improve workflow.

emnlp2020-debiasing-unknown

etherscan-labels

Full label data dump of etherscan in JSON/CSV.

ev_charging_stations

finetuning_fsdp_qlora

Training LLMs with QLoRA + FSDP

future-triggered-backdoors

Code to reproduce experiments from the paper Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities in LLMs

glip

Grounded Language-Image Pre-training

llasm

LLaSM: Large Language and Speech Model

llms-finetuning-safety

We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20 via OpenAI’s APIs.

ltu

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

math-tools-nyu

DS-GA 1013 Mathematical Tools for Data Science

mats_sae_training

mdetr

pandagpt

PandaGPT: One Model To Instruction-Follow Them All

predicting-wildfires-1001

Code for a project forecasting wildfire risk in California using GIS data

salmonn

SALMONN: Speech Audio Language Music Open Neural Network

satbench

A benchmark of the speed-accuracy tradeoff in object recognition by humans and dynamic neural networks

sbp354.github.io

text-od-robustness

Evaluating the robustness of text-conditioned OD models such as MDETR

toxic_debias

Code for our Natural Language Understand (NLU) project may 2022: Applying Self Debiasing Techniques to Toxic Language Detection Models

tricd

Testing Robust Image Understanding Through Contextual Phrase Detection

whisper_attack