williamberrios

BrainScore-Transformers

Code from the paper "Joint rotational invariance and adversarial training of a dual-stream Transformer yields state of the art Brain-Score for Area V4" in BSW at Cosyne 2022

Upside-Down-Detector

robustness

A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.

Applied-Deep-Learning

Applied Deep Learning Course

CKA-Centered-Kernel-Alignment

Reproduce CKA: Similarity of Neural Network Representations Revisited

CLIP

Contrastive Language-Image Pretraining

DALLE2-pytorch

Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

fast_adversarial

[ICLR 2020] A repository for extremely fast adversarial training using FGSM

guided-diffusion

leetcode-patterns

A curated list of leetcode questions grouped by their common patterns

notebooks

Jupyter notebooks for the Natural Language Processing with Transformers book

pytorch-image-models

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

TallerUPCH

the-incredible-pytorch

The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.

visual_prompting

Exploring Visual Prompts for Adapting Large-Scale Models

williamberrios.github.io

Personal website: https://williamberrios.github.io/

BLIP

PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

classify_by_description_release

cv

LaTeX Curriculum Vitae template (filled with my personal info, extendable to anyone)

dsp

𝗗𝗦𝗣: Demonstrate-Search-Predict. A framework for composing retrieval and language models for knowledge-intensive NLP.

gpt_llm

Multi-GPU setup for inference with GPT NeoX 20B and OPT-30B models in huggingface

gpu-tester

gpu tester detects broken and slow gpus in a cluster

gritlm

Generative Representational Instruction Tuning

kaggle-feedback-effectiveness-1st-place-solution

Winning solution for the Kaggle Feedback Prize Challenge.

Kaggle-OTTO-Comp

multiearth-challenge

Repository for the MultiEarth 2023 public challenge.

mvit

Code Release for MViTv2 on Image Recognition.

pix2seq

Pix2Seq - A general framework for turning RGB pixels into semantically meaningful sequences

prompt-eng

notes for prompt engineering

self-rag

This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.