Omar U. Florez's repositories
scratch_mlp
Explaining the Math of how neural networks learn
learning_emotions_with_emojis
Predict human emotions in tweets by mapping emojis into the Valence-Arousal space (Russell, 2005). LSTM models the sequence learning of words within the tweets.
memory-augmented-neural-network
Given an annotated utterance (x, y), we encode x with an encoder (LSTM, Transformer) and cache similar latent representations generated during training into an external memory. Storage and retrieval operations are differentiable using attention over memory entries and extend encoder's capacity.
practicals-2019
Practical notebooks for Khipu 2019, held in Universidad de la República in Montevideo.
VQA-ModuleNetworks
Question Answering capabilities of Module Networks. Language guides the generation of neural architectures that maximizes the likelihood of answering a question correctly when correlated with visual embeddings.
llm_online
Augment LLM reasoning with results from a search engine.
auto-cot
Official implementation for "Automatic Chain of Thought Prompting in Large Language Models" (stay tuned & more will be updated)
chain-of-thought-hub
Benchmarking LLM reasoning performance w. chain-of-thought prompting
DLFS_code
Code for the book Deep Learning From Scratch, from O'Reilly September 2019
encoder4editing
Official implementation of "Desinging an Encoder for StyleGAN Image Manipulation" https://arxiv.org/abs/2102.02766
evals
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
first-order-model
This repository contains the source code for the paper First Order Motion Model for Image Animation
KernelGAT
The source codes for Fine-grained Fact Verification with Kernel Graph Attention Network.
langchain-tutorials
Overview and tutorial of the LangChain Library
latent-diffusion
High-Resolution Image Synthesis with Latent Diffusion Models
meme_challenge
Repository containing code from team Kingsterdam for the Hateful Memes Challenge
mona_lisa_eyes
A machine learning project. Turn on your webcam. Mona Lisa's eyes will follow you around.
nn-zero-to-hero
Neural Networks: Zero to Hero
ocr-with-tesseract
A comprehensive tutorial for OCR in python using Tesseract-OCR and OpenCV
pytorch-seq2seq
Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.
react-flow-web-audio
A simple Web Audio playground built with React Flow. Follow the tutorial to learn how to build it yourself.
stable-diffusion
A latent text-to-image diffusion model
text-to-text-transfer-transformer
Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"