Alif Munim's repositories
r-tensorflow
Deep learning projects using TensorFlow, Keras in R.
rye-connect
A social network for Ryerson University computer science students.
alif-munim.github.io
My journey as a computer scientist.
deep-learning
Exploring the applications of deep learning in image recognition, natural language understanding, and more
echo-vqgan
ViT-VQGAN for echocardiogram quality enhancement.
language-models
Exploring fine-tuning methods for LLMs and other models.
llm-reversal
Curing the reversal curse in language models.
AR-Examples
Augmented Reality examples for the web.
deepmind-research
This repository contains implementations and illustrative code to accompany DeepMind publications
ETAB
A Benchmark Suite for Visual Representation Learning in Echocardiography
graphql-start
Getting familiar with GraphQL.
imagen-pytorch
Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch
java-server-tools
Java EE server that takes basic user input and enters it into a MySQL database.
jekyll-init
Learning to use the jekyll framework for static site generation.
learning-docker
Going through the Docker tutorial to get a better understanding of containerization.
mech-interp
A repository for learning about mechanistic interpretability in language models.
medical-diffusion
Exploration of computer vision for my thesis paper.
nodejs-projects
A review of node.js basics
peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
PETs-Bootcamp
A collection of demos and utilities prepared ahead of the Vector Institute Privacy Enhancing Techniques (PETs) Bootcamp.
pytorchvideo
A deep learning library for video understanding research.
raspberry-pi
A repository for raspberry pi and general hardware scripts.
StockAlertBot
Faced with the scenario of scalpers using bots to hog up all the inventory of popular holiday toys and sell them at ridiculously high markup prices, I decided to put up a fight so we can get our hands on things we need to survive the #Coronavirus quarantine(s).
VideoMamba
VideoMamba: State Space Model for Efficient Video Understanding