finbarrtimbers Goto Github PK

.files

My dotfiles config; recently updated to be more modular.

anon

tweet about anonymous Wikipedia edits from particular IP address ranges

artfintel-experiments

categorised-review-extraction

Code I wrote for a problem to discuss how I would extract sentences from reviews.

codeexamples

Each folder contains the code for the technical posts I make on my [blog](finbarr.ca). Clone the repo and `cd` into a folder and the code should work exactly as described in the blog post.

cube

Cube: A system for time series visualization.

docker-nginx-pagespeed

NGINX + Google PageSpeed (for Debian), minimal Docker image

docker-talk

Source for the talk I gave at the Edmonton Data Science Meetup on October 5th, 2016.

feature-extraction-text-autoencoder

finbarrtimbers.github.io

Newer, simpler version of my site

gpt-2

Code for the paper "Language Models are Unsupervised Multitask Learners"

hire-us

There's a bunch of us looking for jobs... Hire us!

ijepa

Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive architecture."

learning-deep-learning

Teaching myself Deep Learning using PyTorch.

maxtext

A simple, performant and scalable Jax LLM!

misc-experiments

Various experiments that I haven't found a better place for.

modular_rl

Implementation of TRPO and related algorithms

old-site

Personal website. http://finbarr.ca/disclaimer.html

project-euler

Solving all of Project Euler, in C++.

pytorch-distillation

Distillation library for PyTorch.

samples-rmarkdown-metropolis

RMarkdown with Metropolis/Mtheme for Beamer

scikit-learn

scikit-learn: machine learning in Python

stormpath-flask

Build simple, secure web applications with Stormpath and Flask!

svd-coding-task

Uses SVD to calculate PCA and finds the top N keywords using the scores.

tensorflow

Computation using data flow graphs for scalable machine learning

user-2016

The slides for my talk at useR! 2016 (http://www.user2016.org) about automating our work at Darkhorse Analytics (http://www.dha.io).