leonericsson Goto Github PK

alphafour

From-scratch implementation of AlphaZero applied to Connect Four :robot:

bb-transformer

Transformer implementation using custom PyTorch modules

benchmark-correlations

Calculate statistical correlations between LLM benchmarks

chess

Chess is a two-player strategy board game played on a checkered board with 64 squares arranged in an 8×8 square grid, this is my implementation of the classic board game

echogen

Auto-regressive character level generator of new things

ensemble4dflownet

Super Resolution 4D Flow MRI using Ensemble Learning

gpu-puzzles

[Completed 07/01/24 ✅]

kattis

Kattis is an online code judging platform similar to LeetCode. This is a collection of my solutions to problems within Dynamic Programming, Arithmetic, Graph Theory, Search and Computation Geometry.

leetcode

LeetCode is an online code judging platform that provides thousands of programming problems for anyone to tackle. This is a collection of my solutions to some of these problems.

leonericsson

leonericsson.github.io

Personal research blog 📚 & website 👨🏼‍💻

llama.cpp

Port of Facebook's LLaMA model in C/C++

llmcontext

:anger: Pressure testing the context window of open LLMs

llmjudge

Exploring limitations of LLM-as-a-judge

mini-projects

This is a collection of various smaller projects such as Game of Life, TSP, Huffmancoding, Trailblazer and Robots (Game)

mlx

MLX: An array framework for Apple silicon

mlx-examples

Examples in the MLX framework

pintos

Pintos is a simple operating system framework for the 80x86 architecture with several implemented OS features. The OS is written in C++.

scrapers

Project that scrapes facebook posts from a buy-&-sell group. Uses BeautifulSoup to parse through HTML code, then sends notification to user when a post with desired key word is made

tensor-puzzles

[Completed 03/01/24 ✅]

tetris

Tetris is a tile-matching video game first published in 1984, this is a modified version of the game with new features such as powerup-states.

tracker

Visual Object Trackers on the OTB-mini dataset.

yet-another-applied-llm-benchmark

A benchmark to evaluate language models on questions I've previously asked them to solve.