📘🌼 A bunch of Pollen recipes

Export org file to the beauty Tufte html

Implementation of Facebook's FastText model in Torch

A pure Julia implementation of denoising diffusion probabilistic models

Simple, blazing fast, transformer components.

Fork of https://bitbucket.org/omerlevy/hyperwords

Inference Llama 2 in one file of pure C & one file with CUDA

An introduction to ARM64 assembly on Apple Silicon Macs

A concise set of Latex templates that serves a small set of needs - CV, Essays, Articles and Problem Sets

A poor guide to Pollen, that amazing document formatting system in Racket

Github host for Julia GPU tutorial hosted at https://jenni-westoby.github.io/Julia_GPU_examples/dev/

🦄 Modern Org Style

Julia package for inference and training of Llama-style language models

Let's be honest: mostly Emacs.

SpikingJelly is an open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch.

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…

Multi-GPU CUDA stress test

RL starter files in order to immediately train, visualize and evaluate an agent without writing any line of code

Mamba SSM architecture

Emacs highlighting using Ethan Schoonover’s Solarized color scheme

Julia code for the book Reinforcement Learning An Introduction

Annotated version of the Mamba paper

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

A simple LLM client for Emacs

A ChatGPT mode for the Julia REPL

An implementation of Maximum Mean Discrepancy (MMD) as a differentiable loss in PyTorch.