A latent flow-based diffusion model trained on the 2012 ImageNet dataset from scratch.

I Just thought it would look cool

Repo I use for all my causal transformer experiments.

Demo used for AI Club

Just some tests I ran

Code for the paper "Cottention: Linear Transformers With Cosine Attention"

I feel like building a calculator for matrix gradients, but where the function has an ambiguous input gradient like in a machine learning backprop context.

Creating a diffusion model from scratch in PyTorch to learn exactly how they work.

I need to learn some RL

I just want some data

Repo to store a base trainer for a GPT-style model with huggingface

Some repo to throw stuff

Diffusion TTS - Synthesized voice using stable diffusion to map between noise and stylized speech

Finetuning Some Wizard Models With QLoRA

A working example of a 4bit QLoRA Falcon model using huggingface

IDK what this is? We'll see if anything comes out of it.