A latent text-to-image diffusion model

Instruct-tune LLaMA on consumer hardware

QLoRA: Efficient Finetuning of Quantized LLMs

Zero-Shot Speech Editing and Text-to-Speech in the Wild

Face Image Motion Model (Photo-2-Video) based on "first-order-model" repository.

Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates

A proof of concept model based on Llama 3.1-8B, featuring reasoning capabilities in Bulgarian.