sIlENtbuffER/Generative-Models

Implementation of rectified flow and some of its followup research / improvements in Pytorch

A resource for learning about Machine learning & Deep Learning

Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.

A repository for generative models

GPT-2-style LLM built from scratch in C/CUDA with hand-written backprop, BPE tokenizer, FlashAttention, pretraining, and SFT.

From-scratch PyTorch replications of classic and SOTA AI/ML papers: transformers, attention, GANs, diffusion, CLIP, LoRA, MoE and more, with reproducible training code.

A deep learning library built from scratch with complex neural networks examples built on top for learning purposes.