High-Performance Scientific Modeling with Julia and SciML

Agents for SLMs from scratch

A truly open version of gpt-oss which shows the entire pre-training from scratch

Fast R-CNN

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

Ground-up implementation of LLMs with minimal dependencies

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

Implementation of Physics-Informed Neural Networks for Computational Mechanics based on the DeepXDE package.