ML Frameworks

TimesFM is a pretrained decoder-only transformer that turns historical sequences into point and quantile forecasts without training from scratch.

Google's attempt to own the full machine-learning stack, from research lab to Raspberry Pi.

A tiny deep-learning model that guesses what a file actually contains, not just what its extension claims.

It wraps local inference and fine-tuning for open models in a web UI, using custom kernels to squeeze more performance out of desktop GPUs than standard tooling.

It teaches how LLMs work by implementing tokenization, attention, pretraining, and finetuning in pure PyTorch, one notebook at a time.

It centralizes model definitions so the same architecture works across PyTorch, JAX, vLLM, and llama.cpp without rewrites.

Ultralytics wants to stop you from stitching together separate repos for every computer vision task by bundling detection, segmentation, tracking, and pose estimation into one YOLO-backed package.

A readable reference for how classic machine learning actually works under the hood, from backprop to genetic algorithms.

A PyTorch toolkit that treats robot learning like Hugging Face treats NLP: standardized datasets, pretrained policies, and one interface for many arms.

A rewrite of minGPT that prioritizes working, hackable training code over educational scaffolding.

PyTorch exists to give researchers and engineers GPU-accelerated tensor math and automatic differentiation without forcing them to leave Python’s debugger and stack traces behind.

nanochat is a minimal, hackable harness that lets you train and chat with a GPT-2-class LLM on a single GPU node for under $100—no hyperparameter spreadsheets required.

Because 'the model said so' is not an explanation, SHAP uses Shapley values from game theory to assign every feature its exact contribution to any prediction.

It exists because keeping up with the training loops, quantization tricks, and inference stacks of 100+ models is a full-time job most developers would rather delegate.

An open standard that lets you train in PyTorch and deploy on hardware that has never heard of it.

exo auto-discovers Apple devices on your network and shards frontier models across them, turning a pile of Macs into a single inference engine.

Megatron-LM splits into a reference training stack and a composable core for anyone who needs to squeeze every FLOP from a GPU cluster.

Jupyter notebooks that prove you can write a GPT with little more than high-school calculus and stubbornness.

It exists to handle the tedious wiring—annotations, dataset formats, tracking—that sits between a trained model and a useful application.

Companion notebooks for an 800-page quantitative finance textbook, from linear regression to deep reinforcement learning trading agents.