deep-learning

A native macOS lab for teaching tiny language models to think — build the architecture, train the weights, and watch a small LLM emerge from scratch, locally on Apple Silicon with custom data, tokenizers, checkpoints, and MLX acceleration.

Implementation of the world model architecture for self driving out of Wayve

🔍 AI-powered diagnosis for Scikit-learn models: Detect overfitting, data leakage, class imbalance & more with LLM-generated insights

Official PyTorch Implementation for the "Unsupervised Model Tree Heritage Recovery" paper (ICLR 2025).

PyTorch – SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models.

Error Correction Code Transformer

7 Day AI ML Fundamentals Workshop The purpose of this FREE workshop is 1. To give you a boost of getting started with AI. 2. A life-long community with a similar mindset. 3. strong grip on fundamentals that the advanced concepts will be easy to understand.

[ICLR 2024 Spotlight] This is the official code for the paper "SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training"

A numpy implementation of the Transformer model in "Attention is All You Need"

Repository containing the open source code of works published at the FBK MT unit.

Tune efficiently any LLM model from HuggingFace using distributed training (multiple GPU) and DeepSpeed. Uses Ray AIR to orchestrate the training on multiple AWS GPU instances

Implementation of OmniNet, Omnidirectional Representations from Transformers, in Pytorch

Implementation of Mind Evolution, Evolving Deeper LLM Thinking, from Deepmind

Classification and Gradient-based Localization of Chest Radiographs using PyTorch.

Pytorch reimplementation of Molecule Attention Transformer, which uses a transformer to tackle the graph-like structure of molecules

Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto

Time series explainability via self-supervised model behavior consistency

Generate 3D meshes from a single 2D image using TripoSR, complete with manual geometry editing and texture baking support

🤖 Python implementations of some of the fundamental Machine Learning models and algorithms from scratch with interactive Jupyter demos and math being explained.

TextBoost: Towards One-Shot Personalization of Text-to-Image Models via Fine-tuning Text Encoder