Awesome GitHub RepositoriesOverfitting Debuggers

This project is an educational resource providing practical code examples and implementations of machine learning algorithms using the Python language. It serves as a guide for constructing predictive pipelines, clustering models, and dimensionality reduction within the Scikit-Learn ecosystem. The repository includes comprehensive demonstrations for supervised and unsupervised learning, as well as detailed examples for implementing neural networks and deep architectures. It also provides practical guidance on exporting model parameters to JSON and wrapping trained models in web APIs for produ

Axolotl is a configuration-driven framework designed for the fine-tuning, evaluation, and quantization of large language models. It functions as a comprehensive orchestrator for distributed training, enabling users to manage complex workflows across multi-node and multi-GPU environments. By utilizing structured configuration files, the platform streamlines the setup of training parameters, dataset paths, and hardware distribution strategies. The project distinguishes itself through its support for diverse training methodologies, including full-parameter tuning, parameter-efficient adaptation,

Quantaxis is a quantitative trading framework designed for building, backtesting, and executing automated strategies across global equities, futures, and cryptocurrencies. It integrates an event-driven backtesting engine, a multi-market execution gateway for order routing, and a quantitative data pipeline for ingesting and storing multi-asset market data. The system features a Rust-accelerated financial library that utilizes Apache Arrow for high-performance technical indicator calculation and zero-copy data processing. It provides a containerized infrastructure model designed for orchestrati

CatBoost is a gradient boosting machine learning library used to train decision tree ensembles for regression, classification, and ranking tasks. It functions as a high-performance framework that provides a categorical data processor for transforming non-numeric features, a distributed trainer for large-scale datasets, and GPU acceleration to speed up model construction. The library distinguishes itself through native handling of categorical data and text features, removing the need for manual encoding. It includes a specialized model interpretability tool that leverages SHAP values and featu

This repository collects illustrated single-page cheat sheets that compress the core topics of Stanford's CS 230 deep learning course into visual reference summaries. The collection covers convolutional neural networks, recurrent neural networks, and practical training techniques, pairing schematic diagrams with mathematical notation to bridge intuition and formal understanding. The cheat sheets are organized by subject area and link related concepts across topics, such as connecting vanishing gradients to LSTM gates, to reinforce the full deep learning workflow. Practical training advice on

This repository is a curated study resource of interview questions and answers for data science roles. It covers the core domains of machine learning, statistics, Python programming, SQL databases, deep learning, and algorithmic problem solving. The content is organized as static Markdown files with a structured question-and-answer format, making it easy to read and navigate without any server-side processing. The material distinguishes itself by pairing each question with a detailed explanation and often a code example, covering both conceptual knowledge and practical application. Topics ran

Grok este un framework de antrenare a rețelelor neuronale și o suită de experimente de machine learning concepută pentru cercetarea generalizării algoritmice. Oferă un set de instrumente pentru a studia modul în care rețelele neuronale trec de la memorarea datelor de antrenament la descoperirea regulilor generale atunci când sunt antrenate pe seturi de date mici. Implementarea se concentrează pe analiza overfitting-ului în deep learning și evaluarea antrenării rețelelor neuronale. Permite execuția buclelor de antrenament pentru a observa fenomenul de "grokking" și pentru a măsura performanța modelului pe date algoritmice neobservate anterior. Codul sursă acoperă domenii de capabilități precum eșantionarea seturilor de date algoritmice, optimizarea iterativă a gradientului și monitorizarea generalizării bazată pe pierdere (loss) pentru a urmări decalajul dintre pierderea de antrenament și cea de validare.