Awesome GitHub RepositoriesPositional Encoding Techniques

This project is an educational platform and research toolkit designed to teach deep learning through a combination of mathematical theory, visual diagrams, and executable code. It provides a comprehensive environment for building, training, and evaluating neural networks, grounding complex concepts in interactive computational notebooks that allow for hands-on experimentation. The framework distinguishes itself by interleaving theoretical foundations—including linear algebra, calculus, and probability—with practical implementations across multiple industry-standard libraries. It supports flex

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

This project is a comprehensive educational curriculum and structured learning path covering the full lifecycle of large language models. It provides a guided progression through the theory, architecture, training, and deployment of these models. The curriculum includes specialized guides on transformer architecture, model training tutorials, and frameworks for designing autonomous agents. It also provides dedicated resources for studying model safety and ethics. The material covers a wide range of technical capabilities, including distributed training strategies, parameter-efficient fine-tu

The Annotated Transformer is an educational resource that provides annotated code implementations of the Transformer architecture for sequence-to-sequence tasks, built with PyTorch. It serves as a learning tool for understanding attention mechanisms, multi-head parallel attention, and scaled dot-product attention through executable examples that walk through each component of the model. The project covers the full Transformer pipeline, including stacked encoder-decoder layers with residual connections and layer normalization, sinusoidal positional encoding for order-aware representation, and

PlugNPlay-Modules is a collection of reusable PyTorch computer vision modules and deep learning architectural components. It provides a library of standardized building blocks for constructing neural networks, focusing on attention mechanisms, signal processing layers, and feature fusion modules. The project is distinguished by its extensive variety of attention primitives, covering spatial, channel, and temporal weighting, as well as specialized variants like deformable, frequency-enhanced, and linear-complexity attention. It also implements advanced signal processing tools within the neural

Acest proiect este o implementare PyTorch a unei rețele neuronale bazate pe atenție, concepută pentru sarcini de deep learning de tip sequence-to-sequence. Servește drept bibliotecă pentru construirea de modele de secvențe de deep learning care utilizează structuri de encoder și decoder pentru a procesa limbajul natural și datele secvențiale. Implementarea se concentrează pe un mecanism de atenție multi-head pentru a captura relații diverse între token-uri fără a utiliza recurența. Include codificarea pozițională sinusoidală pentru a menține ordinea secvenței și rețele feed-forward punctuale pentru a transforma pozițiile token-urilor în mod independent. Arhitectura încorporează normalizarea bazată pe straturi pentru a stabiliza antrenarea și a accelera convergența. Oferă componentele necesare pentru designul arhitecturii rețelelor neuronale în domeniile procesării limbajului natural și învățării sequence-to-sequence.

Tiny Universe is an educational monorepo that delivers multiple independent implementations of core AI subsystems as self-contained Jupyter notebooks. It provides from-scratch constructions of foundational architectures including a complete Transformer model built from the original paper specification, a denoising diffusion probabilistic model for image generation, and a ReAct-style autonomous agent framework that equips an LLM with tools for planning and multi-step task execution. The project distinguishes itself by covering the full lifecycle of modern AI systems through hands-on implementa

DeiT este un framework PyTorch vision transformer conceput pentru clasificarea imaginilor. Implementează o arhitectură bazată pe transformer care procesează imaginile ca secvențe de patch-uri aplatizate folosind straturi de self-attention și modelarea secvenței conștientă de poziție în loc de filtre convoluționale. Proiectul se concentrează pe antrenarea eficientă a datelor printr-un framework de knowledge distillation. Acest sistem permite unui model student să imite soft label-urile unui model profesor de înaltă performanță pentru a îmbunătăți acuratețea și generalizarea, în special atunci când se antrenează pe seturi de date mai mici. Biblioteca acoperă întregul ciclu de viață al dezvoltării, inclusiv antrenarea clasificării imaginilor, optimizarea pierderii cross-entropy și deployment-ul ponderilor pre-antrenate pentru inferență. Include, de asemenea, un instrument de benchmarking pentru a evalua performanța și acuratețea modelului față de seturile de date standard.

Neuraloperator is a library for learning mappings between infinite-dimensional function spaces, serving as a tool to accelerate physics simulations and partial differential equation solving. It implements resolution-invariant models and spectral neural networks that can produce consistent predictions regardless of the input grid resolution or spatial discretization. The framework incorporates physics-informed neural networks that enforce physical constraints and differential equations through specialized loss functions. It utilizes Fourier transforms and spectral projections to process multid