Awesome GitHub RepositoriesSequence Models

This project is a speech recognition and translation engine that utilizes a sequence-to-sequence transformer architecture to convert audio into text. It is built upon a weakly supervised learning framework, which leverages large-scale, unlabelled audio-transcript data to create generalized speech representations capable of performing simultaneous transcription, language identification, and translation. The system distinguishes itself through a unified multi-task modeling approach that shares token sequences across different objectives, allowing it to handle diverse languages and vocabularies

This project is an open-source, interactive educational platform designed to teach deep learning through a comprehensive, code-first curriculum. It provides a structured learning path that covers foundational mathematics, modern neural network architectures, and practical optimization techniques, enabling practitioners to master complex artificial intelligence concepts through hands-on experimentation. The platform distinguishes itself by integrating technical explanations with executable Jupyter notebooks. This design allows readers to modify code and hyperparameters in real-time, facilitati

The algorithm is a distributed recommendation engine pipeline designed to construct and serve personalized content timelines. It functions as a multi-stage orchestration layer that aggregates candidate content from diverse social graphs and high-dimensional embedding spaces, processing user interaction data to deliver a unified, ranked experience. The system utilizes a high-performance machine learning serving infrastructure to execute deep learning models that predict engagement probabilities in real-time. It distinguishes itself through a hybrid retrieval strategy that combines graph-traver

This project is a comprehensive Chinese translation of a technical deep learning textbook, providing an educational resource on the theory and implementation of neural networks. It functions as a collaborative technical translation project designed to make complex academic AI literature accessible to non-English speakers. The project utilizes a community-driven translation model that integrates external suggestions and pull requests to refine linguistic accuracy and reduce bias. It employs standardized terminology mapping to ensure a uniform vocabulary throughout the translated content. To i

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

This project is an educational resource focused on the internal mechanics and design principles of transformer-based neural networks. It provides a structured guide to the fundamental components of generative artificial intelligence, including sequence modeling, semantic embeddings, and the mathematical foundations of large language models. The repository distinguishes itself through a heavy emphasis on visual documentation, utilizing diagrams and step-by-step explanations to clarify how data flows through complex neural architectures. It serves as a technical reference for developers seeking

This project is a comprehensive deep learning framework and educational platform designed for constructing, training, and evaluating neural network architectures. It provides a modular environment for building models through tensor operations and automatic differentiation, supporting a wide range of tasks from image classification and object detection to sequential data processing. Beyond its core technical capabilities, the project distinguishes itself by integrating professional career development resources directly into its learning ecosystem. It offers structured guidance, resume reviews,

Mamba is a deep learning framework designed for building and training sequence models that process long-range data dependencies with linear-time computational efficiency. By utilizing selective state space modeling, the library enables the construction of neural network architectures that replace traditional attention mechanisms with high-performance state space operations. The framework distinguishes itself through the use of data-dependent state gating, which allows the model to dynamically filter information flow based on the input sequence. To ensure high throughput, it incorporates hardw

This repository is a deep learning for natural language processing course and curriculum. It provides educational material and guides focused on neural network architectures used for processing natural language, speech signals, and text classification. The content includes instructional tutorials on sequence modeling and neural language modeling, covering the implementation of n-gram and recurrent neural networks. It also provides a framework for studying word embeddings to map linguistic meanings into numerical representations. The curriculum covers a broad range of capabilities, including

This project is a Python-based educational framework designed to simulate reinforcement learning algorithms and environments. It serves as a platform for reproducing classic textbook examples, allowing users to study agent behavior, policy improvement, and the fundamental mechanics of decision-making in controlled settings. The library provides implementations for core reinforcement learning concepts, including temporal difference learning, Monte Carlo episode sampling, and tabular value function approximation. It enables the analysis of specific algorithmic behaviors, such as identifying and

Ludwig is a declarative machine learning framework designed for training neural networks and large language models using configuration files instead of manual coding. It functions as a multimodal model builder and a low-code tool for supervised fine-tuning, allowing users to build models that process mixed inputs of text, images, audio, and tabular data. The project distinguishes itself through an automated hyperparameter optimizer and a system for large language model fine-tuning using parameter-efficient adapters. It features a multimodal data pipeline and the ability to automatically gener

DeepCTR is a specialized software framework and deep learning model library designed for predicting click-through rates and implementing recommendation systems. It provides a suite of tabular data models and architectures tailored for binary classification and sparse feature processing. The framework includes dedicated toolkits for multi-task learning and sequential interest modeling. It allows for the simultaneous estimation of multiple related targets through shared-bottom and gated expert neural networks, while capturing evolving user behavior using attention mechanisms and transformers.

Qwen-Image is a text-to-image model and large language model image generation framework. It functions as an AI image editing suite and a personalized image trainer, capable of producing high-fidelity visuals and accurate typography from natural language descriptions. The system is distinguished by its precision text rendering engine, which integrates multi-script calligraphy and layout-coherent alphabetic text into images. It provides specialized capabilities for subject identity preservation and consistent subject generation across different poses and viewpoints, alongside a training pipelin

Este es un framework de machine learning para tratar diversas tareas de procesamiento de lenguaje natural como un problema unificado de texto a texto. Proporciona un toolkit para pre-entrenar y ajustar modelos transformer a gran escala, utilizando un sistema donde tanto las entradas como las salidas se formatean como secuencias de texto crudo. El framework se distingue por su sistema de entrenamiento distribuido, que utiliza estrategias basadas en malla para escalar pesos de modelos y lotes de entrenamiento a través de múltiples núcleos TPU. Soporta aprendizaje multitarea combinando diversos datasets en un único flujo de entrenamiento utilizando tasas de mezcla configurables, permitiendo que un único modelo maneje varias tareas de lenguaje. El sistema cubre una amplia gama de capacidades, incluyendo arquitecturas codificador-decodificador, decodificación de búsqueda de haz (beam-search) para generación de texto y flujos de trabajo de transfer learning. Incluye utilidades para la preparación de datasets de NLP, evaluación del rendimiento del modelo y exportación de checkpoints entrenados para servir en producción. La biblioteca soporta la carga de checkpoints de modelos pre-entrenados de varios tamaños para acelerar el desarrollo.

Sapiens es un modelo de visión humana de alta resolución diseñado para tareas de visión artificial centradas en el ser humano de alta precisión. Funciona como un conjunto de herramientas para estimar la pose humana, la profundidad y la geometría de la superficie. El proyecto utiliza un backbone de vision transformer para realizar múltiples tareas a través de un codificador compartido. Esta arquitectura permite la predicción simultánea de estructuras esqueléticas, ubicaciones de articulaciones y la distancia entre una cámara y un sujeto humano. Las capacidades del modelo cubren la segmentación de partes del cuerpo humano para aislar regiones anatómicas de los fondos y la predicción de normales de superficie para recuperar detalles geométricos 3D a partir de imágenes 2D. Estas tareas están respaldadas por un framework de aprendizaje multitarea que emplea regresión a nivel de píxel y enmascaramiento de segmentación semántica.

Flash Linear Attention is a training framework and inference engine for sequence models that use linear attention and state space mechanisms, designed to process long contexts with reduced memory and compute overhead. It provides hardware-optimized token mixing layers and fused CUDA kernels that minimize memory bandwidth and launch overhead across different GPU architectures, and includes a causal inference engine that generates text token-by-token using cached hidden states for efficient autoregressive decoding. The project supports building hybrid sequence models that interleave standard at

EconML es una biblioteca de Python para inferencia causal diseñada para estimar efectos de tratamiento heterogéneos utilizando una combinación de aprendizaje automático y econometría. Sirve como kit de herramientas para calcular efectos de tratamiento promedio condicionales para determinar cómo las intervenciones específicas impactan a individuos o subgrupos. El proyecto proporciona un framework para el aprendizaje automático doble y el aprendizaje automático ortogonal para aislar señales causales de factores de confusión de alta dimensión. Incluye implementaciones especializadas para bosques causales y aprendices de variables instrumentales, lo que permite la recuperación de relaciones causales incluso en presencia de factores de confusión no observados. La biblioteca cubre una amplia gama de capacidades, incluyendo la validación de modelos causales mediante pruebas de refutación y curvas de calibración, la construcción de políticas de tratamiento personalizadas y el análisis de regímenes de tratamiento dinámicos. También admite la inferencia estadística para la cuantificación de la incertidumbre y la interpretación de la heterogeneidad del efecto utilizando modelos basados en árboles y valores de Shapley. El proyecto se implementa y demuestra principalmente a través de Jupyter Notebooks.

This project is a distributed machine learning platform and sparse deep learning framework designed for training and serving models with high-dimensional sparse data. It functions as an online model serving infrastructure and recommendation system engine, enabling real-time item retrieval and scoring using deep tree matching and neural networks. The system distinguishes itself through a multi-task learning framework that optimizes multiple objective functions within a shared representation space. It features a specialized online serving infrastructure that supports dynamic model hot-loading a

Open Flamingo es un framework de entrenamiento de modelos de lenguaje multimodal de gran tamaño diseñado para integrar codificadores de visión preentrenados con modelos de lenguaje. Implementa una arquitectura de visión-lenguaje que utiliza capas de atención cruzada para procesar secuencias intercaladas de imágenes y texto. El sistema se caracteriza por sus capacidades de aprendizaje multimodal few-shot, permitiendo al modelo adaptarse a nuevas tareas visuales utilizando un pequeño conjunto de ejemplos de imagen-texto proporcionados en el prompt. Admite aprendizaje en contexto y generación de texto multimodal para tareas como respuesta a preguntas visuales y subtitulado. El framework incluye un entrenador de modelos distribuido que emplea paralelismo de datos y checkpointing de gradiente para la optimización de memoria a través de múltiples GPUs. También proporciona utilidades para la carga de datasets multimodales fragmentados, evaluación de modelos paralelizada e infraestructura para alojar modelos a gran escala para inferencia.