Awesome GitHub RepositoriesAutoregressive Models

Bark is a generative audio engine and machine learning inference library designed to convert written text into high-fidelity speech and sound effects. It functions as a text-to-audio transformer, utilizing multi-stage neural network architectures to map semantic input tokens into detailed audio codebooks for synthesis. The system distinguishes itself through a hierarchical transformer stacking approach that separates semantic understanding from acoustic realization. By employing autoregressive token prediction and vector quantized codebook mapping, the engine bridges linguistic and sonic doma

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

minGPT is a minimal implementation of the Transformer architecture designed for training and experimenting with language models. It functions as a neural network training framework and a text generation engine, providing the necessary tools to manage data loading, backpropagation, and parameter updates for custom deep learning models. The project is structured as an educational resource for understanding how transformer architectures function by building and training models from scratch. It utilizes a modular block architecture and transformer-based self-attention to process sequences, allowi

CosyVoice is a speech synthesis framework that utilizes large language models to generate expressive, multilingual audio. The system functions as an audio generation engine capable of producing natural-sounding speech across multiple languages while preserving regional dialects and specific emotional tones. The platform distinguishes itself through its zero-shot voice cloning capabilities, which allow for the creation of synthetic voice profiles from short audio samples without requiring additional model training. It provides fine-grained control over vocal attributes, enabling users to adjus

Qwen3-VL is a multimodal vision-language model designed to process and reason across images, videos, and text. It functions as a computer vision framework capable of identifying objects, extracting structured data from documents, and interpreting spatial elements within visual media. The system operates as an automated user interface interaction agent, interpreting screen data to navigate software and mobile applications. By utilizing a unified transformer architecture, it performs complex visual reasoning to execute user-defined tasks without manual input. Beyond interface navigation, the m

Janus is a multimodal large language model and unified framework that integrates visual understanding and image generation within a single neural network. It functions as both a visual understanding model for analyzing images and a text-to-image generator. The system uses a unified transformer backbone and a multimodal latent space to bridge the gap between text and visual data. This architecture employs decoupled visual encoding and cross-modal tokenization to separate the paths for discriminative understanding and generative tasks, representing images as grids of discrete codes. The projec

FramePack is a neural video synthesis engine and generation framework designed to produce long, temporally consistent video sequences. It functions as a diffusion model optimizer, providing a suite of techniques to manage the computational demands of high-parameter video models while maintaining visual stability during extended generation tasks. The system distinguishes itself through a hierarchical approach to frame prediction, which plans distant anchor frames before filling in intermediate content to prevent cumulative temporal drift. By utilizing constant-length context compression and to

ChatGLM2-6B is a bilingual chat large language model designed for natural conversation and text generation in both English and Chinese. It functions as a fine-tunable language model that supports updating weights via specialized scripts to adapt to specific datasets and tasks. The project serves as a quantized inference engine and multi-GPU model orchestrator, enabling the execution of large models on consumer-grade hardware. It is capable of processing long context sequences up to 32K tokens to maintain understanding across extended documents. The system covers capabilities for multilingual

Spark-TTS is a deep learning text-to-speech synthesis engine designed to convert written text into high-fidelity audio. It utilizes a transformer-based architecture and autoregressive sequence modeling to generate coherent speech, transforming linguistic input into natural-sounding waveforms through neural speech codec synthesis. The platform distinguishes itself through zero-shot voice cloning, which allows users to mimic a target speaker’s unique vocal identity using only a short reference audio sample without requiring additional model training. It also features cross-lingual phonetic mapp

CodeGeeX is an open-source code model and multilingual large language model designed to generate, translate, and complete source code across multiple programming languages. It functions as an AI coding assistant and a cross-lingual code translator that produces executable code and technical documentation. The project enables natural language programming by turning plain English descriptions into functional programs. It also provides the ability to convert source code from one programming language to another while preserving the original logic and functionality. The system covers a range of c

VAR is a visual autoregressive model and image generation framework that applies large language model scaling laws to visual data. It functions as an image generator that uses a coarse-to-fine next-scale prediction approach rather than traditional raster-scan tokenization. The system utilizes scale-based tokenization to represent images as a hierarchy of discrete tokens. It generates high-resolution content by iteratively predicting the next resolution level, refining coarse predictions into fine-grained details. The project covers a broad range of capabilities including autoregressive image

Jukebox is a generative audio model and AI music synthesis tool designed to create high-fidelity music samples and singing voices. It functions as a deep learning system that synthesizes raw audio conditioned on genre and artist metadata, utilizing a neural audio codec to convert raw audio into discrete codes for generative modeling and reconstruction. The system enables musical style steering and AI music composition by conditioning generation on specific artists, genres, and lyrics. It supports audio priming, allowing existing wave files to guide the creation of new musical sequences, and p

GraphCast is a machine learning model that uses graph neural networks to produce global weather forecasts up to ten days ahead at high spatial resolution. The system represents the Earth's surface as an icosahedral mesh, enabling message passing between mesh nodes to capture atmospheric dynamics, and combines this with a learned multiscale processor that operates across coarse-to-fine mesh resolutions. The model is trained on historical ERA5 reanalysis data through a supervised learning objective, and its autoregressive rollout loop feeds predictions back as input to generate multi-step forec

Taming Transformers is a generative system for high-resolution image synthesis that combines a vector-quantized GAN image encoder with an autoregressive transformer. It utilizes a discrete latent space to represent images as codebook tokens, enabling the production of high-fidelity visuals through a hybrid architecture. The project provides specialized capabilities for layout-based scene synthesis, allowing for the creation of complex images by placing objects according to defined bounding box coordinates. It also includes tools for image inpainting to fill missing sections of an image by ana

Este proyecto es un framework de procesamiento de lenguaje natural centrado en un preentrenador autorregresivo generalizado diseñado para la representación de lenguaje no supervisado. Implementa un modelo de lenguaje que combina el entrenamiento basado en permutaciones con un backbone Transformer-XL para funcionar como un procesador de texto de contexto largo. El sistema destaca por su capacidad para manejar secuencias de texto que exceden los límites de longitud estándar mediante el uso de recurrencia a nivel de segmento y codificación posicional relativa. Escala el preentrenamiento de alto rendimiento a través de múltiples GPUs y clusters de TPU utilizando implementaciones de entrenamiento distribuido. El código base cubre el flujo de trabajo completo de machine learning, incluyendo limpieza de texto y tokenización de subpalabras para el preprocesamiento de datos, así como ajuste fino (fine-tuning) específico para tareas de respuesta a preguntas, comprensión lectora y clasificación de texto. Incluye utilidades para optimización de parámetros, programación de tasas de aprendizaje y evaluación de probabilidades de respuesta mediante métricas de precisión-recall. El proyecto proporciona configuraciones para gestionar hiperparámetros del modelo y entrenamiento acelerado por hardware en múltiples hosts.

x-transformers es una biblioteca de PyTorch y kit de herramientas de investigación para construir arquitecturas transformer. Proporciona un framework modular para implementar investigación experimental en transformers, incluyendo un conjunto de mecanismos de atención avanzados, herramientas de modelado de secuencias largas y un framework para vision transformers. El proyecto se distingue por su enfoque en componentes de alto rendimiento y eficiencia de memoria, como Flash Attention con kernels en mosaico (tiled kernels) y atención multi-query. También implementa métodos especializados para extender ventanas de contexto, incluyendo recurrencia de secuencias y embeddings posicionales rotatorios. La biblioteca cubre una amplia gama de capacidades arquitectónicas, incluyendo varios esquemas de normalización para estabilizar el entrenamiento, redes feedforward con puertas (gated) y topologías de capas personalizadas como las redes Macaron. Admite construcciones tanto de codificador como de decodificador, proporcionando herramientas para la generación de secuencias autorregresivas y tareas de visión-lenguaje como el subtitulado de imágenes.

PyTorch Forecasting is a deep learning framework designed for building and training neural network architectures specifically for time series forecasting. It serves as a comprehensive toolkit for implementing autoregressive models, multi-horizon forecasting, and probabilistic prediction intervals using PyTorch tensors. The library distinguishes itself through a probabilistic forecasting toolkit that generates prediction intervals and quantile forecasts using both parametric and non-parametric distributions. It further provides a neural network model optimizer for automated hyperparameter tuni

OmniGen2 es un modelo de generación de imágenes unificado y un modelo de lenguaje grande multimodal diseñado para manejar la generación de texto a imagen, tareas de imagen a imagen y edición de imágenes dentro de un único framework. Funciona como un motor visual de modelo de lenguaje causal capaz de generar y editar imágenes basadas en entradas combinadas de texto y visuales. El sistema cuenta con composición visual en contexto y generación impulsada por sujetos, permitiéndole extraer sujetos de imágenes de referencia y colocarlos en nuevas escenas. También admite la edición de imágenes basada en instrucciones, donde objetos o estilos específicos se modifican mediante comandos de lenguaje natural mientras se preserva el resto de la imagen. Las capacidades del modelo se extienden al análisis y razonamiento de contenido visual, permitiendo el reconocimiento de objetos a través de entradas combinadas de texto y visión. Para mejorar la calidad de salida, emplea un proceso de refinamiento visual iterativo con un mecanismo de autocorrección. El rendimiento se gestiona mediante la optimización del uso de VRAM a través de la descarga dinámica de pesos y la aceleración de la velocidad de inferencia utilizando técnicas de caché.

FastVideo is a comprehensive system for accelerated video generation, serving as a video generation inference engine, a video diffusion training framework, and a modular pipeline orchestrator. It provides a distributed transformer optimizer and a distillation toolkit designed to reduce denoising steps and model complexity to increase frame rates. The project distinguishes itself through specialized acceleration techniques, including joint distillation and sparse attention training. It implements low-step video generation and weight quantization to FP8 or FP4 precision to increase throughput a