Awesome GitHub RepositoriesLarge Language Models

Este proyecto es un directorio curado por la comunidad de software de código abierto diseñado para su implementación en entornos de servidores privados y laboratorios domésticos. Sirve como un recurso integral para descubrir alternativas independientes y autohospedadas a los servicios en la nube convencionales, permitiendo a los usuarios mantener la propiedad total de los datos y el control sobre su infraestructura digital. El directorio está estructurado a través de una taxonomía jerárquica que organiza una vasta colección de aplicaciones en categorías lógicas, que van desde la gestión de medios y análisis de datos hasta la comunicación privada y herramientas de productividad en equipo. Se distingue por un proceso de revisión por pares colaborativo, donde los miembros de la comunidad validan la calidad y relevancia de cada envío para garantizar que el directorio siga siendo preciso y confiable. El proyecto cubre una amplia superficie de capacidades, incluyendo automatización de infraestructura, implementación de servicios basados en contenedores y gestión de configuración declarativa. Estas herramientas ayudan a los usuarios a mantener entornos de servidor reproducibles y gestionar dependencias de servicios complejas en hardware privado. El directorio se mantiene como un repositorio con control de versiones, asegurando que todas las actualizaciones y cambios impulsados por la comunidad sean rastreados y transparentes.

DeepSeek-R1 is an open-weights large language model focused on advanced reasoning. It uses chain-of-thought processing and internal monologues to solve complex mathematical and logical problems by breaking tasks into sequential, verifiable thought processes. The model is developed using reinforcement learning to optimize reasoning patterns and verify logical steps. It employs a distillation process to transfer these high-performance logic capabilities from a large teacher model into smaller, computationally efficient versions. The training framework incorporates group relative policy optimiz

Odysseus is a self-hosted AI workspace and autonomous agent framework designed for deploying and managing large language models. It serves as a centralized platform for orchestrating agentic tasks, utilizing a model context protocol server to connect AI models to external system utilities, browser automation, and local hardware. The system distinguishes itself through a combination of retrieval-augmented generation and a RAG knowledge base, using vector stores and local embeddings to provide persistent semantic memory. It further integrates AI-driven communication management to triage email i

This project is a collection of deep learning research papers translated into annotated code. It serves as a resource for reproducing academic research, providing implementations of transformers, diffusion models, and reinforcement learning architectures. The library distinguishes itself by using a side-by-side annotation format that combines executable Python code with descriptive markdown notes. This approach provides a structured way to explain the logic of neural network papers alongside their PyTorch-based implementations. The codebase covers several major capability areas, including ge

Llama is a large language model runtime and inference engine designed to load and execute autoregressive transformer models. It enables the generation of natural language text completions from prompts using pretrained weights. The system features multi-GPU model parallelism, which distributes model weights and workloads across multiple graphics processors to support larger parameter counts. It also incorporates a content safety filter that uses classifiers to intercept and block unsafe inputs or outputs during the inference process. The project covers broad capabilities in distributed model

This project is a comprehensive dataset and archive of classical Chinese poetry, prose, and Confucian classics. It serves as a digital humanities corpus, providing machine-readable access to hundreds of thousands of poems and detailed poet biographies, specifically spanning the Tang and Song dynasties. The collection is distinguished by its scholarly depth, incorporating textual variation annotations to track disputed characters across different source editions. It also includes tonal pattern mapping to describe the rhythmic and phonetic structures of the verse, alongside a popularity ranking

Grok-1 is an open-weights large language model implementation featuring a sparse mixture-of-experts architecture. It is designed for high-performance text generation and natural language processing by activating only a subset of specialized expert layers per token. The model utilizes 8-bit weight quantization to reduce memory overhead and accelerate loading. To manage its high parameter count, the implementation supports activation sharding, which distributes the memory load across multiple hardware devices during execution. The project covers large-scale model inference, including text comp

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 a community-driven directory and knowledge base for the PHP ecosystem. It serves as a comprehensive index of high-quality libraries, frameworks, tools, and educational materials, designed to help developers navigate the landscape and select appropriate solutions for their software projects. The directory distinguishes itself through a hierarchical taxonomy that organizes vast amounts of technical information into a logical, human-readable structure. By relying on distributed contributions from the developer community, it maintains a current and vetted collection of references

Llama 3 is a collection of pretrained, autoregressive transformer-based models designed for natural language generation, reasoning, and complex instruction following. It functions as a generative AI framework that provides the infrastructure for managing model weights, executing neural network inference, and handling computational workloads across diverse knowledge domains. The project distinguishes itself through an integrated AI safety toolkit that employs secondary classification filtering to inspect inputs and outputs, ensuring adherence to usage compliance and safety standards. It suppor

Sglang is a high-performance inference engine and serving system designed for large language and multimodal models. It provides a programmable interface for orchestrating complex generation workflows, enabling developers to coordinate multi-turn dialogues, tool invocations, and reasoning chains through a domain-specific language. The platform is built to support production-scale deployments, offering an OpenAI-compatible API that allows for integration with existing application ecosystems. The system distinguishes itself through a disaggregated architecture that separates compute-intensive pr

This project is a command line AI client and API wrapper designed to facilitate interaction with a large language model. It functions as a terminal interface for sending multi-line prompts and receiving generated text, providing a means of conversational AI integration through a programmable interface. The system utilizes a reverse-engineered API interface and HTTP-based request simulation to communicate with the model. It includes an AI plugin manager that allows for the installation and management of external extensions to increase the functional capabilities of the language model. The imp

Qwen2.5 is a suite of large language model foundation models designed for natural language generation, code production, and complex mathematical reasoning. The project encompasses a multilingual language model capable of processing dozens of languages and a specialized code generation model for technical problem solving and debugging. The framework is distinguished by its long context capabilities, enabling the analysis of massive inputs ranging from 256K up to 1 million tokens. It further functions as an agentic framework, utilizing standardized templates and parsers to execute autonomous wo

Qwen3 is a transformer-based large language model designed as a generative AI foundation for understanding, reasoning, and generating human language. It functions as a comprehensive ecosystem for model training, fine-tuning, and production-ready inference, providing the underlying architecture and weights necessary to build diverse artificial intelligence applications. The project distinguishes itself through extensive support for model quantization and distributed inference, enabling efficient execution across a wide range of hardware from consumer-grade devices to scalable cloud infrastruct

SHAP is a machine learning explainer that uses a game-theoretic framework to estimate the contribution of each feature to a model prediction. It provides a set of tools for quantifying how individual input features push a specific output away from a baseline value. The project includes specialized explainers for different architectures, including high-speed implementations for decision trees and ensemble models, linearization algorithms for deep learning networks, and covariance integration for linear models. It also features a model-agnostic interpretability tool that uses a kernel method to

JARVIS is a system for large language model task orchestration, deployment management, and automation benchmarking. It utilizes a task orchestrator to decompose complex requests into actionable steps and coordinates various expert models to synthesize final responses. The project includes an AI model deployment manager to handle the local deployment of expert models across different hardware scales. It further provides an AI workflow API consisting of web endpoints used to trigger automated task workflows and retrieve results from model selection stages. The framework incorporates an automat

Open-AutoGLM is an autonomous agent framework designed to perform complex user workflows on mobile devices. By translating natural language instructions into precise sequences of taps, scrolls, and text inputs, the system enables the automation of mobile application interactions and testing. The platform distinguishes itself through a combination of vision-language processing and reinforcement learning. It converts graphical user interfaces into structured data, allowing agents to parse screen elements and map natural language commands to coordinate-based actions. To ensure reliability, the s

verl is a distributed training system designed for large language model alignment and reinforcement learning. It provides a framework for executing post-training pipelines, including supervised fine-tuning and reinforcement learning from human feedback, to refine model behavior and agentic capabilities. The system utilizes a hybrid training and inference engine that optimizes memory and communication when switching between model generation and gradient updates. It supports multi-modal reinforcement learning for models processing both image and text data, and implements algorithms such as PPO

This project is a distributed training infrastructure designed for aligning large language models through reinforcement learning. It functions as an end-to-end engine for complex alignment tasks, including proximal policy optimization, direct preference optimization, and iterative self-play. By providing a unified framework for multi-turn interactions and tool-use scenarios, it enables the development of models capable of reasoning and external environment engagement. The framework distinguishes itself through a decoupled architecture that separates model training from sample generation. This

RAG-Anything is a retrieval-augmented generation framework designed to index diverse document formats and perform semantic search using local machine learning models. It functions as a local multimodal data processor, extracting and organizing information from various file types into a unified knowledge base to facilitate private document analysis. The system distinguishes itself through its high-throughput ingestion engine, which processes large batches of documents into searchable vector embeddings. By executing machine learning models directly on local hardware, the framework ensures that