Awesome GitHub RepositoriesAdvanced Reasoning Models

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

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

This project is an agentic workflow orchestrator designed for building and deploying autonomous systems that perform multi-step reasoning. It functions as a tool-augmented engine, enabling developers to chain model calls with external function execution to complete complex, user-defined tasks. By integrating large language models with persistent memory and stateful logic, the framework supports the creation of intelligent applications capable of independent operation. The platform distinguishes itself through graph-based state orchestration, which allows developers to define logic steps and t

Qwen3-Coder is a specialized large language model designed for software development, technical reasoning, and automated code synthesis. Built on transformer-based sequence modeling, it functions as a multilingual programming assistant capable of generating, completing, and debugging source code across more than one hundred programming languages. The model distinguishes itself through its capacity to process and maintain logical coherence across massive datasets, supporting context windows of up to one million tokens. This allows for repository-scale reasoning, enabling the model to analyze co

GLM-4 is an open weights large language model designed as a multimodal chat system. It functions as a reasoning-focused and multilingual model capable of processing and generating responses across text and visual data types. The model is distinguished by its function-calling capabilities, allowing it to interface with external tools and APIs to execute tasks and retrieve real-time information. It is optimized for complex logical reasoning, mathematical problem solving, and deep research involving long-form content generation. Broad capabilities include multilingual text generation, the creat

LLM-RL-Visualized is a visual reference library and collection of knowledge maps designed to explain Large Language Model and Reinforcement Learning algorithms. It provides a structured system of conceptual diagrams and taxonomies covering the intersection of language model alignment and reinforcement learning. The project distinguishes itself through detailed visual mappings of complex workflows, such as the coordination of reward models and policy optimization in reinforcement learning from human feedback. It contrasts different preference optimization architectures, such as RLHF and Direct

Ce projet est un guide d'étude complet et une référence technique pour apprendre les architectures et les méthodes d'entraînement des Transformers et des grands modèles de langage. Il sert d'aperçu technique pour comprendre comment les réseaux de neurones traitent les données et comment aligner le comportement du modèle avec des objectifs de performance spécifiques. Le dépôt fournit des guides spécialisés sur plusieurs domaines clés du développement de modèles. Cela inclut des références détaillées pour les architectures de transformateurs, des frameworks d'implémentation pour la génération augmentée par récupération (RAG) et les flux de travail agentiques, ainsi que des guides techniques pour l'optimisation et le fine-tuning des modèles. Le contenu couvre un large éventail de capacités, y compris le fine-tuning supervisé, l'adaptation de bas rang (LoRA) et l'alignement basé sur les préférences. Il aborde également l'efficacité des modèles via la quantification, la distillation et les architectures de mélange d'experts, ainsi que l'étude des mécanismes d'auto-attention et de flash attention. Les ressources et les exemples sont fournis pour le développement en C#, JavaScript et Python.

Ce projet est un système de gestion de compte de grands modèles de langage et un proxy multi-utilisateurs. Il fournit une passerelle qui permet à plusieurs utilisateurs authentifiés de partager un seul abonnement IA premium ou une clé API OpenAI. Le système fonctionne comme une couche de proxy qui intercepte les requêtes des clients et les transmet à l'API officielle tout en injectant des identifiants partagés. Il inclut un backend sécurisé pour la gestion centralisée des identifiants et un système de contrôle d'accès basé sur des jetons pour valider les identités des utilisateurs. Pour maintenir la confidentialité et l'organisation, le projet implémente une isolation de contexte basée sur la session pour empêcher la fuite de conversation entre les utilisateurs. Il dispose également d'un middleware pour l'audit d'activité afin de suivre l'utilisation et surveiller le comportement individuel des utilisateurs. L'interface fournit un accès aux capacités avancées des modèles, incluant la génération d'images, l'analyse de fichiers et l'exécution de code.

GLM-4.5 is a multimodal large language model and advanced reasoning system. It functions as an AI coding assistant, an autonomous AI agent, and a multimodal content generator capable of processing and generating text, images, audio, and video within a single unified system. The project is distinguished by its deep reasoning capabilities, utilizing chain-of-thought processing to solve complex mathematical, logical, and technical problems. It features an agentic architecture that allows for autonomous task execution, long-horizon goal planning, and the ability to interact with external tools an