awesome-repositories.com
Blog
MCP
awesome-repositories.com

Découvrez les meilleurs dépôts open-source grâce à notre recherche par IA.

ExplorerRecherches sélectionnéesAlternatives open sourceLogiciels auto-hébergésBlogPlan du site
ProjetÀ proposNotre méthodologiePresseServeur MCP
Mentions légalesConfidentialitéConditions d'utilisation
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
Jiayi-Pan avatar

Jiayi-Pan/TinyZero

0
View on GitHub↗
13,168 stars·1,585 forks·Python·Apache-2.0·9 vues

TinyZero

TinyZero is a reinforcement learning framework and implementation designed to train language models to develop reasoning and self-verification abilities. It provides a training pipeline to optimize model performance on mathematical and logical tasks.

The project serves as a minimal reproduction of the DeepSeek R1 architectural and training approach. It focuses on creating reasoning models that can solve structured problems through autonomous chain-of-thought discovery.

The framework incorporates group relative policy optimization and reward-based self-correction to improve accuracy on logical tasks such as counting and multiplication. These capabilities are supported by Monte Carlo rollouts and a reward system based on final answer accuracy and format correctness.

Features

  • Reinforcement Learning Alignment - Implements a reinforcement learning alignment framework using Group Relative Policy Optimization (GRPO).
  • Chain-of-Thought Prompting - Utilizes chain-of-thought prompting to enable the model to generate intermediate reasoning steps.
  • Model Fine-Tuning - Provides procedures for fine-tuning models to solve structured logical and mathematical problems.
  • Self-Correction Loops - Provides self-correction loops that use reward signals to refine internal reasoning logic.
  • Reasoning Model Training Suites - Provides a training suite designed to develop self-verification and logic abilities in language models.
  • Reasoning Models - Implements a reasoning model optimized for complex logical deduction and multi-step processing.
  • Reinforcement Learning Optimizers - Optimizes model policies using reward-based techniques to improve performance on mathematical tasks.
  • Reinforcement Learning Training Pipelines - Ships a training pipeline that orchestrates the lifecycle of reinforcement learning for logical tasks.
  • Reinforcement Learning Training Utilities - Includes utilities for training model weights via reinforcement learning to improve logical task accuracy.
  • Replications - Serves as a minimal reproduction of the DeepSeek R1 architectural and training approach.
  • Monte Carlo Trajectory Estimators - Uses Monte Carlo trajectory estimators to evaluate multiple completion paths for logical accuracy.
  • Model Implementations - Minimal reproduction of reasoning-focused language models.
  • Reasoning Models - Minimalist implementation of reasoning-focused training.
  • Reinforcement Learning Frameworks - Efficient reinforcement learning implementation for small reasoning models.

Historique des stars

Graphique de l'historique des stars pour jiayi-pan/tinyzeroGraphique de l'historique des stars pour jiayi-pan/tinyzero

Recherche par IA

Explorez plus de dépôts awesome

Décrivez vos besoins en langage naturel — l'IA classe des milliers de projets open source sélectionnés par pertinence.

Start searching with AI

Alternatives open source à TinyZero

Projets open source similaires, classés selon le nombre de fonctionnalités partagées avec TinyZero.
  • deepseek-ai/deepseek-r1Avatar de deepseek-ai

    deepseek-ai/DeepSeek-R1

    91,996Voir sur GitHub↗

    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

    Voir sur GitHub↗91,996
  • huggingface/open-r1Avatar de huggingface

    huggingface/open-r1

    26,326Voir sur GitHub↗

    Open-r1 is a framework designed for the large-scale training, distillation, and optimization of language models focused on complex reasoning and programming tasks. It provides a comprehensive suite of tools for managing distributed training jobs across multi-node clusters, enabling the development of high-performance models through reinforcement learning and supervised fine-tuning. The project distinguishes itself by integrating secure, containerized code execution environments directly into the training and evaluation lifecycle. By allowing models to run and verify code snippets against test

    Python
    Voir sur GitHub↗26,326
  • inclusionai/arealAvatar de inclusionAI

    inclusionAI/AReaL

    3,559Voir sur GitHub↗

    AReaL is a system for agent orchestration, distributed model training, and parameter-efficient tuning. It provides a framework for developing multi-turn reasoning agents and training large models using reinforcement learning from human feedback. The project implements a toolkit for improving the visual reasoning and geometry problem solving capabilities of vision-language models. It utilizes a memory-efficient tuning system to optimize mathematical and reasoning models across different inference backends. The infrastructure supports large-scale training through tensor, pipeline, and expert p

    Pythonagentllmllm-agent
    Voir sur GitHub↗3,559
  • hiyouga/easyr1Avatar de hiyouga

    hiyouga/EasyR1

    5,034Voir sur GitHub↗

    EasyR1 is a distributed model training system and reinforcement learning framework for large language and vision-language models. It functions as a multimodal trainer and an implementation of a Proximal Policy Optimization pipeline designed to refine the reasoning and perception capabilities of models that process both text and images. The system specializes in distributing reinforcement learning workloads across multiple compute nodes to manage high memory requirements. It optimizes hardware utilization through padding-free training and fine-tuning to fit large models onto available graphics

    Python
    Voir sur GitHub↗5,034
Voir les 30 alternatives à TinyZero→

Questions fréquentes

Que fait jiayi-pan/tinyzero ?

TinyZero is a reinforcement learning framework and implementation designed to train language models to develop reasoning and self-verification abilities. It provides a training pipeline to optimize model performance on mathematical and logical tasks.

Quelles sont les fonctionnalités principales de jiayi-pan/tinyzero ?

Les fonctionnalités principales de jiayi-pan/tinyzero sont : Reinforcement Learning Alignment, Chain-of-Thought Prompting, Model Fine-Tuning, Self-Correction Loops, Reasoning Model Training Suites, Reasoning Models, Reinforcement Learning Optimizers, Reinforcement Learning Training Pipelines.

Quelles sont les alternatives open-source à jiayi-pan/tinyzero ?

Les alternatives open-source à jiayi-pan/tinyzero incluent : deepseek-ai/deepseek-r1 — DeepSeek-R1 is an open-weights large language model focused on advanced reasoning. It uses chain-of-thought processing… huggingface/open-r1 — Open-r1 is a framework designed for the large-scale training, distillation, and optimization of language models… inclusionai/areal — AReaL is a system for agent orchestration, distributed model training, and parameter-efficient tuning. It provides a… hiyouga/easyr1 — EasyR1 is a distributed model training system and reinforcement learning framework for large language and… openmanus/openmanus-rl — OpenManus-RL is a reinforcement learning framework and distributed training pipeline designed to train large language… volcengine/verl — verl is a distributed training system designed for large language model alignment and reinforcement learning. It…