What are the main features of open-reasoner-zero/open-reasoner-zero?

The main features of open-reasoner-zero/open-reasoner-zero are: Critic-Based Algorithms, Frontier Reasoning Models, Reasoning Datasets, Reasoning Models, Reinforcement Learning Frameworks.

What are some open-source alternatives to open-reasoner-zero/open-reasoner-zero?

Open-source alternatives to open-reasoner-zero/open-reasoner-zero include: agentica-project/rllm — 🚀 Reinforcement Learning for Language Agents🌟. skyworkai/skywork-or1 — ✊ Unleashing the Power of Reinforcement Learning for Math and Code Reasoners 🤖. hiyouga/easyr1 — EasyR1 is a distributed model training system and reinforcement learning framework for large language and… deep-agent/r1-v. gair-nlp/limo — 📄 Paper | 🌐 Dataset (v2) | 📘 Model (v2). deepseek-ai/deepseek-r1 — DeepSeek-R1 is an open-weights large language model focused on advanced reasoning. It uses chain-of-thought processing…

Open Reasoner Zero - scale RL on base LLMs

Name: open-reasoner-zero/open-reasoner-zero
Author: Open-Reasoner-Zero

An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model

Features

Critic-Based Algorithms - Scaling reinforcement learning on base models using open approaches.
Frontier Reasoning Models - Approach for scaling reinforcement learning on base models.
Reasoning Datasets - Scaling reinforcement learning on base models.
Reasoning Models - Zero-shot reasoning model implementation.
Reinforcement Learning Frameworks - Implementation of reasoning models trained with minimal data.

How this analysis was created: This summary and feature list were written by an AI model that read the project's README and public documentation pages. Each feature links to the documentation it came from; stars, license and language come straight from the GitHub API. The model does not read the source code, and the analysis is refreshed when the project is re-analysed. Learn more on our About page.

An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model

Features

Critic-Based Algorithms - Scaling reinforcement learning on base models using open approaches.
Frontier Reasoning Models - Approach for scaling reinforcement learning on base models.
Reasoning Datasets - Scaling reinforcement learning on base models.
Reasoning Models - Zero-shot reasoning model implementation.
Reinforcement Learning Frameworks - Implementation of reasoning models trained with minimal data.

SkyworkAI/Skywork-OR1

745View on GitHub

✊ Unleashing the Power of Reinforcement Learning for Math and Code Reasoners 🤖

agentica-project/rllm

400View on GitHub

🚀 Reinforcement Learning for Language Agents🌟

deepseek-ai/DeepSeek-R1

91,996View on 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

Deep-Agent/R1-V

0View on GitHub