GD-ML/Open-RS1

Model

GPG: A Simple and Strong Reinforcement Learning

8 commits

1 linked in READMEs

updated May 8, 2025

See the code

README

GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning https://arxiv.org/abs/2504.02546

The RL model trained on the Open-r1 dataset based on GPG, using DeepSeek-R1-Distill-Qwen-1.5B as the baseline model.

qwen2

safetensors

Contributors

xiao23451

8 commits

Similar repos

GD-ML/Qwen2.5-Math-7B-GPG

Model

Model ID

Simple-Efficient/RLFactory-Qwen3-8B-GRPO

Model

AMAP-ML/GPG

[ICLR26]GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning

181

htxu91/zero-tir-7b-550step

Model

konkazzz/GT-r1

Model

TencentBAC/ReSeek-qwen2.5-3b-em-grpo

Model

Yuqian-Fu/SRFT-Qwen2.5-Math-7B

Model

📄 Introduction

deepseek-ai/DeepSeek-R1-Distill-Qwen-32B

Model

DeepSeek-R1

1,624

Linked in READMEs

AMAP-ML/GPG

[ICLR26]GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning

181

README badge

GD-ML/Open-RS1

Model

GPG: A Simple and Strong Reinforcement Learning

8 commits

1 linked in READMEs

updated May 8, 2025

See the code

README

GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning https://arxiv.org/abs/2504.02546

The RL model trained on the Open-r1 dataset based on GPG, using DeepSeek-R1-Distill-Qwen-1.5B as the baseline model.

qwen2

safetensors

Similar repos

GD-ML/Qwen2.5-Math-7B-GPG

Model

Model ID

Simple-Efficient/RLFactory-Qwen3-8B-GRPO

Model

AMAP-ML/GPG

[ICLR26]GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning

181

htxu91/zero-tir-7b-550step

Model

konkazzz/GT-r1

Model

TencentBAC/ReSeek-qwen2.5-3b-em-grpo

Model

Yuqian-Fu/SRFT-Qwen2.5-Math-7B

Model

📄 Introduction

deepseek-ai/DeepSeek-R1-Distill-Qwen-32B

Model

DeepSeek-R1

1,624

Linked in READMEs

AMAP-ML/GPG

[ICLR26]GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning

181

README badge

Contributors

xiao23451

8 commits