Safetensors
English
qwen2

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.

Downloads last month
928
Safetensors
Model size
1.78B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for GD-ML/Open-RS1

Finetuned
(307)
this model

Dataset used to train GD-ML/Open-RS1