Safetensors
English
qwen2
Open-RS1 / README.md
xiao23451's picture
Update README.md
5d3772d verified
|
raw
history blame
376 Bytes
metadata
license: apache-2.0
datasets:
  - knoveleng/open-rs
language:
  - en
metrics:
  - accuracy
base_model:
  - deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

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.