Model Summary

Use

This is an older step-conditional control model for our paper used only for the Discussion section. You can evaluate using the information here.

Training information

Visualize in Weights & Biases

  • TRL: 0.13.0
  • Transformers: 4.48.0
  • Pytorch: 2.3.1
  • Datasets: 3.0.1
  • Tokenizers: 0.21.0

Citation

@misc{muennighoff2025s1simpletesttimescaling,
      title={s1: Simple test-time scaling}, 
      author={Niklas Muennighoff and Zitong Yang and Weijia Shi and Xiang Lisa Li and Li Fei-Fei and Hannaneh Hajishirzi and Luke Zettlemoyer and Percy Liang and Emmanuel Candรจs and Tatsunori Hashimoto},
      year={2025},
      eprint={2501.19393},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2501.19393}, 
}
Downloads last month
180
Safetensors
Model size
32.8B params
Tensor type
F32
ยท
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for simplescaling/step-conditional-control-old

Base model

Qwen/Qwen2.5-32B
Finetuned
(142)
this model

Spaces using simplescaling/step-conditional-control-old 4