0.99zoo_op2-20+0.01teacher_op2/README.md

---
license: other
library_name: transformers
tags:
- reasoning
- context-learning
- pretraining
- synthetic-data
- transformers
---

# 0.99zoo_op2-20+0.01teacher_op2

99% zoo op2-20, 1% teacher op2 pretraining mixture. This directory contains the final op2-only pretraining checkpoint and corresponding final RL checkpoints.

This is a context B pretraining checkpoint where the teacher component uses only op2.

## Citation

```bibtex
@misc{zhang2025interplaypretrainingmidtrainingrl,
      title={On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models},
      author={Charlie Zhang and Graham Neubig and Xiang Yue},
      year={2025},
      eprint={2512.07783},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2512.07783},
}
```