skandermoalla/qrpo-paper-mistral-sft-magpieair-armorm-temp1-ref50-offpolicy2random-armorm

---
license: mit
tags:
- reinforcement-learning
- alignment
- qrpo
---

# qrpo-paper-mistral-sft-magpieair-armorm-temp1-ref50-offpolicy2random-armorm

Dataset with reference completions and rewards for a specific model and reward model, ready for training with the **QRPO reference codebase** (https://github.com/CLAIRE-Labo/quantile-reward-policy-optimization).

Part of the dataset collection for the paper **Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions** (https://arxiv.org/pdf/2507.08068).

许可证：MIT许可证
标签：
- 强化学习（reinforcement learning）
- 对齐（alignment）
- QRPO

# qrpo-paper-mistral-sft-magpieair-armorm-temp1-ref50-offpolicy2random-armorm

本数据集包含针对特定模型与奖励模型的参考补全结果与奖励值，可直接用于**QRPO（Quantile Reward Policy Optimization）参考代码库**（https://github.com/CLAIRE-Labo/quantile-reward-policy-optimization）的训练。

本数据集为论文《分位数奖励策略优化：基于逐点回归与精确配分函数的对齐》（Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions，https://arxiv.org/pdf/2507.08068）的数据集集合之一部分。