five

typhoon-r1-sft-data

收藏
魔搭社区2025-12-05 更新2025-06-14 收录
下载链接:
https://modelscope.cn/datasets/scb10x/typhoon-r1-sft-data
下载链接
链接失效反馈
官方服务:
资源简介:
# Typhoon2 R1 Preview Data ## Overview This dataset is used to align Typhoon2-70B Instruct with DeepSeek-R1-70B Distill for the final merge. It is based on [https://arxiv.org/abs/2502.09056](https://arxiv.org/abs/2502.09056) SFTv3 configuration. ## Citation ``` @misc{pipatanakul2025adaptinglanguagespecificllmsreasoning, title={Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging - An Open Recipe}, author={Kunat Pipatanakul and Pittawat Taveekitworachai and Potsawee Manakul and Kasima Tharnpipitchai}, year={2025}, eprint={2502.09056}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2502.09056}, } ```

# Typhoon2 R1 预览数据集 ## 概述 本数据集用于将Typhoon2-70B Instruct与DeepSeek-R1-70B Distill进行对齐,以支撑最终的模型合并工作。其基于[https://arxiv.org/abs/2502.09056](https://arxiv.org/abs/2502.09056) 中的监督微调v3(SFTv3)配置构建。 ## 引用 @misc{pipatanakul2025adaptinglanguagespecificllmsreasoning, title={《基于模型合并的单日语言专用大语言模型向推理模型转型——一份开源方案》}, author={Kunat Pipatanakul and Pittawat Taveekitworachai and Potsawee Manakul and Kasima Tharnpipitchai}, year={2025}, eprint={2502.09056}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2502.09056}, }
提供机构:
maas
创建时间:
2025-05-23
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作