SOLAR_Merge_Adapter_DPO_Orca/README.md

license, datasets, language, pipeline_tag

license	datasets	language	pipeline_tag
cc-by-nc-4.0	Intel/orca_dpo_pairs	en	text-generation

Explanation

• Merge two base models using mergekit (slerp)
• Apply DPO to the merged model, just an adapter part is saved
• merge the adpater and the merged model

Base Model

• upstage/SOLAR-10.7B-Instruct-v1.0
• beomi/OPEN-SOLAR-KO-10.7B

Training Corpus

• Intel/orca_dpo_pairs

Score

Average	ARC	HellaSwag	MMLU	TruthfulQA	Winogrande	GSM8K
65.96	63.91	84.58	63.18	51.49	82	50.57

Log

• 2024.02.05: Initial version Upload
• 2024.02.10: Readme update

LICENSE
Following the upstage/SOLAR-10.7B-Instruct-v1.0 License

• cc-by-nc-4.0

Citation

• beomi/OPEN-SOLAR-KO-10.7B

@misc {solar_ko_junbum_2023,
    author       = { {L. Junbum} },
    title        = { Solar-Ko-10.7b },
    year         = 2024,
    url          = { https://huggingface.co/beomi/SOLAR-KO-10.7B },
    publisher    = { Hugging Face }
}

• upstage/SOLAR-10.7B-Instruct-v1.0

@misc{kim2023solar,
      title={SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling}, 
      author={Dahyun Kim and Chanjun Park and Sanghoon Kim and Wonsung Lee and Wonho Song and Yunsu Kim and Hyeonwoo Kim and Yungi Kim and Hyeonju Lee and Jihoo Kim and Changbae Ahn and Seonghoon Yang and Sukyung Lee and Hyunbyung Park and Gyoungjin Gim and Mikyoung Cha and Hwalsuk Lee and Sunghun Kim},
      year={2023},
      eprint={2312.15166},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}