SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling

Sanghoon Kim, Dahyun Kim, Chanjun Park, Wonsung Lee, Wonho Song, Yunsu Kim, Hyeonwoo Kim, Yungi Kim, Hyeonju Lee, Jihoo Kim, Changbae Ahn, Seonghoon Yang, Sukyung Lee, Hyunbyung Park, Gyoungjin Gim, Mikyoung Cha, Hwalsuk Lee, Sunghun Kim


Abstract
We introduce SOLAR 10.7B, a large language model (LLM) with 10.7 billion parameters, demonstrating superior performance in various natural language processing (NLP) tasks. Inspired by recent efforts to efficiently up-scale LLMs, we present a method for scaling LLMs called depth up-scaling (DUS), which encompasses depthwise scaling and continued pretraining. In contrast to other LLM up-scaling methods that use mixture-of-experts, DUS does not require complex changes to train and inference efficiently. We show experimentally that DUS is simple yet effective in scaling up high-performance LLMs from small ones. Building on the DUS model, we additionally present SOLAR 10.7B-Instruct, a variant fine-tuned for instruction-following capabilities, surpassing Mixtral-8x7B-Instruct. SOLAR 10.7B is publicly available under the Apache 2.0 license, promoting broad access and application in the LLM field.
Anthology ID:
2024.naacl-industry.3
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 6: Industry Track)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Yi Yang, Aida Davani, Avi Sil, Anoop Kumar
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
23–35
Language:
URL:
https://aclanthology.org/2024.naacl-industry.3
DOI:
10.18653/v1/2024.naacl-industry.3
Bibkey:
Cite (ACL):
Sanghoon Kim, Dahyun Kim, Chanjun Park, Wonsung Lee, Wonho Song, Yunsu Kim, Hyeonwoo Kim, Yungi Kim, Hyeonju Lee, Jihoo Kim, Changbae Ahn, Seonghoon Yang, Sukyung Lee, Hyunbyung Park, Gyoungjin Gim, Mikyoung Cha, Hwalsuk Lee, and Sunghun Kim. 2024. SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 6: Industry Track), pages 23–35, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling (Kim et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-industry.3.pdf