Solar Open Technical Report
By: Sungrae Park , Sanghoon Kim , Jungho Cho and more
We introduce Solar Open, a 102B-parameter bilingual Mixture-of-Experts language model for underserved languages. Solar Open demonstrates a systematic methodology for building competitive LLMs by addressing three interconnected challenges. First, to train effectively despite data scarcity for underserved languages, we synthesize 4.5T tokens of high-quality, domain-specific, and RL-oriented data. Second, we coordinate this data through a progressive curriculum jointly optimizing composition, quality thresholds, and domain coverage across 20 trillion tokens. Third, to enable reasoning capabilities through scalable RL, we apply our proposed framework SnapPO for efficient optimization. Across benchmarks in English and Korean, Solar Open achieves competitive performance, demonstrating the effectiveness of this methodology for underserved language AI development.
Similar Papers
Helios: A Foundational Language Model for Smart Energy Knowledge Reasoning and Application
Artificial Intelligence
Helps power grids work smarter and cleaner.
Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages
Computation and Language
Lets computers understand over 1,600 languages.
KORMo: Korean Open Reasoning Model for Everyone
Computation and Language
Makes smart computer talk Korean better with fake words.