KAERI-MLP/AtomicGPT-gemma3-27b
KAERI-MLP/AtomicGPT-gemma3-27b is a 27 billion parameter bilingual (Korean-English) large language model developed by KAERI-MLP. It is continually pre-trained and instruction-tuned on nuclear engineering datasets, making it specialized for nuclear-domain applications. This model excels at tasks related to reactor physics, safety, materials, and regulation within the nuclear field. It serves as an open-weight variant of the AtomicGPT architecture, enabling reproducible research in domain-specific LLM adaptation.
Loading preview...
AtomicGPT-gemma3-27b: A Specialized Nuclear-Domain LLM
AtomicGPT-gemma3-27b, developed by KAERI-MLP, is a 27 billion parameter bilingual (Korean–English) large language model built upon the Gemma3-27B-pt base. This model is uniquely specialized for the nuclear engineering domain, covering topics such as reactor physics, safety, materials, regulation, and terminology.
Key Capabilities & Training
- Domain Specialization: Achieved through continual pre-training (CPT) on extensive nuclear-domain corpora.
- Instruction Tuning: Further refined with instruction tuning (IT) using bilingual nuclear question-answering datasets.
- Bilingual Support: Proficient in both Korean and English for nuclear-related queries.
Performance Highlights
Evaluated on a bilingual nuclear-domain benchmark, AtomicGPT-gemma3-27b demonstrates significant improvements over its base model:
- MCQ (Exact Match): Achieved 49, outperforming the base Gemma3-27B-pt (35) and closely matching GPT-4 (48).
- Short Answer (F1): Scored 33.78%, surpassing the base model (22.49%) and GPT-4 (31.29%).
- Descriptive (LLM Judge): Received a score of 7.14, a notable increase from the base model's 5.23.
This model is particularly well-suited for applications requiring deep understanding and generation of content within the nuclear engineering field.