JGOS-Model/JGOS-31B-Citizen
JGOS-31B-Citizen
<p align="center"> <img src="https://huggingface.co/JGOS-Model/JGOS-31B-Citizen/resolve/main/k-ai.png" alt="#1 on the K-AI Leaderboard" width="780"/> </p>
<p align="center"> ๐ <b>#1 on the K-AI Leaderboard</b> · Korea's national Korean-language AI benchmark (<a href="https://leaderboard.aihub.or.kr/leaderboard">leaderboard.aihub.or.kr</a>) </p>
JGOS-31B-Citizen is a Korean, multimodal large language model specialized for administrative & public-sector AI services โ civil-complaint response, public-document understanding, and government-domain question answering.
Overview
JGOS-31B-Citizen is built on VIDRAFT's Darwin V8 platform.
- Base + FFN transfer, breeding & evolution (Darwin V8). Starting from our in-house gemma4-31b base, the feed-forward network (FFN) blocks of multiple source models are extracted and grafted, then bred (merged) and evolved across multiple generations through the Darwin V8 pipeline to accumulate capability.
- Korean administrative-domain fine-tuning. The evolved model is further trained on Korean-specialized datasets to strengthen Korean comprehension, reasoning, and administrative/public-sector domain performance.
The set of grafted source models, the number of evolution generations, the breeding strategy, dataset composition, and training configuration are proprietary and not disclosed.
Specifications
Highlights
- ๐ #1 on the K-AI Leaderboard โ Korea's national Korean-language AI benchmark (KMMLU-Pro ยท CLIcK ยท HLE ยท MuSR ยท Com2)
- GPQA Diamond: 84.34%
Evaluation
GPQA Diamond (198 questions)
Training Datasets
JGOS-31B-Citizen was trained using large-scale Korean corpora sourced from the Korean AI Hub (AIHub) โ Korea's national AI data repository operated by NIA. The following datasets were used to optimize performance on the K-AI Leaderboard benchmarks (KoMMLU-Pro, CLIcK, HLE, MuSR, Com2):
All datasets are publicly available via AIHub (registration required).
License
This model is built on a Gemma-family architecture and is distributed under the **Gemma Terms of Use**. By using this model, you agree to the Gemma license terms.
