Instructions to use JGOS-Model/JGOS-31B-Citizen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JGOS-Model/JGOS-31B-Citizen with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="JGOS-Model/JGOS-31B-Citizen")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("JGOS-Model/JGOS-31B-Citizen")
model = AutoModelForImageTextToText.from_pretrained("JGOS-Model/JGOS-31B-Citizen")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use JGOS-Model/JGOS-31B-Citizen with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JGOS-Model/JGOS-31B-Citizen"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JGOS-Model/JGOS-31B-Citizen",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/JGOS-Model/JGOS-31B-Citizen

SGLang

How to use JGOS-Model/JGOS-31B-Citizen with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "JGOS-Model/JGOS-31B-Citizen" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JGOS-Model/JGOS-31B-Citizen",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "JGOS-Model/JGOS-31B-Citizen" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JGOS-Model/JGOS-31B-Citizen",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use JGOS-Model/JGOS-31B-Citizen with Docker Model Runner:
```
docker model run hf.co/JGOS-Model/JGOS-31B-Citizen
```

JGOS-31B-Citizen

#1 on the K-AI Leaderboard

🏆 #1 on the K-AI Leaderboard · Korea's national Korean-language AI benchmark (leaderboard.aihub.or.kr)

JGOS-31B-Citizen is a Korean, multimodal large language model specialized for administrative & public-sector AI services — 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

Item	Value
Parameters	~31B (dense)
Modality	Text + Image (multimodal)
Context length	up to 256K tokens
Base family	gemma4-31b (Gemma-compatible architecture)
Focus	Administrative & public-sector AI services

Highlights

🏆 #1 on the K-AI Leaderboard — Korea's national Korean-language AI benchmark (KMMLU-Pro · CLIcK · HLE · MuSR · Com2)
GPQA Diamond: 84.34%

Evaluation

GPQA Diamond (198 questions)

Method (test-time compute)	Score
maj@8 + tie-retry + DELPHI + near-miss maj@32-64 (weighted vote)	84.34% (167/198)

Training Datasets

JGOS-31B-Citizen was trained using large-scale Korean corpora sourced from the Korean AI Hub (AIHub) — 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):

#	Dataset Name	AIHub Link
1	Medical and Legal Professional Books Corpus	71487
2	Financial and Legal Document Machine Reading Comprehension	71610
3	Large-scale Web-based Korean Corpus	624
4	Large-scale Book-based Korean Corpus	653
5	National Records Large-scale AI Learning Corpus	71788
6	Korean Generation-based Common Sense Reasoning Dataset	459
7	Multi-session Dialogue Corpus	pkg1
8	Essential Medical Knowledge Data (142GB)	71875
9	Specialized Medical Knowledge Data (206GB)	71874
10	Korean Dialogue Dataset	272

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.

Downloads last month: 180

Safetensors

Model size

31B params

Tensor type

BF16

Evaluation results

Diamond on Idavidrein/gpqa View evaluation results leaderboard

84.34 ^*