Downloads · 30 days
17
3% of all-time downloads
moche-ai/jojangju-KR-31B
jojangju-KR-31B is a image-text-to-text model from moche-ai. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as gemma.
Downloads · 30 days
17
3% of all-time downloads
All-time downloads
509
Public
Parameters
31.3B
125 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors62.5 GB · 100%
From the Hugging Face model README
<a href="https://moche.ai"><img src="https://raw.githubusercontent.com/moche-ai/moche-core/main/brand/hero.gif?v=h2" width="100%" alt="moche"></a>
Korean multimodal reasoning on gemma-4-31B — text + image
🏠 moche.ai · 🎮 Playground · 📝 Blog · 💻 GitHub · 🤗 Org
</div>moche-ai는 두 계보를 함께 굴립니다. 밑바닥 코어(moche-native)는 G0→G4로 성숙해가고, 병렬로 이 병합(merge) 라인이 강한 공개 base 위에서 한국어 멀티모달을 지금 당장 증명합니다 — 같은 옴니 목표로 수렴하는 제품 트랙.
from transformers import AutoProcessor, AutoModelForImageTextToText
import torch
model_id = "moche-ai/jojangju-KR-31B"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForImageTextToText.from_pretrained(
model_id, torch_dtype=torch.bfloat16, device_map="auto")
messages = [{"role": "user", "content": [
{"type": "image", "url": "https://example.com/photo.jpg"},
{"type": "text", "text": "이 이미지를 한국어로 설명해줘."},
]}]
inputs = processor.apply_chat_template(
messages, add_generation_prompt=True, tokenize=True,
return_dict=True, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
</details>
| Item | Value |
|---|---|
| Parameters | ~31B (dense) |
| Architecture | Gemma4ForConditionalGeneration (gemma4) |
| Text layers / hidden / intermediate | 60 / 5376 / 21504 |
| Attention heads (Q / KV) | 32 / 16 |
| Modality | Text + Image (multimodal) |
| Context length | up to 262,144 tokens (256K) |
| Vocabulary | 262,144 |
| Precision | bfloat16 |
| Base | google/gemma-4-31B-it |
적응·후처리 세부 사항은 비공개(proprietary)입니다. 가중치 수준의 후처리만 수행하며, 어떤 벤치마크 평가 데이터도 학습·병합에 사용하지 않습니다.
Adaptation and post-training details are proprietary and not disclosed in this release. Only weight-level post-processing is performed, and no benchmark evaluation data is used in the process.
Protocol: generative multiple-choice, log-probability argmax over answer tokens,
apply_chat_template, single-GPU (bf16 / 4-bit nf4). Numbers below are from an internal
proxy evaluation on a held-out split (kept strictly separate from any selection signal).
Official K-AI Leaderboard (operated by AI Hub / NIA on non-public benchmark data) numbers are
pending submission and are authoritative.
아래 수치는 자체 로컬 프록시(홀드아웃) 결과이며, 공식 K-AI Leaderboard(AI Hub/NIA 운영, 비공개 벤치마크) 점수와 다를 수 있습니다. 공식 수치가 정본입니다.
| Benchmark | gemma-4-31B-it (base) | jojangju-KR-31B |
|---|---|---|
| CLIcK (한국어 문화·상식, full) | 0.840 | 0.980 |
| MuSR (다단계 추론) | 0.490 | 0.635 |
| Com2 (인과·상식 추론) | — | 0.716 |
| KMMLU* (지식, 자체 홀드아웃) | 0.646 | 0.663 |
* KMMLU-Pro–style reproduction in our own harness — not the official private leaderboard set. Official K-AI Leaderboard numbers are pending submission.
No benchmark test data is used in adaptation or merging. The held-out split is kept strictly separate from any selection signal to avoid selecting on the eval.
from transformers import AutoProcessor, Gemma4ForConditionalGeneration
import torch
model_id = "moche-ai/jojangju-KR-31B"
processor = AutoProcessor.from_pretrained(model_id)
model = Gemma4ForConditionalGeneration.from_pretrained(
model_id, torch_dtype=torch.bfloat16, device_map="auto"
)
messages = [{"role": "user", "content": [{"type": "text", "text": "대한민국 행정법의 기본 원칙을 설명해줘."}]}]
inputs = processor.apply_chat_template(
messages, add_generation_prompt=True, tokenize=True,
return_dict=True, return_tensors="pt",
).to(model.device)
out = model.generate(**inputs, max_new_tokens=512)
print(processor.decode(out[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
객관식 평가 시에는 고정 디코딩(greedy)을 권장합니다. 모델은 Gemma-4 chat template을 사용합니다.
Memory note. The 262,144-token vocabulary makes the output logits large. For single-GPU eval/serving prefer 4-bit (nf4) loading and
PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True.
Built on a Gemma-family architecture and distributed under the Gemma Terms of Use. By using this model you agree to the Gemma license terms.
Base model: google/gemma-4-31B-it.