HumanF-MarkrAI/Gukbap-Gemma3-4B-VL๐Ÿš

Model Details๐Ÿš

Model Description

  • Developed by: HumanF-MarkrAI
  • Model type: Korean-VL-Gemma3-4B
  • Language(s): Korean + English
  • Context Length: 2048
  • License: cc-by-4.0
  • Finetuned from model: google/gemma-3-4b-it.

Model Sources

When training, we used H100 80GB GPUx4.

Implications๐Ÿš

If you want to know our model's details, please see ๐Ÿ”ฅGukbap-LMM Blog๐Ÿ”ฅ.

Training Method (SFT)๐Ÿง

The following papers contain the foundational methodologies for the dataset and training methods we are currently proceeding.

SFT Text-Datasets (Private)

When we made the Open-Source based dataset, we use microsoft/WizardLM-2-8x22B through DeepInfra.
Our datasets are made by Evolving system, which is propsed by WizardLM. In training, we used 1849 training dataset, and 200 validation dataset.

Benchmakrs๐Ÿค—

Korean MM Benchmark Score (Zero-shot)

We internally evaluated ๐Ÿ”ฅour code๐Ÿ”ฅ.
We utilized gpt-4o-2024-08-06 in K-LLAVA-W evaluation.

Model K-MMBench K-MMStar K-DTCBench K-LLAVA-W AVG
Gukbap-Gemma3-4B๐Ÿš 74.73 40.67 44.17 60.00 54.89
gemma-3-4b-it 75.84 40.60 49.58 62.67 57.17
Gukbap-Gemma2-9B-VL๐Ÿš 80.16 54.20 52.92 63.83 62.78
Ovis1.6-Gemma2-9B 52.46 50.40 47.08 55.67 51.40
VARCO-VISION-14B 87.16 58.13 85.42 51.17 70.47
llama-3.2-Korean-Bllossom-AICA-5B 26.01 21.60 17.08 45.33 27.51

MM Benchmarks

Gukbap-VL Series models๐Ÿš๐Ÿš

BibTeX

@article{HumanF-MarkrAI,
  title={Gukbap-Gemma3-4B-VL},
  author={MarkrAI},
  year={2025},
  url={https://huggingface.co/HumanF-MarkrAI}
}
Downloads last month
17
Safetensors
Model size
4B params
Tensor type
F16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Collection including Markr-AI/Gukbap-Gemma3-4B-VL

Papers for Markr-AI/Gukbap-Gemma3-4B-VL