---
library_name: transformers
tags: []
---

# HumanF-MarkrAI/Gukbap-Gemma2-9B-VL🍚

## Model Details🍚

### Model Description
- **Developed by:** HumanF-MarkrAI
- **Model type:** Korean-VL-Gemma2-9B
- **Language(s):** Korean + English
- **Context Length:** 2048
- **License:** cc-by-nc-4.0
- **Finetuned from model:** [AIDC-AI/Ovis1.6-Gemma2-9B](https://huggingface.co/AIDC-AI/Ovis1.6-Gemma2-9B).  
  
### Model Sources
When training, we used `H100 80GB GPU`x4.

  
### Implications🍚
If you want to know our model's details, please see [🔥Gukbap-LMM Blog🔥](coming_soon).  
And also, we provided the Korean-LMM training code based Ovis!! [🔥Github🔥](coming_soon). Please star⭐⭐!!

  
### Training Method (SFT)🧐
The following papers contain the foundational methodologies for the dataset and training methods we are currently proceeding.  
- [LIMA](https://arxiv.org/abs/2305.11206).
- [Ovis](https://arxiv.org/abs/2405.20797).  

  
### SFT Text-Datasets (Private)
When we made the `Open-Source based dataset`, we use `microsoft/WizardLM-2-8x22B` through [DeepInfra](https://deepinfra.com/).  
Our datasets are made by `Evolving system`, which is propsed by [WizardLM](https://wizardlm.github.io/WizardLM2/).
In training, we used 1849 training dataset, and 200 validation dataset.
  
- **Wizard-Korea-Datasets:** [MarkrAI/Markr_WizardLM_train_ver4](https://huggingface.co/datasets/MarkrAI/Markr_WizardLM_train_ver4).   
> Learning rate: 1e-5; Epoch: 2

    
## Benchmakrs🤗

### Global MM Benchmark Score (Zero-shot)

We internally evaluated [VLMEvalKit](https://github.com/open-compass/VLMEvalKit?tab=readme-ov-file).  
We utilized **chatgpt-0125**, **gpt-4o-mini** and **gpt-4-turbo** in `MMBench`, `MathVista` and `MMVet`, respectively.  
   
| Model | MMStar | MathVista | HallusionBench | AI2D | OCRBench | MMVet | MMBench_V11 | AVG |
|:---------:|:-----:|:------:|:-----:|:-----:|:----:|:-----:|:-----:|:-----:|
| Step-1o (closed model) | 69.3 | **74.7** | **89.1** | 55.8 | **92.6** | **82.8** | 87.3 | **78.8** |
| InternVL2.5-78B-MPO (Open) | **72.1** | 76.6 | 58.1 | **89.2** | 90.9 | 73.5 | **87.8** | 78.3 |
| InternVL2.5-38B-MPO (Open) | 70.1 | 73.6 | 59.7 | 87.9 | 89.4 | 72.6 | 85.4 | 77.0 |
| Ovis1.6-Gemma2-27B (Open) | 63.5 | 70.1 | 54.1 | 86.6 | 85.6 | 68.0 | 82.2 | 72.9 |
| Gemini-2.0-Flash | 69.4 | 70.4 | 58.0 | 83.1 | 82.5 | 73.6 | 71.0 | 72.6 |
| GPT-4o-20241120 | 65.1 | 59.9 | 56.2 | 84.9 | 80.6 | 74.5 | 84.3 | 72.2 |
| **Ovis1.6-Gemma2-9B (Open)** | 62.00 | 67.10 | 84.42 | 51.96 | 82.60 | 64.68 | 82.20 | 70.71 |
|:---------:|:-----:|:------:|:-----:|:-----:|:----:|:-----:|:-----:|:-----:|
| **Gukbap-Gemma2-9B-VL🍚** | 62.13 | 66.00 | 84.49 | 53.01 | 82.80 | 63.90 | 82.20 | **70.65** |
|:---------:|:-----:|:------:|:-----:|:-----:|:----:|:-----:|:-----:|:-----:|
| LLaVA-OneVision-72B | 65.8 | 68.4 | 47.9 | 86.2 | 74.1| 60.6 | 84.5 | 69.6 |
| VARCO-VISION-14B (NCSoft) | 64.1 | 67.6 | 46.8 | 83.9 | 81.5 | 53.0 | 81.2 | 68.3 |
| GPT-4o-mini-20240718 | 54.8 | 52.4 | 46.1 | 77.8 | 78.5 | 66.9 | 76.0 | 64.6 |
> HallusionBench score: (aAcc + fAcc + qAcc) / 3
  
### Korean MM Benchmark Score (Zero-shot)

We internally evaluated [our code](coming_soon).  
We utilized **gpt-4o-2024-08-06** in `K-LLAVA-W` evaluation.  
  
| Model | K-MMBench | K-MMStar | K-DTCBench | K-LLAVA-W | AVG |
|:---------:|:-----:|:------:|:-----:|:-----:|:----:|
| GPT-4o-20241120 | NaN | NaN | NaN | **85.50** | NaN |
|:---------:|:-----:|:------:|:-----:|:-----:|:----:|
| **Gukbap-Gemma2-9B-VL🍚** | 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
- Global MM Bench dataset: [OpenCampass MM leaderboard](https://rank.opencompass.org.cn/leaderboard-multimodal)
- Korean MM Bench dataset: [NCSOFT](https://huggingface.co/NCSOFT).


## Chat Prompt😶‍🌫️
```yaml
<start_of_turn>user<image>
Hello! My favorite food is Gukbap🍚!<end_of_turn>
<start_of_turn>model
(model answer)
```

     
## Gukbap-VL Series models🍚🍚
- [HumanF-MarkrAI/Gukbap-Qwen2.5-34B-VL](https://huggingface.co/HumanF-MarkrAI/Gukbap-Qwen2.5-34B-VL)
   
  
## BibTeX
```
@article{HumanF-MarkrAI,
  title={Gukbap-Gemma2-9B-VL},
  author={MarkrAI},
  year={2025},
  url={https://huggingface.co/HumanF-MarkrAI}
}
```