---
license: other
base_model: OpenGVLab/InternVL3_5-1B
language:
- ko
- en
pipeline_tag: image-text-to-text
library_name: transformers
tags:
- internvl
- mllm
- korean
- vision-language
---

# internvl3_5-1b-korean-347k

`OpenGVLab/InternVL3_5-1B` 를 한국어 멀티모달 데이터로 파인튜닝한 InternVL3.5 specialist.

| 항목 | 값 |
|---|---|
| Base model | [`OpenGVLab/InternVL3_5-1B`](https://huggingface.co/OpenGVLab/InternVL3_5-1B) |
| Method | Full FT |
| Domain | 한국어 종합 347k |

## Hyperparameters
- num_train_epochs: `5`
- steps: `10000` / max `13575`
- train_batch_size: `2`
- peak learning_rate: `3.999999772287927e-05`

## Training Loss
- init **1.5136** → final **0.3429** (min **0.3178**)

| step | loss |
|---|---|
| 10 | 1.5136 |
| 1010 | 0.7029 |
| 2010 | 0.6294 |
| 3010 | 0.5353 |
| 4010 | 0.4988 |
| 5010 | 0.5090 |
| 6010 | 0.4190 |
| 7010 | 0.4065 |
| 8010 | 0.3964 |
| 9010 | 0.3448 |
| 10000 | 0.3429 |

## Training Data
구성: **18개 서브셋** (한국어 specialist SFT)

| subset | repeat |
|---|---|
| `aihub_visual_ShortQA_30k` | 1 |
| `hf_korLlava_Caption_20k` | 1 |
| `llava_ko_recap_30k` | 1 |
| `out_kor_llava_20k` | 1 |
| `chartRqa1_30k` | 1 |
| `chartRqa2_20k` | 1 |
| `tableVqa_Reason_20k` | 1 |
| `tableVqa_Caption_20k` | 1 |
| `aihub_subjectTxt_OCR_20k` | 1 |
| `aihub_visual_OCR_15k` | 1 |
| `kisti_arxiv_OCR_15k` | 1 |
| `kisti_hanbat_Reason_30k` | 1 |
| `kisti_documen_Reason_10k` | 1 |
| `aihub_mathMultiple_kor_M0` | 1 |
| `aihub_mathSubjective_kor_M0` | 1 |
| `kisti_hanbat_Vqa_25k` | 1 |
| `hf_latexUpdate_15k` | 1 |
| `aihub_subjectImg_Parse_10k` | 1 |

## Usage
```python
from transformers import AutoModel, AutoTokenizer
import torch
m = AutoModel.from_pretrained("yujuyeon/internvl3_5-1b-korean-347k", torch_dtype=torch.bfloat16,
                              trust_remote_code=True).eval().cuda()
tok = AutoTokenizer.from_pretrained("yujuyeon/internvl3_5-1b-korean-347k", trust_remote_code=True, use_fast=False)
```