Instructions to use yujuyeon/internvl3_5-8b-korean-fullft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yujuyeon/internvl3_5-8b-korean-fullft with Transformers:

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

pipe = pipeline("image-text-to-text", model="yujuyeon/internvl3_5-8b-korean-fullft")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("yujuyeon/internvl3_5-8b-korean-fullft")
model = AutoModelForMultimodalLM.from_pretrained("yujuyeon/internvl3_5-8b-korean-fullft")
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 yujuyeon/internvl3_5-8b-korean-fullft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yujuyeon/internvl3_5-8b-korean-fullft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yujuyeon/internvl3_5-8b-korean-fullft",
		"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/yujuyeon/internvl3_5-8b-korean-fullft

SGLang

How to use yujuyeon/internvl3_5-8b-korean-fullft 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 "yujuyeon/internvl3_5-8b-korean-fullft" \
    --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": "yujuyeon/internvl3_5-8b-korean-fullft",
		"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 "yujuyeon/internvl3_5-8b-korean-fullft" \
        --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": "yujuyeon/internvl3_5-8b-korean-fullft",
		"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 yujuyeon/internvl3_5-8b-korean-fullft with Docker Model Runner:
```
docker model run hf.co/yujuyeon/internvl3_5-8b-korean-fullft
```

internvl3_5-8b-korean-fullft

OpenGVLab/InternVL3_5-8B-Instruct 를 한국어 멀티모달 데이터로 파인튜닝한 InternVL3.5 specialist.

항목	값
Base model	`OpenGVLab/InternVL3_5-8B-Instruct`
Method	Full FT
Domain	한국어 종합

Hyperparameters

별도 서버 학습 — 하이퍼파라미터 로그 미동봉.

Training Loss

학습 loss 로그 미동봉 (별도 서버 학습).

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

from transformers import AutoModel, AutoTokenizer
import torch
m = AutoModel.from_pretrained("yujuyeon/internvl3_5-8b-korean-fullft", torch_dtype=torch.bfloat16,
                              trust_remote_code=True).eval().cuda()
tok = AutoTokenizer.from_pretrained("yujuyeon/internvl3_5-8b-korean-fullft", trust_remote_code=True, use_fast=False)

Downloads last month: -

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for yujuyeon/internvl3_5-8b-korean-fullft

Base model

OpenGVLab/InternVL3_5-8B-Pretrained

Finetuned

OpenGVLab/InternVL3_5-8B-Instruct

Finetuned

(3)

this model