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

Libraries

How to use yujuyeon/internvl3_5-8b-kth-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-kth-fullft", trust_remote_code=True)
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 AutoModel
model = AutoModel.from_pretrained("yujuyeon/internvl3_5-8b-kth-fullft", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yujuyeon/internvl3_5-8b-kth-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-kth-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-kth-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-kth-fullft

SGLang

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

internvl3_5-8b-kth-fullft

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

항목	값
Base model	`OpenGVLab/InternVL3_5-8B-Pretrained`
Method	Full FT
Domain	별도 서버 학습 — 학습 로그 미동봉. (Korean multimodal, stage1)

Hyperparameters

별도 서버 학습 — 하이퍼파라미터 로그 미동봉.

Training Loss

학습 loss 로그 미동봉 (별도 서버 학습).

Training Data

Korean multimodal SFT (stage1). 데이터 구성 비공개.

Usage

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

Downloads last month: 24

Safetensors

Model size

11B params

Tensor type

F32

BF16

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

Base model

OpenGVLab/InternVL3_5-8B-Pretrained

Finetuned

(5)

this model