Instructions to use jiwon9703/gemma-4-26B-A4B-ko-sft-v1.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jiwon9703/gemma-4-26B-A4B-ko-sft-v1.1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="jiwon9703/gemma-4-26B-A4B-ko-sft-v1.1")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("jiwon9703/gemma-4-26B-A4B-ko-sft-v1.1")
model = AutoModelForImageTextToText.from_pretrained("jiwon9703/gemma-4-26B-A4B-ko-sft-v1.1")
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 jiwon9703/gemma-4-26B-A4B-ko-sft-v1.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jiwon9703/gemma-4-26B-A4B-ko-sft-v1.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jiwon9703/gemma-4-26B-A4B-ko-sft-v1.1",
		"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/jiwon9703/gemma-4-26B-A4B-ko-sft-v1.1

SGLang

How to use jiwon9703/gemma-4-26B-A4B-ko-sft-v1.1 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 "jiwon9703/gemma-4-26B-A4B-ko-sft-v1.1" \
    --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": "jiwon9703/gemma-4-26B-A4B-ko-sft-v1.1",
		"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 "jiwon9703/gemma-4-26B-A4B-ko-sft-v1.1" \
        --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": "jiwon9703/gemma-4-26B-A4B-ko-sft-v1.1",
		"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 jiwon9703/gemma-4-26B-A4B-ko-sft-v1.1 with Docker Model Runner:
```
docker model run hf.co/jiwon9703/gemma-4-26B-A4B-ko-sft-v1.1
```

gemma-4-26B-A4B-ko-sft-v1.1

Gemma4-26B-A4B 한국어 SFT v1.1 — reasoning(openthoughts/click_augment/kmmlu/komagpie) + 일반 응답 혼합. LoRA r=16, 1 epoch, LR 5e-5.

모델 정보

항목	내용
Base Model	unsloth/gemma-4-26B-A4B-it
학습 방법	LoRA SFT (Unsloth + TRL)
프레임워크	transformers, peft
라이센스	Apache 2.0

사용법

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("jiwon9703/gemma-4-26B-A4B-ko-sft-v1.1")
tokenizer = AutoTokenizer.from_pretrained("jiwon9703/gemma-4-26B-A4B-ko-sft-v1.1")

vLLM 서빙

vllm serve jiwon9703/gemma-4-26B-A4B-ko-sft-v1.1 --max-model-len 8192 --reasoning-parser gemma4

Downloads last month: 8

Safetensors

Model size

26B params

Tensor type

BF16

Model tree for jiwon9703/gemma-4-26B-A4B-ko-sft-v1.1

Base model

google/gemma-4-26B-A4B

Finetuned

google/gemma-4-26B-A4B-it

Finetuned

unsloth/gemma-4-26B-A4B-it

Finetuned

(12)

this model