Instructions to use naver-hyperclovax/HyperCLOVAX-SEED-Vision-Instruct-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use naver-hyperclovax/HyperCLOVAX-SEED-Vision-Instruct-3B with Transformers:

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

pipe = pipeline("text-generation", model="naver-hyperclovax/HyperCLOVAX-SEED-Vision-Instruct-3B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("naver-hyperclovax/HyperCLOVAX-SEED-Vision-Instruct-3B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use naver-hyperclovax/HyperCLOVAX-SEED-Vision-Instruct-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "naver-hyperclovax/HyperCLOVAX-SEED-Vision-Instruct-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "naver-hyperclovax/HyperCLOVAX-SEED-Vision-Instruct-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/naver-hyperclovax/HyperCLOVAX-SEED-Vision-Instruct-3B

SGLang

How to use naver-hyperclovax/HyperCLOVAX-SEED-Vision-Instruct-3B 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 "naver-hyperclovax/HyperCLOVAX-SEED-Vision-Instruct-3B" \
    --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": "naver-hyperclovax/HyperCLOVAX-SEED-Vision-Instruct-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "naver-hyperclovax/HyperCLOVAX-SEED-Vision-Instruct-3B" \
        --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": "naver-hyperclovax/HyperCLOVAX-SEED-Vision-Instruct-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use naver-hyperclovax/HyperCLOVAX-SEED-Vision-Instruct-3B with Docker Model Runner:
```
docker model run hf.co/naver-hyperclovax/HyperCLOVAX-SEED-Vision-Instruct-3B
```

가중치 4비트 양자화 후 예시 코드의 vlm_chat 실행 불가

#13

by gowns - opened Apr 30, 2025

Discussion

gowns

Apr 30, 2025

다음과 같은 코드로 4비트 양자화 했습니다.

quantization_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_compute_dtype=torch.float32,
    bnb_4bit_use_double_quant=True,
    bnb_4bit_quant_type="nf4"
)


model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, quantization_config=quantization_config, torch_dtype=torch.float32).to(device="cuda")
preprocessor = AutoProcessor.from_pretrained(model_name, trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name)

양자화 적용 전에는 정상적으로 실행되는 것을 확인했습니다. 양자화 적용 후에는 예시의 chat 부분은 정상적으로 실행되나 vlm_chat 부분에서 첨부한 이미지와 같은 에러가 발생합니다. 설정이 잘 못 된 것일까요?

DongHyunKim

May 21, 2025

저희 hyperclovax 모델에 관심을 가져 주셔서 감사합니다.

모델은 byte 로 양자화되어 있지만, input 은 양자화되어있지 않아 생기는 이슈로 보입니다.
내부적으로도 양자화 모델은 아직 제공하고 있지 않아, 도움을 드리긴 어려울 것 같습니다.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment