Instructions to use naver-hyperclovax/HyperCLOVAX-SEED-Omni-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use naver-hyperclovax/HyperCLOVAX-SEED-Omni-8B with Transformers:

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

pipe = pipeline("text-generation", model="naver-hyperclovax/HyperCLOVAX-SEED-Omni-8B", 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-Omni-8B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use naver-hyperclovax/HyperCLOVAX-SEED-Omni-8B 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-Omni-8B"
# 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-Omni-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/naver-hyperclovax/HyperCLOVAX-SEED-Omni-8B

SGLang

How to use naver-hyperclovax/HyperCLOVAX-SEED-Omni-8B 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-Omni-8B" \
    --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-Omni-8B",
		"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-Omni-8B" \
        --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-Omni-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use naver-hyperclovax/HyperCLOVAX-SEED-Omni-8B with Docker Model Runner:
```
docker model run hf.co/naver-hyperclovax/HyperCLOVAX-SEED-Omni-8B
```

NOTICE : Major Code Update Scheduled for March (vLLM, Refactoring, BC-BREAK)

by bigshanedogg - opened Mar 9

Discussion

bigshanedogg

Mar 9

We have a major code update scheduled for March, 2025.
This update will introduce significant changes to the model's input/output format and processor's input/output format, resulting in breaking changes (BC-break).
To ensure existing users can continue using the current functionality without disruption, we plan to tag the current version. Users who wish to maintain the existing behavior are advised to use the revision argument.

Schedule

Update 1 — vLLM Support (Expected within ~1 week)
Will be released alongside the corresponding vLLM-compatible PR.

Update 2 — HuggingFace-Compatible Support (Expected in March)
Full HF-native compatibility support is planned for later in March, along with the release of the HF-compatible 32B model.

Thank you for your continued interest and support for our model.
HyperCLOVA Team.

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