Instructions to use naver-hyperclovax/HyperCLOVAX-SEED-Think-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use naver-hyperclovax/HyperCLOVAX-SEED-Think-14B with Transformers:

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

pipe = pipeline("text-generation", model="naver-hyperclovax/HyperCLOVAX-SEED-Think-14B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("naver-hyperclovax/HyperCLOVAX-SEED-Think-14B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("naver-hyperclovax/HyperCLOVAX-SEED-Think-14B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use naver-hyperclovax/HyperCLOVAX-SEED-Think-14B 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-Think-14B"
# 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-Think-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/naver-hyperclovax/HyperCLOVAX-SEED-Think-14B

SGLang

How to use naver-hyperclovax/HyperCLOVAX-SEED-Think-14B 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-Think-14B" \
    --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-Think-14B",
		"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-Think-14B" \
        --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-Think-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use naver-hyperclovax/HyperCLOVAX-SEED-Think-14B with Docker Model Runner:
```
docker model run hf.co/naver-hyperclovax/HyperCLOVAX-SEED-Think-14B
```

Request to Update API Example Path

by sionic - opened Jul 22, 2025

Discussion

sionic

Jul 22, 2025

I'd like to request a minor update to the vLLM API usage example.

Currently, the example uses the path /v1/completions, but vLLM only supports the /generate path. Please update the example as follows:

curl http://localhost:8000/generate \
-H "Content-Type: application/json" \
-d '{
  "prompt": "<|im_start|>tool_list\n<|im_end|>\n<|im_start|>system\n- The AI language model is named \"CLOVA X\" and was developed by NAVER.\n- Today is Friday, July 18, 2025.<|im_end|>\n<|im_start|>user\nExplain in as much detail as possible the relationship between the Schrödinger equation and quantum mechanics.<|im_end|>\n<|im_start|>assistant/think\n",
  "top_k": -1,
  "temperature": 0.5,
  "top_p": 0.6,
  "repetition_penalty": 1.05,
  "stop": ["<|im_end|><|endofturn|>", "<|im_end|><|stop|>"],
  "max_tokens": 8192,
  "skip_special_tokens": false
}'

Thank you!

lssj14

Jul 22, 2025

•

edited Jul 22, 2025

Hello, Sionic,

You're right, the example wasn't using the OpenAI API server, so we should update the API endpoint accordingly.
Thank you for pointing that out!

hyperclovax

HyperCLOVA X org Jul 22, 2025

Hello Sionic,

Thank you so much for your interest in our model and for taking the time to point out the issue in the README.
We’ve updated the README to reflect your feedback and have replaced the previous example with one using vllm.entrypoints.openai.api_server as you suggested.

We really appreciate your help!

hyperclovax changed discussion status to closed Jul 23, 2025

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