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
```

max_new_tokens Issue

by JungZoona - opened Apr 24, 2025

Discussion

JungZoona

Apr 24, 2025

First of all, thank you for sharing such a great model.

I just wanted to report that in the VLM Example section of the example code in the model card, setting max_new_tokens does not seem to control the number of output tokens. On the other hand, setting max_length does apply the token limit as expected.

While max_new_tokens works as intended in the LLM Example section, it doesn't seem to function properly in the VLM Example.

Could you please check if max_new_tokens is being applied correctly?

DongHyunKim

Apr 24, 2025

Hello, and thank you for bringing this to our attention. We apologize for any inconvenience caused.
As you pointed out, We've noticed max_new_tokens is not being applied correctly.
This appears to be a bug in the modeling_hyperclovax, and we will correct it promptly.
Thank you for letting us know.

DongHyunKim

Apr 24, 2025

Model code has been updated. Can you try once more? (with removal of a local machine's hf-cache?)

JungZoona

Apr 24, 2025

Thank you for the quick feedback and update!

I checked the updated modeling_hyperclovax.py and confirmed that **kwargs has been added to the call to self.language_model.generate() inside the generate() function, which is great.

However, when I call generate() and explicitly pass max_new_tokens, the following error occurs:

TypeError: generate() got multiple values for keyword argument 'max_new_tokens'

The issue seems to come from this line inside the same function, where self.language_model.generate() is called like this:

pred = self.language_model.generate(
    ...
    max_new_tokens=max_length,
    ...
    **kwargs,
)

In this structure, when max_new_tokens is passed externally via **kwargs, it conflicts with the explicitly set max_new_tokens=max_length, resulting in the error above.

Additionally, since max_length has a default value of 196, this causes the model to always generate 196 tokens, regardless of the max_new_tokens value provided externally. So even when the error is avoided, the max_new_tokens parameter is effectively ignored.

Just wanted to share this in case further refinement is needed.

DongHyunKim

Apr 24, 2025

•

edited Apr 24, 2025

This is quite a serious bug. :(
The behaviors of max_length and max_new_tokens should clearly be different.
I've updated the code and completed some tests.

Thank you for bringing this to our attention.

JungZoona changed discussion status to closed Apr 25, 2025

WatsonOverHere

Jun 7, 2025

Jung, could you please approve my request for the Qwen 2.5 gated LoRa adapters? Thank you kindly!!!

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