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
```

텍스트 전용 데이터 훈련 관련 오류 발생

#23

by Tae-Gyun - opened Jun 4, 2025

Discussion

Tae-Gyun

Jun 4, 2025

안녕하세요!
해당 모델을 텍스트 전용 데이터로 파인튜닝을 진행하려할 때 다음과 같은 오류가 발생하고 있습니다.

File "/home/work/.cache/huggingface/modules/transformers_modules/naver-hyperclovax/HyperCLOVAX-SEED-Vision-Instruct-3B/cd33a27fcc2348f809bb70b8bc0623547279bf0b/modeling_hyperclovax.py", line 621, in forward
[rank1]: inputs_embeds = self.extract_inputs_embeds(
[rank1]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank1]: File "/home/work/.cache/huggingface/modules/transformers_modules/naver-hyperclovax/HyperCLOVAX-SEED-Vision-Instruct-3B/cd33a27fcc2348f809bb70b8bc0623547279bf0b/modeling_hyperclovax.py", line 823, in extract_inputs_embeds
[rank1]: len_pixel_values = [len(pixel_value) for pixel_value in pixel_values]
[rank1]: ^^^^^^^^^^^^
[rank1]: TypeError: 'NoneType' object is not iterable

모델의 modeling_hyperclovax.py 파일에 있는 forward 메서드를 확인해보니 pixel_values 인자가 Optional로 정의되어 있지만,
extract_inputs_embeds 함수 내부에서는 pixel_values가 None인지 확인하지 않고 곧바로 순회하려는 로직이 있는 것으로 보이는데
이로 인해 pixel_values가 제공되지 않을 때 에러가 발생하는 것으로 파악하고 있습니다.

해당 모델이 순수한 텍스트 데이터만으로 훈련이 가능한지, 가능하다면 pixel_values를 어떻게 처리하는 것이 권장되는지 알려주시면 감사하겠습니다.

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