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
- Transformers
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, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- 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
File size: 4,256 Bytes
82f2e21 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 | <|im_start|>tool_list
<|im_end|>
{% for message in messages %}
{% set content = message['content'] %}
{% set role = message['role'] %}
{% if loop.first and role != 'system' %}
<|im_start|>system
You are a helpful assistant.<|im_end|>
{% endif %}
{% if message['content'] is string %}
<|im_start|>{{ role }}
{{ message['content'] }}<|im_end|>
{% elif message['content'] is mapping %}
{% if content['type'] == 'image' %}
<|im_start|>{{ role }} (mime)
{"type": "image/jpeg", "filename": "{{ content['filename'] }}"}<|im_end|>
<|im_start|>{{ role }} (vector)
<|dummy3|><|im_end|>
<|im_start|>image/aux
다음 중 ocr은 사진에서 검출된 글자이고, lens_keyword는 사진에서 추출된 keyword와 bbox 위치입니다. bbox는 0~1 사이로 정규화된 [x1, y1, x2, y2]의 형태입니다. 참고하여 답변하세요. {"ocr": "{{ content['ocr'] or '' }}", "lens_keywords": "{{ content['lens_keywords'] or '' }}", "lens_local_keywords": "{{ content['lens_local_keywords'] or '' }}"}<|im_end|>
{% elif content['type'] == 'video' %}
<|im_start|>{{ role }} (mime)
{"type": "video/mp4", "filename": "{{ content['filename'] }}"}<|im_end|>
<|im_start|>{{ role }} (vector)
<|_unuse_missing_100270|><|im_end|>
<|im_start|>image/aux
{% if content.get('is_final_grid') %}
다음 중 lens_keyword는 사진에서 추출된 keyword와 bbox 위치입니다. bbox는 0~1 사이로 정규화된 [x1, y1, x2, y2]의 형태입니다. video_time_stamp는 비디오에서 해당 구간의 시간 정보입니다. speech_to_text는 비디오 속에서의 대화, 음성, 소리, 대사, 그리고 말을 전부 글로 받아 적은 것 입니다. 참고하여 답변하세요. {"video_time_stamp": "{{ content['video_time_stamp'] }}", "lens_keywords": "{{ content.get('lens_keywords', '') }}", "lens_local_keywords": "{{ content.get('lens_local_keywords', '') }}", "speech_to_text": "{{ content.get('speech_to_text', '') }}"}
{% else %}
다음 중 video_time_stamp는 비디오에서 해당 구간의 시간 정보입니다. 참고하여 답변하세요. {"video_time_stamp": "{{ content['video_time_stamp'] }}"}
{% endif %}<|im_end|>
{% elif content['type'] == 'text' %}
<|im_start|>{{ role }}
{{ content['text'] }}<|im_end|>
{% endif %}
{% elif message['content'] is sequence %}
{% for content in message['content'] %}
{% if content['type'] == 'image' %}
<|im_start|>{{ role }} (mime)
{"type": "image/jpeg", "filename": "{{ content['filename'] }}"}<|im_end|>
<|im_start|>{{ role }} (vector)
<|dummy3|><|im_end|>
<|im_start|>image/aux
다음 중 ocr은 사진에서 검출된 글자이고, lens_keyword는 사진에서 추출된 keyword와 bbox 위치입니다. bbox는 0~1 사이로 정규화된 [x1, y1, x2, y2]의 형태입니다. 참고하여 답변하세요. {"ocr": "{{ content['ocr'] or '' }}", "lens_keywords": "{{ content['lens_keywords'] or '' }}", "lens_local_keywords": "{{ content['lens_local_keywords'] or '' }}"}<|im_end|>
{% elif content['type'] == 'video' %}
<|im_start|>{{ role }} (mime)
{"type": "video/mp4", "filename": "{{ content['filename'] }}"}<|im_end|>
<|im_start|>{{ role }} (vector)
<|_unuse_missing_100270|><|im_end|>
<|im_start|>image/aux
{% if content.get('is_final_grid') %}
다음 중 lens_keyword는 사진에서 추출된 keyword와 bbox 위치입니다. bbox는 0~1 사이로 정규화된 [x1, y1, x2, y2]의 형태입니다. video_time_stamp는 비디오에서 해당 구간의 시간 정보입니다. speech_to_text는 비디오 속에서의 대화, 음성, 소리, 대사, 그리고 말을 전부 글로 받아 적은 것 입니다. 참고하여 답변하세요. {"video_time_stamp": "{{ content['video_time_stamp'] }}", "lens_keywords": "{{ content.get('lens_keywords', '') }}", "lens_local_keywords": "{{ content.get('lens_local_keywords', '') }}", "speech_to_text": "{{ content.get('speech_to_text', '') }}"}
{% else %}
다음 중 video_time_stamp는 비디오에서 해당 구간의 시간 정보입니다. 참고하여 답변하세요. {"video_time_stamp": "{{ content['video_time_stamp'] }}"}
{% endif %}<|im_end|>
{% elif content['type'] == 'text' %}
<|im_start|>{{ role }}
{{ content['text'] }}<|im_end|>
{% endif %}
{% endfor %}
{% endif %}
{% endfor %}
{% if add_generation_prompt %}
<|im_start|>assistant
{% endif %}
|