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, 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
```

dong.hyun commited on Jul 8, 2025

Commit

db17193

1 Parent(s): 82f2e21

Update README & remove redundant code

Browse files

Files changed (2) hide show

README.md +4 -4
processing_hyperclovax.py +1 -15

README.md CHANGED Viewed

@@ -85,7 +85,7 @@ from transformers import AutoModelForCausalLM, AutoProcessor, AutoTokenizer
 model_name = "naver-hyperclovax/HyperCLOVAX-SEED-Vision-Instruct-3B"
 model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True).to(device="cuda")
-preprocessor = AutoProcessor.from_pretrained(model_name, trust_remote_code=True)
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 # LLM Example
@@ -106,7 +106,7 @@ llm_chat = [
 model_inputs = processor.apply_chat_template(
         llm_chat, tokenize=True, return_dict=True, return_tensors="pt", add_generation_prompt=True
 )
-model_inputs = model_inputs.to(device=DEVICE)
 # Please adjust parameters like top_p appropriately for your use case.
 output_ids = model.generate(
@@ -165,8 +165,8 @@ vlm_chat = [
 model_inputs = processor.apply_chat_template(
         vlm_chat, tokenize=True, return_dict=True, return_tensors="pt", add_generation_prompt=True,
 )
-model_inputs = model_inputs.to(device=DEVICE)
-        output_ids = model.generate(
         **model_inputs,
         max_new_tokens=64,
         do_sample=True,

 model_name = "naver-hyperclovax/HyperCLOVAX-SEED-Vision-Instruct-3B"
 model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True).to(device="cuda")
+processor = AutoProcessor.from_pretrained(model_name, trust_remote_code=True)
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 # LLM Example
 model_inputs = processor.apply_chat_template(
         llm_chat, tokenize=True, return_dict=True, return_tensors="pt", add_generation_prompt=True
 )
+model_inputs = model_inputs.to(device="cuda")
 # Please adjust parameters like top_p appropriately for your use case.
 output_ids = model.generate(
 model_inputs = processor.apply_chat_template(
         vlm_chat, tokenize=True, return_dict=True, return_tensors="pt", add_generation_prompt=True,
 )
+model_inputs = model_inputs.to(device="cuda")
+output_ids = model.generate(
         **model_inputs,
         max_new_tokens=64,
         do_sample=True,

processing_hyperclovax.py CHANGED Viewed

@@ -136,17 +136,6 @@ class HCXProcessor(ProcessorMixin):
         # vllm needs vision_query_lengths, but we don't need it
         del model_inputs["vision_query_lengths_images"]
         del model_inputs["vision_query_lengths_videos"]
-        # # vllm 호환성을 위해 이곳에서 token 을 vision_query_length만큼 늘리기 처리
-        # if "input_ids" in model_inputs:
-        #     # self.image_token 모두 찾기
-        #     input_ids = self.repeat_dummy_tokens(
-        #         model_inputs["input_ids"], self.image_token_id, model_inputs["vision_query_lengths_images"]
-        #     )
-        #     input_ids = self.repeat_dummy_tokens(
-        #         input_ids, self.video_token_id, model_inputs["vision_query_lengths_videos"]
-        #     )
-        #     model_inputs["input_ids"] = input_ids
         return model_inputs
@@ -439,10 +428,7 @@ class HCXProcessor(ProcessorMixin):
             def _replacer(match_obj):
                 # return self.image_token
                 num_query_tokens = next(_iterator)
-                return "".join(
-                    [_target_token for _ in range(num_query_tokens)]
-                )  # vision_query_legnth 만큼 image token 을 복제
             return _replacer
         text_inputs = {}

         # vllm needs vision_query_lengths, but we don't need it
         del model_inputs["vision_query_lengths_images"]
         del model_inputs["vision_query_lengths_videos"]
         return model_inputs
             def _replacer(match_obj):
                 # return self.image_token
                 num_query_tokens = next(_iterator)
+                return "".join([_target_token for _ in range(num_query_tokens)])
             return _replacer
         text_inputs = {}