Instructions to use naver-hyperclovax/HyperCLOVAX-SEED-Think-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use naver-hyperclovax/HyperCLOVAX-SEED-Think-32B with Transformers:

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

pipe = pipeline("image-text-to-text", model="naver-hyperclovax/HyperCLOVAX-SEED-Think-32B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("naver-hyperclovax/HyperCLOVAX-SEED-Think-32B")
model = AutoModelForMultimodalLM.from_pretrained("naver-hyperclovax/HyperCLOVAX-SEED-Think-32B", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use naver-hyperclovax/HyperCLOVAX-SEED-Think-32B 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-32B"
# 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-32B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/naver-hyperclovax/HyperCLOVAX-SEED-Think-32B

SGLang

How to use naver-hyperclovax/HyperCLOVAX-SEED-Think-32B 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-32B" \
    --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-32B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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-32B" \
        --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-32B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use naver-hyperclovax/HyperCLOVAX-SEED-Think-32B with Docker Model Runner:
```
docker model run hf.co/naver-hyperclovax/HyperCLOVAX-SEED-Think-32B
```

bigshanedogg commited on Jul 27

Commit

f962e4f

verified ·

1 Parent(s): c685e77

Align processor_class to native Exaone4_5_Processor

Browse files

- processor_config.json: processor_class -> Exaone4_5_Processor; image/video processor -> Qwen2VLImageProcessor / Qwen2VLVideoProcessor
- tokenizer_config.json: processor_class -> Exaone4_5_Processor; drop remote-code auto_map (AutoProcessor)

Following the transformers reviewer's suggestion, HyperCLOVAXVisionV2Processor is not a separate subclass but is mapped directly to Exaone4_5_Processor in processing auto (hyperclovax_vision_v2 -> Exaone4_5_Processor), since the subclass was a pass-through with no override.
Ref: https://github.com/huggingface/transformers/pull/44314#discussion_r3631794142

Files changed (2) hide show

processor_config.json +3 -3
tokenizer_config.json +1 -4

processor_config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "processor_class": "HyperCLOVAXVisionV2Processor",
   "image_processor": {
     "discrete_image_end_token": "<|discrete_image_end|>",
     "discrete_image_ratios": [
@@ -56,7 +56,7 @@
       0.4578275,
       0.40821073
     ],
-    "image_processor_type": "HyperCLOVAXVisionV2ImageProcessor",
     "image_start_token": "<|image_start|>",
     "image_std": [
       0.26862954,
@@ -105,7 +105,7 @@
     "use_audio_in_video": false,
     "use_discrete_token": false,
     "video_end_token": "<|video_end|>",
-    "video_processor_type": "HyperCLOVAXVisionV2VideoProcessor",
     "video_start_token": "<|video_start|>",
     "video_token": "<|VIDEO_PAD|>",
     "video_audio_token": "<|VIDEO_AUDIO_PAD|>",

 {
+  "processor_class": "Exaone4_5_Processor",
   "image_processor": {
     "discrete_image_end_token": "<|discrete_image_end|>",
     "discrete_image_ratios": [
       0.4578275,
       0.40821073
     ],
+    "image_processor_type": "Qwen2VLImageProcessor",
     "image_start_token": "<|image_start|>",
     "image_std": [
       0.26862954,
     "use_audio_in_video": false,
     "use_discrete_token": false,
     "video_end_token": "<|video_end|>",
+    "video_processor_type": "Qwen2VLVideoProcessor",
     "video_start_token": "<|video_start|>",
     "video_token": "<|VIDEO_PAD|>",
     "video_audio_token": "<|VIDEO_AUDIO_PAD|>",

tokenizer_config.json CHANGED Viewed

@@ -2058,9 +2058,6 @@
       "special": true
     }
   },
-  "auto_map": {
-    "AutoProcessor": "processing_hyperclovax_seed.HyperCLOVAXSeedProcessor"
-  },
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|im_end|>",
@@ -2072,7 +2069,7 @@
   "image_token": "<|IMAGE_PAD|>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|endoftext|>",
-  "processor_class": "HyperCLOVAXSeedProcessor",
   "sep_token": "<|endoftext|>",
   "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": "<|endoftext|>",

       "special": true
     }
   },
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|im_end|>",
   "image_token": "<|IMAGE_PAD|>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|endoftext|>",
+  "processor_class": "Exaone4_5_Processor",
   "sep_token": "<|endoftext|>",
   "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": "<|endoftext|>",