Instructions to use ZJU-AI4H/Hulu-Med-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ZJU-AI4H/Hulu-Med-32B with Transformers:

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

pipe = pipeline("image-text-to-text", model="ZJU-AI4H/Hulu-Med-32B", trust_remote_code=True)
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)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ZJU-AI4H/Hulu-Med-32B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ZJU-AI4H/Hulu-Med-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ZJU-AI4H/Hulu-Med-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": "ZJU-AI4H/Hulu-Med-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/ZJU-AI4H/Hulu-Med-32B

SGLang

How to use ZJU-AI4H/Hulu-Med-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 "ZJU-AI4H/Hulu-Med-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": "ZJU-AI4H/Hulu-Med-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 "ZJU-AI4H/Hulu-Med-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": "ZJU-AI4H/Hulu-Med-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 ZJU-AI4H/Hulu-Med-32B with Docker Model Runner:
```
docker model run hf.co/ZJU-AI4H/Hulu-Med-32B
```

'image_token' is undefined

by dddwzl3703 - opened Feb 6

Discussion

dddwzl3703

Feb 6

•

edited Feb 6

followed vLLM Installation instruction, tested with official example:

# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
    -H "Content-Type: application/json" \
    --data '{
        "model": "ZJU-AI4H/Hulu-Med-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"
                        }
                    }
                ]
            }
        ]
    }'

and get:

(APIServer pid=2750956) INFO:     127.0.0.1:44528 - "POST /v1/chat/completions HTTP/1.1" 400 Bad Request
(APIServer pid=2750956) ERROR 02-06 11:03:09 [chat_utils.py:1777] An error occurred in `transformers` while applying chat template
(APIServer pid=2750956) ERROR 02-06 11:03:09 [chat_utils.py:1777] Traceback (most recent call last):
(APIServer pid=2750956) ERROR 02-06 11:03:09 [chat_utils.py:1777]   File "/home/user/workspace/vllm/.venv/lib/python3.12/site-packages/vllm/entrypoints/chat_utils.py", line 1764, in apply_hf_chat_template
(APIServer pid=2750956) ERROR 02-06 11:03:09 [chat_utils.py:1777]     return tokenizer.apply_chat_template(
(APIServer pid=2750956) ERROR 02-06 11:03:09 [chat_utils.py:1777]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=2750956) ERROR 02-06 11:03:09 [chat_utils.py:1777]   File "/home/user/workspace/vllm/.venv/lib/python3.12/site-packages/transformers/tokenization_utils_base.py", line 1667, in apply_chat_template
(APIServer pid=2750956) ERROR 02-06 11:03:09 [chat_utils.py:1777]     rendered_chat, generation_indices = render_jinja_template(
(APIServer pid=2750956) ERROR 02-06 11:03:09 [chat_utils.py:1777]                                         ^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=2750956) ERROR 02-06 11:03:09 [chat_utils.py:1777]   File "/home/user/workspace/vllm/.venv/lib/python3.12/site-packages/transformers/utils/chat_template_utils.py", line 539, in render_jinja_template
(APIServer pid=2750956) ERROR 02-06 11:03:09 [chat_utils.py:1777]     rendered_chat = compiled_template.render(
(APIServer pid=2750956) ERROR 02-06 11:03:09 [chat_utils.py:1777]                     ^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=2750956) ERROR 02-06 11:03:09 [chat_utils.py:1777]   File "/home/user/workspace/vllm/.venv/lib/python3.12/site-packages/jinja2/environment.py", line 1295, in render
(APIServer pid=2750956) ERROR 02-06 11:03:09 [chat_utils.py:1777]     self.environment.handle_exception()
(APIServer pid=2750956) ERROR 02-06 11:03:09 [chat_utils.py:1777]   File "/home/user/workspace/vllm/.venv/lib/python3.12/site-packages/jinja2/environment.py", line 942, in handle_exception
(APIServer pid=2750956) ERROR 02-06 11:03:09 [chat_utils.py:1777]     raise rewrite_traceback_stack(source=source)
(APIServer pid=2750956) ERROR 02-06 11:03:09 [chat_utils.py:1777]   File "<template>", line 29, in top-level template code
(APIServer pid=2750956) ERROR 02-06 11:03:09 [chat_utils.py:1777] jinja2.exceptions.UndefinedError: 'image_token' is undefined
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258] Error in preprocessing prompt inputs
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258] Traceback (most recent call last):
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258]   File "/home/user/workspace/vllm/.venv/lib/python3.12/site-packages/vllm/entrypoints/chat_utils.py", line 1764, in apply_hf_chat_template
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258]     return tokenizer.apply_chat_template(
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258]   File "/home/user/workspace/vllm/.venv/lib/python3.12/site-packages/transformers/tokenization_utils_base.py", line 1667, in apply_chat_template
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258]     rendered_chat, generation_indices = render_jinja_template(
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258]                                         ^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258]   File "/home/user/workspace/vllm/.venv/lib/python3.12/site-packages/transformers/utils/chat_template_utils.py", line 539, in render_jinja_template
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258]     rendered_chat = compiled_template.render(
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258]                     ^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258]   File "/home/user/workspace/vllm/.venv/lib/python3.12/site-packages/jinja2/environment.py", line 1295, in render
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258]     self.environment.handle_exception()
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258]   File "/home/user/workspace/vllm/.venv/lib/python3.12/site-packages/jinja2/environment.py", line 942, in handle_exception
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258]     raise rewrite_traceback_stack(source=source)
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258]   File "<template>", line 29, in top-level template code
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258] jinja2.exceptions.UndefinedError: 'image_token' is undefined
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258] 
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258] The above exception was the direct cause of the following exception:
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258] 
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258] Traceback (most recent call last):
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258]   File "/home/user/workspace/vllm/.venv/lib/python3.12/site-packages/vllm/entrypoints/openai/serving_chat.py", line 236, in create_chat_completion
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258]     ) = await self._preprocess_chat(
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258]         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258]   File "/home/user/workspace/vllm/.venv/lib/python3.12/site-packages/vllm/entrypoints/openai/serving_engine.py", line 1134, in _preprocess_chat
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258]     request_prompt = apply_hf_chat_template(
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258]                      ^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258]   File "/home/user/workspace/vllm/.venv/lib/python3.12/site-packages/vllm/entrypoints/chat_utils.py", line 1780, in apply_hf_chat_template
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258]     raise ValueError(str(e)) from e
(APIServer pid=2750956) ERROR 02-06 11:03:09 [serving_chat.py:258] ValueError: 'image_token' is undefined

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