Instructions to use OpenGVLab/Mini-InternVL2-4B-DA-BDD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/Mini-InternVL2-4B-DA-BDD with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/Mini-InternVL2-4B-DA-BDD", 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 AutoModel
model = AutoModel.from_pretrained("OpenGVLab/Mini-InternVL2-4B-DA-BDD", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenGVLab/Mini-InternVL2-4B-DA-BDD with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/Mini-InternVL2-4B-DA-BDD"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenGVLab/Mini-InternVL2-4B-DA-BDD",
		"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/OpenGVLab/Mini-InternVL2-4B-DA-BDD

SGLang

How to use OpenGVLab/Mini-InternVL2-4B-DA-BDD 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 "OpenGVLab/Mini-InternVL2-4B-DA-BDD" \
    --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": "OpenGVLab/Mini-InternVL2-4B-DA-BDD",
		"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 "OpenGVLab/Mini-InternVL2-4B-DA-BDD" \
        --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": "OpenGVLab/Mini-InternVL2-4B-DA-BDD",
		"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 OpenGVLab/Mini-InternVL2-4B-DA-BDD with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/Mini-InternVL2-4B-DA-BDD
```

Error when running the official demo codes

by dtf0709 - opened Jun 24, 2025

Discussion

dtf0709

Jun 24, 2025

If I directly run the demo codes, tokenlizer will have TypeError like this:

Exception has occurred: TypeError
expected str, bytes or os.PathLike object, not NoneType
File "/mnt/training_yrfs/p8n/camera/personal/tengfei.da/aidrive_data_extract_0616/label_aeb_odd_data/Mini-InternVL2-4B-DA-BDD.py", line 93, in
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True, use_fast=False)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: expected str, bytes or os.PathLike object, not NoneType

If remove use_fast=False from tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True, use_fast=False), then model.chat will have such error:
Traceback (most recent call last):
File "", line 2, in
File "/root/.cache/huggingface/modules/transformers_modules/OpenGVLab/Mini-InternVL2-4B-DA-BDD/dc4724a225f46f6f8dd78db74d01730245b28ee1/modeling_internvl_chat.py", line 291, in chat
generation_output = self.generate(
^^^^^^^^^^^^^^
File "/mnt/training_yrfs/prediction/aidrive/miniconda3/envs/aidrive-torch26-py312/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/root/.cache/huggingface/modules/transformers_modules/OpenGVLab/Mini-InternVL2-4B-DA-BDD/dc4724a225f46f6f8dd78db74d01730245b28ee1/modeling_internvl_chat.py", line 340, in generate
outputs = self.language_model.generate(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/training_yrfs/prediction/aidrive/miniconda3/envs/aidrive-torch26-py312/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1928, in getattr
raise AttributeError(
AttributeError: 'Phi3ForCausalLM' object has no attribute 'generate'

But it is OK to run with OpenGVLab/Mini-InternVL2-1B-DA-BDD. What's the cause to the problems?

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