Instructions to use OpenGVLab/InternVL3_5-38B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/InternVL3_5-38B with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL3_5-38B", 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/InternVL3_5-38B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenGVLab/InternVL3_5-38B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/InternVL3_5-38B"
# 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/InternVL3_5-38B",
		"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/InternVL3_5-38B

SGLang

How to use OpenGVLab/InternVL3_5-38B 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/InternVL3_5-38B" \
    --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/InternVL3_5-38B",
		"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/InternVL3_5-38B" \
        --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/InternVL3_5-38B",
		"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/InternVL3_5-38B with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/InternVL3_5-38B
```

Improve InternVL3_5-38B Model Card with Paper Abstract and Project Links

by nielsr HF Staff - opened Sep 29, 2025

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

+152

-50

nielsr

Sep 29, 2025

Hi there,

I've opened this PR to enhance the model card for InternVL3_5-38B by incorporating explicit information from the research paper and clarifying project links, as per our community science guidelines.

Here's a summary of the changes:

Metadata: Added papers: - 2412.05271 to explicitly link the primary paper and tags: - internvl3.5 for better discoverability.
Paper and Abstract: Introduced dedicated "Paper" and "Abstract" sections at the top, featuring the provided paper (Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling) and its abstract. The Hugging Face demo URL mentioned in the abstract is now explicitly linked.
Project Links: Consolidated the GitHub repository link, the new Hugging Face Space link (https://huggingface.co/spaces/OpenGVLab/InternVL), and the existing Chat Demo link into structured "Project Pages" and "GitHub Repository" sections.
More InternVL Papers: Moved the existing list of related InternVL papers to a dedicated section for better organization.
Model Introduction: Renamed the original "Introduction" (which describes InternVL3.5) to "Model Introduction" to clearly distinguish it from the general paper abstract and ensure the model-specific details are retained and properly contextualized.

The existing library_name: transformers and license: apache-2.0 are correct and have been retained. The sample usage section is comprehensive and remains unchanged.

These updates aim to provide clearer and more comprehensive documentation for users.

Best,
Niels

Improve InternVL3_5-38B Model Card with Paper Abstract and Project Linksfa29caeb

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment