Instructions to use OpenGVLab/InternVL-Chat-V1-5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/InternVL-Chat-V1-5 with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL-Chat-V1-5", 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/InternVL-Chat-V1-5", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenGVLab/InternVL-Chat-V1-5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/InternVL-Chat-V1-5"
# 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/InternVL-Chat-V1-5",
		"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/InternVL-Chat-V1-5

SGLang

How to use OpenGVLab/InternVL-Chat-V1-5 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/InternVL-Chat-V1-5" \
    --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/InternVL-Chat-V1-5",
		"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/InternVL-Chat-V1-5" \
        --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/InternVL-Chat-V1-5",
		"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/InternVL-Chat-V1-5 with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/InternVL-Chat-V1-5
```

Where can I deploy this model for inference?

by catworld1212 - opened Apr 27, 2024

Discussion

catworld1212

Apr 27, 2024

Hi, I'm impressed with the work on InternVL and I'm interested in deploying its inference as an endpoint. Unfortunately, vLLM and TGI don't support this. Could anyone offer guidance on how to achieve this? I'd appreciate any suggestions you may have.

whai362

Apr 28, 2024

See "Chat Web Demo" at https://github.com/OpenGVLab/InternVL/blob/main/README.md

catworld1212

Apr 30, 2024

See "Chat Web Demo" at https://github.com/OpenGVLab/InternVL/blob/main/README.md

I want to deploy it as an inference not run it as a demo, Can you tell do InternVL-Chat-V1-5 requires flash attention?

catworld1212

May 2, 2024

Hi @whai362 @czczup what's the proper way to few-shot prompting (also called in-context learning? How do I give the previous context? I'm using lmdeploy to serve the inference can you help me, please?

czczup

OpenGVLab org Aug 22, 2024

Hi @whai362 @czczup what's the proper way to few-shot prompting (also called in-context learning? How do I give the previous context? I'm using lmdeploy to serve the inference can you help me, please?

Hi, you can perform few-shot prompting in the form of multi-turn dialogue, placing the few-shot examples in the conversation history. I think this shouldn't be different from how other VLMs perform few-shot prompting.

czczup changed discussion status to closed Aug 22, 2024

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