Instructions to use OpenGVLab/InternVL2_5-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/InternVL2_5-8B with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL2_5-8B", 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/InternVL2_5-8B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenGVLab/InternVL2_5-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/InternVL2_5-8B"
# 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/InternVL2_5-8B",
		"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/InternVL2_5-8B

SGLang

How to use OpenGVLab/InternVL2_5-8B 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/InternVL2_5-8B" \
    --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/InternVL2_5-8B",
		"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/InternVL2_5-8B" \
        --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/InternVL2_5-8B",
		"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/InternVL2_5-8B with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/InternVL2_5-8B
```

zwgao commited on Dec 5, 2024

Commit

5626362

verified ·

1 Parent(s): 37c32f9

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -16

README.md CHANGED Viewed

@@ -50,22 +50,6 @@ InternVL 2.5 is a multimodal large language model series, featuring models of va
 ## Performance
-Here is the converted table in Markdown with the rows and columns swapped and the `\cite{}` references removed:
-| Metric      | Ovis1.6-Gemma2-9B | MiniCPM-V2.6       | Qwen2-VL-7B        | InternVL2-8B       | InternVL2.5-8B      |
-|-------------|-------------------|--------------------|--------------------|--------------------|---------------------|
-| **\MMMU**       | 55.0              | 49.8               | 54.1               | 52.6               | 56.0                |
-| **\MMMUT**      | --                | --                 | --                 | 44.3               | 48.9                |
-| **\MMMUPRO**    | --                | 30.2 / 24.2 / 27.2 | 34.1 / 27.0 / 30.5 | 32.5 / 25.4 / 29.0 | 38.2 / 30.4 / 34.3 |
-| **\MathVista**  | 67.2              | 60.6               | 58.2               | 58.3               | 64.4                |
-| **\MathVision** | \rsp / 18.8       | 16.1 / 17.5        | 22.0 / 16.3        | 20.4 / 18.4        | 22.0 / 19.7         |
-| **\MathVe**     | --                | 25.7               | 31.9               | 37.0               | 39.5                |
-| **\Olympiad**   | --                | --                 | --                 | 1.9                | 4.9                 |
-**Notes:**
-- The commented-out line for `Molmo-7B-D` has been removed.
-- The `\rowcolor{gray!15}` command is omitted as Markdown does not support row coloring.
-- Ensure that any custom LaTeX commands like `\rsp` are properly defined or replaced if necessary in your Markdown renderer.
 ### Image Benchmarks


50
51	## Performance
52
















53
54	### Image Benchmarks
55