Instructions to use OpenGVLab/InternVL2-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/InternVL2-8B with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL2-8B", 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/InternVL2-8B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenGVLab/InternVL2-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/InternVL2-8B"
# 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/InternVL2-8B",
		"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/InternVL2-8B

SGLang

How to use OpenGVLab/InternVL2-8B 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/InternVL2-8B" \
    --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/InternVL2-8B",
		"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/InternVL2-8B" \
        --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/InternVL2-8B",
		"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/InternVL2-8B with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/InternVL2-8B
```

Weiyun1025 commited on Jul 3, 2024

Commit

b40962a

verified ·

1 Parent(s): 2ccebcf

Upload folder using huggingface_hub

Browse files

Files changed (1) hide show

README.md +20 -20

README.md CHANGED Viewed

@@ -23,26 +23,26 @@ InternVL2 is a multimodal large language model series, featuring models of vario
 ## Performance
-|          Benchmark           | MiniCPM-Llama3-V-2_5 | InternVL-Chat-V1-5 ｜ InternVL2-8B |
-| :--------------------------: | :------------------: | :----------: | :----------: |
-|          Model Size          |         8.5B         |  |   8.1B     |
-|                              |                      |  |            |
-|    DocVQA<sub>test</sub>     |         84.8         |  |   91.6     |
-|    ChartQA<sub>test</sub>    |          -           |  |   83.3     |
-|    InfoVQA<sub>test</sub>    |          -           |  |   74.8     |
-|    TextVQA<sub>val</sub>     |         76.6         |  |   77.4     |
-|           OCRBench           |         725          |  |   794      |
-|      MME<sub>sum</sub>       |        2024.6        |  |  2210.3    |
-|         RealWorldQA          |         63.5         |  |   64.4     |
-|     AI2D<sub>test</sub>      |         78.4         |  |   83.8     |
-|      MMMU<sub>val</sub>      |         45.8         |  |   49.3     |
-|  MMBench-EN<sub>test</sub>   |         77.2         |  |   81.7     |
-|  MMBench-CN<sub>test</sub>   |         74.2         |  |   81.2     |
-|    CCBench<sub>dev</sub>     |         45.9         |  |   75.9     |
-|  MMVet<sub>GPT-4-0613</sub>  |          -           |  |   60.0     |
-|          SEED-Image          |         72.3         |  |   76.2     |
-|   HallBench<sub>avg</sub>    |         42.4         |  |   45.2     |
-| MathVista<sub>testmini</sub> |         54.3         |  |   58.3     |
 - We simultaneously use InternVL and VLMEvalKit repositories for model evaluation. Specifically, the results reported for DocVQA, ChartQA, InfoVQA, TextVQA, MME, AI2D, MMBench, CCBench, MMVet, and SEED-Image were tested using the InternVL repository. MMMU, OCRBench, RealWorldQA, HallBench, and MathVista were evaluated using the VLMEvalKit.

 ## Performance
+|          Benchmark           | MiniCPM-Llama3-V-2_5 | InternVL-Chat-V1-5 | InternVL2-8B |
+| :--------------------------: | :------------------: | :----------------: | :----------: |
+|          Model Size          |         8.5B         |       25.5B        |     8.1B     |
+|                              |                      |                    |              |
+|    DocVQA<sub>test</sub>     |         84.8         |        90.9        |     91.6     |
+|    ChartQA<sub>test</sub>    |          -           |        83.8        |     83.3     |
+|    InfoVQA<sub>test</sub>    |          -           |        72.5        |     74.8     |
+|    TextVQA<sub>val</sub>     |         76.6         |        80.6        |     77.4     |
+|           OCRBench           |         725          |        724         |     794      |
+|      MME<sub>sum</sub>       |        2024.6        |       2187.8       |    2210.3    |
+|         RealWorldQA          |         63.5         |        66.0        |     64.4     |
+|     AI2D<sub>test</sub>      |         78.4         |        80.7        |     83.8     |
+|      MMMU<sub>val</sub>      |         45.8         |        45.2        |     49.3     |
+|  MMBench-EN<sub>test</sub>   |         77.2         |        82.2        |     81.7     |
+|  MMBench-CN<sub>test</sub>   |         74.2         |        82.0        |     81.2     |
+|    CCBench<sub>dev</sub>     |         45.9         |        69.8        |     75.9     |
+|  MMVet<sub>GPT-4-0613</sub>  |          -           |        62.8        |     60.0     |
+|          SEED-Image          |         72.3         |        76.0        |     76.2     |
+|   HallBench<sub>avg</sub>    |         42.4         |        49.3        |     45.2     |
+| MathVista<sub>testmini</sub> |         54.3         |        53.5        |     58.3     |
 - We simultaneously use InternVL and VLMEvalKit repositories for model evaluation. Specifically, the results reported for DocVQA, ChartQA, InfoVQA, TextVQA, MME, AI2D, MMBench, CCBench, MMVet, and SEED-Image were tested using the InternVL repository. MMMU, OCRBench, RealWorldQA, HallBench, and MathVista were evaluated using the VLMEvalKit.