Instructions to use OpenGVLab/Mini-InternVL-Chat-2B-V1-5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/Mini-InternVL-Chat-2B-V1-5 with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/Mini-InternVL-Chat-2B-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/Mini-InternVL-Chat-2B-V1-5", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenGVLab/Mini-InternVL-Chat-2B-V1-5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/Mini-InternVL-Chat-2B-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/Mini-InternVL-Chat-2B-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/Mini-InternVL-Chat-2B-V1-5

SGLang

How to use OpenGVLab/Mini-InternVL-Chat-2B-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/Mini-InternVL-Chat-2B-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/Mini-InternVL-Chat-2B-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/Mini-InternVL-Chat-2B-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/Mini-InternVL-Chat-2B-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/Mini-InternVL-Chat-2B-V1-5 with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/Mini-InternVL-Chat-2B-V1-5
```

opengvlab-admin commited on May 28, 2024

Commit

3ec3d5c

verified ·

1 Parent(s): f2f20b3

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -4

README.md CHANGED Viewed

@@ -21,16 +21,19 @@ pipeline_tag: visual-question-answering
 You can run multimodal large models using a 1080Ti now.
-We are delighted to introduce Mini-InternVL-Chat-2B-V1-5. In the era of large language models, many researchers have started to focus on smaller language models, such as Gemma-2B, Qwen-1.8B, and InternLM2-1.8B. Inspired by their efforts, we have distilled our vision foundation model InternViT-6B-448px-V1-5 down to 300M and used InternLM2-Chat-1.8B as our language model. This resulted in a small multimodal model with excellent performance.
-As shown in the figure below, we adopted the same model architecture as InternVL 1.5. We simply replaced the original InternViT-6B with InternViT-300M and InternLM2-Chat-20B with InternLM2-Chat-1.8B. For training, we used the same data as InternVL 1.5 to train this smaller model. Additionally, due to the lower training costs of smaller models, we used a context length of 8K during training.
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/64119264f0f81eb569e0d569/SmtrR0c5NVhmSTvnwwCE9.png)
 ## Model Details
 - **Model Type:** multimodal large language model (MLLM)
 - **Model Stats:**
-  - Architecture: InternViT-300M-448px + MLP + [InternLM2-Chat-1.8B](https://huggingface.co/internlm/internlm2-chat-1_8b)
   - Image size: dynamic resolution, max to 40 tiles of 448 x 448 (4K resolution).
   - Params: 2.2B

 You can run multimodal large models using a 1080Ti now.
+We are delighted to introduce the Mini-InternVL-Chat series. In the era of large language models, many researchers have started to focus on smaller language models, such as Gemma-2B, Qwen-1.8B, and InternLM2-1.8B. Inspired by their efforts, we have distilled our vision foundation model [InternViT-6B-448px-V1-5](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V1-5) down to 300M and used [InternLM2-Chat-1.8B](https://huggingface.co/internlm/internlm2-chat-1_8b) or [Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) as our language model. This resulted in a small multimodal model with excellent performance.
+As shown in the figure below, we adopted the same model architecture as InternVL 1.5. We simply replaced the original InternViT-6B with InternViT-300M and InternLM2-Chat-20B with InternLM2-Chat-1.8B / Phi-3-mini-128k-instruct. For training, we used the same data as InternVL 1.5 to train this smaller model. Additionally, due to the lower training costs of smaller models, we used a context length of 8K during training.
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64006c09330a45b03605bba3/rDyoe66Sqev44T0wsP5Z7.png)
 ## Model Details
 - **Model Type:** multimodal large language model (MLLM)
 - **Model Stats:**
+  - Architecture: [InternViT-300M-448px](https://huggingface.co/OpenGVLab/InternViT-300M-448px) + MLP + [InternLM2-Chat-1.8B](https://huggingface.co/internlm/internlm2-chat-1_8b)
   - Image size: dynamic resolution, max to 40 tiles of 448 x 448 (4K resolution).
   - Params: 2.2B