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

Libraries

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Install from pip and serve model

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

SGLang

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

cyyang822 commited on Dec 13, 2024

Commit

3b68028

1 Parent(s): f764292

update README.md

Browse files

Files changed (1) hide show

README.md +15 -0

README.md CHANGED Viewed

@@ -16,7 +16,9 @@ tags:
 # PVC-InternVL2-8B
 [\[📂 GitHub\]](https://github.com/OpenGVLab/PVC)
 ## Introduction
@@ -227,6 +229,19 @@ response = model.chat(tokenizer, pixel_values, question, generation_config, data
 print(f'User: {question}\nAssistant: {response}')
 ```
 ## License
 This project is released under the MIT license. Parts of this project contain code and models from other sources, which are subject to their respective licenses.

 # PVC-InternVL2-8B
+[\[📜 Paper\]](https://arxiv.org/abs/2412.09613)
 [\[📂 GitHub\]](https://github.com/OpenGVLab/PVC)
+[\[🚀 Quick Start\]](#quick-start)
 ## Introduction
 print(f'User: {question}\nAssistant: {response}')
 ```
+## 🖊️ Citation
+If you find this work helpful in your research, please consider citing:
+```bibtex
+@article{yang2024pvc,
+  title={PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models},
+  author={Yang, Chenyu and Dong, Xuan and Zhu, Xizhou and Su, Weijie and Wang, Jiahao and Tian, Hao and Chen, Zhe and Wang, Wenhai and Lu, Lewei and and Dai, Jifeng},
+  journal={arXiv preprint arXiv:2412.09613},
+  year={2024}
+}
+```
 ## License
 This project is released under the MIT license. Parts of this project contain code and models from other sources, which are subject to their respective licenses.