Instructions to use rp-yu/Qwen2-VL-2b-VPT-CLIP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rp-yu/Qwen2-VL-2b-VPT-CLIP with Transformers:

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

pipe = pipeline("image-text-to-text", model="rp-yu/Qwen2-VL-2b-VPT-CLIP")
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 AutoModelForSeq2SeqLM
model = AutoModelForSeq2SeqLM.from_pretrained("rp-yu/Qwen2-VL-2b-VPT-CLIP", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rp-yu/Qwen2-VL-2b-VPT-CLIP with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rp-yu/Qwen2-VL-2b-VPT-CLIP"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rp-yu/Qwen2-VL-2b-VPT-CLIP",
		"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/rp-yu/Qwen2-VL-2b-VPT-CLIP

SGLang

How to use rp-yu/Qwen2-VL-2b-VPT-CLIP 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 "rp-yu/Qwen2-VL-2b-VPT-CLIP" \
    --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": "rp-yu/Qwen2-VL-2b-VPT-CLIP",
		"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 "rp-yu/Qwen2-VL-2b-VPT-CLIP" \
        --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": "rp-yu/Qwen2-VL-2b-VPT-CLIP",
		"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 rp-yu/Qwen2-VL-2b-VPT-CLIP with Docker Model Runner:
```
docker model run hf.co/rp-yu/Qwen2-VL-2b-VPT-CLIP
```

Qwen2-VL-2b-VPT-CLIP / README.md

rp-yu

Update README.md

2560534 verified about 1 year ago

preview code

raw

history blame contribute delete

622 Bytes

metadata

base_model:
  - Qwen/Qwen2-VL-2B-Instruct
datasets:
  - rp-yu/VPT_Datasets
language:
  - en
library_name: transformers
license: apache-2.0
metrics:
  - accuracy
pipeline_tag: image-text-to-text

Introducing Visual Perception Token into Multimodal Large Language Model

This repository contains models based on the paper Introducing Visual Perception Token into Multimodal Large Language Model. These models utilize Visual Perception Tokens to enhance the visual perception capabilities of multimodal large language models (MLLMs).

Code: https://github.com/yu-rp/VisualPerceptionToken