Instructions to use tencent/Youtu-VL-4B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tencent/Youtu-VL-4B-Instruct with Transformers:

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

pipe = pipeline("image-text-to-text", model="tencent/Youtu-VL-4B-Instruct", 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 AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("tencent/Youtu-VL-4B-Instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tencent/Youtu-VL-4B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tencent/Youtu-VL-4B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tencent/Youtu-VL-4B-Instruct",
		"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/tencent/Youtu-VL-4B-Instruct

SGLang

How to use tencent/Youtu-VL-4B-Instruct 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 "tencent/Youtu-VL-4B-Instruct" \
    --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": "tencent/Youtu-VL-4B-Instruct",
		"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 "tencent/Youtu-VL-4B-Instruct" \
        --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": "tencent/Youtu-VL-4B-Instruct",
		"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 tencent/Youtu-VL-4B-Instruct with Docker Model Runner:
```
docker model run hf.co/tencent/Youtu-VL-4B-Instruct
```

Add link to Demo for VL and CV tasks to README

by zhixiangwei - opened Feb 6

base: refs/heads/main

←

from: refs/pr/7

Discussion Files changed

+31

-0

Files changed (1) hide show

README.md +31 -0

README.md CHANGED Viewed

@@ -127,6 +127,37 @@ generated_text = outputs[0]
 print(f"Youtu-VL output: {generated_text}")
 ```
 ## 🎉 Citation
 If you find our work useful in your research, please consider citing our paper:

 print(f"Youtu-VL output: {generated_text}")
 ```
+### Demo for VL and CV tasks
+A simple demo for quick start, including VL and CV tasks: [jupyter notebook](https://github.com/TencentCloudADP/youtu-vl/blob/main/demo/demo.ipynb)
+The core part of this demo is three lines below:
+```python
+model_path = "tencent/Youtu-VL-4B-Instruct"
+youtu_vl = YoutuVL(model_path)
+response = youtu_vl(prompt, img_path, seg_mode=seg_mode)
+```
+### Qualitative Results
+* **Task: Grounding**
+    > **Prompt:** Please provide the bounding box coordinate of the region this sentence describes: a black and white cat sitting on the edge of the bathtub
+    >
+    > <img src="https://cdn-uploads.huggingface.co/production/uploads/656312995475849b82c38bc4/349v2vYasfz4GtF_T_D09.png" width="300px">
+* **Task: Object Detection**
+    > **Prompt:** Detect all objects in the provided image.
+    >
+    > <img src="https://cdn-uploads.huggingface.co/production/uploads/656312995475849b82c38bc4/rUJ6PzIjGJWwK4e9owPlY.png" width="300px">
+* **Task: Referring Segmentation**
+    > **Prompt:** Can you segment "hotdog on left" in this image?
+    >
+    > <img src="https://cdn-uploads.huggingface.co/production/uploads/656312995475849b82c38bc4/K-5UG6HSLb28UFGx2pdPX.png" width="300px">
+For more examples, please refer to paper and Jupyter notebooks.
 ## 🎉 Citation
 If you find our work useful in your research, please consider citing our paper: