Instructions to use TIGER-Lab/VL-Rethinker-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TIGER-Lab/VL-Rethinker-7B with Transformers:

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

pipe = pipeline("image-text-to-text", model="TIGER-Lab/VL-Rethinker-7B")
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 AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("TIGER-Lab/VL-Rethinker-7B")
model = AutoModelForImageTextToText.from_pretrained("TIGER-Lab/VL-Rethinker-7B")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TIGER-Lab/VL-Rethinker-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TIGER-Lab/VL-Rethinker-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TIGER-Lab/VL-Rethinker-7B",
		"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/TIGER-Lab/VL-Rethinker-7B

SGLang

How to use TIGER-Lab/VL-Rethinker-7B 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 "TIGER-Lab/VL-Rethinker-7B" \
    --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": "TIGER-Lab/VL-Rethinker-7B",
		"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 "TIGER-Lab/VL-Rethinker-7B" \
        --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": "TIGER-Lab/VL-Rethinker-7B",
		"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 TIGER-Lab/VL-Rethinker-7B with Docker Model Runner:
```
docker model run hf.co/TIGER-Lab/VL-Rethinker-7B
```

wenhu commited on Apr 15, 2025

Commit

0797bad

verified ·

1 Parent(s): 5da532b

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -22,16 +22,16 @@ For details of training and evaluation, please see our [code repo](https://githu
 Explore further via the following links:
-| [**🚀Project Page**](https://tiger-ai-lab.github.io/VL-Rethinker/) | [**📖Paper**](https://github.com/TIGER-AI-Lab/VL-Rethinker/blob/main/paper.pdf) | [**🔗Github**](https://github.com/TIGER-AI-Lab/VL-Rethinker/) | [**🤗Data** (Coming Soon)]()  |
 ## Citation
 If you feel this model useful, please give us a free cite:
 ```
-@article{VLRethinker,
-    title={VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning},
-    author={Wang, Haozhe and Qu, Chao and Huang, Zuming and Chu, Wei and Fangzhen, Lin and Wenhu Chen},
-    journal={ArXiv},
-    year={2025},
 }
 ```

 Explore further via the following links:
+| [**🚀Project Page**](https://tiger-ai-lab.github.io/VL-Rethinker/) | [**📖Paper**](https://arxiv.org/abs/2504.08837) | [**🔗Github**](https://github.com/TIGER-AI-Lab/VL-Rethinker/) | [**🤗Data** (Coming Soon)]()  |
 ## Citation
 If you feel this model useful, please give us a free cite:
 ```
+@article{vl-rethinker,
+      title={VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning},
+      author = {Wang, Haozhe and Qu, Chao and Huang, Zuming and Chu, Wei and Lin, Fangzhen and Chen, Wenhu},
+      journal={arXiv preprint arXiv:2504.08837},
+      year={2025}
 }
 ```