Instructions to use YannQi/R-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use YannQi/R-4B with Transformers:

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

pipe = pipeline("image-text-to-text", model="YannQi/R-4B", 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("YannQi/R-4B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use YannQi/R-4B with vLLM:

Install from pip and serve model

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

SGLang

How to use YannQi/R-4B 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 "YannQi/R-4B" \
    --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": "YannQi/R-4B",
		"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 "YannQi/R-4B" \
        --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": "YannQi/R-4B",
		"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 YannQi/R-4B with Docker Model Runner:
```
docker model run hf.co/YannQi/R-4B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning

[📚 Arxiv Paper] [🤗 Hugging Face] [🤖️ ModelScope] [💻 Code]

⭐️ Introduction

In this repo, we present R-4B, a multimodal large language model designed for general-purpose auto-thinking, autonomously switching between step-by-step thinking and direct response generation based on task complexity. This capability enables R-4B to deliver high-quality responses while significantly improving inference efficiency and reducing computational costs.

The development of R-4B follows a two-stage training paradigm: (1) Bi-mode Annealing, which establishes both thinking and non-thinking capabilities for VQA; and (2) Bi-mode Policy Optimization (BPO), which enables the model to adaptively switch between thinking and non-thinking modes based on input demands.

🚀 Key Features

🧠 Think Smart, Act Fast: Adaptive & Controllable Thinking! Our model provides three-mode control over the response process.
- Auto-thinking Mode: Unleash auto-thinking that works across general topics, from simple Q&A to complex scientific analysis. It saves time and computation by thinking only when it matters.
- Support Manual Control: Explicitly command the model to use its thinking or non-thinking capabilities, enabling you to make your choices for every job.
🏆 Strong Performance, Open for Everyone! Our model is now fully open-source. It achieves state-of-the-art performance among models of comparable size.

📢 News

[2025.08.20] 🚀 vLLM Support is Here! Our R-4B model is now fully compatible with vLLM for high-performance inference.
[2025.08.18] 🏆 Top Rank Achieved! We are thrilled to announce that R-4B is now ranked #1 among all open-source models on the OpenCompass Multi-modal Reasoning Leaderboard!
[2025.08.11] 🥇 Rank #1! R-4B ranks first under 20B parameters on the OpenCompass Multi-modal Academic Leaderboard!
[2025.08.05] 🎉 R-4B is Released! Our model is now publicly available. You can download it from Hugging Face.

🔥 Quickstart

Below, we provide simple examples to show how to use R-4B with 🤗 Transformers.

Using 🤗 Transformers to Chat

Users can dynamically control the model's response by selecting one of three modes (auto-thinking, thinking, or non-thinking) with thinking_mode. thinking_mode=auto for auto-thinking mode; thinking_mode=long for thinking mode; thinking_mode=short for non-thinking mode. Default is auto-thinking.

import requests
from PIL import Image
import torch
from transformers import AutoModel, AutoProcessor

model_path = "YannQi/R-4B"

# Load model
model = AutoModel.from_pretrained(
    model_path,
    torch_dtype=torch.float32,
    trust_remote_code=True,
).to("cuda")

# Load processor
processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True)

# Define conversation messages
messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "http://images.cocodataset.org/val2017/000000039769.jpg",
            },
            {"type": "text", "text": "Describe this image."},
        ],
    }
]

# Apply chat template
text = processor.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    thinking_mode="auto"
)

# Load image
image_url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(image_url, stream=True).raw)

# Process inputs
inputs = processor(
    images=image,
    text=text,
    return_tensors="pt"
).to("cuda")

# Generate output
generated_ids = model.generate(**inputs, max_new_tokens=16384)
output_ids = generated_ids[0][len(inputs.input_ids[0]):]

# Decode output
output_text = processor.decode(
    output_ids,
    skip_special_tokens=True,
    clean_up_tokenization_spaces=False
)

# Print result
print("Auto-Thinking Output:", output_text)

Using vLLM for fast R-4B deployment and inference.

We recommend using vLLM for fast R-4B deployment and inference.

Install

The code of R-4B requires the newest vllm now. Please install from local source:

git clone https://github.com/vllm-project/vllm.git
cd vllm
VLLM_USE_PRECOMPILED=1 uv pip install --editable .

Online Serving

The thinking_mode switch is also available in APIs created by vLLM. Default is auto-thinking.

Serve

vllm serve \
    yannqi/R-4B \
    --served-model-name r4b \
    --tensor-parallel-size 8 \
    --gpu-memory-utilization 0.8 \
    --host 0.0.0.0 \
    --port 8000 \
    --trust-remote-code

Openai Chat Completion Client

import base64
from PIL import Image
from openai import OpenAI


# Set OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)

# image url
image_messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image_url",
                "image_url": {
                    "url": "http://images.cocodataset.org/val2017/000000039769.jpg"
                },
            },
            {"type": "text", "text": "Describe this image."},
        ],
    },
]



chat_response = client.chat.completions.create(
    model="r4b",
    messages=image_messages,
    max_tokens=16384,
    extra_body={
        "chat_template_kwargs": {"thinking_mode": "auto"},
    },
)
print("Chat response:", chat_response)

📈 Experimental Results

R-4B establishes itself with powerful, state-of-the-art perceptual abilities that are competitive with larger models.
In evaluation sets that require complex logical reasoning and mathematical problem-solving, such as WeMath, MathVerse, and LogicVista, R-4B displays a strong performance curve. This highlights its advanced adaptive thinking capacity for logical deduction and solving complex quantitative problems.

✒️ Citation

@misc{yang2025r4bincentivizinggeneralpurposeautothinking,
      title={R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning}, 
      author={Qi Yang and Bolin Ni and Shiming Xiang and Han Hu and Houwen Peng and Jie Jiang},
      year={2025},
      eprint={2508.21113},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2508.21113}, 
}

Acknowledgements

R-4B is developed based on the codebases of the following projects: LLaVA-Next, SigLIP2, Qwen3, Qwen2.5-VL, VLMEvalKit. We sincerely thank these projects for their outstanding work.