Instructions to use WaltonFuture/Qwen2.5VL-7b-RLCS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WaltonFuture/Qwen2.5VL-7b-RLCS with Transformers:

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

pipe = pipeline("image-text-to-text", model="WaltonFuture/Qwen2.5VL-7b-RLCS")
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("WaltonFuture/Qwen2.5VL-7b-RLCS")
model = AutoModelForImageTextToText.from_pretrained("WaltonFuture/Qwen2.5VL-7b-RLCS")
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 WaltonFuture/Qwen2.5VL-7b-RLCS with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WaltonFuture/Qwen2.5VL-7b-RLCS"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WaltonFuture/Qwen2.5VL-7b-RLCS",
		"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/WaltonFuture/Qwen2.5VL-7b-RLCS

SGLang

How to use WaltonFuture/Qwen2.5VL-7b-RLCS 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 "WaltonFuture/Qwen2.5VL-7b-RLCS" \
    --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": "WaltonFuture/Qwen2.5VL-7b-RLCS",
		"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 "WaltonFuture/Qwen2.5VL-7b-RLCS" \
        --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": "WaltonFuture/Qwen2.5VL-7b-RLCS",
		"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 WaltonFuture/Qwen2.5VL-7b-RLCS with Docker Model Runner:
```
docker model run hf.co/WaltonFuture/Qwen2.5VL-7b-RLCS
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

🐙 GitHub Repo: waltonfuture/RL-with-Cold-Start
📜 Paper (arXiv): Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start (arXiv:2505.22334)

Cold Start Stage

We conduct supervised fine-tuning on Qwen2.5-VL-3B and Qwen2.5-VL-7B using ms-swift. In this stage, please refer to this curated dataset distilled from Qwen2.5-VL-32B using rejection sampling.

Setup

git clone https://github.com/waltonfuture/RL-with-Cold-Start.git
cd RL-with-Cold-Start/SFT
pip install -e .

Prepare Data

python convert_data.py

SFT

bash qwen2.5vl_sft.sh

The checkpoint can be found in SFT/output.

RL Stage

We further conduct GRPO using EasyR1. Please refer to this dataset for the GRPO training.

Setup

git clone https://github.com/waltonfuture/RL-with-Cold-Start.git
cd RL-with-Cold-Start/GRPO
pip install -e .

GRPO Training (replace the checkpoint with the model after SFT)

bash examples/qwen2_5_vl_7b_grpo.sh

Merge Checkpoint in Hugging Face Format

python3 scripts/model_merger.py --local_dir checkpoints/easyr1/qwen2_5_vl_7b_grpo/global_step_80/actor

Data Access

Our two stage datasets are now available on Huggingface.

Stage	Data
Cold Start	Multimodal-Cold-Start
RL	Multimodal-RL-Data

Model Access

Our models are now available on Huggingface.

Backbone	Our model
Qwen2.5-VL-7b	Qwen2.5VL-7b-RL-with-Cold-Start
Qwen2.5-VL-3b	Qwen2.5VL-3b-RL-with-Cold-Start

Acknowledgment

Our models are built upon the amazing Qwen2.5-VL family. We thank EasyR1 and ms-swift for their training codes.

Contact

Please contact Lai Wei (waltonfuture@sjtu.edu.cn) if needed.

Citation

@article{wei2025advancing,
  title={Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start},
  author={Wei, Lai and Li, Yuting and Zheng, Kaipeng and Wang, Chen and Wang, Yue and Kong, Linghe and Sun, Lichao and Huang, Weiran},
  journal={arXiv preprint arXiv:2505.22334},
  year={2025}
}