Skywork VL Reward 7B

🚀 Skywork-VL Reward

Skywork-VL Reward is a 7B multimodal reward model that addresses the lack of such models in the market, promoting the development of multimodal reinforcement learning.

🔥 News

• May 12, 2025: Our technical report is now available on arXiv and we welcome citations: Skywork-VL Reward: An Effective Reward Model for Multimodal Understanding and Reasoning.
• April 24, 2025: We released Skywork-VL-Reward-7B, a state-of-the-art multimodal reward model on VLRewardBench, and have released our technical report on the R1V GitHub repository.

✨ Features

The lack of multimodal reward models on the market has become a major bottleneck restricting the development of multimodal reinforcement technology. We open source the 7B multimodal reward model Skywork-VL-Reward, injecting new momentum into the industry and opening a new chapter in multimodal reinforcement learning.

Skywork-VL-Reward is based on the Qwen2.5-VL-7B-Instruct architecture with the addition of a value head structure for training reward model. We obtained SOTA of 73.1 in VL-RewardBench and high score of 90.1 in RewardBench. In addition, our MPO trained on Skywork-R1V-2.0 further validates the effectiveness of the model. We hope that this multimodal reward model will contribute to the open source community! Please refer to our technical report for more details.

📚 Documentation

Skywork-VL Reward: An Effective Reward Model for Multimodal Understanding and Reasoning

📊 Evaluation

VL-RewardBench

RewardBench

📦 Installation

Set Up the Environment

conda create -n vl-reward python=3.11
conda activate vl-reward
bash setup.sh

💻 Usage Examples

Basic Usage

import torch
from transformers import AutoProcessor, Qwen2_5_VLForConditionalGeneration
from trl import AutoModelForCausalLMWithValueHead
from qwen_vl_utils import process_vision_info
from transformers.utils import cached_file
from safetensors import safe_open


processor = AutoProcessor.from_pretrained("Skywork/Skywork-VL-Reward-7B")
# The default range for the number of visual tokens per image in the model is 4-16384.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# min_pixels = 256*28*28
# max_pixels = 1280*28*28
# processor = AutoProcessor.from_pretrained("Skywork/Skywork-VL-Reward-7B", min_pixels=min_pixels, max_pixels=max_pixels)

model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    "Skywork/Skywork-VL-Reward-7B",
    device_map="auto",
    torch_dtype=torch.bfloat16,
)
# We recommend enabling flash_attention_2 for better acceleration and memory saving
# pip install flash-attn --no-build-isolation
#
# model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
#     "Skywork/Skywork-VL-Reward-7B",
#     device_map="auto",
#     torch_dtype=torch.bfloat16,
#     attn_implementation="flash_attention_2",
# )

model = AutoModelForCausalLMWithValueHead.from_pretrained(model)
vhead_file = cached_file(
    path_or_repo_id="Skywork/Skywork-VL-Reward-7B", filename="value_head.safetensors"
)
with safe_open(vhead_file, framework="pt", device="cpu") as f:
    vhead_params = {key: f.get_tensor(key) for key in f.keys()}
model.load_state_dict(vhead_params, strict=False)
model.requires_grad_(False)
model.eval()

# score: 23.89
# if you use flash_attention_2 the score will be 23.76
demo_image = "demo.jpg"
demo_question = "Hint: Please answer the question and provide the correct option letter, e.g., A, B, C, D, at the end.\nQuestion: Is Purple the highest value?\nChoices:\n(A) no\n(B) yes"
demo_answer = "The answer is: B"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": demo_image,
            },
            {
                "type": "text",
                "text": demo_question,
            },
        ],
    },
    {
        "role": "assistant",
        "content": demo_answer,
    },
]
text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=False
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    return_tensors="pt",
)
inputs = inputs.to("cuda")
values = model(**inputs, return_dict=True, use_cache=False)[-1]
scores = values.gather(
    dim=-1, index=(inputs["attention_mask"].sum(dim=-1, keepdim=True) - 1)
)
score = scores[0].item()
print("Reward Score is: ", score)

📄 License

This project is licensed under the MIT license.

📚 Citation

If you use this work in your research, please cite:

@misc{wang2025skyworkvlrewardeffectivereward,
      title={Skywork-VL Reward: An Effective Reward Model for Multimodal Understanding and Reasoning}, 
      author={Xiaokun Wang and Chris and Jiangbo Pei and Wei Shen and Yi Peng and Yunzhuo Hao and Weijie Qiu and Ai Jian and Tianyidan Xie and Xuchen Song and Yang Liu and Yahui Zhou},
      year={2025},
      eprint={2505.07263},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2505.07263}, 
}