from transformers import AutoProcessor, Qwen3VLForConditionalGeneration
from peft import PeftModel

base_model = Qwen3VLForConditionalGeneration.from_pretrained(
    "aisingapore/Qwen-SEA-LION-v4-8B-VL",
    torch_dtype="bfloat16",
    device_map="auto",
)
model = PeftModel.from_pretrained(base_model, "aagdeyogipramana/SFT-Qwen-SEA-LION-v4-8B-VL-US")
processor = AutoProcessor.from_pretrained("aagdeyogipramana/SFT-Qwen-SEA-LION-v4-8B-VL-US")

Citation

bibtex

@article{lai2025med,
  title={Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models},
  author={Lai, Yuxiang and Zhong, Jike and Li, Ming and Zhao, Shitian and Yang, Xiaofeng},
  journal={arXiv preprint arXiv:2503.13939},
  year={2025}
}