During November 2024, Baole worked on the modelscope/ms-swift repository, focusing on maintaining compatibility between the Qwen2 Transformer model and TorchAcc when using transformers version 4.45 or higher. He addressed a complex issue involving rotary positional embeddings and causal mask logic, updating the attention mechanism to ensure correct embedding alignment and autoregressive behavior with the latest library changes. Using deep learning expertise and Python, Baole validated the fix to support stable production usage. His work demonstrated a strong understanding of model optimization and library integration, ensuring that modelscope/ms-swift remained robust and functional across evolving dependencies.