Zhang, Renrui and Han, Jiaming and Liu, Chris and Gao, Peng and Zhou, Aojun and Hu, Xiangfei and Yan, Shilin and Lu, Pan and Li, Hongsheng and Qiao, Yu ::: LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention

• The base model - llama with7B parameter is a text ot text chatbot, it cannot understand audio,
• appended to transformer, and trained with it, with the base frozen
• llama forward behaviours
• why transposea
• how it works, as a illustration