Converting an AWQ model to TinyChatEngine format example

[ylhsieh]

Hi, I have a model from huggingface hub that is already in AWQ format, i.e., the model consists of WQLinear_GEMM modules. It appears that using llama_exporter.py is not suitable for this action. Is there a way to convert them into TinyChatEngine-compatible format? Thanks! P.S. the model is from huggingface.co/yentinglin/Taiwan-LLM-7B-v2.0.1-chat-awq for your reference.