python tools/patch_model.py --base_model <path_or_name_to_original_model>
                            --patch_model openlmlab/open-chinese-llama-7b-patch
                            --base_model_format <hf_or_raw>

python cli_demo.py --model openlmlab/open-chinese-llama-7b-patch
                   --devices 0
                   --max_length 1024
                   --do_sample true
                   --top_k 40
                   --top_p 0.8
                   --temperature 0.7
                   --penalty 1.02

python convert_model.py --model_path <path_or_name_to_your_hf_or_raw_model>
                        --source_format hf
                        --target_format raw
                        --target_path <path_you_want_to_save_the_converted_model>
                        --raw_parallel_degree 2
                        --raw_parallel_devices 0,1