How I can load Grok-2 model in llama.cpp?

[Totorong-Bot]

As I know a pr for Grok-2 was already merged to mater branch. however, I still faced "unknown tokenizer error" even on b6490
I used unsloth's rok-2-UD-Q5_K_XL GGUF

print_info: file format = GGUF V3 (latest) print_info: file type = Q5_K - Medium print_info: file size = 177.91 GiB (5.67 BPW) llama_model_load: error loading model: error loading model vocabulary: unknown pre-tokenizer type: 'grok-2' llama_model_load_from_file_impl: failed to load model common_init_from_params: failed to load model './grok_gguf/grok-2-UD-Q5_K_XL-00001-of-00004.gguf' srv load_model: failed to load model, './grok_gguf/grok-2-UD-Q5_K_XL-00001-of-00004.gguf' srv operator(): operator(): cleaning up before exit... main: exiting due to model loading error

totorong@tomato-2 llama.cpp % git fetch
totorong@tomato-2 llama.cpp % git pull
Already up to date.

Could anyone give some advice for me?

[CISC]

Are you sure you are on the master branch? Check src/llama-vocab.cpp, it should have "grok-2" in it.