Error when trying to run llamafile prepared on this gguf version
#1
by
cyrusmsk
- opened
M1 Pro
macOS 13.3.1
After llamafile-convert
Just running prepared llamafile gives an error:
llama_model_load: error loading model: error loading model vocabulary: unknown pre-tokenizer type: 'smaug-bpe'
llama_load_model_from_file: failed to load model
llama_init_from_gpt_params: error: failed to load model 't-lite-instruct-0.1-q4_k_m.gguf'
{"function":"load_model","level":"ERR","line":450,"model":"t-lite-instruct-0.1-q4_k_m.gguf","msg":"unable to load model","tid":"34364426944","timestamp":1721641732}