failed to load model

#1
by 21world - opened

llama_model_load: error loading model: error loading model vocabulary: unknown pre-tokenizer type: 'falcon3'
llama_load_model_from_file: failed to load model

error from llama.cpp

Technology Innovation Institute org

Hi @21world
There is an ongoing fix for this: https://github.com/ggerganov/llama.cpp/pull/10883 once that PR gets merged you will be able to load the GGUF file

dir:
llama.cpp/src

file to edit :
llama.cpp

line :6578:
edit from:
tokenizer_pre == "falcon"){
to:
tokenizer_pre == "falcon"||tokenizer_pre == "falcon3") {

save file ,exit and compile with make

Thats all you need to make it work

Sign up or log in to comment