llama.cpp

3fec68be - convert : add support of codeqwen due to tokenizer (#6707)

convert : add support of codeqwen due to tokenizer (#6707) * add support of codeqwen due to tokenizer * override load_hparams * fix typo * fix load_params * convert : fix whitespace --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>