Co-authored-by: matteo serva <matteo.serva@gmail.com>
* llama_sampler_penalties : clamp penalty_last_n to zero
arg.cpp
* common : move arg parser to arg.cpp * better categorize args * add cmake * missing climits * missing cstdarg * common : more explicit includes * fix build * refactor gpt_params_parse * update server readme * fix test --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>