search

kaust-generative-ai / local-deployment-llama-cpp

Project to help you get started working with LLMs locally with LLaMA C++.
Apache License 2.0
1 stars 1 forks source link

Add some logging examples #14

Open davidrpugh opened 1 month ago

davidrpugh commented 1 month ago

Lots of ways to customize the logging. From the docs for llama-cli...

-ld,   --logdir LOGDIR                  path under which to save YAML logs (no logging if unset)
--log-disable                           Log disable
--log-file FNAME                        Log to file
--log-colors                            Enable colored logging
                                        (env: LLAMA_LOG_COLORS)
-v,    --verbose, --log-verbose         Set verbosity level to infinity (i.e. log all messages, useful for
                                        debugging)
-lv,   --verbosity, --log-verbosity N   Set the verbosity threshold. Messages with a higher verbosity will be
                                        ignored.
                                        (env: LLAMA_LOG_VERBOSITY)
--log-prefix                            Enable prefx in log messages
                                        (env: LLAMA_LOG_PREFIX)
--log-timestamps                        Enable timestamps in log messages
                                        (env: LLAMA_LOG_TIMESTAMPS)

...not all of these flags are working on my source build at the moment. Maybe there is an issue with my build. Should try these with an official release.