google / gemma.cpp

lightweight, standalone C++ inference engine for Google's Gemma models.
Apache License 2.0
5.8k stars 491 forks source link

Add support for custom sampling function to runtime config. #217

Closed szabadka closed 1 month ago

szabadka commented 1 month ago

With this addition the ComputeCrossEntropy function can be moved to its own library, because now we can compute it using only the public API functions from gemma.h