Cleanup: add wrapper functions and rename vars to interleaved

google / gemma.cpp

lightweight, standalone C++ inference engine for Google's Gemma models.

Apache License 2.0

5.9k stars 499 forks source link

Closed copybara-service[bot] closed 1 month ago

copybara-service[bot] commented 1 month ago

Cleanup: add wrapper functions and rename vars to interleaved

Simplifies the TransformerLayer function. Use interleaved* instead of _and_queries.