mirror of https://github.com/google/gemma.cpp.git
- Allow scaling of SFP weights - Allow using uncompressed weights - Do not try to compress weights in the main model calls - Reduce code duplication in weight handling with some macros Co-authored-by: Eugene Kliuchnikov <eustas@google.com> Co-authored-by: Thomas Fischbacher <tfish@google.com> Co-authored-by: Zoltan Szabadka <szabadka@google.com> |
||
|---|---|---|
| .. | ||
| BUILD | ||
| analyze.h | ||
| blob_store.cc | ||
| blob_store.h | ||
| compress-inl.h | ||
| compress.h | ||
| distortion.h | ||
| nuq-inl.h | ||
| nuq.h | ||
| nuq_test.cc | ||
| sfp-inl.h | ||
| sfp.h | ||
| sfp_test.cc | ||
| stats.cc | ||
| stats.h | ||
| test_util.h | ||