happyz
/
gemma.cpp
mirror of https://github.com/google/gemma.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
gemma.cpp/gemma
History
Daniel Keysers e54d9cbddd Fix Griffin model: 
- use HalfRope position encodings
- zero-initialize the caches for each Generate at position 0

The lack of the latter made the tests in gemma_test dependent on each other.

PiperOrigin-RevId: 694509054
 		2024-11-08 08:30:53 -08:00
..
evals Add MMLU eval to github 2024-05-20 10:20:53 -07:00
instantiations Eliminated TConfig. 2024-10-17 05:04:22 -07:00
activations.h Simpler MatMul interface, vocab types, Tristate for use_spinning 2024-11-04 07:48:29 -08:00
common.cc Eliminated TConfig. 2024-10-17 05:04:22 -07:00
common.h Fix PaliGemma's GenerateImageTokensT(). 2024-10-18 01:34:13 -07:00
configs.cc Fix Griffin model: 2024-11-08 08:30:53 -08:00
configs.h Simpler MatMul interface, vocab types, Tristate for use_spinning 2024-11-04 07:48:29 -08:00
configs_test.cc Fix Griffin model: 2024-11-08 08:30:53 -08:00
gemma-inl.h Fix Griffin model: 2024-11-08 08:30:53 -08:00
gemma.cc Simpler MatMul interface, vocab types, Tristate for use_spinning 2024-11-04 07:48:29 -08:00
gemma.h Simpler MatMul interface, vocab types, Tristate for use_spinning 2024-11-04 07:48:29 -08:00
kv_cache.cc Fix Griffin model: 2024-11-08 08:30:53 -08:00
kv_cache.h Fix Griffin model: 2024-11-08 08:30:53 -08:00
run.cc Simpler MatMul interface, vocab types, Tristate for use_spinning 2024-11-04 07:48:29 -08:00
tokenizer.cc Factor out addition of ViTConfig to a ModelConfig. 2024-10-28 05:29:33 -07:00
tokenizer.h 7x compile time speedup: shard gemma.cc 2024-07-03 06:35:04 -07:00
weights.cc Use NestedPools, add NUMA infra 2024-10-18 08:11:18 -07:00
weights.h Simpler MatMul interface, vocab types, Tristate for use_spinning 2024-11-04 07:48:29 -08:00