gemma.cpp/gemma
Daniel Keysers f8835fe4a4 Add support for PaliGemma Vision-LM (224x224) to gemma.cpp
See https://arxiv.org/abs/2407.07726 for a description of the model.
Because PaliGemma operates as a prefix-LM on the image+prompt, add support for that.

PiperOrigin-RevId: 677841119
2024-09-23 10:09:38 -07:00
..
evals Add MMLU eval to github 2024-05-20 10:20:53 -07:00
instantiations Add support for PaliGemma Vision-LM (224x224) to gemma.cpp 2024-09-23 10:09:38 -07:00
activations.h Add support for PaliGemma Vision-LM (224x224) to gemma.cpp 2024-09-23 10:09:38 -07:00
common.cc Add support for PaliGemma Vision-LM (224x224) to gemma.cpp 2024-09-23 10:09:38 -07:00
common.h Add support for PaliGemma Vision-LM (224x224) to gemma.cpp 2024-09-23 10:09:38 -07:00
configs.h Add support for PaliGemma Vision-LM (224x224) to gemma.cpp 2024-09-23 10:09:38 -07:00
gemma-inl.h Add support for PaliGemma Vision-LM (224x224) to gemma.cpp 2024-09-23 10:09:38 -07:00
gemma.cc Add support for PaliGemma Vision-LM (224x224) to gemma.cpp 2024-09-23 10:09:38 -07:00
gemma.h Add support for PaliGemma Vision-LM (224x224) to gemma.cpp 2024-09-23 10:09:38 -07:00
kv_cache.cc Major revamp #2 of Prefill: fix token order, parallel for multi-query 2024-07-25 03:28:55 -07:00
kv_cache.h Major revamp #2 of Prefill: fix token order, parallel for multi-query 2024-07-25 03:28:55 -07:00
run.cc Add support for PaliGemma Vision-LM (224x224) to gemma.cpp 2024-09-23 10:09:38 -07:00
tokenizer.cc Add support for PaliGemma Vision-LM (224x224) to gemma.cpp 2024-09-23 10:09:38 -07:00
tokenizer.h 7x compile time speedup: shard gemma.cc 2024-07-03 06:35:04 -07:00
weights.cc 1.3x prefill, 0.95x decode: matmul replacing last matvec 2024-08-12 03:36:01 -07:00
weights.h Add support for PaliGemma Vision-LM (224x224) to gemma.cpp 2024-09-23 10:09:38 -07:00