| .. |
|
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
|
Internal change.
|
2025-03-11 23:20:20 -07:00 |
|
common.cc
|
Add note on attention length and SFP
|
2025-03-20 00:39:06 -07:00 |
|
common.h
|
Rename ModelTraining to PromptWrapping which is a more accurate name.
|
2024-12-13 07:45:59 -08:00 |
|
configs.cc
|
Set the secondary EOS for Gemma2
|
2025-03-22 01:32:22 +08:00 |
|
configs.h
|
Add support for a secondary EOS token
|
2025-03-20 12:28:31 -07:00 |
|
configs_test.cc
|
Moved the vit config fields to their own config struct
|
2025-01-15 01:09:49 -08:00 |
|
gemma-inl.h
|
Fix the EOS checking
|
2025-03-22 01:32:22 +08:00 |
|
gemma.cc
|
Refactor Gemma ctor and improve pool NUMA support
|
2025-03-14 10:19:00 -07:00 |
|
gemma.h
|
Refactor Gemma ctor and improve pool NUMA support
|
2025-03-14 10:19:00 -07:00 |
|
kv_cache.cc
|
Add KVCache.DeepCopy() . Will be useful for implementing sampling functionality like beam sampling, parallel sampling, CoT Decoding (à la https://arxiv.org/abs/2402.10200)
|
2025-02-10 04:10:29 -08:00 |
|
kv_cache.h
|
Add KVCache.DeepCopy() . Will be useful for implementing sampling functionality like beam sampling, parallel sampling, CoT Decoding (à la https://arxiv.org/abs/2402.10200)
|
2025-02-10 04:10:29 -08:00 |
|
run.cc
|
Set the secondary EOS for Gemma2
|
2025-03-22 01:32:22 +08:00 |
|
tensor_index.cc
|
Internal change.
|
2025-03-11 23:20:20 -07:00 |
|
tensor_index.h
|
Added the TensorInfo arg to the compressor so the shape and scale can be output correctly to the file in future.
|
2024-12-11 01:26:35 -08:00 |
|
tensor_index_test.cc
|
Moved the vit config fields to their own config struct
|
2025-01-15 01:09:49 -08:00 |
|
tokenizer.cc
|
Internal change.
|
2025-03-11 23:20:20 -07:00 |
|
tokenizer.h
|
Add support for a secondary EOS token
|
2025-03-20 12:28:31 -07:00 |
|
weights.cc
|
Fix the link error when building `compress_weights` with Clang on macOS
|
2025-02-09 00:13:25 +08:00 |
|
weights.h
|
Fix PaliGemma models.
|
2025-03-13 06:28:29 -07:00 |
d42deaa27c