Georgi GerganovandGitHub 30caac3a68 llama : the WPM vocabs use the CLS token as BOS (#10930) ...

* llama : the WPM vocabs use the CLS token as BOS

ggml-ci

* llama : add comment

2024-12-24 09:44:20 +02:00

..

CMakeLists.txt

remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797)

2024-12-12 19:02:49 +01:00

llama-grammar.cpp

llama : minor grammar refactor (#10897)

2024-12-19 17:42:13 +02:00

llama-grammar.h

llama : minor grammar refactor (#10897)

2024-12-19 17:42:13 +02:00

llama-impl.h

log : add CONT level for continuing previous log entry (#9610)

2024-09-24 10:15:35 +03:00

llama-sampling.cpp

sampling : refactor + optimize penalties sampler (#10803)

2024-12-16 12:31:14 +02:00

llama-sampling.h

llama : add DRY sampler (#9702)

2024-10-25 19:07:34 +03:00

llama-vocab.cpp

llama : the WPM vocabs use the CLS token as BOS (#10930)

2024-12-24 09:44:20 +02:00

llama-vocab.h

llama : the WPM vocabs use the CLS token as BOS (#10930)

2024-12-24 09:44:20 +02:00

llama.cpp

llama : support InfiniAI Megrez 3b (#10893)

2024-12-23 01:35:44 +01:00

unicode-data.cpp

server : better security control for public deployments (#9776)

2024-10-08 13:27:04 +02:00

unicode-data.h

llama : reduce compile time and binary size (#9712)

2024-10-02 15:49:55 +02:00

unicode.cpp

unicode : improve naming style (#10838)

2024-12-16 12:31:45 +02:00

unicode.h

unicode : improve naming style (#10838)

2024-12-16 12:31:45 +02:00