| .. |
|
CMakeLists.txt
|
938943cdbf
llama : move vocab, grammar and sampling into separate files (#8508)
|
1 year ago |
|
llama-grammar.cpp
|
df270ef745
llama : refactor sampling v2 (#9294)
|
1 year ago |
|
llama-grammar.h
|
df270ef745
llama : refactor sampling v2 (#9294)
|
1 year ago |
|
llama-impl.h
|
cea1486ecf
log : add CONT level for continuing previous log entry (#9610)
|
1 year ago |
|
llama-sampling.cpp
|
b0f27361f3
sampling : avoid expensive softmax during greedy sampling (#9605)
|
1 year ago |
|
llama-sampling.h
|
19f4a7b296
llama : refactor samplers internal implementation (#9370)
|
1 year ago |
|
llama-vocab.cpp
|
31ac5834fe
llama : keep track of all EOG tokens in the vocab (#9609)
|
1 year ago |
|
llama-vocab.h
|
31ac5834fe
llama : keep track of all EOG tokens in the vocab (#9609)
|
1 year ago |
|
llama.cpp
|
31ac5834fe
llama : keep track of all EOG tokens in the vocab (#9609)
|
1 year ago |
|
unicode-data.cpp
|
07a3fc0608
Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. (#8258)
|
1 year ago |
|
unicode-data.h
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
1 year ago |
|
unicode.cpp
|
503147a9f9
unicode : add <algorithm> (#9508)
|
1 year ago |
|
unicode.h
|
938943cdbf
llama : move vocab, grammar and sampling into separate files (#8508)
|
1 year ago |
Georgi Gerganov
31ac5834fe
llama : keep track of all EOG tokens in the vocab (#9609)