| .. |
|
CMakeLists.txt
|
938943cdbf
llama : move vocab, grammar and sampling into separate files (#8508)
|
hai 1 ano |
|
llama-grammar.cpp
|
2b1f616b20
ggml : reduce hash table reset cost (#8698)
|
hai 1 ano |
|
llama-grammar.h
|
4226a8d10e
llama : fix build + fix fabs compile warnings (#8683)
|
hai 1 ano |
|
llama-impl.h
|
938943cdbf
llama : move vocab, grammar and sampling into separate files (#8508)
|
hai 1 ano |
|
llama-sampling.cpp
|
938943cdbf
llama : move vocab, grammar and sampling into separate files (#8508)
|
hai 1 ano |
|
llama-sampling.h
|
938943cdbf
llama : move vocab, grammar and sampling into separate files (#8508)
|
hai 1 ano |
|
llama-vocab.cpp
|
cdd1889de6
convert : add support for XLMRoberta embedding models (#8658)
|
hai 1 ano |
|
llama-vocab.h
|
d3f0c7166a
Stop the generation when <|eom_id|> token is encountered - needed for Llama 3.1 tool call support (#8858)
|
hai 1 ano |
|
llama.cpp
|
d3f0c7166a
Stop the generation when <|eom_id|> token is encountered - needed for Llama 3.1 tool call support (#8858)
|
hai 1 ano |
|
unicode-data.cpp
|
07a3fc0608
Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. (#8258)
|
hai 1 ano |
|
unicode-data.h
|
f3f65429c4
llama : reorganize source code + improve CMake (#8006)
|
hai 1 ano |
|
unicode.cpp
|
938943cdbf
llama : move vocab, grammar and sampling into separate files (#8508)
|
hai 1 ano |
|
unicode.h
|
938943cdbf
llama : move vocab, grammar and sampling into separate files (#8508)
|
hai 1 ano |
Douglas Hanley
cdd1889de6
convert : add support for XLMRoberta embedding models (#8658)