]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 3752217)
llama : infill sampling handle very long tokens (#9924)
authorGeorgi Gerganov <redacted>
Thu, 17 Oct 2024 19:32:47 +0000 (22:32 +0300)
committerGitHub <redacted>
Thu, 17 Oct 2024 19:32:47 +0000 (22:32 +0300)
commit99bd4ac28c32cd17c0e337ff5601393b033dc5fc
tree33e073f53b9b595bf4c20357a1b2e9fd039482e6tree
parent3752217ed5a6a11864682fbf009bcb36afffd6bccommit | diff
llama : infill sampling handle very long tokens (#9924)

* llama : infill sampling handle very long tokens

ggml-ci

* cont : better indices

ggml-ci
include/llama.h diff | blob | history
src/llama-sampling.cpp diff | blob | history
src/llama-vocab.cpp diff | blob | history
src/llama.cpp diff | blob | history
Packaging of ggml-org/llama.cpp