1
0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-04-23 08:16:06 +00:00
Georgi Gerganov 11ac9800af
llama : improve infill support and special token detection ()
* llama : improve infill support

ggml-ci

* llama : add more FIM token strings

ggml-ci

* server : update prompt on slot restore ()

* gguf : deprecate old FIM token KVs
2024-10-12 08:21:51 +03:00
..