mirror of
https://github.com/ggerganov/llama.cpp
synced 2026-03-09 00:29:38 +01:00
* add n_embd_full to support extended embed * don't change output * rename to n_embd_inp * restore n_embd where applicable |
||
|---|---|---|
| .. | ||
| llama-cpp.h | ||
| llama.h | ||