mirror of
https://github.com/ggerganov/llama.cpp
synced 2026-04-16 04:05:45 +02:00
36680f6e40
1. guess n_layers; 2. relax warnings on context size; 3. add a note that its derivations are also supported. Co-authored-by: Judd <foldl@boxvest.com> |
||
|---|---|---|
| .. | ||
| CMakeLists.txt | ||
| perplexity.cpp | ||
| README.md | ||
perplexity
TODO