mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-05-15 01:52:36 +08:00
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>
perplexity
TODO