vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama : fix parentheses in attention layer count sanity check

Browse source 
There was otherwise a warning when compiling.
This commit is contained in:
Francis Couture-Harpin 2024-04-08 14:41:39 -04:00
parent 6804714190
commit 7bab4c055c
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama.cpp
View file

@ -13483,7 +13483,7 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
// - qs.n_attention_wv == 0 for Mamba models
// - qs.n_attention_wv == model.hparams.n_layer for Transformer models
//
GGML_ASSERT(qs.n_attention_wv == 0 || qs.n_attention_wv == (int)model.hparams.n_layer && "n_attention_wv is unexpected");
GGML_ASSERT((qs.n_attention_wv == 0 || qs.n_attention_wv == (int)model.hparams.n_layer) && "n_attention_wv is unexpected");
size_t total_size_org = 0;
size_t total_size_new = 0;