llama : use n_embd_gqa instead of n_embd to handle llama-2 70B (#2433)

1 files changed, 1 insertions, 0 deletions

diff --git a/examples/save-load-state/save-load-state.cpp b/examples/save-load-state/save-load-state.cpp
index 4c86885..61c71c3 100644
--- a/examples/save-load-state/save-load-state.cpp
+++ b/examples/save-load-state/save-load-state.cpp
@@ -26,6 +26,7 @@ int main(int argc, char ** argv) {
     auto lparams = llama_context_default_params();
 
     lparams.n_ctx     = params.n_ctx;
+    lparams.n_gqa     = params.n_gqa;
     lparams.seed      = params.seed;
     lparams.f16_kv    = params.memory_f16;
     lparams.use_mmap  = params.use_mmap;