Skip to content

Commit db2d562

Browse files
committed
Remove debug assert
1 parent c07f5d7 commit db2d562

File tree

1 file changed

+0
-2
lines changed

1 file changed

+0
-2
lines changed

src/llama-quant.cpp

Lines changed: 0 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -765,8 +765,6 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
765765
}
766766
}
767767

768-
GGML_ASSERT(qs.n_ffn_down_exp != 0);
769-
770768
qs.n_ffn_down = qs.n_ffn_gate = qs.n_ffn_up = (int)model.hparams.n_layer;
771769

772770
// sanity checks for models that have attention layers

0 commit comments

Comments
 (0)