1 files changed, 1 insertions, 0 deletions
diff --git a/llama.h b/llama.h
index 6e5e1df6..422f2852 100644
--- a/llama.h
+++ b/llama.h
@@ -164,6 +164,7 @@ extern "C" {
         enum llama_ftype ftype;      // quantize to this llama_ftype
         bool allow_requantize;       // allow quantizing non-f32/f16 tensors
         bool quantize_output_tensor; // quantize output.weight
+        bool only_copy;              // only copy tensors - ftype, allow_requantize and quantize_output_tensor are ignored
     } llama_model_quantize_params;
 
     // grammar types