Don't crash on ftype (formerly f16) == 4 (#917)

1 files changed, 1 insertions, 0 deletions

diff --git a/llama.h b/llama.h
index 8a0d50fb..7a258a1e 100644
--- a/llama.h
+++ b/llama.h
@@ -71,6 +71,7 @@ extern "C" {
         LLAMA_FTYPE_MOSTLY_F16  = 1,  // except 1d tensors
         LLAMA_FTYPE_MOSTLY_Q4_0 = 2,  // except 1d tensors
         LLAMA_FTYPE_MOSTLY_Q4_1 = 3,  // except 1d tensors
+        LLAMA_FTYPE_MOSTLY_Q4_1_SOME_F16 = 4, // tok_embeddings.weight and output.weight are F16
     };
 
     LLAMA_API struct llama_context_params llama_context_default_params();