typo correction (#8891)

diff --git a/include/llama.h b/include/llama.h
index f23355a6bc9593e53d5978ff81b381182dcccd61..66c266298e86f0204f6d466368abd8d86465a99c 100644 (file)
--- a/include/llama.h
+++ b/include/llama.h
@@ -345,7 +345,7 @@ extern "C" {
         int32_t nthread;                     // number of threads to use for quantizing, if <=0 will use std::thread::hardware_concurrency()
         enum llama_ftype ftype;              // quantize to this llama_ftype
         enum ggml_type output_tensor_type;   // output tensor type
-        enum ggml_type token_embedding_type; // itoken embeddings tensor type
+        enum ggml_type token_embedding_type; // token embeddings tensor type
         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