From 31958546c3e4695a8a24bb7ba3b79a8f76d05afe Mon Sep 17 00:00:00 2001
From: Nexes the Old <124105151+Nexesenex@users.noreply.github.com>
Date: Wed, 7 Aug 2024 01:41:54 +0200
Subject: [PATCH] typo correction (#8891)

---
 include/llama.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/llama.h b/include/llama.h
index f23355a6b..66c266298 100644
--- 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