From 3823ba3c39dc7ec09664b96e96eb3a80597bc401 Mon Sep 17 00:00:00 2001
From: yiranyyu <2606375857@qq.com>
Date: Thu, 23 May 2024 16:35:41 +0800
Subject: [PATCH] update readme

---
 docs/compare_with_phi-3_vision.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/compare_with_phi-3_vision.md b/docs/compare_with_phi-3_vision.md
index 7c2ac77..3df45e2 100644
--- a/docs/compare_with_phi-3_vision.md
+++ b/docs/compare_with_phi-3_vision.md
@@ -6,7 +6,7 @@ Comparison results of Phi-3-vision-128K-Instruct and MiniCPM-Llama3-V 2.5, regar
  
  ## Hardeware Requirements （硬件需求）
 
-With in4 quantization, MiniCPM-Llama3-V 2.5 delivers smooth inference with only 8GB of GPU memory.
+With int4 quantization, MiniCPM-Llama3-V 2.5 delivers smooth inference with only 8GB of GPU memory.
 
 通过 int4 量化，MiniCPM-Llama3-V 2.5 仅需 8GB 显存即可推理。