From 6a299089f3dcff49e0d3d87d32ae4d10c325cf88 Mon Sep 17 00:00:00 2001
From: cjon256 <3659487+cjon256@users.noreply.github.com>
Date: Wed, 27 Sep 2023 10:25:36 -0400
Subject: [PATCH] Update README.md

minor typo (TTS?)
---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index bda9f8e..4cddbcd 100644
--- a/README.md
+++ b/README.md
@@ -13,7 +13,7 @@ Linear Diffusion aims to be to Diffusion Models what Logistic Regression is to L
 Networks. One of my personal favorite benchmarks is that Logistic Regression, often dismissed by 
 data scientists as "just" a linear model, is able to achieve > 90% accuracy on the MNIST data set. 
 While this is far from state of the art, it is much better than many people naively guess. Likewise while Linear
-Diffusion is far from the capabilities of models multiple orders of magnitude inside, it still performs surprisingly well!
+Diffusion is far from the capabilities of models multiple orders of magnitude in size, it still performs surprisingly well!
 
 Diffusion models can be broken down into 3 major parts: