From 6d4f131d0ae62d9e3bf342c7edaeab307c3a9f52 Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Sat, 22 Apr 2023 02:50:35 -0300
Subject: [PATCH] Update Low-VRAM-guide.md

---
 docs/Low-VRAM-guide.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/Low-VRAM-guide.md b/docs/Low-VRAM-guide.md
index d504d4e..1dc86f9 100644
--- a/docs/Low-VRAM-guide.md
+++ b/docs/Low-VRAM-guide.md
@@ -48,4 +48,4 @@ With this, I am able to load a 30b model into my RTX 3090, but it takes 10 secon
 
 ### DeepSpeed (experimental)
 
-An experimental alternative to all of the above is to use DeepSpeed: [guide](https://github.com/oobabooga/text-generation-webui/wiki/DeepSpeed).
\ No newline at end of file
+An experimental alternative to all of the above is to use DeepSpeed: [guide](DeepSpeed.md).