From f71504293b14266e2063cbcc780cbfc277381660 Mon Sep 17 00:00:00 2001
From: YeonwooSung <neos960518@gmail.com>
Date: Thu, 21 Mar 2024 22:44:04 +0900
Subject: [PATCH] docs: Document the garole optimizer

---
 LLMs/training/sft_mistral_7b_garole/README.md | 3 +++
 1 file changed, 3 insertions(+)
 create mode 100644 LLMs/training/sft_mistral_7b_garole/README.md

diff --git a/LLMs/training/sft_mistral_7b_garole/README.md b/LLMs/training/sft_mistral_7b_garole/README.md
new file mode 100644
index 0000000..a4328fc
--- /dev/null
+++ b/LLMs/training/sft_mistral_7b_garole/README.md
@@ -0,0 +1,3 @@
+# Garole Optimizer
+
+With [garole](https://huggingface.co/papers/2403.03507), you could pre-train the 7B LLM model on consumer type hardwares.