From fecce0e1a56e1d5d3def8bbc73feb9e211cfbc16 Mon Sep 17 00:00:00 2001
From: John Smith <yfshi123@163.com>
Date: Sat, 18 Mar 2023 18:21:01 +0800
Subject: [PATCH] Update README.md

---
 README.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/README.md b/README.md
index 30d84e9..a34d5d6 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,8 @@
 # Alpaca Lora 4bit
 Made some adjust for the code in peft and gptq for llama, and make it possible for lora finetuning with a 4 bits base model. The same adjustment can be made for 2, 3 and 8 bits.
 <br>
+Still numerically unstable.
+<br>
 # Requirements
 gptq-for-llama: https://github.com/qwopqwop200/GPTQ-for-LLaMa<br>
 peft: https://github.com/huggingface/peft.git<br>