From 1f329f351aaf7f9c01b32b4e5db2db84e50a533a Mon Sep 17 00:00:00 2001
From: rpan <research4pan@gmail.com>
Date: Tue, 2 Apr 2024 19:54:27 +0800
Subject: [PATCH] Add explanation for LISA with model-parallelism

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

diff --git a/README.md b/README.md
index 881602e8f..010805298 100644
--- a/README.md
+++ b/README.md
@@ -124,6 +124,8 @@ cd data && ./download.sh alpaca && cd -
   --lisa_interval_steps 20
 ```
 
+We are still working on integrating official model-parallelism support for LISA. Please stay tuned :smile:
+
 ### Finetuning (LoRA)
 LoRA is a parameter-efficient finetuning algorithm and is more efficient than full finetuning.
 ```sh