From 076b40ce5bf8fef2a7f34064c289dbf4f4e22908 Mon Sep 17 00:00:00 2001
From: Michel Galley <mgalley@acm.org>
Date: Wed, 22 Jun 2022 10:47:55 -0700
Subject: [PATCH] Point to right diagram

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

diff --git a/README.md b/README.md
index 54f6d719..9102bce7 100644
--- a/README.md
+++ b/README.md
@@ -7,7 +7,7 @@ Project Webpage:
 Arxiv paper: [GODEL: Large-Scale Pre-training for Goal-Directed Dialog
 ]() Author List
 
-![image](doc/DialoGLM.png)
+![image](doc/GODEL.png)
 
 GODEL is a large-scale pre-trained model for goal-directed dialogs. It is parameterized with a Transformer-based encoder-decoder model and trained for response generation grounded in external text, which allows more effective fine-tuning on dialog tasks that require conditioning the response on information that is external to the current conversation (e.g., a retrieved document). The pre-trained model can be efficiently fine-tuned and adapted to accomplish a new dialog task with a handful of task-specific dialogs.