From 2aaf80df0055faf6cd64c6917821154f48e79338 Mon Sep 17 00:00:00 2001
From: Tristan Thrush <tristan@huggingface.co>
Date: Thu, 19 Sep 2024 14:56:17 -0700
Subject: [PATCH] make image url in readme a raw content link

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

diff --git a/README.md b/README.md
index 092fd30..b9117fb 100644
--- a/README.md
+++ b/README.md
@@ -9,7 +9,7 @@ Essentially, our approach encourages training on domains where lower loss is
 very correlated with higher downstream performance. We can use existing and freely available LLMs to do this:
 
 <div align="center">
-  <img src="https://github.com/TristanThrush/perplexity-correlations/blob/main/assets/perplexity_correlations_diagram.png" alt="Perplexity Correlations diagram" width="400"/>
+  <img src="https://raw.githubusercontent.com/TristanThrush/perplexity-correlations/main/assets/perplexity_correlations_diagram.png" alt="Perplexity Correlations diagram" width="400"/>
 </div>
 
 We want to pretrain on these correlated domains, because pretraining on them will