update readme

README.md

@@ -2,6 +2,7 @@ This repo contains sparsity report for each of the pruned model in the table bel
 
 The report (csv) shows layer-wise sparsity, sparsity by tile of 128x16, sparsity by col and row global to its layers.
 
+![Perplexity over Sparsity](./perplexity_vs_sparsity.png)
 
 Pruning ```meta-llama/Meta-Llama-3.1-8B``` with Wanda
 | Weight Target Sparsity | Perplexity (lower is better) |
@@ -15,10 +16,7 @@ Pruning ```meta-llama/Meta-Llama-3.1-8B``` with Wanda
 | 60                      | 20.2265                     |
 | 70                      | 103.5209                    |
 
-![Perplexity over Sparsity](./perplexity_vs_sparsity.png)
-
-
-> For a more granular sparsity report within a given tile, pls continue below
+> For a more granular sparsity report within a given tile, pls continue below.
 
 # Install
 ```pip install torch ipython pandas```