Update README.md

README.md

@@ -2,6 +2,10 @@
 inference: false
 license: apache-2.0
 ---
+# Overview
+This model has been pruned to 20% sparsity using the [Wanda pruning method](https://arxiv.org/abs/2306.11695) on attention layers. This method requires no retraining or weight updates and still achieves competitive performance. A link to the base model can be found [here](https://huggingface.co/lmsys/vicuna-7b-v1.3).
+
+
 # Vicuna Model Card
 
 ## Model Details