Update README.md

README.md

@@ -78,10 +78,12 @@ benchmark [WebClick](https://huggingface.co/datasets/Hcompany/WebClick).
 
 ## Get Started with the Model
 
-We provid starter code for the localization task: i.e. image + instruction -> click coordinates
+We provide starter code for the localization task: i.e. image + instruction -> click coordinates
 
 We trained Holo1 as an Action VLM with extensive use of json and tool calls. Therefore, it can be queried reliably with structured output:
 
+We also provide code to reproduce screenspot evaluations: screenspot_eval.py
+
 ```python
 import json
 import os