Update README.md

README.md

@@ -15,7 +15,7 @@ library_name: tensorflow
 
 # Multimodal Classification Model (BM-v1)
 
-This model combines text and image inputs to perform classification tasks using a ResNet50 backbone for image processing and a text encoder for textual input processing.
+This model combines text and image inputs to predict player moves from in-game screenshots for the popular 4X Civilization VI. In use, screenshot inputs are provided and text inputs generated using an LLM.
 
 ## Model Details
 
@@ -23,10 +23,11 @@ This model combines text and image inputs to perform classification tasks using
 - **Model type:** Multimodal Classification Model
 - **Language(s):** English
 - **License:** MIT
-- **Parent Model:** ResNet50 (for image processing)
 
 ## Uses
 
+Predicts the likely moves a player will make from a complete sample space of all (observed) player moves, based on a provided screenshot and associated text. Can be fine-tuned to specifically predict types of move (scouting, build orders, settle/doesn't settle)
+
 ### Direct Use
 
-The model is designed for multimodal classification tasks that require both image and text inputs. Example usage:
+Predicts the likely moves a player will make, from a complete sample space of all player moves, based on a provided screenshot and associated text.