Update README.md

README.md

@@ -1,6 +1,14 @@
 ---
 license: apache-2.0
 inference: false
+widget:
+ - text: "[INST] <<SYS>>
+Given an image description, generate one or two multiple-choice questions that verifies if the image description is correct.
+Classify each concept into a type (object, human, animal, food, activity, attribute, counting, color, material, spatial, location, shape, other), and then generate a question for each type.
+
+<</SYS>>
+
+Description: a blue rabbit and a red plane [/INST] Entities:"
 pipeline_tag: text-generation
 tags:
 - text-generation-inference