adding example texts for the widget

README.md

@@ -17,6 +17,15 @@ tags:
   - multilingual 
 pipeline_tag: text-classification
 inference: True
+widget:
+- text: "THIS IS WHY YOU NEED. A SHARPIE WITH YOU AT ALL TIMES."
+  example_title: "Sentence 1"
+- text: "WHEN YOU'RE THE FBI, THEY LET YOU DO IT."
+  example_title: "Sentence 2"
+- text: "Move your ships away!\n\noooook\n\nMove your ships away!\n\nNo, and I just added 10 more"
+  example_title: "Sentence 3"
+- text: "Let's Make America Great Again!"
+  example_title: "Sentence 4"
 ---
 
 # Multilingual Persuasion Detection in Memes
@@ -26,12 +35,16 @@ Given only the “textual content” of a meme, the goal is to identify which of
 ### Hierarchy
 <img src="images/persuasion_techniques_hierarchy_graph.png" width="622" height="350">
 
-### Input Example
+### Usage Example
 - **Input:** "I HATE TRUMP\n\nMOST TERRORIST DO",
 - **Outputs:**
   - Child-only Label List: ['Name calling/Labeling', 'Loaded Language']
   - Complete Hierarchical Label List: ['Ethos', 'Ad Hominem', 'Name calling/Labeling', 'Pathos', 'Loaded Language']
 
+Note:
+- Make sure to have the dependencies installed in your environment from requirements.txt
+- Make to have the trained model and tokenizer in the same directory as inference.py
+
 ## Training Hyperparameters 
 - Base Model: "facebook/mbart-large-50-many-to-many-mmt"
 - Learning Rate: 5e-05