Create app.py

app.py

@@ -0,0 +1,50 @@
+# import the main classes
+import gradio as gr
+import torch
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+
+# Load the model.
+tokenizer = AutoTokenizer.from_pretrained("google/flan-t5-base")
+model = AutoModelForSeq2SeqLM.from_pretrained("google/flan-t5-base")
+
+# input examples list
+ex_list = [["Women are not as capable as men in leadership roles."],["Women are capable as men in leadership roles."]]
+
+# generate_text method
+def generate_text(prompt):
+    input_ids = tokenizer.encode(prompt, return_tensors="pt")
+    output = model.generate(
+        input_ids,
+        max_length=512,
+        temperature=0.7,
+        do_sample=True,
+        top_p=0.9,
+        top_k=0,
+        num_return_sequences=1,
+    )
+    return tokenizer.decode(output[0], skip_special_tokens=True)
+
+def classify_gender_equality(input_sentence):
+    # Here goes your code to classify gender equality from input_sentence
+    # Return the result as a string
+
+
+    # sub_text = 'Gender equality is important for the progress of society.'
+    sub_text = input_sentence
+    prompt = f"Please classify the this sentence {sub_text} as promoting or not promoting gender equality:"
+    generated_text = generate_text(prompt)
+    # print("This sentence is",generated_text)
+  
+    return "This sentence is " + generated_text + " for gender equality"
+  
+
+
+
+input_text = gr.inputs.Textbox(label="Input Sentence", default="Women deserve equal pay")
+
+# Create the output text field
+output_text = gr.outputs.Textbox(label="Gender Equality Classification")
+
+# Create the Gradio interface
+gr.Interface(fn=classify_gender_equality, inputs=[input_text], outputs=output_text, title='Gender Equality Classification', examples = ex_list).launch()