Create app.py

app.py

@@ -0,0 +1,40 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForMaskedLM
+import torch
+
+# Load tokenizer and model for masked language modeling
+tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/all-mpnet-base-v2")
+model = AutoModelForMaskedLM.from_pretrained("sentence-transformers/all-mpnet-base-v2")
+
+def fill_mask(text):
+    # Tokenize the input text
+    inputs = tokenizer(text, return_tensors="pt")
+    
+    # Get model predictions for masked tokens
+    with torch.no_grad():
+        outputs = model(**inputs)
+    
+    # Convert logits to token predictions
+    predictions = torch.topk(outputs.logits, k=1).indices.squeeze(0)
+    
+    # Decode the predicted tokens to words
+    decoded_output = tokenizer.decode(predictions)
+    
+    return decoded_output
+
+# Gradio interface setup
+title = "Masked Language Model (MPNet)"
+description = "Provide input text with [MASK] and the model will predict the masked token."
+
+# Gradio interface
+interface = gr.Interface(
+    fn=fill_mask,
+    inputs=gr.Textbox(label="Input Text", placeholder="Type something with [MASK]..."),
+    outputs=gr.Textbox(label="Predicted Text"),
+    title=title,
+    description=description,
+)
+
+# Launch Gradio app
+if __name__ == "__main__":
+    interface.launch()