Update app.py

app.py

@@ -20,10 +20,10 @@ def make_inference(resume):
   batch = tokenizer(f"Below is an a resume, please write an excecutive summary this resume.\n\n### Resume:\n{resume}", return_tensors='pt')
 
   with torch.cuda.amp.autocast():
-    output_tokens = model.generate(**batch, max_new_tokens=200)
-
-  display(Markdown((tokenizer.decode(output_tokens[0], skip_special_tokens=True))))
+    output_tokens = model.generate(**batch, max_new_tokens=50)
 
+  return tokenizer.decode(output_tokens[0], skip_special_tokens=True)
+    
 if __name__ == "__main__":
     import gradio as gr
 
@@ -34,7 +34,7 @@ if __name__ == "__main__":
     ],
     gr.outputs.Textbox(label="Executive Summary"),
     title="Exective Summary Generator",
-    description="Generated Executive Summary",
+    description="This generates an Exectutive Summary from a Resume",
 ).launch()