Add examples

app.py

@@ -27,13 +27,13 @@ Leonardo Moreno contacts:
 
 **Warning:** This space uses the free CPU Basic hardware from Hugging Face. Some steps and LLM models used below (free inference endpoints) can take some time to generate a reply.
 """
-# examples=[
-#     ['Who is Leonardo Moreno?'],
-#     ['Describe Leonardo Moreno\'s professional background.'],
-#     ['What projects has Leonardo Moreno worked on?'],
-#     ["What are Leonardo Moreno's core technical skills?"],
-#     ['How has Leonardo Moreno integrated AI in his work?'],
-# ]
+examples=[
+    ['Who is Leonardo Moreno?'],
+    ['Describe Leonardo Moreno\'s professional background.'],
+    ['What projects has Leonardo Moreno worked on?'],
+    ["What are Leonardo Moreno's core technical skills?"],
+    ['How has Leonardo Moreno integrated AI in his work?'],
+]
 
 # @spaces.GPU
 def generate_response(message, history):
@@ -56,14 +56,13 @@ def generate_response(message, history):
     outputs = pipe(prompt, max_new_tokens=max_new_tokens, do_sample=True,
                    temperature=temperature, top_k=top_k, top_p=top_p, repetition_penalty=1.10)
 
-    print(outputs[0]["generated_text"])
-    return outputs[0]["generated_text"]
+    return outputs[0]["generated_text"].split("<|assistant|>")[-1].lstrip()
 
 if __name__ == "__main__":
     gr.ChatInterface(generate_response, 
                  title=title, 
                  description=description, 
-                 #examples=examples, 
-                 #cache_examples=True, 
+                 examples=examples, 
+                 cache_examples=True, 
                  #additional_inputs=additional_inputs,
                  ).launch()