Update app.py

app.py

@@ -14,6 +14,15 @@ model = AutoModelForCausalLM.from_pretrained("models/google/gemma-2-2b-it", torc
 #model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-large")
 #The model was loaded with use_flash_attention_2=True, which is deprecated and may be removed in a future release. Please use `attn_implementation="flash_attention_2"` instead.
 
+def generate_text(prompt):
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(**inputs)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+iface = gr.Interface(fn=generate_text, inputs="text", outputs="text")
+
+
+"""
 def predict(input, history=[]):
     # tokenize the new input sentence
     new_user_input_ids = tokenizer.encode(
@@ -47,4 +56,5 @@ gr.Interface(
     inputs=["text", "state"],
     outputs=["chatbot", "state"],
     theme="finlaymacklon/boxy_violet",
-).launch()
+).launch()
+"""