Update app.py

app.py

@@ -31,14 +31,13 @@ def respond(
     # Generate response
     output_sequences = model.generate(
         input_ids=inputs['input_ids'],
-        max_length=max_tokens + inputs['input_ids'].shape[1],  # Adjust for input length
-        repetition_penalty=1.2,
-        temperature=temperature,
-        top_p=top_p
+        max_length=max_tokens,
+        repetition_penalty=1.2
     )
     
     # Decode the generated response
-    generated_text = tokenizer.decode(output_sequences[0], skip_special_tokens=True)
+    input_length = inputs['input_ids'].shape[1]
+    generated_text = tokenizer.decode(output_sequences[0][input_length:], skip_special_tokens=True)
     
     return generated_text
 
@@ -46,17 +45,9 @@ demo = gr.ChatInterface(
     respond,
     additional_inputs=[
         gr.Textbox(value="Sampeyan minangka chatbot umum sing tansah mangsuli nganggo basa Jawa.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max tokens"),
     ],
 )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(share=True)