Update app.py

app.py

@@ -26,5 +26,14 @@ model = AutoGPTQForCausalLM.from_quantized(quantized_model_dir,
         use_triton=use_triton,
         quantize_config=quantize_config)
 
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    max_new_tokens=512,
+    temperature=0.1,
+    top_p=0.95,
+    repetition_penalty=1.15
+)
 
 demo.launch()