Update app.py

app.py

@@ -22,7 +22,10 @@ def generate_response(prompt):
     model.to("cuda")
 
     inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
-    outputs = model.generate(**inputs, max_new_tokens=64)
+    outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7,
+    top_p=0.9,
+    top_k=50,
+    do_sample=True,)
     return tokenizer.decode(outputs[0], skip_special_tokens=True)
 
 demo = gr.Interface(fn=generate_response, inputs="text", outputs="text")