bfloat and less tokens

app.py

@@ -8,7 +8,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_name)
 
 def generate_response(prompt):
     inputs = tokenizer(prompt, return_tensors="pt")
-    outputs = model.generate(**inputs, max_new_tokens=20, temperature=1.0)
+    outputs = model.generate(**inputs, max_new_tokens=10, temperature=1.0)
     return tokenizer.decode(outputs[0], skip_special_tokens=True)
 
 iface = gr.Interface(