max token setting

app.py

@@ -90,7 +90,7 @@ def generate_translation(system_prompt, prompt):
     inputs = tokenizer(full_prompt, return_tensors="pt").to(device)
     outputs = model.generate(
         **inputs,
-        max_new_tokens=512,
+        max_new_tokens=2048,
         temperature=0.7,
         top_p=0.9,
         do_sample=True