Update app.py

app.py

@@ -44,6 +44,7 @@ async def generate_text(request: GenerateRequest):
                 do_sample=True,
                 early_stopping=True,
                 repetition_penalty=1.1,
+                eos_token_id=tokenizer.eos_token_id,
                 pad_token_id=tokenizer.eos_token_id
             )