Update app.py

app.py

@@ -42,7 +42,9 @@ async def generate_text(request: GenerateRequest):
                 temperature=request.temperature,
                 do_sample=True,
                 repetition_penalty=1.1,
-                pad_token_id=tokenizer.eos_token_id
+                eos_token_id=tokenizer.eos_token_id,
+                pad_token_id=tokenizer.eos_token_id,
+                use_cache=False
             )
         
         full_text = tokenizer.decode(outputs[0], skip_special_tokens=True)