Update app.py

app.py

@@ -76,7 +76,8 @@ def generate_response(user_message, max_tokens, temperature, top_k, top_p, repet
             "top_p": top_p,
             "repetition_penalty": repetition_penalty,
             "streamer": streamer,
-            "pad_token_id": tokenizer.eos_token_id
+            "pad_token_id": tokenizer.eos_token_id,
+            "eos_token_id": tokenizer.eos_token_id
         }
 
         # Start generation in a separate thread