From 6c7f1875867fabb70723dfdf76c30b06fca8e8a9 Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Wed, 18 Jan 2023 21:59:23 -0300
Subject: [PATCH] Minor change

---
 server.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/server.py b/server.py
index e74a5c3..4991ba5 100644
--- a/server.py
+++ b/server.py
@@ -141,7 +141,7 @@ def generate_reply(question, tokens, inference_settings, selected_model, eos_tok
 
     input_ids = encode(question, 1)
     preset = preset.replace('max_new_tokens=tokens', 'max_new_tokens=1')
-    cuda = ".cuda()" if not args.cpu else ""
+    cuda = "" if args.cpu else ".cuda()"
     for i in range(tokens):
         if eos_token is None:
             output = eval(f"model.generate(input_ids, {preset}){cuda}")