From f79805f4a4bcc775413800f699cade93da3d7921 Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Sat, 18 Feb 2023 22:58:40 -0300
Subject: [PATCH] Change a comment

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

diff --git a/server.py b/server.py
index d19da85..09e79c0 100644
--- a/server.py
+++ b/server.py
@@ -367,7 +367,7 @@ def generate_reply(question, tokens, do_sample, max_new_tokens, temperature, top
         t1 = time.time()
         print(f"Output generated in {(t1-t0):.2f} seconds ({(len(output)-len(input_ids[0]))/(t1-t0)/8:.2f} it/s, {len(output)-len(input_ids[0])} tokens)")
 
-    # Generate the reply 1 token at a time
+    # Generate the reply 8 tokens at a time
     else:
         yield formatted_outputs(original_question, model_name)
         for i in tqdm(range(tokens//8+1)):