From db2ab7077d0b298fb92c912f662c9735e2462cb8 Mon Sep 17 00:00:00 2001
From: SYSTEMS-OPERATOR <155610697+SYSTEMS-OPERATOR@users.noreply.github.com>
Date: Fri, 27 Jun 2025 05:21:52 -0400
Subject: [PATCH] Fix parsing of dataset lines

---
 model/dataset.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/model/dataset.py b/model/dataset.py
index 6f60a14..73e4e0c 100644
--- a/model/dataset.py
+++ b/model/dataset.py
@@ -31,7 +31,7 @@ def __init__(self, datapath: str, window_size: int, vocab_size: int,
     def __iter__(self):
         for line_idx in range(len(self.data)):
 
-            line_tokens = self.data[line_idx].strip().split(' ')
+            line_tokens = self.data[line_idx].split()
 
             if len(line_tokens) <= self.window_size:
                 continue