diff --git a/.gitignore b/.gitignore
index 68bc17f..aaa41a2 100644
--- a/.gitignore
+++ b/.gitignore
@@ -158,3 +158,5 @@ cython_debug/
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
+/openwebtext
+/data_extract.py
diff --git a/eval_split.txt b/eval_split.txt
new file mode 100644
index 0000000..1fabb28
Binary files /dev/null and b/eval_split.txt differ
diff --git a/train_split.txt b/train_split.txt
new file mode 100644
index 0000000..7f16f08
Binary files /dev/null and b/train_split.txt differ
diff --git a/vocab.txt b/vocab.txt
new file mode 100644
index 0000000..89e9b72
Binary files /dev/null and b/vocab.txt differ