From 1f7d20ad4fe6ad91339263d3745bbf54d9aef66c Mon Sep 17 00:00:00 2001
From: edknv <109497216+edknv@users.noreply.github.com>
Date: Thu, 7 Dec 2023 16:42:01 -0800
Subject: [PATCH] fix tokenizer cache file name bug (#36)

---
 crossfit/op/tokenize.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/crossfit/op/tokenize.py b/crossfit/op/tokenize.py
index 3f549e3..dee2ac4 100644
--- a/crossfit/op/tokenize.py
+++ b/crossfit/op/tokenize.py
@@ -159,7 +159,7 @@ def from_pretrained(cls, name, cache_dir=None):
 
             # Save vocabulary to disk
             # `save_vocabulary()` automatically appends `-vocab.txt` suffix.
-            vocab_path = tokenizer.save_vocabulary(cache_dir, "{tokenizer_class}")[0]
+            vocab_path = tokenizer.save_vocabulary(cache_dir, f"{tokenizer_class}")[0]
 
             # Hash the vocabulary and save it
             hash_vocab(vocab_path, hashed_vocab_path)