From fdfab3674f2199b72d577c1c08cefa36b035169a Mon Sep 17 00:00:00 2001 From: Daniel Han Date: Thu, 1 May 2025 06:49:46 -0700 Subject: [PATCH] Update synthetic.py --- unsloth/dataprep/synthetic.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/unsloth/dataprep/synthetic.py b/unsloth/dataprep/synthetic.py index 3a5e9f874a..4e0b2ba3a3 100644 --- a/unsloth/dataprep/synthetic.py +++ b/unsloth/dataprep/synthetic.py @@ -223,7 +223,7 @@ class SyntheticDataKit: all_filenames = [] for i, (left, right) in enumerate(boundaries): chunked_text = self.tokenizer.decode(input_ids[left : right]) - new_filename = os.path.join(filename + f"_{i}", extension) + new_filename = f"{filename}_{i}{extension}" all_filenames.append(new_filename) with open(new_filename, "w") as f: f.write(chunked_text) pass