From 2a9cefb637e6492f48b838c6a901a97cf982db14 Mon Sep 17 00:00:00 2001 From: Daniel Han Date: Wed, 30 Apr 2025 08:56:01 -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 f3c3fc9330..7e0cd872cd 100644 --- a/unsloth/dataprep/synthetic.py +++ b/unsloth/dataprep/synthetic.py @@ -185,7 +185,7 @@ class SyntheticDataKit: with open(filename, "r") as f: text = f.read() - max_tokens = self.max_seq_length - self.max_generation_tokens + self.max_generation_tokens + 2 + max_tokens = self.max_seq_length - self.max_generation_tokens - self.max_generation_tokens + 2 input_ids = self.tokenizer(text).input_ids length = len(text) original_length = len(text)