From 8c506a27c456d4bdc5eb7f4880c3d96cedf1fce3 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Thu, 8 Jan 2026 11:35:21 +0000
Subject: [PATCH] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 tests/test_raw_text.py       | 8 ++++++--
 unsloth/dataprep/raw_text.py | 6 +++++-
 2 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/tests/test_raw_text.py b/tests/test_raw_text.py
index 7c7272a551..9f2e8cda4e 100644
--- a/tests/test_raw_text.py
+++ b/tests/test_raw_text.py
@@ -125,8 +125,12 @@ def test_raw_text_loader():
         ), "input_ids and attention_mask should have same length"
 
         # Verify labels field exists (for causal LM training)
-        assert "labels" in tokenized_dataset.column_names, "Dataset should have 'labels' column"
-        assert first_sample["labels"] == first_sample["input_ids"], "labels should match input_ids"
+        assert (
+            "labels" in tokenized_dataset.column_names
+        ), "Dataset should have 'labels' column"
+        assert (
+            first_sample["labels"] == first_sample["input_ids"]
+        ), "labels should match input_ids"
 
         # Test constructor validation
         try:
diff --git a/unsloth/dataprep/raw_text.py b/unsloth/dataprep/raw_text.py
index da64565bbc..ba010edabb 100644
--- a/unsloth/dataprep/raw_text.py
+++ b/unsloth/dataprep/raw_text.py
@@ -97,7 +97,11 @@ class RawTextDataLoader:
             # Labels are same as input_ids for causal LM training
             labels = [list(ids) for ids in input_ids]
             return Dataset.from_dict(
-                {"input_ids": input_ids, "attention_mask": attention_mask, "labels": labels}
+                {
+                    "input_ids": input_ids,
+                    "attention_mask": attention_mask,
+                    "labels": labels,
+                }
             )
         else:
             # If chunks are text strings (backward compatibility)