From 6c3cd400b57ba1bc1babbc943a73efcb4d7b9a68 Mon Sep 17 00:00:00 2001
From: Youngwoo Kim <ywkim@apache.org>
Date: Wed, 28 May 2025 16:50:44 +0900
Subject: [PATCH] [data] Reading files from cloud is broken (#8182) (#8183)

---
 src/llamafactory/data/data_utils.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/src/llamafactory/data/data_utils.py b/src/llamafactory/data/data_utils.py
index b23423be..12697b6a 100644
--- a/src/llamafactory/data/data_utils.py
+++ b/src/llamafactory/data/data_utils.py
@@ -152,6 +152,8 @@ def setup_fs(path, anon=False):
         fs = fsspec.filesystem("gcs", **storage_options)
     else:
         raise ValueError(f"Unsupported protocol in path: {path}. Use 's3://' or 'gs://'")
+    if not fs.exists(path):
+        raise ValueError(f"Path does not exist: {path}")
     return fs