From b743fdee40df50a942da8422ad21885e1c70d57c Mon Sep 17 00:00:00 2001
From: Raziel <129535+raziel@users.noreply.github.com>
Date: Tue, 6 Aug 2024 15:14:12 -0700
Subject: [PATCH] Update README.md

Fixes comment for when to use unwrap_tensor_subclass
---
 torchao/quantization/README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/torchao/quantization/README.md b/torchao/quantization/README.md
index b53fdcdaf8..d3efde9ffb 100644
--- a/torchao/quantization/README.md
+++ b/torchao/quantization/README.md
@@ -109,7 +109,7 @@ group_size = 32
 quantize_(m, int4_weight_only(group_size=group_size))
 
 # temporary workaround for tensor subclass + torch.compile
-# NOTE: this is only need for torch 2.5+
+# NOTE: this is only need for torch version < 2.5+
 from torchao.utils import TORCH_VERSION_AFTER_2_5
 from torchao.utils import unwrap_tensor_subclass
 if not TORCH_VERSION_AFTER_2_5: