diff --git a/auto_gptq/__init__.py b/auto_gptq/__init__.py
index 6c3c3da..0ec4344 100644
--- a/auto_gptq/__init__.py
+++ b/auto_gptq/__init__.py
@@ -1,5 +1,5 @@
-__version__ = "0.4.2"
+__version__ = "0.4.1"
 from .modeling import BaseQuantizeConfig
 from .modeling import AutoGPTQForCausalLM
 from .utils.peft_utils import get_gptq_peft_model
-from .utils.exllama_utils import exllama_set_max_input_length
+from .utils.exllama_utils import exllama_set_max_input_length
\ No newline at end of file
diff --git a/setup.py b/setup.py
index 451ea2b..546bf7c 100644
--- a/setup.py
+++ b/setup.py
@@ -9,7 +9,7 @@ os.environ["CC"] = "g++"
 os.environ["CXX"] = "g++"
 
 common_setup_kwargs = {
-    "version": "0.4.2",
+    "version": "0.4.1",
     "name": "auto_gptq",
     "author": "PanQiWei",
     "description": "An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.",