diff --git a/README.md b/README.md
index 1db7943..efd7471 100644
--- a/README.md
+++ b/README.md
@@ -11,11 +11,11 @@ This implementation extends the [`timm`](https://github.com/huggingface/pytorch-
 
 ## Installation
 
-<!-- ``` -->
-<!-- pip install soft-moe-pytorch -->
-<!-- ``` -->
+```
+pip install soft-moe
+```
 
-<!-- Or install the entire repo with: -->
+Or install the entire repo with:
 
 ```
 git clone https://github.com/bwconrad/soft-moe
@@ -29,7 +29,7 @@ pip install -r requirements.txt
 
 ```python
 import torch
-from soft_moe_pytorch import SoftMoEVisionTransformer
+from soft_moe import SoftMoEVisionTransformer
 
 net = SoftMoEVisionTransformer(
     num_experts=128,
@@ -51,9 +51,9 @@ preds = net(img)
 Functions are also available to initialize default network configurations:
 
 ```python
-from soft_moe_pytorch import (soft_moe_vit_base, soft_moe_vit_huge,
-                              soft_moe_vit_large, soft_moe_vit_small,
-                              soft_moe_vit_tiny)
+from soft_moe import (soft_moe_vit_base, soft_moe_vit_huge,
+                      soft_moe_vit_large, soft_moe_vit_small,
+                      soft_moe_vit_tiny)
 
 net = soft_moe_vit_tiny()
 net = soft_moe_vit_small()
@@ -95,7 +95,7 @@ The `SoftMoELayerWrapper` class can be used to make any network layer, that take
 import torch
 import torch.nn as nn
 
-from soft_moe_pytorch import SoftMoELayerWrapper
+from soft_moe import SoftMoELayerWrapper
 
 x = torch.rand(1, 16, 128)
 
diff --git a/setup.py b/setup.py
new file mode 100644
index 0000000..c139f00
--- /dev/null
+++ b/setup.py
@@ -0,0 +1,36 @@
+from setuptools import find_packages, setup
+
+with open("README.md") as f:
+    long_description = f.read()
+
+setup(
+    name="soft_moe",
+    packages=find_packages(),
+    version="0.0.1",
+    license="Apache-2.0",
+    description="PyTorch implementation of 'From Sparse to Soft Mixtures of Experts'",
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    author="Ben Conrad",
+    author_email="benwconrad@proton.me",
+    url="https://github.com/bwconrad/soft-moe",
+    keywords=[
+        "transformers",
+        "artificial intelligence",
+        "computer vision",
+        "deep learning",
+    ],
+    install_requires=[
+        "timm >= 0.9.2",
+        "torch >= 2.0.1",
+    ],
+    classifiers=[
+        "Intended Audience :: Developers",
+        "Intended Audience :: Science/Research",
+        "Topic :: Scientific/Engineering :: Artificial Intelligence",
+        "License :: OSI Approved :: Apache Software License",
+        "Programming Language :: Python :: 3.10",
+        "Programming Language :: Python :: 3.11",
+    ],
+    python_requires=">=3.10",
+)
diff --git a/soft_moe/__init__.py b/soft_moe/__init__.py
new file mode 100644
index 0000000..eeade35
--- /dev/null
+++ b/soft_moe/__init__.py
@@ -0,0 +1,5 @@
+from soft_moe.soft_moe import SoftMoELayerWrapper
+from soft_moe.vision_transformer import (SoftMoEVisionTransformer,
+                                         soft_moe_vit_base, soft_moe_vit_huge,
+                                         soft_moe_vit_large,
+                                         soft_moe_vit_small, soft_moe_vit_tiny)
diff --git a/soft_moe_pytorch/soft_moe.py b/soft_moe/soft_moe.py
similarity index 100%
rename from soft_moe_pytorch/soft_moe.py
rename to soft_moe/soft_moe.py
diff --git a/soft_moe_pytorch/vision_transformer.py b/soft_moe/vision_transformer.py
similarity index 100%
rename from soft_moe_pytorch/vision_transformer.py
rename to soft_moe/vision_transformer.py
diff --git a/soft_moe_pytorch/__init__.py b/soft_moe_pytorch/__init__.py
deleted file mode 100644
index 6ed06e5..0000000
--- a/soft_moe_pytorch/__init__.py
+++ /dev/null
@@ -1,4 +0,0 @@
-from .soft_moe import SoftMoELayerWrapper
-from .vision_transformer import (SoftMoEVisionTransformer, soft_moe_vit_base,
-                                 soft_moe_vit_huge, soft_moe_vit_large,
-                                 soft_moe_vit_small, soft_moe_vit_tiny)