diff --git a/README.md b/README.md
index 407ea3a..b651747 100644
--- a/README.md
+++ b/README.md
@@ -72,7 +72,7 @@ directory, provided that you have cloned the saved model checkpoints in `tasks/a
 This will drop you into a REPL, where you can enter two numbers to be added, and step through the
 predicted execution trace. 
 
-Note that for the time being, numbers much be smaller than 1000000000. This is not because of any 
+Note that for the time being, numbers must be smaller than 1000000000. This is not because of any 
 limitations on the part of the NPI, but because of the backend helper functions that display the 
 trace.
 
@@ -237,4 +237,4 @@ call to "ADD 18 7":
     Model Output: 18 + 7 = 25
     Correct Out : 18 + 7 = 25
     Correct!
-```
\ No newline at end of file
+```
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..41c5c14
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,23 @@
+# tensorflow==0.11.0
+
+# https://github.com/tensorflow/tensorflow/blob/v0.11.0/tensorflow/g3doc/get_started/os_setup.md
+#
+# Specifically, I use the following command
+#
+# Ubuntu/Linux 64-bit, CPU only, Python 2.7
+# $ export TF_BINARY_URL=https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.11.0-cp27-none-linux_x86_64.whl
+#
+# Ubuntu/Linux 64-bit, GPU enabled, Python 2.7
+# Requires CUDA toolkit 8.0 and CuDNN v5. For other versions, see "Install from sources" below.
+# $ export TF_BINARY_URL=https://storage.googleapis.com/tensorflow/linux/gpu/tensorflow-0.11.0-cp27-none-linux_x86_64.whl
+#
+# Python 2
+# $ sudo pip install --upgrade $TF_BINARY_URL
+
+tflearn==0.2.1
+scipy==1.1.0
+h5py==2.8.0
+
+
+
+