diff --git a/lib/axon/compiler.ex b/lib/axon/compiler.ex
index 07c73b5a..1816e170 100644
--- a/lib/axon/compiler.ex
+++ b/lib/axon/compiler.ex
@@ -17,7 +17,7 @@ defmodule Axon.CompileError do
       else
         """
 
-        (pass debug: true to build/compile see where the layer was defined)
+        (pass debug: true to build/compile to see where the layer was defined)
 
         """
       end
diff --git a/lib/axon/layers.ex b/lib/axon/layers.ex
index 80dd0a0a..479d8a48 100644
--- a/lib/axon/layers.ex
+++ b/lib/axon/layers.ex
@@ -222,7 +222,7 @@ defmodule Axon.Layers do
   ## Options
 
     * `:strides` - kernel strides. Can be a scalar or a list
-      who's length matches the number of spatial dimensions in
+      whose length matches the number of spatial dimensions in
       the input tensor. Defaults to 1.
 
     * `:padding` - zero padding on the input. Can be one of
@@ -393,7 +393,7 @@ defmodule Axon.Layers do
   ## Options
 
     * `:strides` - kernel strides. Can be a scalar or a list
-      who's length matches the number of spatial dimensions in
+      whose length matches the number of spatial dimensions in
       the input tensor. Defaults to 1.
 
     * `:padding` - zero padding on the input. Can be one of
@@ -516,7 +516,7 @@ defmodule Axon.Layers do
   ## Options
 
     * `:strides` - kernel strides. Can be a scalar or a list
-      who's length matches the number of spatial dimensions in
+      whose length matches the number of spatial dimensions in
       the input tensor. Defaults to 1.
 
     * `:padding` - zero padding on the input. Can be one of
@@ -608,7 +608,7 @@ defmodule Axon.Layers do
   ## Options
 
     * `:strides` - kernel strides. Can be a scalar or a list
-      who's length matches the number of spatial dimensions in
+      whose length matches the number of spatial dimensions in
       the input tensor. Defaults to 1.
 
     * `:padding` - zero padding on the input. Can be one of
@@ -675,7 +675,7 @@ defmodule Axon.Layers do
   ## Options
 
     * `:strides` - kernel strides. Can be a scalar or a list
-      who's length matches the number of spatial dimensions in
+      whose length matches the number of spatial dimensions in
       the input tensor. Defaults to 1.
 
     * `:padding` - zero padding on the input. Can be one of
@@ -735,7 +735,7 @@ defmodule Axon.Layers do
       of the input tensor. Required.
 
     * `:strides` - kernel strides. Can be a scalar or a list
-      who's length matches the number of spatial dimensions in
+      whose length matches the number of spatial dimensions in
       the input tensor. Defaults to size of kernel.
 
     * `:padding` - zero padding on the input. Can be one of
diff --git a/lib/axon/loop.ex b/lib/axon/loop.ex
index e21d8666..71d9d5e8 100644
--- a/lib/axon/loop.ex
+++ b/lib/axon/loop.ex
@@ -455,7 +455,7 @@ defmodule Axon.Loop do
   defp raise_bad_training_inputs!(data, state) do
     raise ArgumentError,
           "invalid arguments given to train-step initialization," <>
-            " this usually happens when you pass a invalid parameters" <>
+            " this usually happens when you pass invalid parameters" <>
             " to Axon.Loop.run with a loop constructed using Axon.Loop.trainer" <>
             " or Axon.Loop.evaluator, supervised training and evaluation loops" <>
             " expect a stream or enumerable of inputs" <>
diff --git a/lib/axon/quantization.ex b/lib/axon/quantization.ex
index ef11dee3..64cf6c21 100644
--- a/lib/axon/quantization.ex
+++ b/lib/axon/quantization.ex
@@ -36,7 +36,7 @@ defmodule Axon.Quantization do
   The only supported conversion is to convert regular dense layers
   to a weight-only 8-bit integer variant. Note that this only replaces
   the properties of the model. If you have a pre-trained model state
-  that you wish to quantize, refer to `Axon.Quantization.quantize_model_state/1`.
+  that you wish to quantize, refer to `Axon.Quantization.quantize_model_state/2`.
 
   All `:dense` layers in the model are replaced with `Axon.Quantization.weight_only_quantized_dense/3`.
   """
@@ -89,7 +89,7 @@ defmodule Axon.Quantization do
   This is equivalent to a dense layer, but works on quantized
   weights for reducing model memory footprint.
 
-  Compiles to `Axon.Quantization.Layers.weight_only_quantized_dense/4`.
+  Compiles to `Axon.Quantization.Layers.weight_only_quantized_dense/3`.
 
   ## Options