From e99c511721607b55fd77f15f8e992cbf676918a6 Mon Sep 17 00:00:00 2001
From: rasbt <mail@sebastianraschka.com>
Date: Mon, 6 May 2024 21:02:13 -0500
Subject: [PATCH] spelling and consistency improvements

---
 .../01_main-chapter-code/appendix-E.ipynb     | 34 +++++++++++++------
 1 file changed, 23 insertions(+), 11 deletions(-)

diff --git a/appendix-E/01_main-chapter-code/appendix-E.ipynb b/appendix-E/01_main-chapter-code/appendix-E.ipynb
index 13d546d..6db9422 100644
--- a/appendix-E/01_main-chapter-code/appendix-E.ipynb
+++ b/appendix-E/01_main-chapter-code/appendix-E.ipynb
@@ -94,10 +94,22 @@
     "\n",
     "$$W_{\\text{updated}} = W + AB$$\n",
     "\n",
-    "- The figure below illustrates these formulas for full finetuning and LoRA side by side\n",
-    "\n",
-    "<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/appendix-e_compressed/lora-1.webp\" width=\"500px\">\n",
-    "\n",
+    "- The figure below illustrates these formulas for full finetuning and LoRA side by side"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a8a7419d-cae9-4525-bb44-1641f6ef4f3b",
+   "metadata": {},
+   "source": [
+    "<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/appendix-e_compressed/lora-1.webp\" width=\"500px\">"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4edd43c9-8ec5-48e6-b3fc-5fb3c16037cc",
+   "metadata": {},
+   "source": [
     "- If you paid close attention, the full finetuning and LoRA depictions in the figure above look slightly different from the formulas I have shown earlier\n",
     "- That's due to the distributive law of matrix multiplication: we don't have to add the weights with the updated weights but can keep them separate\n",
     "- For instance, if $x$ is the input data, then we can write the following for regular finetuning:\n",
@@ -110,7 +122,7 @@
     "\n",
     "- The fact that we can keep the LoRA weight matrices separate makes LoRA especially attractive\n",
     "- In practice, this means that we don't have to modify the weights of the pretrained model at all, as we can apply the LoRA matrices on the fly\n",
-    "- After setting up the dataset and loading the model, we we will implement LoRA in code to make these concepts less abstract"
+    "- After setting up the dataset and loading the model, we will implement LoRA in the code to make these concepts less abstract"
    ]
   },
   {
@@ -129,9 +141,9 @@
    "metadata": {},
    "source": [
     "- This section repeats the code from chapter 6 to load and prepare the dataset\n",
-    "- Instead of repeating this code, one could copy & paste the LoRA code from section E.3 at the end of the chapter 6 notebook\n",
+    "- Instead of repeating this code, one could open and run the chapter 6 notebook and then insert the LoRA code from section E.4 there\n",
     "- (The LoRA code was originally the last section of chapter 6 but was moved to the appendix due to the length of chapter 6)\n",
-    "- In similar fashion, we could also apply LoRA to the models in chapter 7 for instruction finetuning"
+    "- In a similar fashion, we could also apply LoRA to the models in chapter 7 for instruction finetuning"
    ]
   },
   {
@@ -467,7 +479,7 @@
    "id": "8e951cd6-5e42-44d2-b21f-895cb61004fe",
    "metadata": {},
    "source": [
-    "- Lastly, let's calcuate the initial classification accuracy of the non-finetuning model (we expect this to be around 50%, which means that the model is not able to reliably distinguish between spam and non-spam messages, yet)"
+    "- Lastly, let's calculate the initial classification accuracy of the non-finetuning model (we expect this to be around 50%, which means that the model is not able to distinguish between spam and non-spam messages yet reliably)"
    ]
   },
   {
@@ -1218,7 +1230,7 @@
    "id": "13735b3e-f0c3-4dba-ae3d-4141b2878101",
    "metadata": {},
    "source": [
-    "- Let's now get to the interesting part and finetune the model reusing the training function from chapter 6\n",
+    "- Let's now get to the interesting part and finetune the model by reusing the training function from chapter 6\n",
     "- The training takes about 15 minutes on a M3 MacBook Air laptop computer and less than half a minute on a V100 or A100 GPU"
    ]
   },
@@ -1333,7 +1345,7 @@
    "id": "aa074723-e3f7-4f7e-a267-855531a037dc",
    "metadata": {},
    "source": [
-    "- Note that we previously calculated the accuracy values on 10 batches only; below we calculate the accuracies on the full dataset"
+    "- Note that we previously calculated the accuracy values on 10 batches only; below, we calculate the accuracies on the full dataset"
    ]
   },
   {
@@ -1400,7 +1412,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,