Readability and code quality improvements (#959)

* Consistent dataset naming

* consistent section headers

ch02/01_main-chapter-code/ch02.ipynb

@@ -79,6 +79,7 @@
    "id": "2417139b-2357-44d2-bd67-23f5d7f52ae7",
    "metadata": {},
    "source": [
+    " \n",
     "## 2.1 Understanding word embeddings"
    ]
   },
@@ -128,6 +129,7 @@
    "id": "eddbb984-8d23-40c5-bbfa-c3c379e7eec3",
    "metadata": {},
    "source": [
+    " \n",
     "## 2.2 Tokenizing text"
    ]
   },
@@ -445,6 +447,7 @@
    "id": "0b5ce8fe-3a07-4f2a-90f1-a0321ce3a231",
    "metadata": {},
    "source": [
+    " \n",
     "## 2.3 Converting tokens into token IDs"
    ]
   },
@@ -738,6 +741,7 @@
    "id": "4b821ef8-4d53-43b6-a2b2-aef808c343c7",
    "metadata": {},
    "source": [
+    " \n",
     "## 2.4 Adding special context tokens"
    ]
   },
@@ -1013,6 +1017,7 @@
    "id": "5c4ba34b-170f-4e71-939b-77aabb776f14",
    "metadata": {},
    "source": [
+    " \n",
     "## 2.5 BytePair encoding"
    ]
   },
@@ -1528,6 +1533,7 @@
    "id": "2cd2fcda-2fda-4aa8-8bc8-de1e496f9db1",
    "metadata": {},
    "source": [
+    " \n",
     "## 2.7 Creating token embeddings"
    ]
   },
@@ -1715,6 +1721,7 @@
    "id": "c393d270-b950-4bc8-99ea-97d74f2ea0f6",
    "metadata": {},
    "source": [
+    " \n",
     "## 2.8 Encoding word positions"
    ]
   },
@@ -1945,7 +1952,8 @@
    "id": "63230f2e-258f-4497-9e2e-8deee4530364",
    "metadata": {},
    "source": [
-    "# Summary and takeaways"
+    " \n",
+    "## Summary and takeaways"
    ]
   },
   {
@@ -1977,7 +1985,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.16"
+   "version": "3.13.5"
   }
  },
  "nbformat": 4,

ch02/01_main-chapter-code/exercise-solutions.ipynb

@@ -63,7 +63,8 @@
    "id": "6f678e62-7bcb-4405-86ae-dce94f494303",
    "metadata": {},
    "source": [
-    "# Exercise 2.1"
+    " \n",
+    "## Exercise 2.1"
    ]
   },
   {
@@ -273,7 +274,8 @@
    "id": "29e5034a-95ed-46d8-9972-589354dc9fd4",
    "metadata": {},
    "source": [
-    "# Exercise 2.2"
+    " \n",
+    "## Exercise 2.2"
    ]
   },
   {
@@ -407,7 +409,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.16"
+   "version": "3.13.5"
   }
  },
  "nbformat": 4,

ch02/02_bonus_bytepair-encoder/compare-bpe-tiktoken.ipynb

@@ -54,7 +54,7 @@
     "<br>\n",
     "&nbsp;\n",
     "\n",
-    "## Using BPE from `tiktoken`"
+    "## 1. Using BPE from `tiktoken`"
    ]
   },
   {
@@ -157,7 +157,7 @@
     "<br>\n",
     "&nbsp;\n",
     "\n",
-    "## Using the original BPE implementation used in GPT-2"
+    "## 2. Using the original BPE implementation used in GPT-2"
    ]
   },
   {
@@ -247,7 +247,7 @@
     "<br>\n",
     "&nbsp;\n",
     "\n",
-    "## Using the BPE via Hugging Face transformers"
+    "## 3. Using the BPE via Hugging Face transformers"
    ]
   },
   {
@@ -355,7 +355,7 @@
     "<br>\n",
     "&nbsp;\n",
     "\n",
-    "## Using my own from-scratch BPE tokenizer"
+    "## 4. Using my own from-scratch BPE tokenizer"
    ]
   },
   {
@@ -449,7 +449,7 @@
     "<br>\n",
     "&nbsp;\n",
     "\n",
-    "## A quick performance benchmark"
+    "## 5. A quick performance benchmark"
    ]
   },
   {
@@ -468,7 +468,8 @@
    "id": "9c0ae9f0-47a1-4e7f-a210-e1d2721f4d1e",
    "metadata": {},
    "source": [
-    "### Original OpenAI GPT-2 tokenizer"
+    "&nbsp;\n",
+    "### 5.1 Original OpenAI GPT-2 tokenizer"
    ]
   },
   {
@@ -494,7 +495,8 @@
    "id": "ef2ce3f3-1f81-47ce-b563-99fe2c7a1e90",
    "metadata": {},
    "source": [
-    "### Tiktoken OpenAI GPT-2 tokenizer"
+    "&nbsp;\n",
+    "### 5.2 Tiktoken OpenAI GPT-2 tokenizer"
    ]
   },
   {
@@ -520,7 +522,8 @@
    "id": "0c748de8-273e-42df-b078-3a510106da60",
    "metadata": {},
    "source": [
-    "### Hugging Face OpenAI GPT-2 tokenizer"
+    "&nbsp;\n",
+    "### 5.3 Hugging Face OpenAI GPT-2 tokenizer"
    ]
   },
   {
@@ -614,7 +617,8 @@
    "id": "91ac2876-f36e-498c-bd75-8597a39f2d4b",
    "metadata": {},
    "source": [
-    "### My own GPT-2 tokenizer (for educational purposes)"
+    "&nbsp;\n",
+    "### 5.4 My own GPT-2 tokenizer (for educational purposes)"
    ]
   },
   {
@@ -652,7 +656,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.16"
+   "version": "3.13.5"
   }
  },
  "nbformat": 4,