link summary and exercises

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

@@ -16,6 +16,14 @@
     "## 2.1 Understanding word embeddings"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "0b6816ae-e927-43a9-b4dd-e47a9b0e1cf6",
+   "metadata": {},
+   "source": [
+    "- No code in this section"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "eddbb984-8d23-40c5-bbfa-c3c379e7eec3",
@@ -1549,6 +1557,40 @@
     "input_embeddings = token_embeddings + pos_embeddings\n",
     "print(input_embeddings.shape)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "63230f2e-258f-4497-9e2e-8deee4530364",
+   "metadata": {},
+   "source": [
+    "# Summary and takeaways"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8b3293a6-45a5-47cd-aa00-b23e3ca0a73f",
+   "metadata": {},
+   "source": [
+    "**See the [./dataloader.ipynb](./dataloader.ipynb) code notebook**, which is a concise version of the data loader that we implemented in this chapter and will need for training the GPT model in upcoming chapters.\n",
+    "\n",
+    "**See [./exercise-solutions.ipynb](./exercise-solutions.ipynb) for the exercise solutions.**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ce133c96-2ec5-400d-a103-3875d1da6f31",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8352810e-461d-4c33-9c78-3648983a9777",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -1567,7 +1609,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,