minor updates

appendix-A/03_main-chapter-code/code-part1.ipynb

@@ -65,6 +65,28 @@
     "print(torch.cuda.is_available())"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "397ba1ab-3306-4965-8618-1ed5f24fb939",
+   "metadata": {},
+   "source": [
+    "<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/appendix-a_compressed/1.webp\" width=\"400px\">"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1e3c0555-88f6-4515-8c99-aa56b0769d54",
+   "metadata": {},
+   "source": [
+    "<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/appendix-a_compressed/2.webp\" width=\"300px\">\n",
+    "\n",
+    "<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/appendix-a_compressed/3.webp\" width=\"300px\">\n",
+    "\n",
+    "<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/appendix-a_compressed/4.webp\" width=\"500px\">\n",
+    "\n",
+    "<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/appendix-a_compressed/5.webp\" width=\"500px\">"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "2100cf2e-7459-4ab3-92a8-43e86ab35a9b",
@@ -73,6 +95,14 @@
     "## A.2 Understanding tensors"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "3c484e87-bfc9-4105-b0a7-1e23b2a72a30",
+   "metadata": {},
+   "source": [
+    "<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/appendix-a_compressed/6.webp\" width=\"400px\">"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "26d7f785-e048-42bc-9182-a556af6bb7f4",
@@ -392,6 +422,14 @@
     "## A.3 Seeing models as computation graphs"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "0f3e16c3-07df-44b6-9106-a42fb24452a9",
+   "metadata": {},
+   "source": [
+    "<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/appendix-a_compressed/7.webp\" width=\"600px\">"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 16,
@@ -429,6 +467,14 @@
     "## A.4 Automatic differentiation made easy"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "33aa2ee4-6f1d-448d-8707-67cd5278233c",
+   "metadata": {},
+   "source": [
+    "<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/appendix-a_compressed/8.webp\" width=\"600px\">"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 17,
@@ -495,6 +541,14 @@
     "## A.5 Implementing multilayer neural networks"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "d6cb9787-2bc8-4379-9e8c-a3401ac63c51",
+   "metadata": {},
+   "source": [
+    "<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/appendix-a_compressed/9.webp\" width=\"500px\">"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 19,
@@ -723,6 +777,14 @@
     "## A.6 Setting up efficient data loaders"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "0f98d8fc-5618-47a2-bc72-153818972a24",
+   "metadata": {},
+   "source": [
+    "<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/appendix-a_compressed/10.webp\" width=\"600px\">"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 29,
@@ -901,6 +963,14 @@
     "    print(f\"Batch {idx+1}:\", x, y)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "eb03ed57-df38-4ee0-a553-0863450df39b",
+   "metadata": {},
+   "source": [
+    "<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/appendix-a_compressed/11.webp\" width=\"600px\">"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "d904ca82-e50f-4f3d-a3ac-fc6ca53dd00e",
@@ -1239,14 +1309,6 @@
    "source": [
     "See [DDP-script.py](DDP-script.py)"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "b32db94f-f159-4aa3-91cc-5b937eef7fc7",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {

appendix-A/03_main-chapter-code/code-part2.ipynb

@@ -175,7 +175,7 @@
     "id": "c8j1cWDcWAMf"
    },
    "source": [
-    "## A.9.2 Single-GPU training"
+    "### A.9.2 Single-GPU training"
    ]
   },
   {
@@ -431,6 +431,28 @@
    "source": [
     "compute_accuracy(model, test_loader, device=device)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### A.9.3 Training with multiple GPUs"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "See [DDP-script.py](DDP-script.py)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/appendix-a_compressed/12.webp\" width=\"600px\">\n",
+    "<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/appendix-a_compressed/13.webp\" width=\"600px\">"
+   ]
   }
  ],
  "metadata": {
@@ -454,7 +476,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.6"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,

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

@@ -1876,7 +1876,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,