diff --git a/ch05/07_gpt_to_llama/converting-llama2-to-llama3.ipynb b/ch05/07_gpt_to_llama/converting-llama2-to-llama3.ipynb
index 3fb007b..431c8d3 100644
--- a/ch05/07_gpt_to_llama/converting-llama2-to-llama3.ipynb
+++ b/ch05/07_gpt_to_llama/converting-llama2-to-llama3.ipynb
@@ -2094,12 +2094,37 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "9bdbe32f-4c96-4e60-8bf4-52b5217df1e6",
-   "metadata": {},
-   "outputs": [],
+   "execution_count": 10,
+   "id": "a55a8769-1a03-4265-8fd0-15f1c423da53",
+   "metadata": {
+    "id": "a8bc2370-39d2-4bfe-b4c1-6bdd75fe101c"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "New RoPE theta: 31250.0\n"
+     ]
+    }
+   ],
    "source": [
-    "LLAMA31_CONFIG_8B[\"context_length\"] = 8192"
+    "old_context_length = LLAMA31_CONFIG_8B[\"context_length\"]\n",
+    "LLAMA31_CONFIG_8B[\"context_length\"] = 8192\n",
+    "\n",
+    "\n",
+    "def rescale_theta(theta_old, context_length_old, context_length_new):\n",
+    "    scaling_factor = context_length_new / context_length_old\n",
+    "    theta_new = theta_old * scaling_factor\n",
+    "    return theta_new\n",
+    "\n",
+    "LLAMA31_CONFIG_8B[\"rope_base\"] = rescale_theta(\n",
+    "    LLAMA31_CONFIG_8B[\"rope_base\"],\n",
+    "    old_context_length,\n",
+    "    LLAMA31_CONFIG_8B[\"context_length\"]\n",
+    ")\n",
+    "\n",
+    "print(\"New RoPE theta:\", LLAMA31_CONFIG_8B[\"rope_base\"])"
    ]
   },
   {
@@ -2462,12 +2487,31 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "387456c3-c6a1-46fe-8830-6e00eb46ac13",
-   "metadata": {},
-   "outputs": [],
+   "execution_count": 10,
+   "id": "73f001a6-7ae0-4204-aa83-a27a8878dfd2",
+   "metadata": {
+    "id": "a8bc2370-39d2-4bfe-b4c1-6bdd75fe101c"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "New RoPE theta: 31250.0\n"
+     ]
+    }
+   ],
    "source": [
-    "LLAMA32_CONFIG_1B[\"context_length\"] = 8192"
+    "old_context_length = LLAMA32_CONFIG_1B[\"context_length\"]\n",
+    "LLAMA32_CONFIG_1B[\"context_length\"] = 8192\n",
+    "\n",
+    "LLAMA32_CONFIG_1B[\"rope_base\"] = rescale_theta(\n",
+    "    LLAMA32_CONFIG_1B[\"rope_base\"],\n",
+    "    old_context_length,\n",
+    "    LLAMA32_CONFIG_1B[\"context_length\"]\n",
+    ")\n",
+    "\n",
+    "print(\"New RoPE theta:\", LLAMA32_CONFIG_1B[\"rope_base\"])"
    ]
   },
   {
@@ -2689,7 +2733,7 @@
    "provenance": []
   },
   "kernelspec": {
-   "display_name": "pt",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -2703,7 +2747,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.11.4"
   },
   "widgets": {
    "application/vnd.jupyter.widget-state+json": {
diff --git a/ch05/07_gpt_to_llama/standalone-llama32.ipynb b/ch05/07_gpt_to_llama/standalone-llama32.ipynb
index dd8fdf5..8dfb940 100644
--- a/ch05/07_gpt_to_llama/standalone-llama32.ipynb
+++ b/ch05/07_gpt_to_llama/standalone-llama32.ipynb
@@ -3,7 +3,9 @@
   {
    "cell_type": "markdown",
    "id": "e1b280ab-b61f-4d1a-bf7e-44e5f9ed3a5c",
-   "metadata": {},
+   "metadata": {
+    "id": "e1b280ab-b61f-4d1a-bf7e-44e5f9ed3a5c"
+   },
    "source": [
     "<table style=\"width:100%\">\n",
     "<tr>\n",
@@ -23,7 +25,9 @@
   {
    "cell_type": "markdown",
    "id": "efde77f2-6af3-4781-8597-89ecd3f41a52",
-   "metadata": {},
+   "metadata": {
+    "id": "efde77f2-6af3-4781-8597-89ecd3f41a52"
+   },
    "source": [
     "# Llama 3.2 From Scratch (A Standalone Notebook)"
    ]
@@ -31,14 +35,16 @@
   {
    "cell_type": "markdown",
    "id": "55cdef4d-de59-4a65-89f9-fa2a8ef3471d",
-   "metadata": {},
+   "metadata": {
+    "id": "55cdef4d-de59-4a65-89f9-fa2a8ef3471d"
+   },
    "source": [
     "- This notebook is purposefully minimal and focuses on the code to implement the Llama 3.2 1B and 3B LLMs\n",
     "- For a step-by-step guide that explains the individual components and the relationship between GPT, Llama 2, and Llama 3, please see the following companion notebooks:\n",
     "  - [Converting a From-Scratch GPT Architecture to Llama 2](converting-gpt-to-llama2.ipynb)\n",
     "  - [Converting Llama 2 to Llama 3.2 From Scratch](converting-llama2-to-llama3.ipynb)\n",
     "  \n",
-    " \n",
+    "\n",
     "<img src=\"https://sebastianraschka.com/images/LLMs-from-scratch-images/bonus/gpt-to-llama/llama32.webp\" width=\"700px\">\n",
     "  \n",
     "  \n",
@@ -50,8 +56,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
-   "id": "beef121b-2454-4577-8b56-aa00961089cb",
+   "execution_count": null,
+   "id": "7c201adb-747e-437b-9a62-442802941e01",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -60,18 +66,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "id": "dd1b65a8-4301-444a-bd7c-a6f2bd1df9df",
-   "metadata": {},
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "dd1b65a8-4301-444a-bd7c-a6f2bd1df9df",
+    "outputId": "4f762354-e0a3-4cc2-e5d4-e61a227a202c"
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
       "blobfile version: 3.0.0\n",
-      "huggingface_hub version: 0.25.1\n",
-      "tiktoken version: 0.7.0\n",
-      "torch version: 2.4.0\n"
+      "huggingface_hub version: 0.25.2\n",
+      "tiktoken version: 0.8.0\n",
+      "torch version: 2.5.0\n"
      ]
     }
    ],
@@ -91,7 +103,9 @@
   {
    "cell_type": "markdown",
    "id": "653410a6-dd2b-4eb2-a722-23d9782e726d",
-   "metadata": {},
+   "metadata": {
+    "id": "653410a6-dd2b-4eb2-a722-23d9782e726d"
+   },
    "source": [
     "&nbsp;\n",
     "# 1. Architecture code"
@@ -99,9 +113,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "id": "82076c21-9331-4dcd-b017-42b046cf1a60",
-   "metadata": {},
+   "metadata": {
+    "id": "82076c21-9331-4dcd-b017-42b046cf1a60"
+   },
    "outputs": [],
    "source": [
     "import torch\n",
@@ -124,9 +140,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "id": "4b9a346f-5826-4083-9162-abd56afc03f0",
-   "metadata": {},
+   "metadata": {
+    "id": "4b9a346f-5826-4083-9162-abd56afc03f0"
+   },
    "outputs": [],
    "source": [
     "def precompute_rope_params(head_dim, theta_base=10_000, context_length=4096, freq_config=None):\n",
@@ -196,9 +214,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "e8169ab5-f976-4222-a2e1-eb1cabf267cb",
-   "metadata": {},
+   "metadata": {
+    "id": "e8169ab5-f976-4222-a2e1-eb1cabf267cb"
+   },
    "outputs": [],
    "source": [
     "class SharedBuffers:\n",
@@ -308,9 +328,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "id": "457cb2f8-50c1-4045-8a74-f181bfb5fea9",
-   "metadata": {},
+   "metadata": {
+    "id": "457cb2f8-50c1-4045-8a74-f181bfb5fea9"
+   },
    "outputs": [],
    "source": [
     "class TransformerBlock(nn.Module):\n",
@@ -348,9 +370,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "id": "e88de3e3-9f07-42cc-816b-28dbd46e96c4",
-   "metadata": {},
+   "metadata": {
+    "id": "e88de3e3-9f07-42cc-816b-28dbd46e96c4"
+   },
    "outputs": [],
    "source": [
     "class Llama3Model(nn.Module):\n",
@@ -376,7 +400,9 @@
   {
    "cell_type": "markdown",
    "id": "be2d201f-74ad-4d63-ab9c-601b00674a48",
-   "metadata": {},
+   "metadata": {
+    "id": "be2d201f-74ad-4d63-ab9c-601b00674a48"
+   },
    "source": [
     "&nbsp;\n",
     "# 2. Initialize model"
@@ -385,16 +411,20 @@
   {
    "cell_type": "markdown",
    "id": "23dea40c-fe20-4a75-be25-d6fce5863c01",
-   "metadata": {},
+   "metadata": {
+    "id": "23dea40c-fe20-4a75-be25-d6fce5863c01"
+   },
    "source": [
     "- The remainder of this notebook uses the Llama 3.2 1B model; to use the 3B model variant, just uncomment the second configuration file in the following code cell"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "id": "caa142fa-b375-4e78-b392-2072ced666f3",
-   "metadata": {},
+   "metadata": {
+    "id": "caa142fa-b375-4e78-b392-2072ced666f3"
+   },
    "outputs": [],
    "source": [
     "# Llama 3.2 1B\n",
@@ -407,7 +437,7 @@
     "    \"n_layers\": 16,             # Number of layers\n",
     "    \"hidden_dim\": 8192,         # Size of the intermediate dimension in FeedForward\n",
     "    \"n_kv_groups\": 8,           # Key-Value groups for grouped-query attention\n",
-    "    \"rope_base\": 500_000,        # The base in RoPE's \"theta\"\n",
+    "    \"rope_base\": 500_000,       # The base in RoPE's \"theta\"\n",
     "    \"dtype\": torch.bfloat16,    # Lower-precision dtype to save memory\n",
     "    \"rope_freq\": {              # RoPE frequency scaling\n",
     "        \"factor\": 32.0,\n",
@@ -443,26 +473,55 @@
   {
    "cell_type": "markdown",
    "id": "34535172-797e-4dd0-84fb-65bc75ad5b06",
-   "metadata": {},
+   "metadata": {
+    "id": "34535172-797e-4dd0-84fb-65bc75ad5b06"
+   },
    "source": [
     "- Reduce the context length so the model would work fine on a MacBook Air (if you have more RAM, feel free to comment out the lines below):"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 10,
    "id": "a8bc2370-39d2-4bfe-b4c1-6bdd75fe101c",
-   "metadata": {},
-   "outputs": [],
+   "metadata": {
+    "id": "a8bc2370-39d2-4bfe-b4c1-6bdd75fe101c"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "New RoPE theta: 31250.0\n"
+     ]
+    }
+   ],
    "source": [
-    "LLAMA32_CONFIG[\"context_length\"] = 8192"
+    "old_context_length = LLAMA32_CONFIG[\"context_length\"]\n",
+    "LLAMA32_CONFIG[\"context_length\"] = 8192\n",
+    "\n",
+    "\n",
+    "def rescale_theta(theta_old, context_length_old, context_length_new):\n",
+    "    scaling_factor = context_length_new / context_length_old\n",
+    "    theta_new = theta_old * scaling_factor\n",
+    "    return theta_new\n",
+    "\n",
+    "LLAMA32_CONFIG[\"rope_base\"] = rescale_theta(\n",
+    "    LLAMA32_CONFIG[\"rope_base\"],\n",
+    "    old_context_length,\n",
+    "    LLAMA32_CONFIG[\"context_length\"]\n",
+    ")\n",
+    "\n",
+    "print(\"New RoPE theta:\", LLAMA32_CONFIG[\"rope_base\"])"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 11,
    "id": "156253fe-aacd-4da2-8f13-705f05c4b11e",
-   "metadata": {},
+   "metadata": {
+    "id": "156253fe-aacd-4da2-8f13-705f05c4b11e"
+   },
    "outputs": [],
    "source": [
     "model = Llama3Model(LLAMA32_CONFIG)"
@@ -471,16 +530,24 @@
   {
    "cell_type": "markdown",
    "id": "19de6c2c-83ce-456d-8be9-6ec415fe9eb1",
-   "metadata": {},
+   "metadata": {
+    "id": "19de6c2c-83ce-456d-8be9-6ec415fe9eb1"
+   },
    "source": [
     "- The following is expected to print True to confirm buffers are reused instead of being (wastefully) recreated:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 12,
    "id": "0e95db6d-2712-41a5-a5e0-86c49897f4cf",
-   "metadata": {},
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "0e95db6d-2712-41a5-a5e0-86c49897f4cf",
+    "outputId": "8efc4937-e616-40d0-cd59-670d7eb3e841"
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -496,14 +563,20 @@
     "# Check buffers\n",
     "print(model.trf_blocks[0].att.mask is model.trf_blocks[-1].att.mask)\n",
     "print(model.trf_blocks[0].att.cos is model.trf_blocks[-1].att.cos)\n",
-    "print(model.trf_blocks[0].att.sin is model.trf_blocks[-1].att.sin) "
+    "print(model.trf_blocks[0].att.sin is model.trf_blocks[-1].att.sin)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 13,
    "id": "364e76ca-52f8-4fa5-af37-c4069f9694bc",
-   "metadata": {},
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "364e76ca-52f8-4fa5-af37-c4069f9694bc",
+    "outputId": "00d7e983-262e-4c65-f322-f4d999311988"
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -526,9 +599,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 14,
    "id": "fd5efb03-5a07-46e8-8607-93ed47549d2b",
-   "metadata": {},
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "fd5efb03-5a07-46e8-8607-93ed47549d2b",
+    "outputId": "65c1a95e-b502-4150-9e2e-da619d9053d5"
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -570,9 +649,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 15,
    "id": "31f12baf-f79b-499f-85c0-51328a6a20f5",
-   "metadata": {},
+   "metadata": {
+    "id": "31f12baf-f79b-499f-85c0-51328a6a20f5"
+   },
    "outputs": [],
    "source": [
     "if torch.cuda.is_available():\n",
@@ -588,7 +669,9 @@
   {
    "cell_type": "markdown",
    "id": "78e091e1-afa8-4d23-9aea-cced86181bfd",
-   "metadata": {},
+   "metadata": {
+    "id": "78e091e1-afa8-4d23-9aea-cced86181bfd"
+   },
    "source": [
     "&nbsp;\n",
     "# 3. Load tokenizer"
@@ -596,9 +679,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 16,
    "id": "9482b01c-49f9-48e4-ab2c-4a4c75240e77",
-   "metadata": {},
+   "metadata": {
+    "id": "9482b01c-49f9-48e4-ab2c-4a4c75240e77"
+   },
    "outputs": [],
    "source": [
     "import os\n",
@@ -647,7 +732,7 @@
     "\n",
     "    def decode(self, tokens):\n",
     "        return self.model.decode(tokens)\n",
-    "    \n",
+    "\n",
     "\n",
     "class ChatFormat:\n",
     "    def __init__(self, tokenizer):\n",
@@ -681,7 +766,9 @@
   {
    "cell_type": "markdown",
    "id": "b771b60c-c198-4b30-bf10-42031197ae86",
-   "metadata": {},
+   "metadata": {
+    "id": "b771b60c-c198-4b30-bf10-42031197ae86"
+   },
    "source": [
     "- Please note that Meta AI requires that you accept the Llama 3.2 licensing terms before you can download the files; to do this, you have to create a Hugging Face Hub account and visit the [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) repository to accept the terms\n",
     "- Next, you will need to create an access token; to generate an access token with READ permissions, click on the profile picture in the upper right and click on \"Settings\"\n",
@@ -696,23 +783,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 17,
    "id": "e9d96dc8-603a-4cb5-8c3e-4d2ca56862ed",
-   "metadata": {},
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "e9d96dc8-603a-4cb5-8c3e-4d2ca56862ed",
+    "outputId": "e6e6dc05-7330-45bc-a9a7-331919155bdd"
+   },
    "outputs": [
     {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "8cdf801700d64fe9b2b827172a8eebcf",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The token has not been saved to the git credentials helper. Pass `add_to_git_credential=True` in this function directly or `--add-to-git-credential` if using via `huggingface-cli` if you want to set the git credential as well.\n",
+      "Token is valid (permission: read).\n",
+      "Your token has been saved to /teamspace/studios/this_studio/.cache/huggingface/token\n",
+      "Login successful\n"
+     ]
     }
    ],
    "source": [
@@ -723,9 +812,29 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 18,
    "id": "986bc1a0-804f-4154-80f8-44cefbee1368",
-   "metadata": {},
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 141,
+     "referenced_widgets": [
+      "a1608feac06d4687967a3e398f01c489",
+      "518fb202e4b44aaba47f07d1a61b6762",
+      "672cdc5aea954de3af851c001a667ad3",
+      "eebf8874618746b39cf4a21a2728dc7f",
+      "5176834aa8784bba9ec21234b87a8948",
+      "e2dc407afcd945c798e30597fddfcb3c",
+      "0dccd57dcc5c43a588157cef957c07e8",
+      "33ca0cdf2c7f41598a381c4ebe6a4ee1",
+      "ee44487f58454dacb522b1e084ffb733",
+      "d2c41e71a3f441deaed091b620ac5603",
+      "3326b6141a1a4eba9f316df528a9b99a"
+     ]
+    },
+    "id": "986bc1a0-804f-4154-80f8-44cefbee1368",
+    "outputId": "5dd7334b-4c71-465a-94d2-c3e95b9ddc58"
+   },
    "outputs": [],
    "source": [
     "from huggingface_hub import hf_hub_download\n",
@@ -733,15 +842,17 @@
     "tokenizer_file_path = hf_hub_download(\n",
     "    repo_id=f\"meta-llama/Llama-3.2-{LLAMA_SIZE_STR}-Instruct\",\n",
     "    filename=\"original/tokenizer.model\",\n",
-    "    local_dir=\"Llama-3.2-1B-Instruct\"\n",
+    "    local_dir=f\"Llama-3.2-{LLAMA_SIZE_STR}-Instruct\"\n",
     ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
-   "id": "f5a3014f-4c66-4fe2-874e-7b57562c49ad",
-   "metadata": {},
+   "execution_count": 19,
+   "id": "_gBhxDtU_nxo",
+   "metadata": {
+    "id": "_gBhxDtU_nxo"
+   },
    "outputs": [],
    "source": [
     "tokenizer = Tokenizer(tokenizer_file_path)\n",
@@ -751,7 +862,9 @@
   {
    "cell_type": "markdown",
    "id": "c172f89f-d301-439f-b809-46169e5f5945",
-   "metadata": {},
+   "metadata": {
+    "id": "c172f89f-d301-439f-b809-46169e5f5945"
+   },
    "source": [
     "&nbsp;\n",
     "# 4. Load pretrained weights"
@@ -759,9 +872,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 20,
    "id": "75166128-5899-4995-9b88-9672e135650e",
-   "metadata": {},
+   "metadata": {
+    "id": "75166128-5899-4995-9b88-9672e135650e"
+   },
    "outputs": [],
    "source": [
     "def assign(left, right, tensor_name=\"unknown\"):\n",
@@ -840,9 +955,29 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 21,
    "id": "699cb1b8-a67d-49fb-80a6-0dad9d81f392",
-   "metadata": {},
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 17,
+     "referenced_widgets": [
+      "9881b6995c3f49dc89e6992fd9ab660b",
+      "17a3174e65c54476b2e0d1faf8f011ca",
+      "1bbf2e62c0754d1593beb4105a7f1ac1",
+      "b82112e1dec645d98aa1c1ba64abcb61",
+      "271e2bd6a35e4a8b92de8697f7c0be5f",
+      "90a79523187446dfa692723b2e5833a7",
+      "431ffb83b8c14bf182f0430e07ea6154",
+      "a8f1b72a33dd4b548de23fbd95e0da18",
+      "25cc36132d384189acfbecc59483134b",
+      "bfd06423ad544218968648016e731a46",
+      "d029630b63ff44cf807ade428d2eb421"
+     ]
+    },
+    "id": "699cb1b8-a67d-49fb-80a6-0dad9d81f392",
+    "outputId": "55b2f28c-142f-4698-9d23-d27456d3ed6d"
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -860,7 +995,7 @@
     "    weights_file = hf_hub_download(\n",
     "        repo_id=f\"meta-llama/Llama-3.2-{LLAMA_SIZE_STR}-Instruct\",\n",
     "        filename=f\"model.safetensors\",\n",
-    "        local_dir=\"Llama-3.2-1B-Instruct\"\n",
+    "        local_dir=f\"Llama-3.2-{LLAMA_SIZE_STR}-Instruct\"\n",
     "    )\n",
     "    combined_weights = load_file(weights_file)\n",
     "\n",
@@ -871,11 +1006,11 @@
     "        weights_file = hf_hub_download(\n",
     "            repo_id=f\"meta-llama/Llama-3.2-{LLAMA_SIZE_STR}-Instruct\",\n",
     "            filename=f\"model-0000{i}-of-00002.safetensors\",\n",
-    "            local_dir=\"Llama-3.2-1B-Instruct\"\n",
+    "            local_dir=f\"Llama-3.2-{LLAMA_SIZE_STR}-Instruct\"\n",
     "        )\n",
     "        current_weights = load_file(weights_file)\n",
     "        combined_weights.update(current_weights)\n",
-    "    \n",
+    "\n",
     "\n",
     "load_weights_into_llama(model, LLAMA32_CONFIG, combined_weights)\n",
     "model.to(device);"
@@ -883,9 +1018,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 22,
    "id": "7f9f7ccc-70cb-41ff-9c25-44336042fc37",
-   "metadata": {},
+   "metadata": {
+    "id": "7f9f7ccc-70cb-41ff-9c25-44336042fc37"
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -902,7 +1039,9 @@
   {
    "cell_type": "markdown",
    "id": "57d07df1-4401-4792-b549-7c4cc5632323",
-   "metadata": {},
+   "metadata": {
+    "id": "57d07df1-4401-4792-b549-7c4cc5632323"
+   },
    "source": [
     "&nbsp;\n",
     "# 5. Generate text"
@@ -910,9 +1049,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 23,
    "id": "7b8401c6-e244-4cb7-9849-2ba71ce758d5",
-   "metadata": {},
+   "metadata": {
+    "id": "7b8401c6-e244-4cb7-9849-2ba71ce758d5"
+   },
    "outputs": [],
    "source": [
     "def text_to_token_ids(text, tokenizer):\n",
@@ -967,23 +1108,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 24,
    "id": "1c7a04fa-6aac-416b-8f63-f1e19227633d",
-   "metadata": {},
+   "metadata": {
+    "id": "1c7a04fa-6aac-416b-8f63-f1e19227633d"
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
       "Output text:\n",
-      " Llamas are herbivores, which means they primarily eat plants and plant-based foods. Their diet typically consists of:\n",
+      " Llamas are herbivores, which means they primarily eat plants. Their diet consists mainly of:\n",
       "\n",
-      "1. Grasses: Llamas love to graze on various types of grasses, including tall grasses and short grasses.\n",
+      "1. Grasses: Llamas love to graze on various types of grasses, including tall grasses and grassy meadows.\n",
       "2. Hay: Llamas also eat hay, which is a dry, compressed form of grass or other plants.\n",
-      "3. Alfalfa: Alfalfa is a legume that is commonly fed to llamas, as it is high in protein and fiber.\n",
-      "4. Other plants: Llamas will also eat other plants, such as clover, wild grasses, and shrubs.\n",
+      "3. Alfalfa: Alfalfa is a legume that is commonly fed to llamas. It is high in protein and fiber.\n",
+      "4. Other plants: Llamas will also eat other plants, such as wild grasses, shrubs, and trees.\n",
       "\n",
-      "It's worth noting that llamas are adapted to high altitudes and\n"
+      "It's worth noting that the diet of llamas can vary depending on the region, climate,\n"
      ]
     }
    ],
@@ -1021,7 +1164,9 @@
   {
    "cell_type": "markdown",
    "id": "549324d6-5c71-4147-ae21-2e67675faa3d",
-   "metadata": {},
+   "metadata": {
+    "id": "549324d6-5c71-4147-ae21-2e67675faa3d"
+   },
    "source": [
     "&nbsp;\n",
     "# What's next?"
@@ -1030,7 +1175,9 @@
   {
    "cell_type": "markdown",
    "id": "e6edaaae-2de1-406c-8ffa-897cdfa3808c",
-   "metadata": {},
+   "metadata": {
+    "id": "e6edaaae-2de1-406c-8ffa-897cdfa3808c"
+   },
    "source": [
     "- The notebook was kept purposefully minimal; if you are interested in additional explanation about the individual components, check out the following two companion notebooks:\n",
     "\n",
@@ -1046,8 +1193,13 @@
   }
  ],
  "metadata": {
+  "accelerator": "GPU",
+  "colab": {
+   "gpuType": "A100",
+   "provenance": []
+  },
   "kernelspec": {
-   "display_name": "pt",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -1061,7 +1213,731 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.11.4"
+  },
+  "widgets": {
+   "application/vnd.jupyter.widget-state+json": {
+    "0dccd57dcc5c43a588157cef957c07e8": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "2.0.0",
+     "model_name": "HTMLStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "2.0.0",
+      "_model_name": "HTMLStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "2.0.0",
+      "_view_name": "StyleView",
+      "background": null,
+      "description_width": "",
+      "font_size": null,
+      "text_color": null
+     }
+    },
+    "17a3174e65c54476b2e0d1faf8f011ca": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "2.0.0",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "2.0.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "2.0.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_allow_html": false,
+      "layout": "IPY_MODEL_90a79523187446dfa692723b2e5833a7",
+      "placeholder": "​",
+      "style": "IPY_MODEL_431ffb83b8c14bf182f0430e07ea6154",
+      "tabbable": null,
+      "tooltip": null,
+      "value": "model.safetensors:  35%"
+     }
+    },
+    "1bbf2e62c0754d1593beb4105a7f1ac1": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "2.0.0",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "2.0.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "2.0.0",
+      "_view_name": "ProgressView",
+      "bar_style": "",
+      "description": "",
+      "description_allow_html": false,
+      "layout": "IPY_MODEL_a8f1b72a33dd4b548de23fbd95e0da18",
+      "max": 2471645608,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_25cc36132d384189acfbecc59483134b",
+      "tabbable": null,
+      "tooltip": null,
+      "value": 880803840
+     }
+    },
+    "25cc36132d384189acfbecc59483134b": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "2.0.0",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "2.0.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "2.0.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": ""
+     }
+    },
+    "271e2bd6a35e4a8b92de8697f7c0be5f": {
+     "model_module": "@jupyter-widgets/base",
+     "model_module_version": "2.0.0",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "2.0.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "2.0.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border_bottom": null,
+      "border_left": null,
+      "border_right": null,
+      "border_top": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "3326b6141a1a4eba9f316df528a9b99a": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "2.0.0",
+     "model_name": "HTMLStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "2.0.0",
+      "_model_name": "HTMLStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "2.0.0",
+      "_view_name": "StyleView",
+      "background": null,
+      "description_width": "",
+      "font_size": null,
+      "text_color": null
+     }
+    },
+    "33ca0cdf2c7f41598a381c4ebe6a4ee1": {
+     "model_module": "@jupyter-widgets/base",
+     "model_module_version": "2.0.0",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "2.0.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "2.0.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border_bottom": null,
+      "border_left": null,
+      "border_right": null,
+      "border_top": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "431ffb83b8c14bf182f0430e07ea6154": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "2.0.0",
+     "model_name": "HTMLStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "2.0.0",
+      "_model_name": "HTMLStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "2.0.0",
+      "_view_name": "StyleView",
+      "background": null,
+      "description_width": "",
+      "font_size": null,
+      "text_color": null
+     }
+    },
+    "5176834aa8784bba9ec21234b87a8948": {
+     "model_module": "@jupyter-widgets/base",
+     "model_module_version": "2.0.0",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "2.0.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "2.0.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border_bottom": null,
+      "border_left": null,
+      "border_right": null,
+      "border_top": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "518fb202e4b44aaba47f07d1a61b6762": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "2.0.0",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "2.0.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "2.0.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_allow_html": false,
+      "layout": "IPY_MODEL_e2dc407afcd945c798e30597fddfcb3c",
+      "placeholder": "​",
+      "style": "IPY_MODEL_0dccd57dcc5c43a588157cef957c07e8",
+      "tabbable": null,
+      "tooltip": null,
+      "value": "tokenizer.model: 100%"
+     }
+    },
+    "672cdc5aea954de3af851c001a667ad3": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "2.0.0",
+     "model_name": "FloatProgressModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "2.0.0",
+      "_model_name": "FloatProgressModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "2.0.0",
+      "_view_name": "ProgressView",
+      "bar_style": "success",
+      "description": "",
+      "description_allow_html": false,
+      "layout": "IPY_MODEL_33ca0cdf2c7f41598a381c4ebe6a4ee1",
+      "max": 2183982,
+      "min": 0,
+      "orientation": "horizontal",
+      "style": "IPY_MODEL_ee44487f58454dacb522b1e084ffb733",
+      "tabbable": null,
+      "tooltip": null,
+      "value": 2183982
+     }
+    },
+    "90a79523187446dfa692723b2e5833a7": {
+     "model_module": "@jupyter-widgets/base",
+     "model_module_version": "2.0.0",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "2.0.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "2.0.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border_bottom": null,
+      "border_left": null,
+      "border_right": null,
+      "border_top": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "9881b6995c3f49dc89e6992fd9ab660b": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "2.0.0",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "2.0.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "2.0.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_17a3174e65c54476b2e0d1faf8f011ca",
+       "IPY_MODEL_1bbf2e62c0754d1593beb4105a7f1ac1",
+       "IPY_MODEL_b82112e1dec645d98aa1c1ba64abcb61"
+      ],
+      "layout": "IPY_MODEL_271e2bd6a35e4a8b92de8697f7c0be5f",
+      "tabbable": null,
+      "tooltip": null
+     }
+    },
+    "a1608feac06d4687967a3e398f01c489": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "2.0.0",
+     "model_name": "HBoxModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "2.0.0",
+      "_model_name": "HBoxModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "2.0.0",
+      "_view_name": "HBoxView",
+      "box_style": "",
+      "children": [
+       "IPY_MODEL_518fb202e4b44aaba47f07d1a61b6762",
+       "IPY_MODEL_672cdc5aea954de3af851c001a667ad3",
+       "IPY_MODEL_eebf8874618746b39cf4a21a2728dc7f"
+      ],
+      "layout": "IPY_MODEL_5176834aa8784bba9ec21234b87a8948",
+      "tabbable": null,
+      "tooltip": null
+     }
+    },
+    "a8f1b72a33dd4b548de23fbd95e0da18": {
+     "model_module": "@jupyter-widgets/base",
+     "model_module_version": "2.0.0",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "2.0.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "2.0.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border_bottom": null,
+      "border_left": null,
+      "border_right": null,
+      "border_top": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "b82112e1dec645d98aa1c1ba64abcb61": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "2.0.0",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "2.0.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "2.0.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_allow_html": false,
+      "layout": "IPY_MODEL_bfd06423ad544218968648016e731a46",
+      "placeholder": "​",
+      "style": "IPY_MODEL_d029630b63ff44cf807ade428d2eb421",
+      "tabbable": null,
+      "tooltip": null,
+      "value": " 870M/2.47G [00:20&lt;00:37, 42.8MB/s]"
+     }
+    },
+    "bfd06423ad544218968648016e731a46": {
+     "model_module": "@jupyter-widgets/base",
+     "model_module_version": "2.0.0",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "2.0.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "2.0.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border_bottom": null,
+      "border_left": null,
+      "border_right": null,
+      "border_top": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "d029630b63ff44cf807ade428d2eb421": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "2.0.0",
+     "model_name": "HTMLStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "2.0.0",
+      "_model_name": "HTMLStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "2.0.0",
+      "_view_name": "StyleView",
+      "background": null,
+      "description_width": "",
+      "font_size": null,
+      "text_color": null
+     }
+    },
+    "d2c41e71a3f441deaed091b620ac5603": {
+     "model_module": "@jupyter-widgets/base",
+     "model_module_version": "2.0.0",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "2.0.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "2.0.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border_bottom": null,
+      "border_left": null,
+      "border_right": null,
+      "border_top": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "e2dc407afcd945c798e30597fddfcb3c": {
+     "model_module": "@jupyter-widgets/base",
+     "model_module_version": "2.0.0",
+     "model_name": "LayoutModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/base",
+      "_model_module_version": "2.0.0",
+      "_model_name": "LayoutModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "2.0.0",
+      "_view_name": "LayoutView",
+      "align_content": null,
+      "align_items": null,
+      "align_self": null,
+      "border_bottom": null,
+      "border_left": null,
+      "border_right": null,
+      "border_top": null,
+      "bottom": null,
+      "display": null,
+      "flex": null,
+      "flex_flow": null,
+      "grid_area": null,
+      "grid_auto_columns": null,
+      "grid_auto_flow": null,
+      "grid_auto_rows": null,
+      "grid_column": null,
+      "grid_gap": null,
+      "grid_row": null,
+      "grid_template_areas": null,
+      "grid_template_columns": null,
+      "grid_template_rows": null,
+      "height": null,
+      "justify_content": null,
+      "justify_items": null,
+      "left": null,
+      "margin": null,
+      "max_height": null,
+      "max_width": null,
+      "min_height": null,
+      "min_width": null,
+      "object_fit": null,
+      "object_position": null,
+      "order": null,
+      "overflow": null,
+      "padding": null,
+      "right": null,
+      "top": null,
+      "visibility": null,
+      "width": null
+     }
+    },
+    "ee44487f58454dacb522b1e084ffb733": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "2.0.0",
+     "model_name": "ProgressStyleModel",
+     "state": {
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "2.0.0",
+      "_model_name": "ProgressStyleModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/base",
+      "_view_module_version": "2.0.0",
+      "_view_name": "StyleView",
+      "bar_color": null,
+      "description_width": ""
+     }
+    },
+    "eebf8874618746b39cf4a21a2728dc7f": {
+     "model_module": "@jupyter-widgets/controls",
+     "model_module_version": "2.0.0",
+     "model_name": "HTMLModel",
+     "state": {
+      "_dom_classes": [],
+      "_model_module": "@jupyter-widgets/controls",
+      "_model_module_version": "2.0.0",
+      "_model_name": "HTMLModel",
+      "_view_count": null,
+      "_view_module": "@jupyter-widgets/controls",
+      "_view_module_version": "2.0.0",
+      "_view_name": "HTMLView",
+      "description": "",
+      "description_allow_html": false,
+      "layout": "IPY_MODEL_d2c41e71a3f441deaed091b620ac5603",
+      "placeholder": "​",
+      "style": "IPY_MODEL_3326b6141a1a4eba9f316df528a9b99a",
+      "tabbable": null,
+      "tooltip": null,
+      "value": " 2.18M/2.18M [00:00&lt;00:00, 9.47MB/s]"
+     }
+    }
+   }
   }
  },
  "nbformat": 4,