diff --git "a/LLAMA_3B_A10.ipynb" "b/LLAMA_3B_A10.ipynb"
new file mode 100644--- /dev/null
+++ "b/LLAMA_3B_A10.ipynb"
@@ -0,0 +1,5438 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "id": "0c24ca36-1782-4ce8-8094-6f6528dada19",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 302,
+          "referenced_widgets": [
+            "b9b391ea3142453fbf4e6cefbd6ef1fc",
+            "3a7fb309595f4a2b961615a5c778171e",
+            "2b92f64605104b99be7cf51241596fc8",
+            "726ff8d697984455986196bf4605df3f",
+            "9c05d7227ff8424195c9523625b6cac9",
+            "ef89047b71f441998faaf1ac2a22d489",
+            "551d6f25992749cc88de42e19116dada",
+            "6fce58e90a484b9482f582e043cfb291",
+            "41da26346546415ebc4a9ce731d5427c",
+            "e3fcacb0b6c94010b16873a659b64026",
+            "594921b118444b218af3fa5ed4dfe04e",
+            "fbd86d4f0c3b4cb2a732d38b5bf9b63d",
+            "c99cb68a2ecc4c62875cfbc683a8bbd5",
+            "ff4ef96f8719449ab188fdabaf498351",
+            "7ce58a71e9bd42bdbb7ac28048425da0",
+            "0a3ddabdfb4f40b3a1a27029b6bef8e5",
+            "e21da6bcc0bb496e86dee50630a1208c"
+          ]
+        },
+        "id": "0c24ca36-1782-4ce8-8094-6f6528dada19",
+        "outputId": "4cda93f1-0758-4136-e7b0-34393d149c5c"
+      },
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
+            ],
+            "application/vnd.jupyter.widget-view+json": {
+              "version_major": 2,
+              "version_minor": 0,
+              "model_id": "b9b391ea3142453fbf4e6cefbd6ef1fc"
+            }
+          },
+          "metadata": {}
+        }
+      ],
+      "source": [
+        "from huggingface_hub import notebook_login\n",
+        "notebook_login()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!pip install unsloth\n",
+        "!pip install --force-reinstall --no-cache-dir --no-deps git+https://github.com/unslothai/unsloth.git"
+      ],
+      "metadata": {
+        "id": "REqA0fPKcTST",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "9f015ccd-1d47-47a5-d993-d92128462269"
+      },
+      "id": "REqA0fPKcTST",
+      "execution_count": 2,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Requirement already satisfied: unsloth in /usr/local/lib/python3.11/dist-packages (2025.1.7)\n",
+            "Collecting git+https://github.com/unslothai/unsloth.git\n",
+            "  Cloning https://github.com/unslothai/unsloth.git to /tmp/pip-req-build-hn4_8bun\n",
+            "  Running command git clone --filter=blob:none --quiet https://github.com/unslothai/unsloth.git /tmp/pip-req-build-hn4_8bun\n",
+            "  Resolved https://github.com/unslothai/unsloth.git to commit bdf0cd6033595be4e7ed23d0d002bb176d343152\n",
+            "  Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
+            "  Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
+            "  Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
+            "Building wheels for collected packages: unsloth\n",
+            "  Building wheel for unsloth (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
+            "  Created wheel for unsloth: filename=unsloth-2025.1.7-py3-none-any.whl size=174896 sha256=77ed48d77dff5eed828dd3f43ca94a0151e32dda1afa1b3699ccb9905e4ded7c\n",
+            "  Stored in directory: /tmp/pip-ephem-wheel-cache-sudawao1/wheels/d1/17/05/850ab10c33284a4763b0595cd8ea9d01fce6e221cac24b3c01\n",
+            "Successfully built unsloth\n",
+            "Installing collected packages: unsloth\n",
+            "  Attempting uninstall: unsloth\n",
+            "    Found existing installation: unsloth 2025.1.7\n",
+            "    Uninstalling unsloth-2025.1.7:\n",
+            "      Successfully uninstalled unsloth-2025.1.7\n",
+            "Successfully installed unsloth-2025.1.7\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 3,
+      "id": "50190966-b741-47c4-915e-43c81fd1413a",
+      "metadata": {
+        "id": "50190966-b741-47c4-915e-43c81fd1413a",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "7c8c7c3d-b7cd-4d0f-c5b5-0e7d6c2929f2"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Requirement already satisfied: datasets in /usr/local/lib/python3.11/dist-packages (3.2.0)\n",
+            "Requirement already satisfied: tqdm in /usr/local/lib/python3.11/dist-packages (4.67.1)\n",
+            "Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from datasets) (3.17.0)\n",
+            "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.11/dist-packages (from datasets) (1.26.4)\n",
+            "Requirement already satisfied: pyarrow>=15.0.0 in /usr/local/lib/python3.11/dist-packages (from datasets) (17.0.0)\n",
+            "Requirement already satisfied: dill<0.3.9,>=0.3.0 in /usr/local/lib/python3.11/dist-packages (from datasets) (0.3.8)\n",
+            "Requirement already satisfied: pandas in /usr/local/lib/python3.11/dist-packages (from datasets) (2.2.2)\n",
+            "Requirement already satisfied: requests>=2.32.2 in /usr/local/lib/python3.11/dist-packages (from datasets) (2.32.3)\n",
+            "Requirement already satisfied: xxhash in /usr/local/lib/python3.11/dist-packages (from datasets) (3.5.0)\n",
+            "Requirement already satisfied: multiprocess<0.70.17 in /usr/local/lib/python3.11/dist-packages (from datasets) (0.70.16)\n",
+            "Requirement already satisfied: fsspec<=2024.9.0,>=2023.1.0 in /usr/local/lib/python3.11/dist-packages (from fsspec[http]<=2024.9.0,>=2023.1.0->datasets) (2024.9.0)\n",
+            "Requirement already satisfied: aiohttp in /usr/local/lib/python3.11/dist-packages (from datasets) (3.11.11)\n",
+            "Requirement already satisfied: huggingface-hub>=0.23.0 in /usr/local/lib/python3.11/dist-packages (from datasets) (0.27.1)\n",
+            "Requirement already satisfied: packaging in /usr/local/lib/python3.11/dist-packages (from datasets) (24.2)\n",
+            "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.11/dist-packages (from datasets) (6.0.2)\n",
+            "Requirement already satisfied: aiohappyeyeballs>=2.3.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets) (2.4.4)\n",
+            "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets) (1.3.2)\n",
+            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets) (24.3.0)\n",
+            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets) (1.5.0)\n",
+            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets) (6.1.0)\n",
+            "Requirement already satisfied: propcache>=0.2.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets) (0.2.1)\n",
+            "Requirement already satisfied: yarl<2.0,>=1.17.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets) (1.18.3)\n",
+            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.11/dist-packages (from huggingface-hub>=0.23.0->datasets) (4.12.2)\n",
+            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests>=2.32.2->datasets) (3.4.1)\n",
+            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests>=2.32.2->datasets) (3.10)\n",
+            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests>=2.32.2->datasets) (2.3.0)\n",
+            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/dist-packages (from requests>=2.32.2->datasets) (2024.12.14)\n",
+            "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.11/dist-packages (from pandas->datasets) (2.8.2)\n",
+            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas->datasets) (2024.2)\n",
+            "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.11/dist-packages (from pandas->datasets) (2025.1)\n",
+            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/dist-packages (from python-dateutil>=2.8.2->pandas->datasets) (1.17.0)\n",
+            "Requirement already satisfied: unsloth in /usr/local/lib/python3.11/dist-packages (2025.1.7)\n",
+            "Collecting git+https://github.com/unslothai/unsloth.git\n",
+            "  Cloning https://github.com/unslothai/unsloth.git to /tmp/pip-req-build-8ejsks9w\n",
+            "  Running command git clone --filter=blob:none --quiet https://github.com/unslothai/unsloth.git /tmp/pip-req-build-8ejsks9w\n",
+            "  Resolved https://github.com/unslothai/unsloth.git to commit bdf0cd6033595be4e7ed23d0d002bb176d343152\n",
+            "  Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
+            "  Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
+            "  Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
+            "Building wheels for collected packages: unsloth\n",
+            "  Building wheel for unsloth (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
+            "  Created wheel for unsloth: filename=unsloth-2025.1.7-py3-none-any.whl size=174896 sha256=6f84b8552af682ed774249b52bbdc201dd83256a85cc98dac44b34ebd70eab56\n",
+            "  Stored in directory: /tmp/pip-ephem-wheel-cache-43bo4nyp/wheels/d1/17/05/850ab10c33284a4763b0595cd8ea9d01fce6e221cac24b3c01\n",
+            "Successfully built unsloth\n",
+            "Installing collected packages: unsloth\n",
+            "  Attempting uninstall: unsloth\n",
+            "    Found existing installation: unsloth 2025.1.7\n",
+            "    Uninstalling unsloth-2025.1.7:\n",
+            "      Successfully uninstalled unsloth-2025.1.7\n",
+            "Successfully installed unsloth-2025.1.7\n"
+          ]
+        }
+      ],
+      "source": [
+        "!pip install datasets tqdm\n",
+        "!pip install unsloth\n",
+        "!pip install --force-reinstall --no-cache-dir --no-deps git+https://github.com/unslothai/unsloth.git"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 4,
+      "id": "fbc9900d-28d2-4bda-9848-b572fbe778d2",
+      "metadata": {
+        "id": "fbc9900d-28d2-4bda-9848-b572fbe778d2",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 1000,
+          "referenced_widgets": [
+            "06af4d907cba475bb0d6d53005671e0f",
+            "c5648f7fa3fa4e6a97bdf67f2275fa14",
+            "084f9365e98c423e9ceda9f4b095d820",
+            "4256bf31907b49adb6bdeac23f9cabf3",
+            "11c242383b26482484f1cdf9ff182814",
+            "9a4659b332b04a1ea2ea2a1178e53fb9",
+            "daa33e7b6b07404fb5551d6582906164",
+            "6fb5a05a50ad49afa35e64e758bc9c54",
+            "594fe19fc2f04c6eaec987691c515bda",
+            "659292ec3fc14c1ea28d8ad2b7a1ee7f",
+            "9281e91ab739424ea4c13a539ff8ccbd",
+            "99dbcf3b567047a98731ddad8ee5311d",
+            "bf35cd8cddf0462db86cad41640c84a2",
+            "bfb555f021694899a1888dc69d98d4d9",
+            "dcdd65424cf646c2ab0a12366dd80f30",
+            "f7e326fc56e841a3a688eb7d0baa1006",
+            "a8c38373c1f04b46a6589092e074173c",
+            "0d34758fbc9d495ba2a20337d7d8d016",
+            "bceb0ff3af904a4f97d5e7d5d9bb2c57",
+            "42d843503af946c293799fea9f8170c3",
+            "171dc3ad2d75492c8c782fa03f905659",
+            "8a370978ed384ce39d1da8047cd684b0",
+            "e2681c452e504af9858d30218f062078",
+            "02f1be48cf8f4c16be2e6df1f34e4169",
+            "0726c62296484dee803598e796be023e",
+            "30ab1c8ce4464b6b80772fd099330ce6",
+            "dcec0609e7654d5689920fefa6513772",
+            "443bb62f011a46fdab191054837f4238",
+            "c8c7b2e3543d4969b13590d0d07b2dd9",
+            "8f342291573f41f3ab5b89dd1870a5f0",
+            "faa4c5dd2b114e67a8579d5a47b7efb4",
+            "3c9b5c165a5549f3b9895d24920e55e1",
+            "3265d7be7689485fb595643786879cdf",
+            "522c6479448d4e8bb4268b33d385f83e",
+            "c8148bf4baab44d481bbead4df316b91",
+            "7a5b13ab59d84326b71d57e401bfe713",
+            "72d28303d29b402f8095d7d9c760df00",
+            "e31e65305361421c9278c071cb7cfba2",
+            "d118c47eb13a49c0b1a241baa63a4835",
+            "11f30495fb384117bb03d3c60a5ff6e8",
+            "c3ef607d2fb942ab8a0083d97cff52e4",
+            "9cc274e1219c4f33b60a57be63e069a9",
+            "65db2cfdad674681b956c66c994e15bb",
+            "cc499d66cd6043129c19378af8a86931",
+            "baf343fdb1314fe693e35995833dcb00",
+            "436072026c25407cbc33fdf7f38813b3",
+            "8463894bc0914c8f8bbf7fb4d60c65f8",
+            "6cc93e1749e646928d71621df8858015",
+            "0e51722a80e0414c99510f4c13ce5607",
+            "915261a80e7048dd9586a4dfe6965746",
+            "af655bb83551407e9f3444b0136721cf",
+            "4c2ac70bc81949029c5ab61d8cc04824",
+            "e5681521f1444e50aba3b9ddb7aa0b0a",
+            "b5c1ea4f85eb4d2c923d2605239a9c25",
+            "8cf502758aba44718b421d25c147620a",
+            "2180408c22cc4b88aa70d89933f6fb28",
+            "1c15b88000614b2c9a79505645ae53be",
+            "217c025a71914dd2bf674e36a8a6d0fd",
+            "7fac231b948643889d57347ede0bc194",
+            "c41c89d84cdf4101aa9ddffc5ebd855f",
+            "00cd88ecc0954dd6b2f69754b7bcefb3",
+            "1d30b45c9dbf4297bf630aad5420c2da",
+            "27d2bfbae8d44c06aaba3f1625cf1501",
+            "afb13af7de5c4d1f8f41fd6fbd581048",
+            "e20db576997a495d8467bc19245a2125",
+            "0a6fa2764d1c4e4998a036fbe306be88",
+            "daf4481446364fa1811c5e7c7f80bb35",
+            "4e64572fb0514967be674bb78c0817e2",
+            "a882747cdc18400fa1ec875e47428871",
+            "5f9076efcfa547e78fe7302055ebe236",
+            "b9dfa47fefdb41d2a83bd8a1d7601b87",
+            "7882ba346a7c4ecabe26ee84b590214e",
+            "8c380d6a7080440eb141d42090d20ee4",
+            "b77abff029aa49ed865c0caec3a4ec06",
+            "0bbd609552594bbe998bf1e17bb2b381",
+            "dc5bb0a2b37d40b2898f183b9477ea99",
+            "97c54e559f8a4051a6955e8a107c84ef",
+            "2861b7e53ab34cc284bc19a8b29c53fa",
+            "dc2c12fae9dc4ef388678d89c966791e",
+            "fff5ffb7d6064945b474812ea600735c",
+            "a21f133b406b4bee91de264da24b24ad",
+            "aec2edc99db046daab086f9656c497be",
+            "b7b2fa33bb224ab3900a6852cf5068d5",
+            "9123f310b13741458753ecea7b95b2ff",
+            "ecab267628b14759b343295657c0843e",
+            "ddd8172014af4d5db7815c3302813c79",
+            "c75b1a426d6348c8b426201b5b66b94d",
+            "f2bcfac07568438cb78bb4adc5f045b6"
+          ]
+        },
+        "outputId": "f4f0fee0-3f19-4614-9ed7-567ee2674910"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "🦥 Unsloth: Will patch your computer to enable 2x faster free finetuning.\n",
+            "🦥 Unsloth Zoo will now patch everything to make training faster!\n",
+            "==((====))==  Unsloth 2025.1.7: Fast Llama patching. Transformers: 4.47.1.\n",
+            "   \\\\   /|    GPU: NVIDIA A100-SXM4-40GB. Max memory: 39.564 GB. Platform: Linux.\n",
+            "O^O/ \\_/ \\    Torch: 2.5.1+cu121. CUDA: 8.0. CUDA Toolkit: 12.1. Triton: 3.1.0\n",
+            "\\        /    Bfloat16 = TRUE. FA [Xformers = 0.0.29.post1. FA2 = False]\n",
+            " \"-____-\"     Free Apache license: http://github.com/unslothai/unsloth\n",
+            "Unsloth: Fast downloading is enabled - ignore downloading bars which are red colored!\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]"
+            ],
+            "application/vnd.jupyter.widget-view+json": {
+              "version_major": 2,
+              "version_minor": 0,
+              "model_id": "06af4d907cba475bb0d6d53005671e0f"
+            }
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "model-00001-of-00002.safetensors:  43%|####2     | 2.12G/4.97G [00:00<?, ?B/s]"
+            ],
+            "application/vnd.jupyter.widget-view+json": {
+              "version_major": 2,
+              "version_minor": 0,
+              "model_id": "99dbcf3b567047a98731ddad8ee5311d"
+            }
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "model-00002-of-00002.safetensors:   0%|          | 0.00/1.46G [00:00<?, ?B/s]"
+            ],
+            "application/vnd.jupyter.widget-view+json": {
+              "version_major": 2,
+              "version_minor": 0,
+              "model_id": "e2681c452e504af9858d30218f062078"
+            }
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]"
+            ],
+            "application/vnd.jupyter.widget-view+json": {
+              "version_major": 2,
+              "version_minor": 0,
+              "model_id": "522c6479448d4e8bb4268b33d385f83e"
+            }
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "generation_config.json:   0%|          | 0.00/234 [00:00<?, ?B/s]"
+            ],
+            "application/vnd.jupyter.widget-view+json": {
+              "version_major": 2,
+              "version_minor": 0,
+              "model_id": "baf343fdb1314fe693e35995833dcb00"
+            }
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "tokenizer_config.json:   0%|          | 0.00/54.7k [00:00<?, ?B/s]"
+            ],
+            "application/vnd.jupyter.widget-view+json": {
+              "version_major": 2,
+              "version_minor": 0,
+              "model_id": "2180408c22cc4b88aa70d89933f6fb28"
+            }
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "tokenizer.json:   0%|          | 0.00/17.2M [00:00<?, ?B/s]"
+            ],
+            "application/vnd.jupyter.widget-view+json": {
+              "version_major": 2,
+              "version_minor": 0,
+              "model_id": "daf4481446364fa1811c5e7c7f80bb35"
+            }
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "special_tokens_map.json:   0%|          | 0.00/454 [00:00<?, ?B/s]"
+            ],
+            "application/vnd.jupyter.widget-view+json": {
+              "version_major": 2,
+              "version_minor": 0,
+              "model_id": "2861b7e53ab34cc284bc19a8b29c53fa"
+            }
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "Unsloth 2025.1.7 patched 28 layers with 28 QKV layers, 28 O layers and 28 MLP layers.\n"
+          ]
+        },
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "PeftModelForCausalLM(\n",
+              "  (base_model): LoraModel(\n",
+              "    (model): LlamaForCausalLM(\n",
+              "      (model): LlamaModel(\n",
+              "        (embed_tokens): Embedding(128256, 3072, padding_idx=128004)\n",
+              "        (layers): ModuleList(\n",
+              "          (0-27): 28 x LlamaDecoderLayer(\n",
+              "            (self_attn): LlamaAttention(\n",
+              "              (q_proj): lora.Linear(\n",
+              "                (base_layer): Linear(in_features=3072, out_features=3072, bias=False)\n",
+              "                (lora_dropout): ModuleDict(\n",
+              "                  (default): Identity()\n",
+              "                )\n",
+              "                (lora_A): ModuleDict(\n",
+              "                  (default): Linear(in_features=3072, out_features=16, bias=False)\n",
+              "                )\n",
+              "                (lora_B): ModuleDict(\n",
+              "                  (default): Linear(in_features=16, out_features=3072, bias=False)\n",
+              "                )\n",
+              "                (lora_embedding_A): ParameterDict()\n",
+              "                (lora_embedding_B): ParameterDict()\n",
+              "                (lora_magnitude_vector): ModuleDict()\n",
+              "              )\n",
+              "              (k_proj): lora.Linear(\n",
+              "                (base_layer): Linear(in_features=3072, out_features=1024, bias=False)\n",
+              "                (lora_dropout): ModuleDict(\n",
+              "                  (default): Identity()\n",
+              "                )\n",
+              "                (lora_A): ModuleDict(\n",
+              "                  (default): Linear(in_features=3072, out_features=16, bias=False)\n",
+              "                )\n",
+              "                (lora_B): ModuleDict(\n",
+              "                  (default): Linear(in_features=16, out_features=1024, bias=False)\n",
+              "                )\n",
+              "                (lora_embedding_A): ParameterDict()\n",
+              "                (lora_embedding_B): ParameterDict()\n",
+              "                (lora_magnitude_vector): ModuleDict()\n",
+              "              )\n",
+              "              (v_proj): lora.Linear(\n",
+              "                (base_layer): Linear(in_features=3072, out_features=1024, bias=False)\n",
+              "                (lora_dropout): ModuleDict(\n",
+              "                  (default): Identity()\n",
+              "                )\n",
+              "                (lora_A): ModuleDict(\n",
+              "                  (default): Linear(in_features=3072, out_features=16, bias=False)\n",
+              "                )\n",
+              "                (lora_B): ModuleDict(\n",
+              "                  (default): Linear(in_features=16, out_features=1024, bias=False)\n",
+              "                )\n",
+              "                (lora_embedding_A): ParameterDict()\n",
+              "                (lora_embedding_B): ParameterDict()\n",
+              "                (lora_magnitude_vector): ModuleDict()\n",
+              "              )\n",
+              "              (o_proj): lora.Linear(\n",
+              "                (base_layer): Linear(in_features=3072, out_features=3072, bias=False)\n",
+              "                (lora_dropout): ModuleDict(\n",
+              "                  (default): Identity()\n",
+              "                )\n",
+              "                (lora_A): ModuleDict(\n",
+              "                  (default): Linear(in_features=3072, out_features=16, bias=False)\n",
+              "                )\n",
+              "                (lora_B): ModuleDict(\n",
+              "                  (default): Linear(in_features=16, out_features=3072, bias=False)\n",
+              "                )\n",
+              "                (lora_embedding_A): ParameterDict()\n",
+              "                (lora_embedding_B): ParameterDict()\n",
+              "                (lora_magnitude_vector): ModuleDict()\n",
+              "              )\n",
+              "              (rotary_emb): LlamaRotaryEmbedding()\n",
+              "            )\n",
+              "            (mlp): LlamaMLP(\n",
+              "              (gate_proj): lora.Linear(\n",
+              "                (base_layer): Linear(in_features=3072, out_features=8192, bias=False)\n",
+              "                (lora_dropout): ModuleDict(\n",
+              "                  (default): Identity()\n",
+              "                )\n",
+              "                (lora_A): ModuleDict(\n",
+              "                  (default): Linear(in_features=3072, out_features=16, bias=False)\n",
+              "                )\n",
+              "                (lora_B): ModuleDict(\n",
+              "                  (default): Linear(in_features=16, out_features=8192, bias=False)\n",
+              "                )\n",
+              "                (lora_embedding_A): ParameterDict()\n",
+              "                (lora_embedding_B): ParameterDict()\n",
+              "                (lora_magnitude_vector): ModuleDict()\n",
+              "              )\n",
+              "              (up_proj): lora.Linear(\n",
+              "                (base_layer): Linear(in_features=3072, out_features=8192, bias=False)\n",
+              "                (lora_dropout): ModuleDict(\n",
+              "                  (default): Identity()\n",
+              "                )\n",
+              "                (lora_A): ModuleDict(\n",
+              "                  (default): Linear(in_features=3072, out_features=16, bias=False)\n",
+              "                )\n",
+              "                (lora_B): ModuleDict(\n",
+              "                  (default): Linear(in_features=16, out_features=8192, bias=False)\n",
+              "                )\n",
+              "                (lora_embedding_A): ParameterDict()\n",
+              "                (lora_embedding_B): ParameterDict()\n",
+              "                (lora_magnitude_vector): ModuleDict()\n",
+              "              )\n",
+              "              (down_proj): lora.Linear(\n",
+              "                (base_layer): Linear(in_features=8192, out_features=3072, bias=False)\n",
+              "                (lora_dropout): ModuleDict(\n",
+              "                  (default): Identity()\n",
+              "                )\n",
+              "                (lora_A): ModuleDict(\n",
+              "                  (default): Linear(in_features=8192, out_features=16, bias=False)\n",
+              "                )\n",
+              "                (lora_B): ModuleDict(\n",
+              "                  (default): Linear(in_features=16, out_features=3072, bias=False)\n",
+              "                )\n",
+              "                (lora_embedding_A): ParameterDict()\n",
+              "                (lora_embedding_B): ParameterDict()\n",
+              "                (lora_magnitude_vector): ModuleDict()\n",
+              "              )\n",
+              "              (act_fn): SiLU()\n",
+              "            )\n",
+              "            (input_layernorm): LlamaRMSNorm((3072,), eps=1e-05)\n",
+              "            (post_attention_layernorm): LlamaRMSNorm((3072,), eps=1e-05)\n",
+              "          )\n",
+              "        )\n",
+              "        (norm): LlamaRMSNorm((3072,), eps=1e-05)\n",
+              "        (rotary_emb): LlamaRotaryEmbedding()\n",
+              "      )\n",
+              "      (lm_head): Linear(in_features=3072, out_features=128256, bias=False)\n",
+              "    )\n",
+              "  )\n",
+              ")"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 4
+        }
+      ],
+      "source": [
+        "from unsloth import FastLanguageModel\n",
+        "import pandas as pd\n",
+        "from datasets import load_dataset\n",
+        "import os\n",
+        "import torch\n",
+        "import torch.nn.functional as F\n",
+        "from transformers import AutoTokenizer, AutoModelForCausalLM\n",
+        "from tqdm import tqdm\n",
+        "tqdm.pandas()\n",
+        "max_seq_length = 2048\n",
+        "load_in_4bit = False\n",
+        "name = \"DrishtiSharma/LLAMA-3B-A10\"\n",
+        "model, tokenizer = FastLanguageModel.from_pretrained(model_name = name, max_seq_length = max_seq_length, load_in_4bit = load_in_4bit,)\n",
+        "model = FastLanguageModel.get_peft_model( model, r = 16, target_modules = [\"q_proj\", \"k_proj\", \"v_proj\", \"o_proj\", \"gate_proj\", \"up_proj\", \"down_proj\",], lora_alpha = 16, lora_dropout = 0, bias = \"none\", use_gradient_checkpointing = \"unsloth\", random_state = 3407, use_rslora = False, loftq_config = None,)\n",
+        "FastLanguageModel.for_inference(model)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "##**SINGLE TEST CASE**"
+      ],
+      "metadata": {
+        "id": "FICHwqm5aLUV"
+      },
+      "id": "FICHwqm5aLUV"
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "input_text = \"जोड़ें 46,911 + 653,092 ### A) 699,903 B) 700,003 C) 913,203 D) 1,122,202 ### MCQ ###\"\n",
+        "prompt = f\"### INPUT : {input_text} RESPONSE : \"\n",
+        "message = [{\"role\": \"user\", \"content\": prompt}]\n",
+        "inputs = tokenizer.apply_chat_template(message, tokenize=True, add_generation_prompt=True, return_tensors=\"pt\").to(\"cuda\")\n",
+        "outputs = model.generate(input_ids=inputs, max_new_tokens=200, use_cache=True, temperature=0.1, min_p=0.1, pad_token_id=tokenizer.eos_token_id)\n",
+        "response = tokenizer.decode(outputs[0], skip_special_tokens=True)\n",
+        "processed_response = response.split(\"### RESPONSE :\\nmodel\")[-1].strip()\n",
+        "print(f\"Generated Response (20 tokens):\\n{processed_response}\\n\")\n",
+        "with torch.no_grad():\n",
+        "    outputs = model.generate(input_ids=inputs, max_new_tokens=3, use_cache=True, pad_token_id=tokenizer.eos_token_id, return_dict_in_generate=True, output_scores=True)\n",
+        "    scores = outputs.scores\n",
+        "token_ids_a = tokenizer.encode('A', add_special_tokens=False)[0]\n",
+        "token_ids_b = tokenizer.encode('B', add_special_tokens=False)[0]\n",
+        "token_ids_c = tokenizer.encode('C', add_special_tokens=False)[0]\n",
+        "token_ids_d = tokenizer.encode('D', add_special_tokens=False)[0]\n",
+        "for i, score in enumerate(scores, 1):\n",
+        "    probs = F.softmax(score, dim=-1)\n",
+        "    prob_a = probs[0, token_ids_a].item()\n",
+        "    prob_b = probs[0, token_ids_b].item()\n",
+        "    prob_c = probs[0, token_ids_c].item()\n",
+        "    prob_d = probs[0, token_ids_d].item()\n",
+        "    print(f\"Probability of 'A' at token {i}: {prob_a:.4f}\")\n",
+        "    print(f\"Probability of 'B' at token {i}: {prob_b:.4f}\")\n",
+        "    print(f\"Probability of 'C' at token {i}: {prob_c:.4f}\")\n",
+        "    print(f\"Probability of 'D' at token {i}: {prob_d:.4f}\")"
+      ],
+      "metadata": {
+        "id": "r1dozae-gO5B",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "3828fe08-c92e-4e0a-e483-f1e93406e03e"
+      },
+      "id": "r1dozae-gO5B",
+      "execution_count": 5,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "The attention mask is not set and cannot be inferred from input because pad token is same as eos token. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Generated Response (20 tokens):\n",
+            "system\n",
+            "\n",
+            "Cutting Knowledge Date: December 2023\n",
+            "Today Date: 28 Jan 2025\n",
+            "\n",
+            "user\n",
+            "\n",
+            "### INPUT : जोड़ें 46,911 + 653,092 ### A) 699,903 B) 700,003 C) 913,203 D) 1,122,202 ### MCQ ### RESPONSE :assistant\n",
+            "\n",
+            "सटीक उत्तर है A) 699,903\n",
+            "\n",
+            "Probability of 'A' at token 1: 0.0564\n",
+            "Probability of 'B' at token 1: 0.1053\n",
+            "Probability of 'C' at token 1: 0.0000\n",
+            "Probability of 'D' at token 1: 0.0000\n",
+            "Probability of 'A' at token 2: 0.0000\n",
+            "Probability of 'B' at token 2: 0.0000\n",
+            "Probability of 'C' at token 2: 0.0000\n",
+            "Probability of 'D' at token 2: 0.0000\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "#**ARC CHALLENGE ENGLISH**"
+      ],
+      "metadata": {
+        "id": "7Al9PZfU2bhu"
+      },
+      "id": "7Al9PZfU2bhu"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 6,
+      "id": "1749c745-d1fb-430b-9469-4913bb2a6cb5",
+      "metadata": {
+        "id": "1749c745-d1fb-430b-9469-4913bb2a6cb5",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "5bd80b7b-eddc-4056-95e7-488d1d1abcc9"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "1172\n",
+            "Average 'tok' value: 71.65102389078498\n",
+            "Max 'tok' value: 199\n",
+            "Output\n",
+            "B    311\n",
+            "C    310\n",
+            "D    285\n",
+            "A    266\n",
+            "Name: count, dtype: int64\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "100%|██████████| 1172/1172 [02:39<00:00,  7.33it/s]"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "ANS\n",
+            "B    460\n",
+            "C    358\n",
+            "A    247\n",
+            "D    107\n",
+            "Name: count, dtype: int64\n",
+            "Accuracy: 0.6084\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "\n"
+          ]
+        }
+      ],
+      "source": [
+        "dataset = load_dataset(\"1-800-LLMs/Test-Collection\", data_files=\"ARC_Challenge_E.csv\", split=\"train\")\n",
+        "df = dataset.to_pandas()\n",
+        "print(len(df))\n",
+        "df['tok'] = df['Input'].apply(lambda x: len(tokenizer.encode(x)))\n",
+        "print(f\"Average 'tok' value: {df['tok'].mean()}\")\n",
+        "print(f\"Max 'tok' value: {df['tok'].max()}\")\n",
+        "df = df.sort_values('tok', ascending=False)\n",
+        "df['Output'] = df['Output'].replace({'1': 'A', '2': 'B', '3': 'C', '4': 'D'})\n",
+        "print(df['Output'].value_counts())\n",
+        "responses = []\n",
+        "prob_a1_list = []\n",
+        "prob_a2_list = []\n",
+        "prob_a3_list = []\n",
+        "prob_b1_list = []\n",
+        "prob_b2_list = []\n",
+        "prob_b3_list = []\n",
+        "prob_c1_list = []\n",
+        "prob_c2_list = []\n",
+        "prob_c3_list = []\n",
+        "prob_d1_list = []\n",
+        "prob_d2_list = []\n",
+        "prob_d3_list = []\n",
+        "batch_size = 1\n",
+        "for start in tqdm(range(0, len(df), batch_size)):\n",
+        "    batch_texts = df['Input'][start:start+batch_size].tolist()\n",
+        "    for input_text in batch_texts:\n",
+        "        prompt = f\"### INPUT : {input_text} Respond with just one letter based on these options : \"\n",
+        "        message = [{\"role\": \"user\", \"content\": prompt}]\n",
+        "        inputs = tokenizer.apply_chat_template(message, tokenize=True, add_generation_prompt=True, return_tensors=\"pt\").to(\"cuda\")\n",
+        "        with torch.no_grad():\n",
+        "            outputs = model.generate(input_ids=inputs, max_new_tokens=3, use_cache=True, pad_token_id=tokenizer.eos_token_id, return_dict_in_generate=True, output_scores=True)\n",
+        "            scores = outputs.scores  # tuple of [batch_size, vocab_size] for each token\n",
+        "        token_ids_a = tokenizer.encode('A', add_special_tokens=False)[0]\n",
+        "        token_ids_b = tokenizer.encode('B', add_special_tokens=False)[0]\n",
+        "        token_ids_c = tokenizer.encode('C', add_special_tokens=False)[0]\n",
+        "        token_ids_d = tokenizer.encode('D', add_special_tokens=False)[0]\n",
+        "        for i in range(3):\n",
+        "            if i < len(scores):\n",
+        "                probs = F.softmax(scores[i], dim=-1)\n",
+        "                prob_a = probs[0, token_ids_a].item()\n",
+        "                prob_b = probs[0, token_ids_b].item()\n",
+        "                prob_c = probs[0, token_ids_c].item()\n",
+        "                prob_d = probs[0, token_ids_d].item()\n",
+        "            else:\n",
+        "                prob_a, prob_b, prob_c, prob_d = 0.0, 0.0, 0.0, 0.0\n",
+        "            if i == 0:\n",
+        "                prob_a1_list.append(prob_a)\n",
+        "                prob_b1_list.append(prob_b)\n",
+        "                prob_c1_list.append(prob_c)\n",
+        "                prob_d1_list.append(prob_d)\n",
+        "            elif i == 1:\n",
+        "                prob_a2_list.append(prob_a)\n",
+        "                prob_b2_list.append(prob_b)\n",
+        "                prob_c2_list.append(prob_c)\n",
+        "                prob_d2_list.append(prob_d)\n",
+        "            elif i == 2:\n",
+        "                prob_a3_list.append(prob_a)\n",
+        "                prob_b3_list.append(prob_b)\n",
+        "                prob_c3_list.append(prob_c)\n",
+        "                prob_d3_list.append(prob_d)\n",
+        "df['A1'] = prob_a1_list\n",
+        "df['A2'] = prob_a2_list\n",
+        "df['A3'] = prob_a3_list\n",
+        "df['B1'] = prob_b1_list\n",
+        "df['B2'] = prob_b2_list\n",
+        "df['B3'] = prob_b3_list\n",
+        "df['C1'] = prob_c1_list\n",
+        "df['C2'] = prob_c2_list\n",
+        "df['C3'] = prob_c3_list\n",
+        "df['D1'] = prob_d1_list\n",
+        "df['D2'] = prob_d2_list\n",
+        "df['D3'] = prob_d3_list\n",
+        "df['A'] = df['A1'] + df['A2'] + df['A3']\n",
+        "df['B'] = df['B1'] + df['B2'] + df['B3']\n",
+        "df['C'] = df['C1'] + df['C2'] + df['C3']\n",
+        "df['D'] = df['D1'] + df['D2'] + df['D3']\n",
+        "df['ANS'] = df[['A', 'B', 'C', 'D']].idxmax(axis=1)\n",
+        "print(df['ANS'].value_counts())\n",
+        "accuracy_arc_c_eng = (df['Output'] == df['ANS']).mean()\n",
+        "print(f\"Accuracy: {accuracy_arc_c_eng:.4f}\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "#**ARC CHALLENGE HINDI**"
+      ],
+      "metadata": {
+        "id": "PubN4p-32_EC"
+      },
+      "id": "PubN4p-32_EC"
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "dataset = load_dataset(\"1-800-LLMs/Test-Collection\", data_files=\"ARC_Challenge_H.csv\", split=\"train\")\n",
+        "df = dataset.to_pandas()\n",
+        "print(len(df))\n",
+        "df['tok'] = df['Input'].apply(lambda x: len(tokenizer.encode(x)))\n",
+        "print(f\"Average 'tok' value: {df['tok'].mean()}\")\n",
+        "print(f\"Max 'tok' value: {df['tok'].max()}\")\n",
+        "df = df.sort_values('tok', ascending=False)\n",
+        "df['Output'] = df['Output'].replace({'1': 'A', '2': 'B', '3': 'C', '4': 'D'})\n",
+        "print(df['Output'].value_counts())\n",
+        "responses = []\n",
+        "prob_a1_list = []\n",
+        "prob_a2_list = []\n",
+        "prob_a3_list = []\n",
+        "prob_b1_list = []\n",
+        "prob_b2_list = []\n",
+        "prob_b3_list = []\n",
+        "prob_c1_list = []\n",
+        "prob_c2_list = []\n",
+        "prob_c3_list = []\n",
+        "prob_d1_list = []\n",
+        "prob_d2_list = []\n",
+        "prob_d3_list = []\n",
+        "batch_size = 1\n",
+        "for start in tqdm(range(0, len(df), batch_size)):\n",
+        "    batch_texts = df['Input'][start:start+batch_size].tolist()\n",
+        "    for input_text in batch_texts:\n",
+        "        prompt = f\"### INPUT : {input_text} Respond with just one letter based on these options : \"\n",
+        "        message = [{\"role\": \"user\", \"content\": prompt}]\n",
+        "        inputs = tokenizer.apply_chat_template(message, tokenize=True, add_generation_prompt=True, return_tensors=\"pt\").to(\"cuda\")\n",
+        "        with torch.no_grad():\n",
+        "            outputs = model.generate(input_ids=inputs, max_new_tokens=3, use_cache=True, pad_token_id=tokenizer.eos_token_id, return_dict_in_generate=True, output_scores=True)\n",
+        "            scores = outputs.scores  # tuple of [batch_size, vocab_size] for each token\n",
+        "        token_ids_a = tokenizer.encode('A', add_special_tokens=False)[0]\n",
+        "        token_ids_b = tokenizer.encode('B', add_special_tokens=False)[0]\n",
+        "        token_ids_c = tokenizer.encode('C', add_special_tokens=False)[0]\n",
+        "        token_ids_d = tokenizer.encode('D', add_special_tokens=False)[0]\n",
+        "        for i in range(3):\n",
+        "            if i < len(scores):\n",
+        "                probs = F.softmax(scores[i], dim=-1)\n",
+        "                prob_a = probs[0, token_ids_a].item()\n",
+        "                prob_b = probs[0, token_ids_b].item()\n",
+        "                prob_c = probs[0, token_ids_c].item()\n",
+        "                prob_d = probs[0, token_ids_d].item()\n",
+        "            else:\n",
+        "                prob_a, prob_b, prob_c, prob_d = 0.0, 0.0, 0.0, 0.0\n",
+        "            if i == 0:\n",
+        "                prob_a1_list.append(prob_a)\n",
+        "                prob_b1_list.append(prob_b)\n",
+        "                prob_c1_list.append(prob_c)\n",
+        "                prob_d1_list.append(prob_d)\n",
+        "            elif i == 1:\n",
+        "                prob_a2_list.append(prob_a)\n",
+        "                prob_b2_list.append(prob_b)\n",
+        "                prob_c2_list.append(prob_c)\n",
+        "                prob_d2_list.append(prob_d)\n",
+        "            elif i == 2:\n",
+        "                prob_a3_list.append(prob_a)\n",
+        "                prob_b3_list.append(prob_b)\n",
+        "                prob_c3_list.append(prob_c)\n",
+        "                prob_d3_list.append(prob_d)\n",
+        "df['A1'] = prob_a1_list\n",
+        "df['A2'] = prob_a2_list\n",
+        "df['A3'] = prob_a3_list\n",
+        "df['B1'] = prob_b1_list\n",
+        "df['B2'] = prob_b2_list\n",
+        "df['B3'] = prob_b3_list\n",
+        "df['C1'] = prob_c1_list\n",
+        "df['C2'] = prob_c2_list\n",
+        "df['C3'] = prob_c3_list\n",
+        "df['D1'] = prob_d1_list\n",
+        "df['D2'] = prob_d2_list\n",
+        "df['D3'] = prob_d3_list\n",
+        "df['A'] = df['A1'] + df['A2'] + df['A3']\n",
+        "df['B'] = df['B1'] + df['B2'] + df['B3']\n",
+        "df['C'] = df['C1'] + df['C2'] + df['C3']\n",
+        "df['D'] = df['D1'] + df['D2'] + df['D3']\n",
+        "df['ANS'] = df[['A', 'B', 'C', 'D']].idxmax(axis=1)\n",
+        "print(df['ANS'].value_counts())\n",
+        "accuracy_arc_c_hin = (df['Output'] == df['ANS']).mean()\n",
+        "print(f\"Accuracy: {accuracy_arc_c_hin:.4f}\")"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "mPFAiosJ3jzD",
+        "outputId": "ab6d89bf-cb17-4b8d-881a-3dc9434d0351"
+      },
+      "id": "mPFAiosJ3jzD",
+      "execution_count": 7,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "1172\n",
+            "Average 'tok' value: 151.18088737201364\n",
+            "Max 'tok' value: 504\n",
+            "Output\n",
+            "B    311\n",
+            "C    310\n",
+            "D    285\n",
+            "A    266\n",
+            "Name: count, dtype: int64\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "100%|██████████| 1172/1172 [02:40<00:00,  7.28it/s]"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "ANS\n",
+            "C    489\n",
+            "B    422\n",
+            "A    165\n",
+            "D     96\n",
+            "Name: count, dtype: int64\n",
+            "Accuracy: 0.4198\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "#**ARC EASY ENGLISH**"
+      ],
+      "metadata": {
+        "id": "cT9I3npw43AP"
+      },
+      "id": "cT9I3npw43AP"
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "dataset = load_dataset(\"1-800-LLMs/Test-Collection\", data_files=\"ARC_Easy_E.csv\", split=\"train\")\n",
+        "df = dataset.to_pandas()\n",
+        "print(len(df))\n",
+        "df['tok'] = df['Input'].apply(lambda x: len(tokenizer.encode(x)))\n",
+        "print(f\"Average 'tok' value: {df['tok'].mean()}\")\n",
+        "print(f\"Max 'tok' value: {df['tok'].max()}\")\n",
+        "df = df.sort_values('tok', ascending=False)\n",
+        "df['Output'] = df['Output'].replace({'1': 'A', '2': 'B', '3': 'C', '4': 'D'})\n",
+        "print(df['Output'].value_counts())\n",
+        "responses = []\n",
+        "prob_a1_list = []\n",
+        "prob_a2_list = []\n",
+        "prob_a3_list = []\n",
+        "prob_b1_list = []\n",
+        "prob_b2_list = []\n",
+        "prob_b3_list = []\n",
+        "prob_c1_list = []\n",
+        "prob_c2_list = []\n",
+        "prob_c3_list = []\n",
+        "prob_d1_list = []\n",
+        "prob_d2_list = []\n",
+        "prob_d3_list = []\n",
+        "batch_size = 1\n",
+        "for start in tqdm(range(0, len(df), batch_size)):\n",
+        "    batch_texts = df['Input'][start:start+batch_size].tolist()\n",
+        "    for input_text in batch_texts:\n",
+        "        prompt = f\"### INPUT : {input_text} Respond with just one letter based on these options : \"\n",
+        "        message = [{\"role\": \"user\", \"content\": prompt}]\n",
+        "        inputs = tokenizer.apply_chat_template(message, tokenize=True, add_generation_prompt=True, return_tensors=\"pt\").to(\"cuda\")\n",
+        "        with torch.no_grad():\n",
+        "            outputs = model.generate(input_ids=inputs, max_new_tokens=3, use_cache=True, pad_token_id=tokenizer.eos_token_id, return_dict_in_generate=True, output_scores=True)\n",
+        "            scores = outputs.scores  # tuple of [batch_size, vocab_size] for each token\n",
+        "        token_ids_a = tokenizer.encode('A', add_special_tokens=False)[0]\n",
+        "        token_ids_b = tokenizer.encode('B', add_special_tokens=False)[0]\n",
+        "        token_ids_c = tokenizer.encode('C', add_special_tokens=False)[0]\n",
+        "        token_ids_d = tokenizer.encode('D', add_special_tokens=False)[0]\n",
+        "        for i in range(3):\n",
+        "            if i < len(scores):\n",
+        "                probs = F.softmax(scores[i], dim=-1)\n",
+        "                prob_a = probs[0, token_ids_a].item()\n",
+        "                prob_b = probs[0, token_ids_b].item()\n",
+        "                prob_c = probs[0, token_ids_c].item()\n",
+        "                prob_d = probs[0, token_ids_d].item()\n",
+        "            else:\n",
+        "                prob_a, prob_b, prob_c, prob_d = 0.0, 0.0, 0.0, 0.0\n",
+        "            if i == 0:\n",
+        "                prob_a1_list.append(prob_a)\n",
+        "                prob_b1_list.append(prob_b)\n",
+        "                prob_c1_list.append(prob_c)\n",
+        "                prob_d1_list.append(prob_d)\n",
+        "            elif i == 1:\n",
+        "                prob_a2_list.append(prob_a)\n",
+        "                prob_b2_list.append(prob_b)\n",
+        "                prob_c2_list.append(prob_c)\n",
+        "                prob_d2_list.append(prob_d)\n",
+        "            elif i == 2:\n",
+        "                prob_a3_list.append(prob_a)\n",
+        "                prob_b3_list.append(prob_b)\n",
+        "                prob_c3_list.append(prob_c)\n",
+        "                prob_d3_list.append(prob_d)\n",
+        "df['A1'] = prob_a1_list\n",
+        "df['A2'] = prob_a2_list\n",
+        "df['A3'] = prob_a3_list\n",
+        "df['B1'] = prob_b1_list\n",
+        "df['B2'] = prob_b2_list\n",
+        "df['B3'] = prob_b3_list\n",
+        "df['C1'] = prob_c1_list\n",
+        "df['C2'] = prob_c2_list\n",
+        "df['C3'] = prob_c3_list\n",
+        "df['D1'] = prob_d1_list\n",
+        "df['D2'] = prob_d2_list\n",
+        "df['D3'] = prob_d3_list\n",
+        "df['A'] = df['A1'] + df['A2'] + df['A3']\n",
+        "df['B'] = df['B1'] + df['B2'] + df['B3']\n",
+        "df['C'] = df['C1'] + df['C2'] + df['C3']\n",
+        "df['D'] = df['D1'] + df['D2'] + df['D3']\n",
+        "df['ANS'] = df[['A', 'B', 'C', 'D']].idxmax(axis=1)\n",
+        "print(df['ANS'].value_counts())\n",
+        "accuracy_arc_e_eng = (df['Output'] == df['ANS']).mean()\n",
+        "print(f\"Accuracy: {accuracy_arc_e_eng:.4f}\")"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "6vmG3Z92410E",
+        "outputId": "b4c2ac63-9922-4e4b-dc3d-c4a8415daf58"
+      },
+      "id": "6vmG3Z92410E",
+      "execution_count": 8,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "2376\n",
+            "Average 'tok' value: 62.255050505050505\n",
+            "Max 'tok' value: 198\n",
+            "Output\n",
+            "C    633\n",
+            "A    596\n",
+            "B    585\n",
+            "D    561\n",
+            "E      1\n",
+            "Name: count, dtype: int64\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "100%|██████████| 2376/2376 [05:24<00:00,  7.32it/s]"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "ANS\n",
+            "B    770\n",
+            "C    689\n",
+            "A    655\n",
+            "D    262\n",
+            "Name: count, dtype: int64\n",
+            "Accuracy: 0.7572\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "#**ARC EASY HINDI**"
+      ],
+      "metadata": {
+        "id": "A5dtJYX05T5v"
+      },
+      "id": "A5dtJYX05T5v"
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "dataset = load_dataset(\"1-800-LLMs/Test-Collection\", data_files=\"ARC_Easy_H.csv\", split=\"train\")\n",
+        "df = dataset.to_pandas()\n",
+        "print(len(df))\n",
+        "df['tok'] = df['Input'].apply(lambda x: len(tokenizer.encode(x)))\n",
+        "print(f\"Average 'tok' value: {df['tok'].mean()}\")\n",
+        "print(f\"Max 'tok' value: {df['tok'].max()}\")\n",
+        "df = df.sort_values('tok', ascending=False)\n",
+        "print(df['Output'].value_counts())\n",
+        "df['Output'] = df['Output'].replace({'1': 'A', '2': 'B', '3': 'C', '4': 'D'})\n",
+        "responses = []\n",
+        "prob_a1_list = []\n",
+        "prob_a2_list = []\n",
+        "prob_a3_list = []\n",
+        "prob_b1_list = []\n",
+        "prob_b2_list = []\n",
+        "prob_b3_list = []\n",
+        "prob_c1_list = []\n",
+        "prob_c2_list = []\n",
+        "prob_c3_list = []\n",
+        "prob_d1_list = []\n",
+        "prob_d2_list = []\n",
+        "prob_d3_list = []\n",
+        "batch_size = 1\n",
+        "for start in tqdm(range(0, len(df), batch_size)):\n",
+        "    batch_texts = df['Input'][start:start+batch_size].tolist()\n",
+        "    for input_text in batch_texts:\n",
+        "        prompt = f\"### INPUT : {input_text} Respond with just one letter based on these options : \"\n",
+        "        message = [{\"role\": \"user\", \"content\": prompt}]\n",
+        "        inputs = tokenizer.apply_chat_template(message, tokenize=True, add_generation_prompt=True, return_tensors=\"pt\").to(\"cuda\")\n",
+        "        with torch.no_grad():\n",
+        "            outputs = model.generate(input_ids=inputs, max_new_tokens=3, use_cache=True, pad_token_id=tokenizer.eos_token_id, return_dict_in_generate=True, output_scores=True)\n",
+        "            scores = outputs.scores  # tuple of [batch_size, vocab_size] for each token\n",
+        "        token_ids_a = tokenizer.encode('A', add_special_tokens=False)[0]\n",
+        "        token_ids_b = tokenizer.encode('B', add_special_tokens=False)[0]\n",
+        "        token_ids_c = tokenizer.encode('C', add_special_tokens=False)[0]\n",
+        "        token_ids_d = tokenizer.encode('D', add_special_tokens=False)[0]\n",
+        "        for i in range(3):\n",
+        "            if i < len(scores):\n",
+        "                probs = F.softmax(scores[i], dim=-1)\n",
+        "                prob_a = probs[0, token_ids_a].item()\n",
+        "                prob_b = probs[0, token_ids_b].item()\n",
+        "                prob_c = probs[0, token_ids_c].item()\n",
+        "                prob_d = probs[0, token_ids_d].item()\n",
+        "            else:\n",
+        "                prob_a, prob_b, prob_c, prob_d = 0.0, 0.0, 0.0, 0.0\n",
+        "            if i == 0:\n",
+        "                prob_a1_list.append(prob_a)\n",
+        "                prob_b1_list.append(prob_b)\n",
+        "                prob_c1_list.append(prob_c)\n",
+        "                prob_d1_list.append(prob_d)\n",
+        "            elif i == 1:\n",
+        "                prob_a2_list.append(prob_a)\n",
+        "                prob_b2_list.append(prob_b)\n",
+        "                prob_c2_list.append(prob_c)\n",
+        "                prob_d2_list.append(prob_d)\n",
+        "            elif i == 2:\n",
+        "                prob_a3_list.append(prob_a)\n",
+        "                prob_b3_list.append(prob_b)\n",
+        "                prob_c3_list.append(prob_c)\n",
+        "                prob_d3_list.append(prob_d)\n",
+        "df['A1'] = prob_a1_list\n",
+        "df['A2'] = prob_a2_list\n",
+        "df['A3'] = prob_a3_list\n",
+        "df['B1'] = prob_b1_list\n",
+        "df['B2'] = prob_b2_list\n",
+        "df['B3'] = prob_b3_list\n",
+        "df['C1'] = prob_c1_list\n",
+        "df['C2'] = prob_c2_list\n",
+        "df['C3'] = prob_c3_list\n",
+        "df['D1'] = prob_d1_list\n",
+        "df['D2'] = prob_d2_list\n",
+        "df['D3'] = prob_d3_list\n",
+        "df['A'] = df['A1'] + df['A2'] + df['A3']\n",
+        "df['B'] = df['B1'] + df['B2'] + df['B3']\n",
+        "df['C'] = df['C1'] + df['C2'] + df['C3']\n",
+        "df['D'] = df['D1'] + df['D2'] + df['D3']\n",
+        "df['ANS'] = df[['A', 'B', 'C', 'D']].idxmax(axis=1)\n",
+        "print(df['ANS'].value_counts())\n",
+        "accuracy_arc_e_hin = (df['Output'] == df['ANS']).mean()\n",
+        "print(f\"Accuracy: {accuracy_arc_e_hin:.4f}\")"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "aFPK7wPX5TN7",
+        "outputId": "d2a77780-e335-4172-825c-d8f36b7bc51f"
+      },
+      "id": "aFPK7wPX5TN7",
+      "execution_count": 9,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "2376\n",
+            "Average 'tok' value: 129.7756734006734\n",
+            "Max 'tok' value: 667\n",
+            "Output\n",
+            "C    610\n",
+            "A    570\n",
+            "B    563\n",
+            "D    535\n",
+            "4     26\n",
+            "1     26\n",
+            "3     23\n",
+            "2     22\n",
+            "E      1\n",
+            "Name: count, dtype: int64\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "100%|██████████| 2376/2376 [05:26<00:00,  7.27it/s]"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "ANS\n",
+            "C    875\n",
+            "B    810\n",
+            "A    498\n",
+            "D    193\n",
+            "Name: count, dtype: int64\n",
+            "Accuracy: 0.5547\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "#**MMLU ENGLISH**"
+      ],
+      "metadata": {
+        "id": "pFRbbDbE4Qui"
+      },
+      "id": "pFRbbDbE4Qui"
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "dataset = load_dataset(\"1-800-LLMs/Test-Collection\", data_files=\"MMMLU_E.csv\", split=\"train\")\n",
+        "df = dataset.to_pandas()\n",
+        "print(len(df))\n",
+        "df['tok'] = df['Input'].apply(lambda x: len(tokenizer.encode(x)))\n",
+        "print(f\"Average 'tok' value: {df['tok'].mean()}\")\n",
+        "print(f\"Max 'tok' value: {df['tok'].max()}\")\n",
+        "df = df.sort_values('tok', ascending=False)\n",
+        "print(df['Output'].value_counts())\n",
+        "responses = []\n",
+        "prob_a1_list = []\n",
+        "prob_a2_list = []\n",
+        "prob_a3_list = []\n",
+        "prob_b1_list = []\n",
+        "prob_b2_list = []\n",
+        "prob_b3_list = []\n",
+        "prob_c1_list = []\n",
+        "prob_c2_list = []\n",
+        "prob_c3_list = []\n",
+        "prob_d1_list = []\n",
+        "prob_d2_list = []\n",
+        "prob_d3_list = []\n",
+        "batch_size = 1\n",
+        "for start in tqdm(range(0, len(df), batch_size)):\n",
+        "    batch_texts = df['Input'][start:start+batch_size].tolist()\n",
+        "    for input_text in batch_texts:\n",
+        "        prompt = f\"### INPUT : {input_text} Respond with just one letter based on these options : \"\n",
+        "        message = [{\"role\": \"user\", \"content\": prompt}]\n",
+        "        inputs = tokenizer.apply_chat_template(message, tokenize=True, add_generation_prompt=True, return_tensors=\"pt\").to(\"cuda\")\n",
+        "        with torch.no_grad():\n",
+        "            outputs = model.generate(input_ids=inputs, max_new_tokens=3, use_cache=True, pad_token_id=tokenizer.eos_token_id, return_dict_in_generate=True, output_scores=True)\n",
+        "            scores = outputs.scores  # tuple of [batch_size, vocab_size] for each token\n",
+        "        token_ids_a = tokenizer.encode('A', add_special_tokens=False)[0]\n",
+        "        token_ids_b = tokenizer.encode('B', add_special_tokens=False)[0]\n",
+        "        token_ids_c = tokenizer.encode('C', add_special_tokens=False)[0]\n",
+        "        token_ids_d = tokenizer.encode('D', add_special_tokens=False)[0]\n",
+        "        for i in range(3):\n",
+        "            if i < len(scores):\n",
+        "                probs = F.softmax(scores[i], dim=-1)\n",
+        "                prob_a = probs[0, token_ids_a].item()\n",
+        "                prob_b = probs[0, token_ids_b].item()\n",
+        "                prob_c = probs[0, token_ids_c].item()\n",
+        "                prob_d = probs[0, token_ids_d].item()\n",
+        "            else:\n",
+        "                prob_a, prob_b, prob_c, prob_d = 0.0, 0.0, 0.0, 0.0\n",
+        "            if i == 0:\n",
+        "                prob_a1_list.append(prob_a)\n",
+        "                prob_b1_list.append(prob_b)\n",
+        "                prob_c1_list.append(prob_c)\n",
+        "                prob_d1_list.append(prob_d)\n",
+        "            elif i == 1:\n",
+        "                prob_a2_list.append(prob_a)\n",
+        "                prob_b2_list.append(prob_b)\n",
+        "                prob_c2_list.append(prob_c)\n",
+        "                prob_d2_list.append(prob_d)\n",
+        "            elif i == 2:\n",
+        "                prob_a3_list.append(prob_a)\n",
+        "                prob_b3_list.append(prob_b)\n",
+        "                prob_c3_list.append(prob_c)\n",
+        "                prob_d3_list.append(prob_d)\n",
+        "df['A1'] = prob_a1_list\n",
+        "df['A2'] = prob_a2_list\n",
+        "df['A3'] = prob_a3_list\n",
+        "df['B1'] = prob_b1_list\n",
+        "df['B2'] = prob_b2_list\n",
+        "df['B3'] = prob_b3_list\n",
+        "df['C1'] = prob_c1_list\n",
+        "df['C2'] = prob_c2_list\n",
+        "df['C3'] = prob_c3_list\n",
+        "df['D1'] = prob_d1_list\n",
+        "df['D2'] = prob_d2_list\n",
+        "df['D3'] = prob_d3_list\n",
+        "df['A'] = df['A1'] + df['A2'] + df['A3']\n",
+        "df['B'] = df['B1'] + df['B2'] + df['B3']\n",
+        "df['C'] = df['C1'] + df['C2'] + df['C3']\n",
+        "df['D'] = df['D1'] + df['D2'] + df['D3']\n",
+        "df['ANS'] = df[['A', 'B', 'C', 'D']].idxmax(axis=1)\n",
+        "print(df['ANS'].value_counts())\n",
+        "accuracy_mmmlu_eng = (df['Output'] == df['ANS']).mean()\n",
+        "print(f\"Accuracy: {accuracy_mmmlu_eng:.4f}\")"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "FtThThQC8hs2",
+        "outputId": "e7de23c1-e287-4ea9-b3b4-2c7bac425038"
+      },
+      "id": "FtThThQC8hs2",
+      "execution_count": 10,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "14042\n",
+            "Average 'tok' value: 106.94089161088164\n",
+            "Max 'tok' value: 975\n",
+            "Output\n",
+            "D    3776\n",
+            "C    3582\n",
+            "B    3462\n",
+            "A    3222\n",
+            "Name: count, dtype: int64\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "100%|██████████| 14042/14042 [32:06<00:00,  7.29it/s]"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "ANS\n",
+            "A    4702\n",
+            "B    4269\n",
+            "C    3079\n",
+            "D    1992\n",
+            "Name: count, dtype: int64\n",
+            "Accuracy: 0.5161\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "#**MMMLU HINDI**"
+      ],
+      "metadata": {
+        "id": "FeK3WGqS85al"
+      },
+      "id": "FeK3WGqS85al"
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "dataset = load_dataset(\"1-800-LLMs/Test-Collection\", data_files=\"MMMLU_H.csv\", split=\"train\")\n",
+        "df = dataset.to_pandas()\n",
+        "print(len(df))\n",
+        "df['tok'] = df['Input'].apply(lambda x: len(tokenizer.encode(x)))\n",
+        "print(f\"Average 'tok' value: {df['tok'].mean()}\")\n",
+        "print(f\"Max 'tok' value: {df['tok'].max()}\")\n",
+        "df = df.sort_values('tok', ascending=False)\n",
+        "print(df['Output'].value_counts())\n",
+        "responses = []\n",
+        "prob_a1_list = []\n",
+        "prob_a2_list = []\n",
+        "prob_a3_list = []\n",
+        "prob_b1_list = []\n",
+        "prob_b2_list = []\n",
+        "prob_b3_list = []\n",
+        "prob_c1_list = []\n",
+        "prob_c2_list = []\n",
+        "prob_c3_list = []\n",
+        "prob_d1_list = []\n",
+        "prob_d2_list = []\n",
+        "prob_d3_list = []\n",
+        "batch_size = 1\n",
+        "for start in tqdm(range(0, len(df), batch_size)):\n",
+        "    batch_texts = df['Input'][start:start+batch_size].tolist()\n",
+        "    for input_text in batch_texts:\n",
+        "        prompt = f\"### INPUT : {input_text} Respond with just one letter based on these options : \"\n",
+        "        message = [{\"role\": \"user\", \"content\": prompt}]\n",
+        "        inputs = tokenizer.apply_chat_template(message, tokenize=True, add_generation_prompt=True, return_tensors=\"pt\").to(\"cuda\")\n",
+        "        with torch.no_grad():\n",
+        "            outputs = model.generate(input_ids=inputs, max_new_tokens=3, use_cache=True, pad_token_id=tokenizer.eos_token_id, return_dict_in_generate=True, output_scores=True)\n",
+        "            scores = outputs.scores  # tuple of [batch_size, vocab_size] for each token\n",
+        "        token_ids_a = tokenizer.encode('A', add_special_tokens=False)[0]\n",
+        "        token_ids_b = tokenizer.encode('B', add_special_tokens=False)[0]\n",
+        "        token_ids_c = tokenizer.encode('C', add_special_tokens=False)[0]\n",
+        "        token_ids_d = tokenizer.encode('D', add_special_tokens=False)[0]\n",
+        "        for i in range(3):\n",
+        "            if i < len(scores):\n",
+        "                probs = F.softmax(scores[i], dim=-1)\n",
+        "                prob_a = probs[0, token_ids_a].item()\n",
+        "                prob_b = probs[0, token_ids_b].item()\n",
+        "                prob_c = probs[0, token_ids_c].item()\n",
+        "                prob_d = probs[0, token_ids_d].item()\n",
+        "            else:\n",
+        "                prob_a, prob_b, prob_c, prob_d = 0.0, 0.0, 0.0, 0.0\n",
+        "            if i == 0:\n",
+        "                prob_a1_list.append(prob_a)\n",
+        "                prob_b1_list.append(prob_b)\n",
+        "                prob_c1_list.append(prob_c)\n",
+        "                prob_d1_list.append(prob_d)\n",
+        "            elif i == 1:\n",
+        "                prob_a2_list.append(prob_a)\n",
+        "                prob_b2_list.append(prob_b)\n",
+        "                prob_c2_list.append(prob_c)\n",
+        "                prob_d2_list.append(prob_d)\n",
+        "            elif i == 2:\n",
+        "                prob_a3_list.append(prob_a)\n",
+        "                prob_b3_list.append(prob_b)\n",
+        "                prob_c3_list.append(prob_c)\n",
+        "                prob_d3_list.append(prob_d)\n",
+        "df['A1'] = prob_a1_list\n",
+        "df['A2'] = prob_a2_list\n",
+        "df['A3'] = prob_a3_list\n",
+        "df['B1'] = prob_b1_list\n",
+        "df['B2'] = prob_b2_list\n",
+        "df['B3'] = prob_b3_list\n",
+        "df['C1'] = prob_c1_list\n",
+        "df['C2'] = prob_c2_list\n",
+        "df['C3'] = prob_c3_list\n",
+        "df['D1'] = prob_d1_list\n",
+        "df['D2'] = prob_d2_list\n",
+        "df['D3'] = prob_d3_list\n",
+        "df['A'] = df['A1'] + df['A2'] + df['A3']\n",
+        "df['B'] = df['B1'] + df['B2'] + df['B3']\n",
+        "df['C'] = df['C1'] + df['C2'] + df['C3']\n",
+        "df['D'] = df['D1'] + df['D2'] + df['D3']\n",
+        "df['ANS'] = df[['A', 'B', 'C', 'D']].idxmax(axis=1)\n",
+        "print(df['ANS'].value_counts())\n",
+        "accuracy_mmmlu_hin = (df['Output'] == df['ANS']).mean()\n",
+        "print(f\"Accuracy: {accuracy_mmmlu_hin:.4f}\")"
+      ],
+      "metadata": {
+        "id": "wDxU0TXK85G7",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "1d59c032-54a3-4fde-e343-eb4b0ee510ac"
+      },
+      "id": "wDxU0TXK85G7",
+      "execution_count": 11,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "14042\n",
+            "Average 'tok' value: 243.72283150548355\n",
+            "Max 'tok' value: 2679\n",
+            "Output\n",
+            "D    3776\n",
+            "C    3582\n",
+            "B    3462\n",
+            "A    3222\n",
+            "Name: count, dtype: int64\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "100%|██████████| 14042/14042 [31:53<00:00,  7.34it/s]"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "ANS\n",
+            "C    5207\n",
+            "A    4402\n",
+            "B    3524\n",
+            "D     909\n",
+            "Name: count, dtype: int64\n",
+            "Accuracy: 0.3369\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "#**BOOLQ ENG**"
+      ],
+      "metadata": {
+        "id": "4aC98L-5Gi9D"
+      },
+      "id": "4aC98L-5Gi9D"
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "dataset = load_dataset(\"1-800-LLMs/Test-Collection\", data_files=\"BoolQ_E.csv\", split=\"train\")\n",
+        "df = dataset.to_pandas()\n",
+        "print(len(df))\n",
+        "df['tok'] = df['Input'].apply(lambda x: len(tokenizer.encode(x)))\n",
+        "print(f\"Average 'tok' value: {df['tok'].mean()}\")\n",
+        "print(f\"Max 'tok' value: {df['tok'].max()}\")\n",
+        "df = df.sort_values('tok', ascending=False)\n",
+        "print(df['Output'].value_counts())\n",
+        "responses = []\n",
+        "prob_a1_list = []\n",
+        "prob_a2_list = []\n",
+        "prob_a3_list = []\n",
+        "prob_b1_list = []\n",
+        "prob_b2_list = []\n",
+        "prob_b3_list = []\n",
+        "batch_size = 1\n",
+        "for start in tqdm(range(0, len(df), batch_size)):\n",
+        "    batch_texts = df['Input'][start:start+batch_size].tolist()\n",
+        "    for input_text in batch_texts:\n",
+        "        prompt = f\"### INPUT : {input_text} Respond with just one word based on these options : \"\n",
+        "        message = [{\"role\": \"user\", \"content\": prompt}]\n",
+        "        inputs = tokenizer.apply_chat_template(message, tokenize=True, add_generation_prompt=True, return_tensors=\"pt\").to(\"cuda\")\n",
+        "        with torch.no_grad():\n",
+        "            outputs = model.generate(input_ids=inputs, max_new_tokens=3, use_cache=True, pad_token_id=tokenizer.eos_token_id, return_dict_in_generate=True, output_scores=True)\n",
+        "            scores = outputs.scores  # tuple of [batch_size, vocab_size] for each token\n",
+        "        token_ids_a = tokenizer.encode('True', add_special_tokens=False)[0]\n",
+        "        token_ids_b = tokenizer.encode('False', add_special_tokens=False)[0]\n",
+        "        for i in range(3):\n",
+        "            if i < len(scores):\n",
+        "                probs = F.softmax(scores[i], dim=-1)\n",
+        "                prob_a = probs[0, token_ids_a].item()\n",
+        "                prob_b = probs[0, token_ids_b].item()\n",
+        "            else:\n",
+        "                prob_a, prob_b = 0.0, 0.0\n",
+        "            if i == 0:\n",
+        "                prob_a1_list.append(prob_a)\n",
+        "                prob_b1_list.append(prob_b)\n",
+        "            elif i == 1:\n",
+        "                prob_a2_list.append(prob_a)\n",
+        "                prob_b2_list.append(prob_b)\n",
+        "            elif i == 2:\n",
+        "                prob_a3_list.append(prob_a)\n",
+        "                prob_b3_list.append(prob_b)\n",
+        "df['A1'] = prob_a1_list\n",
+        "df['A2'] = prob_a2_list\n",
+        "df['A3'] = prob_a3_list\n",
+        "df['B1'] = prob_b1_list\n",
+        "df['B2'] = prob_b2_list\n",
+        "df['B3'] = prob_b3_list\n",
+        "df['A'] = df['A1'] + df['A2'] + df['A3']\n",
+        "df['B'] = df['B1'] + df['B2'] + df['B3']\n",
+        "df['ANS'] = df[['A', 'B']].idxmax(axis=1)\n",
+        "df['ANS'] = df['ANS'].replace({'A': 'True', 'B': 'False'})\n",
+        "df['ANS'] = df['ANS'].astype(str)\n",
+        "df['Output'] = df['Output'].astype(str)\n",
+        "print(df['ANS'].value_counts())\n",
+        "accuracy_boolq_eng = (df['Output'] == df['ANS']).mean()\n",
+        "print(f\"Accuracy: {accuracy_boolq_eng:.4f}\")"
+      ],
+      "metadata": {
+        "id": "m7ayEga9Ghkd",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "4bedc9b8-1cfa-4737-82d5-172d8418a5fd"
+      },
+      "id": "m7ayEga9Ghkd",
+      "execution_count": 12,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "3270\n",
+            "Average 'tok' value: 137.02354740061162\n",
+            "Max 'tok' value: 1157\n",
+            "Output\n",
+            "True     2033\n",
+            "False    1237\n",
+            "Name: count, dtype: int64\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "100%|██████████| 3270/3270 [07:26<00:00,  7.32it/s]"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "ANS\n",
+            "True     2897\n",
+            "False     373\n",
+            "Name: count, dtype: int64\n",
+            "Accuracy: 0.6544\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "#**BOOLQ HINDI**"
+      ],
+      "metadata": {
+        "id": "uAhhi93PHZ40"
+      },
+      "id": "uAhhi93PHZ40"
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "dataset = load_dataset(\"1-800-LLMs/Test-Collection\", data_files=\"BoolQ_H.csv\", split=\"train\")\n",
+        "df = dataset.to_pandas()\n",
+        "print(len(df))\n",
+        "df['tok'] = df['Input'].apply(lambda x: len(tokenizer.encode(x)))\n",
+        "print(f\"Average 'tok' value: {df['tok'].mean()}\")\n",
+        "print(f\"Max 'tok' value: {df['tok'].max()}\")\n",
+        "df = df.sort_values('tok', ascending=False)\n",
+        "print(df['Output'].value_counts())\n",
+        "df = df[1:]\n",
+        "responses = []\n",
+        "prob_a1_list = []\n",
+        "prob_a2_list = []\n",
+        "prob_a3_list = []\n",
+        "prob_b1_list = []\n",
+        "prob_b2_list = []\n",
+        "prob_b3_list = []\n",
+        "batch_size = 1\n",
+        "for start in tqdm(range(0, len(df), batch_size)):\n",
+        "    batch_texts = df['Input'][start:start+batch_size].tolist()\n",
+        "    for input_text in batch_texts:\n",
+        "        prompt = f\"### INPUT : {input_text} Respond with just one word based on these options : \"\n",
+        "        message = [{\"role\": \"user\", \"content\": prompt}]\n",
+        "        inputs = tokenizer.apply_chat_template(message, tokenize=True, add_generation_prompt=True, return_tensors=\"pt\").to(\"cuda\")\n",
+        "        with torch.no_grad():\n",
+        "            outputs = model.generate(input_ids=inputs, max_new_tokens=3, use_cache=True, pad_token_id=tokenizer.eos_token_id, return_dict_in_generate=True, output_scores=True)\n",
+        "            scores = outputs.scores  # tuple of [batch_size, vocab_size] for each token\n",
+        "        token_ids_a = tokenizer.encode('True', add_special_tokens=False)[0]\n",
+        "        token_ids_b = tokenizer.encode('False', add_special_tokens=False)[0]\n",
+        "        for i in range(3):\n",
+        "            if i < len(scores):\n",
+        "                probs = F.softmax(scores[i], dim=-1)\n",
+        "                prob_a = probs[0, token_ids_a].item()\n",
+        "                prob_b = probs[0, token_ids_b].item()\n",
+        "            else:\n",
+        "                prob_a, prob_b = 0.0, 0.0\n",
+        "            if i == 0:\n",
+        "                prob_a1_list.append(prob_a)\n",
+        "                prob_b1_list.append(prob_b)\n",
+        "            elif i == 1:\n",
+        "                prob_a2_list.append(prob_a)\n",
+        "                prob_b2_list.append(prob_b)\n",
+        "            elif i == 2:\n",
+        "                prob_a3_list.append(prob_a)\n",
+        "                prob_b3_list.append(prob_b)\n",
+        "df['A1'] = prob_a1_list\n",
+        "df['A2'] = prob_a2_list\n",
+        "df['A3'] = prob_a3_list\n",
+        "df['B1'] = prob_b1_list\n",
+        "df['B2'] = prob_b2_list\n",
+        "df['B3'] = prob_b3_list\n",
+        "df['A'] = df['A1'] + df['A2'] + df['A3']\n",
+        "df['B'] = df['B1'] + df['B2'] + df['B3']\n",
+        "df['ANS'] = df[['A', 'B']].idxmax(axis=1)\n",
+        "df['ANS'] = df['ANS'].replace({'A': 'True', 'B': 'False'})\n",
+        "df['ANS'] = df['ANS'].astype(str)\n",
+        "df['Output'] = df['Output'].astype(str)\n",
+        "print(df['ANS'].value_counts())\n",
+        "accuracy_boolq_hin = (df['Output'] == df['ANS']).mean()\n",
+        "print(f\"Accuracy: {accuracy_boolq_hin:.4f}\")"
+      ],
+      "metadata": {
+        "id": "GOHy6uE285AB",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "9243f6ea-d932-4d97-cd20-7b0125f143f3"
+      },
+      "id": "GOHy6uE285AB",
+      "execution_count": 13,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "3270\n",
+            "Average 'tok' value: 330.30366972477066\n",
+            "Max 'tok' value: 29515\n",
+            "Output\n",
+            "True     2033\n",
+            "False    1237\n",
+            "Name: count, dtype: int64\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "100%|██████████| 3269/3269 [08:16<00:00,  6.59it/s]"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "ANS\n",
+            "True     3139\n",
+            "False     130\n",
+            "Name: count, dtype: int64\n",
+            "Accuracy: 0.6271\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "#**Context MCQ ENGLISH**"
+      ],
+      "metadata": {
+        "id": "1ugA-oyeReI9"
+      },
+      "id": "1ugA-oyeReI9"
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "dataset = load_dataset(\"1-800-LLMs/Test-Collection\", data_files=\"ContextMCQ_E.csv\", split=\"train\")\n",
+        "df = dataset.to_pandas()\n",
+        "print(len(df))\n",
+        "print(df['Output'].value_counts())\n",
+        "responses = []\n",
+        "prob_a1_list = []\n",
+        "prob_a2_list = []\n",
+        "prob_a3_list = []\n",
+        "prob_b1_list = []\n",
+        "prob_b2_list = []\n",
+        "prob_b3_list = []\n",
+        "prob_c1_list = []\n",
+        "prob_c2_list = []\n",
+        "prob_c3_list = []\n",
+        "prob_d1_list = []\n",
+        "prob_d2_list = []\n",
+        "prob_d3_list = []\n",
+        "batch_size = 1\n",
+        "for start in tqdm(range(0, len(df), batch_size)):\n",
+        "    batch_texts = df['Input'][start:start+batch_size].tolist()\n",
+        "    for input_text in batch_texts:\n",
+        "        prompt = f\"### INPUT : {input_text} Respond with just one letter based on these options : \"\n",
+        "        message = [{\"role\": \"user\", \"content\": prompt}]\n",
+        "        inputs = tokenizer.apply_chat_template(message, tokenize=True, add_generation_prompt=True, return_tensors=\"pt\").to(\"cuda\")\n",
+        "        with torch.no_grad():\n",
+        "            outputs = model.generate(input_ids=inputs, max_new_tokens=3, use_cache=True, pad_token_id=tokenizer.eos_token_id, return_dict_in_generate=True, output_scores=True)\n",
+        "            scores = outputs.scores  # tuple of [batch_size, vocab_size] for each token\n",
+        "        token_ids_a = tokenizer.encode('A', add_special_tokens=False)[0]\n",
+        "        token_ids_b = tokenizer.encode('B', add_special_tokens=False)[0]\n",
+        "        token_ids_c = tokenizer.encode('C', add_special_tokens=False)[0]\n",
+        "        token_ids_d = tokenizer.encode('D', add_special_tokens=False)[0]\n",
+        "        for i in range(3):\n",
+        "            if i < len(scores):\n",
+        "                probs = F.softmax(scores[i], dim=-1)\n",
+        "                prob_a = probs[0, token_ids_a].item()\n",
+        "                prob_b = probs[0, token_ids_b].item()\n",
+        "                prob_c = probs[0, token_ids_c].item()\n",
+        "                prob_d = probs[0, token_ids_d].item()\n",
+        "            else:\n",
+        "                prob_a, prob_b, prob_c, prob_d = 0.0, 0.0, 0.0, 0.0\n",
+        "            if i == 0:\n",
+        "                prob_a1_list.append(prob_a)\n",
+        "                prob_b1_list.append(prob_b)\n",
+        "                prob_c1_list.append(prob_c)\n",
+        "                prob_d1_list.append(prob_d)\n",
+        "            elif i == 1:\n",
+        "                prob_a2_list.append(prob_a)\n",
+        "                prob_b2_list.append(prob_b)\n",
+        "                prob_c2_list.append(prob_c)\n",
+        "                prob_d2_list.append(prob_d)\n",
+        "            elif i == 2:\n",
+        "                prob_a3_list.append(prob_a)\n",
+        "                prob_b3_list.append(prob_b)\n",
+        "                prob_c3_list.append(prob_c)\n",
+        "                prob_d3_list.append(prob_d)\n",
+        "df['A1'] = prob_a1_list\n",
+        "df['A2'] = prob_a2_list\n",
+        "df['A3'] = prob_a3_list\n",
+        "df['B1'] = prob_b1_list\n",
+        "df['B2'] = prob_b2_list\n",
+        "df['B3'] = prob_b3_list\n",
+        "df['C1'] = prob_c1_list\n",
+        "df['C2'] = prob_c2_list\n",
+        "df['C3'] = prob_c3_list\n",
+        "df['D1'] = prob_d1_list\n",
+        "df['D2'] = prob_d2_list\n",
+        "df['D3'] = prob_d3_list\n",
+        "df['A'] = df['A1'] + df['A2'] + df['A3']\n",
+        "df['B'] = df['B1'] + df['B2'] + df['B3']\n",
+        "df['C'] = df['C1'] + df['C2'] + df['C3']\n",
+        "df['D'] = df['D1'] + df['D2'] + df['D3']\n",
+        "df['ANS'] = df[['A', 'B', 'C', 'D']].idxmax(axis=1)\n",
+        "print(df['ANS'].value_counts())\n",
+        "accuracy_mcq_eng = (df['Output'] == df['ANS']).mean()\n",
+        "print(f\"Accuracy: {accuracy_mcq_eng:.4f}\")"
+      ],
+      "metadata": {
+        "id": "K4gKxj8ZRdYS",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "9b053b74-c689-4fd1-b5ee-30a37173effc"
+      },
+      "id": "K4gKxj8ZRdYS",
+      "execution_count": 14,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "1000\n",
+            "Output\n",
+            "C    280\n",
+            "B    244\n",
+            "D    241\n",
+            "A    235\n",
+            "Name: count, dtype: int64\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "100%|██████████| 1000/1000 [02:16<00:00,  7.31it/s]"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "ANS\n",
+            "A    309\n",
+            "C    286\n",
+            "B    266\n",
+            "D    139\n",
+            "Name: count, dtype: int64\n",
+            "Accuracy: 0.6860\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "#**Context MCQ HINDI**"
+      ],
+      "metadata": {
+        "id": "JVW_cii1SR3c"
+      },
+      "id": "JVW_cii1SR3c"
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "dataset = load_dataset(\"1-800-LLMs/Test-Collection\", data_files=\"ContextMCQ_H.csv\", split=\"train\")\n",
+        "df = dataset.to_pandas()\n",
+        "print(len(df))\n",
+        "print(df['Output'].value_counts())\n",
+        "responses = []\n",
+        "prob_a1_list = []\n",
+        "prob_a2_list = []\n",
+        "prob_a3_list = []\n",
+        "prob_b1_list = []\n",
+        "prob_b2_list = []\n",
+        "prob_b3_list = []\n",
+        "prob_c1_list = []\n",
+        "prob_c2_list = []\n",
+        "prob_c3_list = []\n",
+        "prob_d1_list = []\n",
+        "prob_d2_list = []\n",
+        "prob_d3_list = []\n",
+        "batch_size = 1\n",
+        "for start in tqdm(range(0, len(df), batch_size)):\n",
+        "    batch_texts = df['Input'][start:start+batch_size].tolist()\n",
+        "    for input_text in batch_texts:\n",
+        "        prompt = f\"### INPUT : {input_text} Respond with just one letter based on these options : \"\n",
+        "        message = [{\"role\": \"user\", \"content\": prompt}]\n",
+        "        inputs = tokenizer.apply_chat_template(message, tokenize=True, add_generation_prompt=True, return_tensors=\"pt\").to(\"cuda\")\n",
+        "        with torch.no_grad():\n",
+        "            outputs = model.generate(input_ids=inputs, max_new_tokens=3, use_cache=True, pad_token_id=tokenizer.eos_token_id, return_dict_in_generate=True, output_scores=True)\n",
+        "            scores = outputs.scores\n",
+        "        token_ids_a = tokenizer.encode('A', add_special_tokens=False)[0]\n",
+        "        token_ids_b = tokenizer.encode('B', add_special_tokens=False)[0]\n",
+        "        token_ids_c = tokenizer.encode('C', add_special_tokens=False)[0]\n",
+        "        token_ids_d = tokenizer.encode('D', add_special_tokens=False)[0]\n",
+        "        for i in range(3):\n",
+        "            if i < len(scores):\n",
+        "                probs = F.softmax(scores[i], dim=-1)\n",
+        "                prob_a = probs[0, token_ids_a].item()\n",
+        "                prob_b = probs[0, token_ids_b].item()\n",
+        "                prob_c = probs[0, token_ids_c].item()\n",
+        "                prob_d = probs[0, token_ids_d].item()\n",
+        "            else:\n",
+        "                prob_a, prob_b, prob_c, prob_d = 0.0, 0.0, 0.0, 0.0\n",
+        "            if i == 0:\n",
+        "                prob_a1_list.append(prob_a)\n",
+        "                prob_b1_list.append(prob_b)\n",
+        "                prob_c1_list.append(prob_c)\n",
+        "                prob_d1_list.append(prob_d)\n",
+        "            elif i == 1:\n",
+        "                prob_a2_list.append(prob_a)\n",
+        "                prob_b2_list.append(prob_b)\n",
+        "                prob_c2_list.append(prob_c)\n",
+        "                prob_d2_list.append(prob_d)\n",
+        "            elif i == 2:\n",
+        "                prob_a3_list.append(prob_a)\n",
+        "                prob_b3_list.append(prob_b)\n",
+        "                prob_c3_list.append(prob_c)\n",
+        "                prob_d3_list.append(prob_d)\n",
+        "df['A1'] = prob_a1_list\n",
+        "df['A2'] = prob_a2_list\n",
+        "df['A3'] = prob_a3_list\n",
+        "df['B1'] = prob_b1_list\n",
+        "df['B2'] = prob_b2_list\n",
+        "df['B3'] = prob_b3_list\n",
+        "df['C1'] = prob_c1_list\n",
+        "df['C2'] = prob_c2_list\n",
+        "df['C3'] = prob_c3_list\n",
+        "df['D1'] = prob_d1_list\n",
+        "df['D2'] = prob_d2_list\n",
+        "df['D3'] = prob_d3_list\n",
+        "df['A'] = df['A1'] + df['A2'] + df['A3']\n",
+        "df['B'] = df['B1'] + df['B2'] + df['B3']\n",
+        "df['C'] = df['C1'] + df['C2'] + df['C3']\n",
+        "df['D'] = df['D1'] + df['D2'] + df['D3']\n",
+        "df['ANS'] = df[['A', 'B', 'C', 'D']].idxmax(axis=1)\n",
+        "print(df['ANS'].value_counts())\n",
+        "accuracy_mcq_hin = (df['Output'] == df['ANS']).mean()\n",
+        "print(f\"Accuracy: {accuracy_mcq_hin:.4f}\")"
+      ],
+      "metadata": {
+        "id": "HrB5mDcf842y",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "e1b60ceb-847a-4314-979b-cc1e73463c37"
+      },
+      "id": "HrB5mDcf842y",
+      "execution_count": 15,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "1000\n",
+            "Output\n",
+            "C    280\n",
+            "B    244\n",
+            "D    241\n",
+            "A    235\n",
+            "Name: count, dtype: int64\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "100%|██████████| 1000/1000 [02:20<00:00,  7.13it/s]"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "ANS\n",
+            "C    415\n",
+            "B    279\n",
+            "A    156\n",
+            "D    150\n",
+            "Name: count, dtype: int64\n",
+            "Accuracy: 0.4910\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "#**END**"
+      ],
+      "metadata": {
+        "id": "JqYw49CH3gfX"
+      },
+      "id": "JqYw49CH3gfX"
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "print(\"BOOLQ ENGLISH : \" ,accuracy_boolq_eng)\n",
+        "print(\"BOOLQ HINDI   : \" ,accuracy_boolq_hin)\n",
+        "print(\"C-MCQ ENGLISH : \" ,accuracy_mcq_eng)\n",
+        "print(\"C-MCQ HINDI   : \" ,accuracy_mcq_hin)\n",
+        "print(\"MMMLU ENGLISH : \" ,accuracy_mmmlu_eng)\n",
+        "print(\"MMMLU HINDI   : \" ,accuracy_mmmlu_hin)\n",
+        "print(\"ARC-E ENGLISH : \" ,accuracy_arc_e_eng)\n",
+        "print(\"ARC-E HINDI   : \" ,accuracy_arc_e_hin)\n",
+        "print(\"ARC-C ENGLISH : \" ,accuracy_arc_c_eng)\n",
+        "print(\"ARC-C HINDI   : \" ,accuracy_arc_c_hin)\n",
+        "avg_hin_acc = (accuracy_boolq_hin + accuracy_mcq_hin + accuracy_mmmlu_hin + accuracy_arc_e_hin + accuracy_arc_c_hin)/5\n",
+        "avg_eng_acc = (accuracy_boolq_eng + accuracy_mcq_eng + accuracy_mmmlu_eng + accuracy_arc_e_eng + accuracy_arc_c_eng)/5\n",
+        "print(\"AVG SCORE : HINDI   : \" ,avg_hin_acc)\n",
+        "print(\"AVG SCORE : ENGLISH : \" ,avg_eng_acc)\n",
+        "avg_tot_acc = (avg_hin_acc + avg_eng_acc)/2\n",
+        "print(\"TOT AVG SCORE : \" ,avg_tot_acc)\n",
+        "print(\"CLICK CTRl+S and wait for 2 sec\")\n",
+        "name = name.split('/')[-1]\n",
+        "name = name + \".ipynb\"\n",
+        "print(\"1) NOTEBOOK NAME SHOULD BE : \", name)\n",
+        "print(\"2) ADD THE CODE TO GITHUB @ https://github.com/1-800-SHARED-TASKS/New-Language-Adaptation/tree/main/Our-Evals/ALL-EVALS/ \")\n",
+        "print(\"3) UPDATE THE GOOGLE SHEET WITH THE SCORES \")"
+      ],
+      "metadata": {
+        "id": "YI3SR_t1Vk2s",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "f76aaaa4-4efd-4eda-e26f-47348fc93c27"
+      },
+      "id": "YI3SR_t1Vk2s",
+      "execution_count": 16,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "BOOLQ ENGLISH :  0.654434250764526\n",
+            "BOOLQ HINDI   :  0.6271030896298562\n",
+            "C-MCQ ENGLISH :  0.686\n",
+            "C-MCQ HINDI   :  0.491\n",
+            "MMMLU ENGLISH :  0.5160945734225894\n",
+            "MMMLU HINDI   :  0.3369178179746475\n",
+            "ARC-E ENGLISH :  0.7571548821548821\n",
+            "ARC-E HINDI   :  0.5547138047138047\n",
+            "ARC-C ENGLISH :  0.6083617747440273\n",
+            "ARC-C HINDI   :  0.4197952218430034\n",
+            "AVG SCORE : HINDI   :  0.48590598683226227\n",
+            "AVG SCORE : ENGLISH :  0.644409096217205\n",
+            "TOT AVG SCORE :  0.5651575415247336\n",
+            "CLICK CTRl+S and wait for 2 sec\n",
+            "1) NOTEBOOK NAME SHOULD BE :  LLAMA-3B-A10.ipynb\n",
+            "2) ADD THE CODE TO GITHUB @ https://github.com/1-800-SHARED-TASKS/New-Language-Adaptation/tree/main/Our-Evals/ALL-EVALS/ \n",
+            "3) UPDATE THE GOOGLE SHEET WITH THE SCORES \n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [],
+      "metadata": {
+        "id": "ljShzEUtnaDH"
+      },
+      "id": "ljShzEUtnaDH",
+      "execution_count": 16,
+      "outputs": []
+    }
+  ],
+  "metadata": {
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.10.12"
+    },
+    "colab": {
+      "provenance": [],
+      "machine_shape": "hm",
+      "gpuType": "A100"
+    },
+    "accelerator": "GPU",
+    "widgets": {
+      "application/vnd.jupyter.widget-state+json": {
+        "b9b391ea3142453fbf4e6cefbd6ef1fc": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "VBoxModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "VBoxModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "VBoxView",
+            "box_style": "",
+            "children": [
+              "IPY_MODEL_3a7fb309595f4a2b961615a5c778171e",
+              "IPY_MODEL_2b92f64605104b99be7cf51241596fc8",
+              "IPY_MODEL_726ff8d697984455986196bf4605df3f",
+              "IPY_MODEL_9c05d7227ff8424195c9523625b6cac9",
+              "IPY_MODEL_ef89047b71f441998faaf1ac2a22d489"
+            ],
+            "layout": "IPY_MODEL_551d6f25992749cc88de42e19116dada"
+          }
+        },
+        "3a7fb309595f4a2b961615a5c778171e": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_6fce58e90a484b9482f582e043cfb291",
+            "placeholder": "​",
+            "style": "IPY_MODEL_41da26346546415ebc4a9ce731d5427c",
+            "value": "<center> <img\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.svg\nalt='Hugging Face'> <br> Copy a token from <a\nhref=\"https://huggingface.co/settings/tokens\" target=\"_blank\">your Hugging Face\ntokens page</a> and paste it below. <br> Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file. </center>"
+          }
+        },
+        "2b92f64605104b99be7cf51241596fc8": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "PasswordModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "PasswordModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "PasswordView",
+            "continuous_update": true,
+            "description": "Token:",
+            "description_tooltip": null,
+            "disabled": false,
+            "layout": "IPY_MODEL_e3fcacb0b6c94010b16873a659b64026",
+            "placeholder": "​",
+            "style": "IPY_MODEL_594921b118444b218af3fa5ed4dfe04e",
+            "value": ""
+          }
+        },
+        "726ff8d697984455986196bf4605df3f": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "CheckboxModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "CheckboxModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "CheckboxView",
+            "description": "Add token as git credential?",
+            "description_tooltip": null,
+            "disabled": false,
+            "indent": true,
+            "layout": "IPY_MODEL_fbd86d4f0c3b4cb2a732d38b5bf9b63d",
+            "style": "IPY_MODEL_c99cb68a2ecc4c62875cfbc683a8bbd5",
+            "value": true
+          }
+        },
+        "9c05d7227ff8424195c9523625b6cac9": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "ButtonModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "ButtonModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "ButtonView",
+            "button_style": "",
+            "description": "Login",
+            "disabled": false,
+            "icon": "",
+            "layout": "IPY_MODEL_ff4ef96f8719449ab188fdabaf498351",
+            "style": "IPY_MODEL_7ce58a71e9bd42bdbb7ac28048425da0",
+            "tooltip": ""
+          }
+        },
+        "ef89047b71f441998faaf1ac2a22d489": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_0a3ddabdfb4f40b3a1a27029b6bef8e5",
+            "placeholder": "​",
+            "style": "IPY_MODEL_e21da6bcc0bb496e86dee50630a1208c",
+            "value": "\n<b>Pro Tip:</b> If you don't already have one, you can create a dedicated\n'notebooks' token with 'write' access, that you can then easily reuse for all\nnotebooks. </center>"
+          }
+        },
+        "551d6f25992749cc88de42e19116dada": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": "center",
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": "flex",
+            "flex": null,
+            "flex_flow": "column",
+            "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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": "50%"
+          }
+        },
+        "6fce58e90a484b9482f582e043cfb291": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "41da26346546415ebc4a9ce731d5427c": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "e3fcacb0b6c94010b16873a659b64026": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "594921b118444b218af3fa5ed4dfe04e": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "fbd86d4f0c3b4cb2a732d38b5bf9b63d": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "c99cb68a2ecc4c62875cfbc683a8bbd5": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "ff4ef96f8719449ab188fdabaf498351": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "7ce58a71e9bd42bdbb7ac28048425da0": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "ButtonStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "ButtonStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "button_color": null,
+            "font_weight": ""
+          }
+        },
+        "0a3ddabdfb4f40b3a1a27029b6bef8e5": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "e21da6bcc0bb496e86dee50630a1208c": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "06af4d907cba475bb0d6d53005671e0f": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HBoxModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HBoxModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HBoxView",
+            "box_style": "",
+            "children": [
+              "IPY_MODEL_c5648f7fa3fa4e6a97bdf67f2275fa14",
+              "IPY_MODEL_084f9365e98c423e9ceda9f4b095d820",
+              "IPY_MODEL_4256bf31907b49adb6bdeac23f9cabf3"
+            ],
+            "layout": "IPY_MODEL_11c242383b26482484f1cdf9ff182814"
+          }
+        },
+        "c5648f7fa3fa4e6a97bdf67f2275fa14": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_9a4659b332b04a1ea2ea2a1178e53fb9",
+            "placeholder": "​",
+            "style": "IPY_MODEL_daa33e7b6b07404fb5551d6582906164",
+            "value": "Downloading shards: 100%"
+          }
+        },
+        "084f9365e98c423e9ceda9f4b095d820": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "FloatProgressModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "FloatProgressModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "ProgressView",
+            "bar_style": "success",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_6fb5a05a50ad49afa35e64e758bc9c54",
+            "max": 2,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_594fe19fc2f04c6eaec987691c515bda",
+            "value": 2
+          }
+        },
+        "4256bf31907b49adb6bdeac23f9cabf3": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_659292ec3fc14c1ea28d8ad2b7a1ee7f",
+            "placeholder": "​",
+            "style": "IPY_MODEL_9281e91ab739424ea4c13a539ff8ccbd",
+            "value": " 2/2 [01:42&lt;00:00, 48.48s/it]"
+          }
+        },
+        "11c242383b26482484f1cdf9ff182814": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "9a4659b332b04a1ea2ea2a1178e53fb9": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "daa33e7b6b07404fb5551d6582906164": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "6fb5a05a50ad49afa35e64e758bc9c54": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "594fe19fc2f04c6eaec987691c515bda": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "ProgressStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "ProgressStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "bar_color": null,
+            "description_width": ""
+          }
+        },
+        "659292ec3fc14c1ea28d8ad2b7a1ee7f": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "9281e91ab739424ea4c13a539ff8ccbd": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "99dbcf3b567047a98731ddad8ee5311d": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HBoxModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HBoxModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HBoxView",
+            "box_style": "",
+            "children": [
+              "IPY_MODEL_bf35cd8cddf0462db86cad41640c84a2",
+              "IPY_MODEL_bfb555f021694899a1888dc69d98d4d9",
+              "IPY_MODEL_dcdd65424cf646c2ab0a12366dd80f30"
+            ],
+            "layout": "IPY_MODEL_f7e326fc56e841a3a688eb7d0baa1006"
+          }
+        },
+        "bf35cd8cddf0462db86cad41640c84a2": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_a8c38373c1f04b46a6589092e074173c",
+            "placeholder": "​",
+            "style": "IPY_MODEL_0d34758fbc9d495ba2a20337d7d8d016",
+            "value": "model-00001-of-00002.safetensors: 100%"
+          }
+        },
+        "bfb555f021694899a1888dc69d98d4d9": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "FloatProgressModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "FloatProgressModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "ProgressView",
+            "bar_style": "success",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_bceb0ff3af904a4f97d5e7d5d9bb2c57",
+            "max": 4965799096,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_42d843503af946c293799fea9f8170c3",
+            "value": 4965799096
+          }
+        },
+        "dcdd65424cf646c2ab0a12366dd80f30": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_171dc3ad2d75492c8c782fa03f905659",
+            "placeholder": "​",
+            "style": "IPY_MODEL_8a370978ed384ce39d1da8047cd684b0",
+            "value": " 4.97G/4.97G [01:07&lt;00:00, 34.1MB/s]"
+          }
+        },
+        "f7e326fc56e841a3a688eb7d0baa1006": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "a8c38373c1f04b46a6589092e074173c": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "0d34758fbc9d495ba2a20337d7d8d016": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "bceb0ff3af904a4f97d5e7d5d9bb2c57": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "42d843503af946c293799fea9f8170c3": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "ProgressStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "ProgressStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "bar_color": null,
+            "description_width": ""
+          }
+        },
+        "171dc3ad2d75492c8c782fa03f905659": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "8a370978ed384ce39d1da8047cd684b0": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "e2681c452e504af9858d30218f062078": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HBoxModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HBoxModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HBoxView",
+            "box_style": "",
+            "children": [
+              "IPY_MODEL_02f1be48cf8f4c16be2e6df1f34e4169",
+              "IPY_MODEL_0726c62296484dee803598e796be023e",
+              "IPY_MODEL_30ab1c8ce4464b6b80772fd099330ce6"
+            ],
+            "layout": "IPY_MODEL_dcec0609e7654d5689920fefa6513772"
+          }
+        },
+        "02f1be48cf8f4c16be2e6df1f34e4169": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_443bb62f011a46fdab191054837f4238",
+            "placeholder": "​",
+            "style": "IPY_MODEL_c8c7b2e3543d4969b13590d0d07b2dd9",
+            "value": "model-00002-of-00002.safetensors: 100%"
+          }
+        },
+        "0726c62296484dee803598e796be023e": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "FloatProgressModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "FloatProgressModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "ProgressView",
+            "bar_style": "success",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_8f342291573f41f3ab5b89dd1870a5f0",
+            "max": 1459729952,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_faa4c5dd2b114e67a8579d5a47b7efb4",
+            "value": 1459729952
+          }
+        },
+        "30ab1c8ce4464b6b80772fd099330ce6": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_3c9b5c165a5549f3b9895d24920e55e1",
+            "placeholder": "​",
+            "style": "IPY_MODEL_3265d7be7689485fb595643786879cdf",
+            "value": " 1.46G/1.46G [00:34&lt;00:00, 43.5MB/s]"
+          }
+        },
+        "dcec0609e7654d5689920fefa6513772": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "443bb62f011a46fdab191054837f4238": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "c8c7b2e3543d4969b13590d0d07b2dd9": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "8f342291573f41f3ab5b89dd1870a5f0": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "faa4c5dd2b114e67a8579d5a47b7efb4": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "ProgressStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "ProgressStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "bar_color": null,
+            "description_width": ""
+          }
+        },
+        "3c9b5c165a5549f3b9895d24920e55e1": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "3265d7be7689485fb595643786879cdf": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "522c6479448d4e8bb4268b33d385f83e": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HBoxModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HBoxModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HBoxView",
+            "box_style": "",
+            "children": [
+              "IPY_MODEL_c8148bf4baab44d481bbead4df316b91",
+              "IPY_MODEL_7a5b13ab59d84326b71d57e401bfe713",
+              "IPY_MODEL_72d28303d29b402f8095d7d9c760df00"
+            ],
+            "layout": "IPY_MODEL_e31e65305361421c9278c071cb7cfba2"
+          }
+        },
+        "c8148bf4baab44d481bbead4df316b91": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_d118c47eb13a49c0b1a241baa63a4835",
+            "placeholder": "​",
+            "style": "IPY_MODEL_11f30495fb384117bb03d3c60a5ff6e8",
+            "value": "Loading checkpoint shards: 100%"
+          }
+        },
+        "7a5b13ab59d84326b71d57e401bfe713": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "FloatProgressModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "FloatProgressModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "ProgressView",
+            "bar_style": "success",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_c3ef607d2fb942ab8a0083d97cff52e4",
+            "max": 2,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_9cc274e1219c4f33b60a57be63e069a9",
+            "value": 2
+          }
+        },
+        "72d28303d29b402f8095d7d9c760df00": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_65db2cfdad674681b956c66c994e15bb",
+            "placeholder": "​",
+            "style": "IPY_MODEL_cc499d66cd6043129c19378af8a86931",
+            "value": " 2/2 [00:02&lt;00:00,  1.27s/it]"
+          }
+        },
+        "e31e65305361421c9278c071cb7cfba2": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "d118c47eb13a49c0b1a241baa63a4835": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "11f30495fb384117bb03d3c60a5ff6e8": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "c3ef607d2fb942ab8a0083d97cff52e4": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "9cc274e1219c4f33b60a57be63e069a9": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "ProgressStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "ProgressStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "bar_color": null,
+            "description_width": ""
+          }
+        },
+        "65db2cfdad674681b956c66c994e15bb": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "cc499d66cd6043129c19378af8a86931": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "baf343fdb1314fe693e35995833dcb00": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HBoxModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HBoxModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HBoxView",
+            "box_style": "",
+            "children": [
+              "IPY_MODEL_436072026c25407cbc33fdf7f38813b3",
+              "IPY_MODEL_8463894bc0914c8f8bbf7fb4d60c65f8",
+              "IPY_MODEL_6cc93e1749e646928d71621df8858015"
+            ],
+            "layout": "IPY_MODEL_0e51722a80e0414c99510f4c13ce5607"
+          }
+        },
+        "436072026c25407cbc33fdf7f38813b3": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_915261a80e7048dd9586a4dfe6965746",
+            "placeholder": "​",
+            "style": "IPY_MODEL_af655bb83551407e9f3444b0136721cf",
+            "value": "generation_config.json: 100%"
+          }
+        },
+        "8463894bc0914c8f8bbf7fb4d60c65f8": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "FloatProgressModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "FloatProgressModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "ProgressView",
+            "bar_style": "success",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_4c2ac70bc81949029c5ab61d8cc04824",
+            "max": 234,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_e5681521f1444e50aba3b9ddb7aa0b0a",
+            "value": 234
+          }
+        },
+        "6cc93e1749e646928d71621df8858015": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_b5c1ea4f85eb4d2c923d2605239a9c25",
+            "placeholder": "​",
+            "style": "IPY_MODEL_8cf502758aba44718b421d25c147620a",
+            "value": " 234/234 [00:00&lt;00:00, 23.7kB/s]"
+          }
+        },
+        "0e51722a80e0414c99510f4c13ce5607": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "915261a80e7048dd9586a4dfe6965746": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "af655bb83551407e9f3444b0136721cf": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "4c2ac70bc81949029c5ab61d8cc04824": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "e5681521f1444e50aba3b9ddb7aa0b0a": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "ProgressStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "ProgressStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "bar_color": null,
+            "description_width": ""
+          }
+        },
+        "b5c1ea4f85eb4d2c923d2605239a9c25": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "8cf502758aba44718b421d25c147620a": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "2180408c22cc4b88aa70d89933f6fb28": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HBoxModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HBoxModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HBoxView",
+            "box_style": "",
+            "children": [
+              "IPY_MODEL_1c15b88000614b2c9a79505645ae53be",
+              "IPY_MODEL_217c025a71914dd2bf674e36a8a6d0fd",
+              "IPY_MODEL_7fac231b948643889d57347ede0bc194"
+            ],
+            "layout": "IPY_MODEL_c41c89d84cdf4101aa9ddffc5ebd855f"
+          }
+        },
+        "1c15b88000614b2c9a79505645ae53be": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_00cd88ecc0954dd6b2f69754b7bcefb3",
+            "placeholder": "​",
+            "style": "IPY_MODEL_1d30b45c9dbf4297bf630aad5420c2da",
+            "value": "tokenizer_config.json: 100%"
+          }
+        },
+        "217c025a71914dd2bf674e36a8a6d0fd": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "FloatProgressModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "FloatProgressModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "ProgressView",
+            "bar_style": "success",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_27d2bfbae8d44c06aaba3f1625cf1501",
+            "max": 54674,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_afb13af7de5c4d1f8f41fd6fbd581048",
+            "value": 54674
+          }
+        },
+        "7fac231b948643889d57347ede0bc194": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_e20db576997a495d8467bc19245a2125",
+            "placeholder": "​",
+            "style": "IPY_MODEL_0a6fa2764d1c4e4998a036fbe306be88",
+            "value": " 54.7k/54.7k [00:00&lt;00:00, 4.44MB/s]"
+          }
+        },
+        "c41c89d84cdf4101aa9ddffc5ebd855f": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "00cd88ecc0954dd6b2f69754b7bcefb3": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "1d30b45c9dbf4297bf630aad5420c2da": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "27d2bfbae8d44c06aaba3f1625cf1501": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "afb13af7de5c4d1f8f41fd6fbd581048": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "ProgressStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "ProgressStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "bar_color": null,
+            "description_width": ""
+          }
+        },
+        "e20db576997a495d8467bc19245a2125": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "0a6fa2764d1c4e4998a036fbe306be88": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "daf4481446364fa1811c5e7c7f80bb35": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HBoxModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HBoxModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HBoxView",
+            "box_style": "",
+            "children": [
+              "IPY_MODEL_4e64572fb0514967be674bb78c0817e2",
+              "IPY_MODEL_a882747cdc18400fa1ec875e47428871",
+              "IPY_MODEL_5f9076efcfa547e78fe7302055ebe236"
+            ],
+            "layout": "IPY_MODEL_b9dfa47fefdb41d2a83bd8a1d7601b87"
+          }
+        },
+        "4e64572fb0514967be674bb78c0817e2": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_7882ba346a7c4ecabe26ee84b590214e",
+            "placeholder": "​",
+            "style": "IPY_MODEL_8c380d6a7080440eb141d42090d20ee4",
+            "value": "tokenizer.json: 100%"
+          }
+        },
+        "a882747cdc18400fa1ec875e47428871": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "FloatProgressModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "FloatProgressModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "ProgressView",
+            "bar_style": "success",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_b77abff029aa49ed865c0caec3a4ec06",
+            "max": 17209920,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_0bbd609552594bbe998bf1e17bb2b381",
+            "value": 17209920
+          }
+        },
+        "5f9076efcfa547e78fe7302055ebe236": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_dc5bb0a2b37d40b2898f183b9477ea99",
+            "placeholder": "​",
+            "style": "IPY_MODEL_97c54e559f8a4051a6955e8a107c84ef",
+            "value": " 17.2M/17.2M [00:00&lt;00:00, 43.3MB/s]"
+          }
+        },
+        "b9dfa47fefdb41d2a83bd8a1d7601b87": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "7882ba346a7c4ecabe26ee84b590214e": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "8c380d6a7080440eb141d42090d20ee4": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "b77abff029aa49ed865c0caec3a4ec06": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "0bbd609552594bbe998bf1e17bb2b381": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "ProgressStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "ProgressStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "bar_color": null,
+            "description_width": ""
+          }
+        },
+        "dc5bb0a2b37d40b2898f183b9477ea99": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "97c54e559f8a4051a6955e8a107c84ef": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "2861b7e53ab34cc284bc19a8b29c53fa": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HBoxModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HBoxModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HBoxView",
+            "box_style": "",
+            "children": [
+              "IPY_MODEL_dc2c12fae9dc4ef388678d89c966791e",
+              "IPY_MODEL_fff5ffb7d6064945b474812ea600735c",
+              "IPY_MODEL_a21f133b406b4bee91de264da24b24ad"
+            ],
+            "layout": "IPY_MODEL_aec2edc99db046daab086f9656c497be"
+          }
+        },
+        "dc2c12fae9dc4ef388678d89c966791e": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_b7b2fa33bb224ab3900a6852cf5068d5",
+            "placeholder": "​",
+            "style": "IPY_MODEL_9123f310b13741458753ecea7b95b2ff",
+            "value": "special_tokens_map.json: 100%"
+          }
+        },
+        "fff5ffb7d6064945b474812ea600735c": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "FloatProgressModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "FloatProgressModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "ProgressView",
+            "bar_style": "success",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_ecab267628b14759b343295657c0843e",
+            "max": 454,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_ddd8172014af4d5db7815c3302813c79",
+            "value": 454
+          }
+        },
+        "a21f133b406b4bee91de264da24b24ad": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_c75b1a426d6348c8b426201b5b66b94d",
+            "placeholder": "​",
+            "style": "IPY_MODEL_f2bcfac07568438cb78bb4adc5f045b6",
+            "value": " 454/454 [00:00&lt;00:00, 43.8kB/s]"
+          }
+        },
+        "aec2edc99db046daab086f9656c497be": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "b7b2fa33bb224ab3900a6852cf5068d5": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "9123f310b13741458753ecea7b95b2ff": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "ecab267628b14759b343295657c0843e": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "ddd8172014af4d5db7815c3302813c79": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "ProgressStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "ProgressStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "bar_color": null,
+            "description_width": ""
+          }
+        },
+        "c75b1a426d6348c8b426201b5b66b94d": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": 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,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "f2bcfac07568438cb78bb4adc5f045b6": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        }
+      }
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 5
+}
\ No newline at end of file