diff --git "a/GEMMA_9B_B60_all_evals.ipynb" "b/GEMMA_9B_B60_all_evals.ipynb"
new file mode 100644--- /dev/null
+++ "b/GEMMA_9B_B60_all_evals.ipynb"
@@ -0,0 +1,6859 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "0c24ca36-1782-4ce8-8094-6f6528dada19",
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 331,
+ "referenced_widgets": [
+ "3bdcbf053400426889ce191e8e631c34",
+ "c436a45ebb964940a65f31c4c032e59a",
+ "64b42b59dbdf419a811678e0343fa14f",
+ "61f0d8a908d8467a833a01645bf4df93",
+ "b3c7f82cdfe941ddb8a322b519f4f8d7",
+ "30a0c3ad3d1643d2988ed6cb1e607f3c",
+ "636b613ccc794d388f3b4859e058a39c",
+ "193ba6195d6240a2be0ab007d617d7d5",
+ "20d9a5b63fb1497aaab412e7165ed55b",
+ "3abc169a4a6546c7b728cea12c6d566e",
+ "09326715e33945359d64e8c981857eea",
+ "4d20a4b6057a44238f382c015649842b",
+ "89aa4177a076483fa584d032251b55ff",
+ "bcfc20a2d38642ce97393c9d2ec2afbd",
+ "bf696b1bb83f4268a60ebe493f8c820f",
+ "5c44c227ee9449ffb035012568fb68b3",
+ "1fcf6c9e4ab34f2985a35fe4693253cc"
+ ]
+ },
+ "id": "0c24ca36-1782-4ce8-8094-6f6528dada19",
+ "outputId": "aa64f424-eeb1-4436-9613-30a61e7d8a16"
+ },
+ "outputs": [
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "3bdcbf053400426889ce191e8e631c34",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(HTML(value='
=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) (25.1.0)\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-qusvkvpa\n",
+ " Running command git clone --filter=blob:none --quiet https://github.com/unslothai/unsloth.git /tmp/pip-req-build-qusvkvpa\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=a4d066cafb63394d66b3d00fb3d64317b9792855fcc85dea5ca314da4fab7f71\n",
+ " Stored in directory: /tmp/pip-ephem-wheel-cache-r6tvmroq/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": null,
+ "id": "fbc9900d-28d2-4bda-9848-b572fbe778d2",
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 1000,
+ "referenced_widgets": [
+ "b0eaa4eebd7647f19f0509e54d1771f5",
+ "ab6a8171c33345489e0f57c4dbf5fe37",
+ "c1b153e792684badad9088b8d23f0f9f",
+ "e2f0f3c9d0f446ce84bc30f562e63aac",
+ "9bd89ecc06214af3a1018701fa3e8758",
+ "d35ba0d1406c48f2862b8989c1c3a2a2",
+ "def55d121c2341b789e777d3ee41a65d",
+ "3cd55085208f4f09b9442d9cc6635935",
+ "1cdec6fd6ccf415888a1cd7275d07e00",
+ "c43792fa6b9b4d51ac11ead6f6f67f47",
+ "c24e7b9712674fb98668c66ec43ca7e6",
+ "3675c39892444fbe8ca27891c90e42ac",
+ "9fb90b385a2b42f6ac973a8bcc20f821",
+ "d59ad8a75d4042db83af02cef430d6ad",
+ "a2b77cdbf6c84540a2d7a30029e8f9f6",
+ "ffea5b009edb4ee7952a37a849faeefa",
+ "e74b100a0c7b428eacf57c06c687ffb2",
+ "3d47320324f74a01825c44dd749ae993",
+ "a4569bde680b4bbdb64b48dd670bfe31",
+ "36aa16e981fb4eb39f10a959940fd232",
+ "c107c6048cd74618bd2644ebdb83bd75",
+ "0e15b63d078247018a18c609af24f26f",
+ "7da997d0770a449fbe8fee7366eb359c",
+ "4936e9872dea435392d95ba1bfb57912",
+ "153279dc656a41bdbb122a4854ee57e0",
+ "1f799b16a76141af80fccc6b88826dea",
+ "7e62258760b044648c0fa12e9e7ed272",
+ "6321877814914b22839afad94092bf59",
+ "ce1582723c79433f8b81668e996bbb78",
+ "cb0fbe81482844b69a96edf5b060819d",
+ "a195da274627424aaaada4cbdc14c746",
+ "1468258495d04649b30cbeb84b9a4ffb",
+ "22f6372c8dc147c58c615ae54ebdda89",
+ "9d7f7e2ef49f443398528e0d38d017a4",
+ "cdf5c75fa4374715b184f5df2ae13f79",
+ "a6f8346aa094436082345670a526e60a",
+ "ab950c5224374ea98f1eb2b55449ac83",
+ "4827149734034b16b96bbf8d207732cb",
+ "bd069c0aa8634c48967a76cec5ba73aa",
+ "29da0c38fded4c3e858fe14e26599db1",
+ "7b7798cf21dd4b61b298d1e7a90d4348",
+ "647e744909fd4482b65b00263dc5d79e",
+ "84a32373f7004819b0c78660a5011e8f",
+ "19d677b42f0a4f729ef3ba823cdeb4dc",
+ "ab1f6fd7b3ae454ebc1f1bba039148fd",
+ "72b87fa4f1714edbb9785829eb9b6306",
+ "0a5cce1a6f8340ee9ef9c1560d6862a1",
+ "ed77c5a5f462433483425e35d059999d",
+ "d9cfd3c729f24e1c85c9787ecf8cd006",
+ "5ed7f8c9d2f848299d531dddd70c23a0",
+ "40a1342f65314d3db775db869ead29a3",
+ "dae1b3da597a497e850796ffaedfd53e",
+ "48cbb73eed8d4621b5c1446c0f1a7fe9",
+ "39842768d1274e8899ab932d587752a6",
+ "5ab44d0a65444d10b311bb9905d93bf0",
+ "3721ff005e8f4dd994a0e9675c335869",
+ "3d4a526a2da743edb3479a822bfce5bc",
+ "85ab309db4114cb188912ed938f9c64d",
+ "44f522242b0c4498b1c6d215d2729f14",
+ "0a425e0835b44e9c8fcab8a3821f7357",
+ "7d548c1dacb840dcb4bb084727ee888b",
+ "0fca5ce21cc54de4aecc26b8b065a530",
+ "a2295ea8bc714eba875bee57ff19e6d5",
+ "da72415268444faeb6295be055c031b8",
+ "4168f8cacfac4125b117e5d8ea1ac2f8",
+ "551219fa0ea64615a816020543489ee5",
+ "e7bc2d94d9834d92ac480e13b7e8afe7",
+ "f0a136dc3667446b82cbf3d259dd98b6",
+ "1e1a3c7734c64907a6476e8d82f8b2d0",
+ "042772fd617b416892d6266d16d39637",
+ "8d3b4aae1dc7447589b62f2380313c41",
+ "7281ea0a8ef3454a9a1c6c61e4115f97",
+ "c3cabdc750864c43816fe6a1b01e1dac",
+ "52da00f8290c4a449862c64f9c2b71b0",
+ "c9096ebfd6784b2487a5043d5effda39",
+ "70a1a4af74424990824201047bca0772",
+ "74ced9d52ff44489bbbd335226bf500f",
+ "0cf59b48c2ca4f84b6ac54cc5116ad34",
+ "26c43a3592af47f3883c5551a22d6a6b",
+ "d68b61cae659412a869d8b180b04bc24",
+ "4e3f56e5a77d48829e01536f3ceac42f",
+ "9a6932b8b097424885bab2f8e25f9cb9",
+ "60ec7eeb0d1a43c1b68223c62d0afc56",
+ "5e3be8ddf57942048b0533763319c737",
+ "652d12e0cf60479a816d93d0e3c279d9",
+ "e8bd76abbf624531a62d615a892a73ef",
+ "649da1635af043dbae9ee7d9d57998b9",
+ "cb92574b700b4b0eb76b63b14288650e",
+ "1861434e373b46eca882d32974a63eb6",
+ "e01aa29eaaea49ca8b3ec4c087907df2",
+ "e017e6a6d8524089b2dd2ce838373b61",
+ "3584d9528775438f9183cdc7db66a3ea",
+ "b9ef15a980704516b449344ee21f384a",
+ "ce46f1b18590456d9f49c32b0d8b5404",
+ "3395a6032b564145a4be7340b61bc3c1",
+ "18ecac3d03ba440684a0fff2308b0f53",
+ "5ce97812052c4908a309a21490955065",
+ "d33d82d85b5f49888434c6d66c55b4a5",
+ "8d019370794a47e1a9802e795dd4f9a5",
+ "42ce8a7b24a847e0bcbf0ae257be355d",
+ "b6599ff6073b405d8519c79d3fb606e4",
+ "25095892b4e34d4f90ece128162bbf5f",
+ "410bb288b4184674a99d32c70abc363b",
+ "f19e0f590c414fe9b0fb9b663a84175c",
+ "7bb90798262f4980bdaa47814fb02e63",
+ "8251b3017d0542febc7e5f40b8efc007",
+ "e40353e4154e49369fa62666ffdf92ac",
+ "c99ac47c21bc463480acf982a2bf7447",
+ "3b607425f5dd40c8bb786561c713a002",
+ "68de27eb6cda4d2987a080c1f53072a5",
+ "ea6fdfeacc7c4e30adc1b951f1edf7d7",
+ "2148560a3ac2403e83a6e2f48063ae1b",
+ "ada70efece51444490ed4e2a82f19c92",
+ "08b569b28a6c40fa82cf98bef02d0fe4",
+ "2b43651e3a254dbe9953b5675f475863",
+ "e7d1bd4874de49088230cd90e6d3ff51",
+ "8cf65a2510b54d77b2b36eaebbf8041d",
+ "f7ccf94d50ec44d38ab8f6cdbe610bf9",
+ "f35ad9d0b27541a991eab1f9a96134c0",
+ "d4bda3955e894fba86c2de83bd6865fb",
+ "efd6fa6da2df4e55ade25161d07b2508",
+ "26e8c457251544659db402a43ac8da1e",
+ "329d0958d1164504b05e74d4958aa046",
+ "a931b15bab1b4dd0a5f3b0da641b5e7b",
+ "05ab17d37a2f4601a8c1ba0ff5a260f5",
+ "d971627899ee41d2ac882bf60c97bb6f",
+ "a67d624dff604cf8b6c6fed04b750b8b",
+ "13b0018d5b184953a3f9541822074922",
+ "bb5c4be41d114cdea4bea73c39abd1bc",
+ "0b9fcb2b7e82478f8556a9efc41f25d1",
+ "aaf65d8d4f4d4f8a967ef026edcf0570",
+ "edee9a32368e4df2aa4a5bc87dccaf04"
+ ]
+ },
+ "id": "fbc9900d-28d2-4bda-9848-b572fbe778d2",
+ "outputId": "d57e8d82-0ee7-4736-aa1b-174881a5ca80"
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "π¦₯ Unsloth: Will patch your computer to enable 2x faster free finetuning.\n",
+ "π¦₯ Unsloth Zoo will now patch everything to make training faster!\n",
+ "Unsloth: If you want to finetune Gemma 2, install flash-attn to make it faster!\n",
+ "To install flash-attn, do the below:\n",
+ "\n",
+ "pip install --no-deps --upgrade \"flash-attn>=2.6.3\"\n",
+ "==((====))== Unsloth 2025.1.7: Fast Gemma2 patching. Transformers: 4.47.1.\n",
+ " \\\\ /| GPU: NVIDIA A100-SXM4-40GB. Max memory: 39.557 GB. Platform: Linux.\n",
+ "O^O/ \\_/ \\ Torch: 2.5.1+cu124. CUDA: 8.0. CUDA Toolkit: 12.4. 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"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "b0eaa4eebd7647f19f0509e54d1771f5",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "model.safetensors.index.json: 0%| | 0.00/39.1k [00:00, ?B/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "3675c39892444fbe8ca27891c90e42ac",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "Downloading shards: 0%| | 0/4 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "7da997d0770a449fbe8fee7366eb359c",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "model-00001-of-00004.safetensors: 0%| | 0.00/4.90G [00:00, ?B/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "9d7f7e2ef49f443398528e0d38d017a4",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "model-00002-of-00004.safetensors: 0%| | 0.00/4.95G [00:00, ?B/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "ab1f6fd7b3ae454ebc1f1bba039148fd",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "model-00003-of-00004.safetensors: 0%| | 0.00/4.96G [00:00, ?B/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "3721ff005e8f4dd994a0e9675c335869",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "model-00004-of-00004.safetensors: 0%| | 0.00/3.67G [00:00, ?B/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "e7bc2d94d9834d92ac480e13b7e8afe7",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "Loading checkpoint shards: 0%| | 0/4 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "0cf59b48c2ca4f84b6ac54cc5116ad34",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "generation_config.json: 0%| | 0.00/190 [00:00, ?B/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "1861434e373b46eca882d32974a63eb6",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "tokenizer_config.json: 0%| | 0.00/47.0k [00:00, ?B/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "42ce8a7b24a847e0bcbf0ae257be355d",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "tokenizer.model: 0%| | 0.00/4.24M [00:00, ?B/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "ea6fdfeacc7c4e30adc1b951f1edf7d7",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "special_tokens_map.json: 0%| | 0.00/636 [00:00, ?B/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "26e8c457251544659db402a43ac8da1e",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "tokenizer.json: 0%| | 0.00/34.4M [00:00, ?B/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Unsloth 2025.1.7 patched 42 layers with 42 QKV layers, 42 O layers and 42 MLP layers.\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "PeftModelForCausalLM(\n",
+ " (base_model): LoraModel(\n",
+ " (model): Gemma2ForCausalLM(\n",
+ " (model): Gemma2Model(\n",
+ " (embed_tokens): Embedding(256000, 3584, padding_idx=0)\n",
+ " (layers): ModuleList(\n",
+ " (0-41): 42 x Gemma2DecoderLayer(\n",
+ " (self_attn): Gemma2Attention(\n",
+ " (q_proj): lora.Linear(\n",
+ " (base_layer): Linear(in_features=3584, out_features=4096, bias=False)\n",
+ " (lora_dropout): ModuleDict(\n",
+ " (default): Identity()\n",
+ " )\n",
+ " (lora_A): ModuleDict(\n",
+ " (default): Linear(in_features=3584, out_features=16, bias=False)\n",
+ " )\n",
+ " (lora_B): ModuleDict(\n",
+ " (default): Linear(in_features=16, out_features=4096, 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=3584, out_features=2048, bias=False)\n",
+ " (lora_dropout): ModuleDict(\n",
+ " (default): Identity()\n",
+ " )\n",
+ " (lora_A): ModuleDict(\n",
+ " (default): Linear(in_features=3584, out_features=16, bias=False)\n",
+ " )\n",
+ " (lora_B): ModuleDict(\n",
+ " (default): Linear(in_features=16, out_features=2048, 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=3584, out_features=2048, bias=False)\n",
+ " (lora_dropout): ModuleDict(\n",
+ " (default): Identity()\n",
+ " )\n",
+ " (lora_A): ModuleDict(\n",
+ " (default): Linear(in_features=3584, out_features=16, bias=False)\n",
+ " )\n",
+ " (lora_B): ModuleDict(\n",
+ " (default): Linear(in_features=16, out_features=2048, 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=4096, out_features=3584, bias=False)\n",
+ " (lora_dropout): ModuleDict(\n",
+ " (default): Identity()\n",
+ " )\n",
+ " (lora_A): ModuleDict(\n",
+ " (default): Linear(in_features=4096, out_features=16, bias=False)\n",
+ " )\n",
+ " (lora_B): ModuleDict(\n",
+ " (default): Linear(in_features=16, out_features=3584, bias=False)\n",
+ " )\n",
+ " (lora_embedding_A): ParameterDict()\n",
+ " (lora_embedding_B): ParameterDict()\n",
+ " (lora_magnitude_vector): ModuleDict()\n",
+ " )\n",
+ " (rotary_emb): GemmaFixedRotaryEmbedding()\n",
+ " )\n",
+ " (mlp): Gemma2MLP(\n",
+ " (gate_proj): lora.Linear(\n",
+ " (base_layer): Linear(in_features=3584, out_features=14336, bias=False)\n",
+ " (lora_dropout): ModuleDict(\n",
+ " (default): Identity()\n",
+ " )\n",
+ " (lora_A): ModuleDict(\n",
+ " (default): Linear(in_features=3584, out_features=16, bias=False)\n",
+ " )\n",
+ " (lora_B): ModuleDict(\n",
+ " (default): Linear(in_features=16, out_features=14336, 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=3584, out_features=14336, bias=False)\n",
+ " (lora_dropout): ModuleDict(\n",
+ " (default): Identity()\n",
+ " )\n",
+ " (lora_A): ModuleDict(\n",
+ " (default): Linear(in_features=3584, out_features=16, bias=False)\n",
+ " )\n",
+ " (lora_B): ModuleDict(\n",
+ " (default): Linear(in_features=16, out_features=14336, 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=14336, out_features=3584, bias=False)\n",
+ " (lora_dropout): ModuleDict(\n",
+ " (default): Identity()\n",
+ " )\n",
+ " (lora_A): ModuleDict(\n",
+ " (default): Linear(in_features=14336, out_features=16, bias=False)\n",
+ " )\n",
+ " (lora_B): ModuleDict(\n",
+ " (default): Linear(in_features=16, out_features=3584, bias=False)\n",
+ " )\n",
+ " (lora_embedding_A): ParameterDict()\n",
+ " (lora_embedding_B): ParameterDict()\n",
+ " (lora_magnitude_vector): ModuleDict()\n",
+ " )\n",
+ " (act_fn): PytorchGELUTanh()\n",
+ " )\n",
+ " (input_layernorm): Gemma2RMSNorm((3584,), eps=1e-06)\n",
+ " (post_attention_layernorm): Gemma2RMSNorm((3584,), eps=1e-06)\n",
+ " (pre_feedforward_layernorm): Gemma2RMSNorm((3584,), eps=1e-06)\n",
+ " (post_feedforward_layernorm): Gemma2RMSNorm((3584,), eps=1e-06)\n",
+ " )\n",
+ " )\n",
+ " (norm): Gemma2RMSNorm((3584,), eps=1e-06)\n",
+ " )\n",
+ " (lm_head): Linear(in_features=3584, out_features=256000, bias=False)\n",
+ " )\n",
+ " )\n",
+ ")"
+ ]
+ },
+ "execution_count": 4,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "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/GEMMA-9B-B60\"\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",
+ "id": "FICHwqm5aLUV",
+ "metadata": {
+ "id": "FICHwqm5aLUV"
+ },
+ "source": [
+ "##**SINGLE TEST CASE**"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "r1dozae-gO5B",
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "r1dozae-gO5B",
+ "outputId": "7da92a7e-6427-44f3-8ed2-4dfc000dae27"
+ },
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "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"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Generated Response (20 tokens):\n",
+ "The correct answer is **B) 700,003**. Here's how to solve it:\n",
+ "\n",
+ "```\n",
+ " 46,911\n",
+ "+ 653,092\n",
+ "----------\n",
+ " 700,003 \n",
+ "```\n",
+ "\n",
+ "Probability of 'A' at token 1: 0.0118\n",
+ "Probability of 'B' at token 1: 0.0056\n",
+ "Probability of 'C' at token 1: 0.0005\n",
+ "Probability of 'D' at token 1: 0.0004\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",
+ "Probability of 'A' at token 3: 0.0000\n",
+ "Probability of 'B' at token 3: 0.0000\n",
+ "Probability of 'C' at token 3: 0.0000\n",
+ "Probability of 'D' at token 3: 0.0000\n"
+ ]
+ }
+ ],
+ "source": [
+ "input_text = \"ΰ€ΰ₯ΰ€‘ΰ€Όΰ₯ΰ€ 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}\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "7Al9PZfU2bhu",
+ "metadata": {
+ "id": "7Al9PZfU2bhu"
+ },
+ "source": [
+ "#**ARC CHALLENGE ENGLISH**"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "1749c745-d1fb-430b-9469-4913bb2a6cb5",
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "1749c745-d1fb-430b-9469-4913bb2a6cb5",
+ "outputId": "6932819b-5ed1-4d0f-85b1-4a2eed1cf259"
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "1172\n",
+ "Average 'tok' value: 70.26706484641639\n",
+ "Max 'tok' value: 197\n",
+ "Output\n",
+ "B 311\n",
+ "C 310\n",
+ "D 285\n",
+ "A 266\n",
+ "Name: count, dtype: int64\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "100%|ββββββββββ| 1172/1172 [04:40<00:00, 4.18it/s]"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "ANS\n",
+ "C 312\n",
+ "B 308\n",
+ "D 277\n",
+ "A 275\n",
+ "Name: count, dtype: int64\n",
+ "Accuracy: 0.8831\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "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",
+ "id": "PubN4p-32_EC",
+ "metadata": {
+ "id": "PubN4p-32_EC"
+ },
+ "source": [
+ "#**ARC CHALLENGE HINDI**"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "mPFAiosJ3jzD",
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "mPFAiosJ3jzD",
+ "outputId": "da6c0aa5-2f23-4d14-f6ba-86b118581da5"
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "1172\n",
+ "Average 'tok' value: 114.31313993174061\n",
+ "Max 'tok' value: 389\n",
+ "Output\n",
+ "B 311\n",
+ "C 310\n",
+ "D 285\n",
+ "A 266\n",
+ "Name: count, dtype: int64\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "100%|ββββββββββ| 1172/1172 [04:45<00:00, 4.11it/s]"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "ANS\n",
+ "C 303\n",
+ "B 301\n",
+ "A 298\n",
+ "D 270\n",
+ "Name: count, dtype: int64\n",
+ "Accuracy: 0.7841\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\n"
+ ]
+ }
+ ],
+ "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}\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "cT9I3npw43AP",
+ "metadata": {
+ "id": "cT9I3npw43AP"
+ },
+ "source": [
+ "#**ARC EASY ENGLISH**"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "6vmG3Z92410E",
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "6vmG3Z92410E",
+ "outputId": "6ed0582e-673d-491a-e54a-c57c854f8002"
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "2376\n",
+ "Average 'tok' value: 60.46590909090909\n",
+ "Max 'tok' value: 193\n",
+ "Output\n",
+ "C 633\n",
+ "A 596\n",
+ "B 585\n",
+ "D 561\n",
+ "E 1\n",
+ "Name: count, dtype: int64\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "100%|ββββββββββ| 2376/2376 [09:30<00:00, 4.16it/s]"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "ANS\n",
+ "C 635\n",
+ "A 608\n",
+ "B 576\n",
+ "D 557\n",
+ "Name: count, dtype: int64\n",
+ "Accuracy: 0.9575\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\n"
+ ]
+ }
+ ],
+ "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}\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "A5dtJYX05T5v",
+ "metadata": {
+ "id": "A5dtJYX05T5v"
+ },
+ "source": [
+ "#**ARC EASY HINDI**"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "aFPK7wPX5TN7",
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "aFPK7wPX5TN7",
+ "outputId": "edc55cbc-1c60-408c-e6a2-b6b01ad57e42"
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "2376\n",
+ "Average 'tok' value: 99.67003367003367\n",
+ "Max 'tok' value: 650\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"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "100%|ββββββββββ| 2376/2376 [09:31<00:00, 4.16it/s]"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "ANS\n",
+ "A 643\n",
+ "C 616\n",
+ "B 573\n",
+ "D 544\n",
+ "Name: count, dtype: int64\n",
+ "Accuracy: 0.9066\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\n"
+ ]
+ }
+ ],
+ "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}\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "pFRbbDbE4Qui",
+ "metadata": {
+ "id": "pFRbbDbE4Qui"
+ },
+ "source": [
+ "#**MMLU ENGLISH**"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "FtThThQC8hs2",
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "FtThThQC8hs2",
+ "outputId": "80c6b942-f523-40c2-9cf0-090976b2c566"
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "14042\n",
+ "Average 'tok' value: 106.63509471585245\n",
+ "Max 'tok' value: 1009\n",
+ "Output\n",
+ "D 3776\n",
+ "C 3582\n",
+ "B 3462\n",
+ "A 3222\n",
+ "Name: count, dtype: int64\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "100%|ββββββββββ| 14042/14042 [56:37<00:00, 4.13it/s]"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "ANS\n",
+ "B 3696\n",
+ "D 3486\n",
+ "A 3461\n",
+ "C 3399\n",
+ "Name: count, dtype: int64\n",
+ "Accuracy: 0.6863\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\n"
+ ]
+ }
+ ],
+ "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}\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "FeK3WGqS85al",
+ "metadata": {
+ "id": "FeK3WGqS85al"
+ },
+ "source": [
+ "#**MMMLU HINDI**"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "wDxU0TXK85G7",
+ "metadata": {
+ "colab": {
+ "background_save": true,
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "wDxU0TXK85G7",
+ "outputId": "8b300950-d0c3-4674-f40d-45a7ee21aff1"
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "14042\n",
+ "Average 'tok' value: 180.577624270047\n",
+ "Max 'tok' value: 1917\n",
+ "Output\n",
+ "D 3776\n",
+ "C 3582\n",
+ "B 3462\n",
+ "A 3222\n",
+ "Name: count, dtype: int64\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "100%|ββββββββββ| 14042/14042 [56:28<00:00, 4.14it/s]"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "ANS\n",
+ "A 3935\n",
+ "B 3680\n",
+ "D 3391\n",
+ "C 3036\n",
+ "Name: count, dtype: int64\n",
+ "Accuracy: 0.5419\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\n"
+ ]
+ }
+ ],
+ "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}\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "4aC98L-5Gi9D",
+ "metadata": {
+ "id": "4aC98L-5Gi9D"
+ },
+ "source": [
+ "#**BOOLQ ENG**"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "m7ayEga9Ghkd",
+ "metadata": {
+ "id": "m7ayEga9Ghkd",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "outputId": "ea86ed57-d039-4a6d-97f6-f7dbcfeb4e58"
+ },
+ "outputs": [
+ {
+ "metadata": {
+ "tags": null
+ },
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "3270\n",
+ "Average 'tok' value: 138.53669724770643\n",
+ "Max 'tok' value: 1248\n",
+ "Output\n",
+ "True 2033\n",
+ "False 1237\n",
+ "Name: count, dtype: int64\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ " 93%|ββββββββββ| 3045/3270 [12:14<00:54, 4.16it/s]"
+ ]
+ }
+ ],
+ "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}\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "uAhhi93PHZ40",
+ "metadata": {
+ "id": "uAhhi93PHZ40"
+ },
+ "source": [
+ "#**BOOLQ HINDI**"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "GOHy6uE285AB",
+ "metadata": {
+ "id": "GOHy6uE285AB"
+ },
+ "outputs": [],
+ "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}\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "1ugA-oyeReI9",
+ "metadata": {
+ "id": "1ugA-oyeReI9"
+ },
+ "source": [
+ "#**Context MCQ ENGLISH**"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "id": "K4gKxj8ZRdYS",
+ "metadata": {
+ "id": "K4gKxj8ZRdYS",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "outputId": "44e932d2-a26a-4e04-e83d-57a4fef16e09"
+ },
+ "outputs": [
+ {
+ "metadata": {
+ "tags": null
+ },
+ "name": "stdout",
+ "output_type": "stream",
+ "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%|ββββββββββ| 1000/1000 [04:05<00:00, 4.07it/s]"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "ANS\n",
+ "C 267\n",
+ "A 265\n",
+ "B 235\n",
+ "D 233\n",
+ "Name: count, dtype: int64\n",
+ "Accuracy: 0.8800\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "\n"
+ ]
+ }
+ ],
+ "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}\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "JVW_cii1SR3c",
+ "metadata": {
+ "id": "JVW_cii1SR3c"
+ },
+ "source": [
+ "#**Context MCQ HINDI**"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 17,
+ "id": "HrB5mDcf842y",
+ "metadata": {
+ "id": "HrB5mDcf842y",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "outputId": "78c3db34-863f-4232-fb08-2a1c501cb305"
+ },
+ "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%|ββββββββββ| 1000/1000 [04:09<00:00, 4.00it/s]"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "ANS\n",
+ "D 273\n",
+ "C 270\n",
+ "A 245\n",
+ "B 212\n",
+ "Name: count, dtype: int64\n",
+ "Accuracy: 0.7890\n"
+ ]
+ },
+ {
+ "output_type": "stream",
+ "name": "stderr",
+ "text": [
+ "\n"
+ ]
+ }
+ ],
+ "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}\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "JqYw49CH3gfX",
+ "metadata": {
+ "id": "JqYw49CH3gfX"
+ },
+ "source": [
+ "#**END**"
+ ]
+ },
+ {
+ "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 \")\n"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "gI14YhuEPPQD",
+ "outputId": "3a2318bb-10d9-4f40-e8dd-e924cab91fe4"
+ },
+ "id": "gI14YhuEPPQD",
+ "execution_count": 18,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "BOOLQ ENGLISH : 0.8681957186544342\n",
+ "BOOLQ HINDI : 0.8519424900581217\n",
+ "C-MCQ ENGLISH : 0.88\n",
+ "C-MCQ HINDI : 0.789\n",
+ "MMMLU ENGLISH : 0.6862982481128045\n",
+ "MMMLU HINDI : 0.5418743768693918\n",
+ "ARC-E ENGLISH : 0.9574915824915825\n",
+ "ARC-E HINDI : 0.9065656565656566\n",
+ "ARC-C ENGLISH : 0.8831058020477816\n",
+ "ARC-C HINDI : 0.7841296928327645\n",
+ "AVG SCORE : HINDI : 0.774702443265187\n",
+ "AVG SCORE : ENGLISH : 0.8550182702613206\n",
+ "TOT AVG SCORE : 0.8148603567632537\n",
+ "CLICK CTRl+S and wait for 2 sec\n",
+ "1) NOTEBOOK NAME SHOULD BE : GEMMA-9B-B60.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": "ZTTdwadzMMB3"
+ },
+ "id": "ZTTdwadzMMB3",
+ "execution_count": null,
+ "outputs": []
+ }
+ ],
+ "metadata": {
+ "accelerator": "GPU",
+ "colab": {
+ "gpuType": "A100",
+ "machine_shape": "hm",
+ "provenance": []
+ },
+ "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"
+ },
+ "widgets": {
+ "application/vnd.jupyter.widget-state+json": {
+ "042772fd617b416892d6266d16d39637": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "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_70a1a4af74424990824201047bca0772",
+ "placeholder": "β",
+ "style": "IPY_MODEL_74ced9d52ff44489bbbd335226bf500f",
+ "value": "β4/4β[00:07<00:00,ββ1.72s/it]"
+ }
+ },
+ "05ab17d37a2f4601a8c1ba0ff5a260f5": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "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_aaf65d8d4f4d4f8a967ef026edcf0570",
+ "placeholder": "β",
+ "style": "IPY_MODEL_edee9a32368e4df2aa4a5bc87dccaf04",
+ "value": "β34.4M/34.4Mβ[00:01<00:00,β21.1MB/s]"
+ }
+ },
+ "08b569b28a6c40fa82cf98bef02d0fe4": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "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_d4bda3955e894fba86c2de83bd6865fb",
+ "placeholder": "β",
+ "style": "IPY_MODEL_efd6fa6da2df4e55ade25161d07b2508",
+ "value": "β636/636β[00:00<00:00,β59.0kB/s]"
+ }
+ },
+ "09326715e33945359d64e8c981857eea": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "0a425e0835b44e9c8fcab8a3821f7357": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "0a5cce1a6f8340ee9ef9c1560d6862a1": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "FloatProgressModel",
+ "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_dae1b3da597a497e850796ffaedfd53e",
+ "max": 4962221464,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_48cbb73eed8d4621b5c1446c0f1a7fe9",
+ "value": 4962221464
+ }
+ },
+ "0b9fcb2b7e82478f8556a9efc41f25d1": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "ProgressStyleModel",
+ "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": ""
+ }
+ },
+ "0cf59b48c2ca4f84b6ac54cc5116ad34": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HBoxModel",
+ "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_26c43a3592af47f3883c5551a22d6a6b",
+ "IPY_MODEL_d68b61cae659412a869d8b180b04bc24",
+ "IPY_MODEL_4e3f56e5a77d48829e01536f3ceac42f"
+ ],
+ "layout": "IPY_MODEL_9a6932b8b097424885bab2f8e25f9cb9"
+ }
+ },
+ "0e15b63d078247018a18c609af24f26f": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "0fca5ce21cc54de4aecc26b8b065a530": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "13b0018d5b184953a3f9541822074922": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "1468258495d04649b30cbeb84b9a4ffb": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "153279dc656a41bdbb122a4854ee57e0": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "FloatProgressModel",
+ "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_cb0fbe81482844b69a96edf5b060819d",
+ "max": 4903351912,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_a195da274627424aaaada4cbdc14c746",
+ "value": 4903351912
+ }
+ },
+ "1861434e373b46eca882d32974a63eb6": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HBoxModel",
+ "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_e01aa29eaaea49ca8b3ec4c087907df2",
+ "IPY_MODEL_e017e6a6d8524089b2dd2ce838373b61",
+ "IPY_MODEL_3584d9528775438f9183cdc7db66a3ea"
+ ],
+ "layout": "IPY_MODEL_b9ef15a980704516b449344ee21f384a"
+ }
+ },
+ "18ecac3d03ba440684a0fff2308b0f53": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "193ba6195d6240a2be0ab007d617d7d5": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "19d677b42f0a4f729ef3ba823cdeb4dc": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "1cdec6fd6ccf415888a1cd7275d07e00": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "ProgressStyleModel",
+ "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": ""
+ }
+ },
+ "1e1a3c7734c64907a6476e8d82f8b2d0": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "FloatProgressModel",
+ "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_52da00f8290c4a449862c64f9c2b71b0",
+ "max": 4,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_c9096ebfd6784b2487a5043d5effda39",
+ "value": 4
+ }
+ },
+ "1f799b16a76141af80fccc6b88826dea": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "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_1468258495d04649b30cbeb84b9a4ffb",
+ "placeholder": "β",
+ "style": "IPY_MODEL_22f6372c8dc147c58c615ae54ebdda89",
+ "value": "β4.90G/4.90Gβ[03:19<00:00,β24.6MB/s]"
+ }
+ },
+ "1fcf6c9e4ab34f2985a35fe4693253cc": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "20d9a5b63fb1497aaab412e7165ed55b": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "2148560a3ac2403e83a6e2f48063ae1b": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "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_e7d1bd4874de49088230cd90e6d3ff51",
+ "placeholder": "β",
+ "style": "IPY_MODEL_8cf65a2510b54d77b2b36eaebbf8041d",
+ "value": "special_tokens_map.json:β100%"
+ }
+ },
+ "22f6372c8dc147c58c615ae54ebdda89": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "25095892b4e34d4f90ece128162bbf5f": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "FloatProgressModel",
+ "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_e40353e4154e49369fa62666ffdf92ac",
+ "max": 4241003,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_c99ac47c21bc463480acf982a2bf7447",
+ "value": 4241003
+ }
+ },
+ "26c43a3592af47f3883c5551a22d6a6b": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "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_60ec7eeb0d1a43c1b68223c62d0afc56",
+ "placeholder": "β",
+ "style": "IPY_MODEL_5e3be8ddf57942048b0533763319c737",
+ "value": "generation_config.json:β100%"
+ }
+ },
+ "26e8c457251544659db402a43ac8da1e": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HBoxModel",
+ "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_329d0958d1164504b05e74d4958aa046",
+ "IPY_MODEL_a931b15bab1b4dd0a5f3b0da641b5e7b",
+ "IPY_MODEL_05ab17d37a2f4601a8c1ba0ff5a260f5"
+ ],
+ "layout": "IPY_MODEL_d971627899ee41d2ac882bf60c97bb6f"
+ }
+ },
+ "29da0c38fded4c3e858fe14e26599db1": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "2b43651e3a254dbe9953b5675f475863": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "30a0c3ad3d1643d2988ed6cb1e607f3c": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "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_5c44c227ee9449ffb035012568fb68b3",
+ "placeholder": "β",
+ "style": "IPY_MODEL_1fcf6c9e4ab34f2985a35fe4693253cc",
+ "value": "\nPro Tip: 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. "
+ }
+ },
+ "329d0958d1164504b05e74d4958aa046": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "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_a67d624dff604cf8b6c6fed04b750b8b",
+ "placeholder": "β",
+ "style": "IPY_MODEL_13b0018d5b184953a3f9541822074922",
+ "value": "tokenizer.json:β100%"
+ }
+ },
+ "3395a6032b564145a4be7340b61bc3c1": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "3584d9528775438f9183cdc7db66a3ea": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "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_d33d82d85b5f49888434c6d66c55b4a5",
+ "placeholder": "β",
+ "style": "IPY_MODEL_8d019370794a47e1a9802e795dd4f9a5",
+ "value": "β47.0k/47.0kβ[00:00<00:00,β3.95MB/s]"
+ }
+ },
+ "3675c39892444fbe8ca27891c90e42ac": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HBoxModel",
+ "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_9fb90b385a2b42f6ac973a8bcc20f821",
+ "IPY_MODEL_d59ad8a75d4042db83af02cef430d6ad",
+ "IPY_MODEL_a2b77cdbf6c84540a2d7a30029e8f9f6"
+ ],
+ "layout": "IPY_MODEL_ffea5b009edb4ee7952a37a849faeefa"
+ }
+ },
+ "36aa16e981fb4eb39f10a959940fd232": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "ProgressStyleModel",
+ "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": ""
+ }
+ },
+ "3721ff005e8f4dd994a0e9675c335869": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HBoxModel",
+ "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_3d4a526a2da743edb3479a822bfce5bc",
+ "IPY_MODEL_85ab309db4114cb188912ed938f9c64d",
+ "IPY_MODEL_44f522242b0c4498b1c6d215d2729f14"
+ ],
+ "layout": "IPY_MODEL_0a425e0835b44e9c8fcab8a3821f7357"
+ }
+ },
+ "39842768d1274e8899ab932d587752a6": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "3abc169a4a6546c7b728cea12c6d566e": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "3b607425f5dd40c8bb786561c713a002": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "3bdcbf053400426889ce191e8e631c34": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "VBoxModel",
+ "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_c436a45ebb964940a65f31c4c032e59a",
+ "IPY_MODEL_64b42b59dbdf419a811678e0343fa14f",
+ "IPY_MODEL_61f0d8a908d8467a833a01645bf4df93",
+ "IPY_MODEL_b3c7f82cdfe941ddb8a322b519f4f8d7",
+ "IPY_MODEL_30a0c3ad3d1643d2988ed6cb1e607f3c"
+ ],
+ "layout": "IPY_MODEL_636b613ccc794d388f3b4859e058a39c"
+ }
+ },
+ "3cd55085208f4f09b9442d9cc6635935": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "3d47320324f74a01825c44dd749ae993": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "3d4a526a2da743edb3479a822bfce5bc": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "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_7d548c1dacb840dcb4bb084727ee888b",
+ "placeholder": "β",
+ "style": "IPY_MODEL_0fca5ce21cc54de4aecc26b8b065a530",
+ "value": "model-00004-of-00004.safetensors:β100%"
+ }
+ },
+ "40a1342f65314d3db775db869ead29a3": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "410bb288b4184674a99d32c70abc363b": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "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_3b607425f5dd40c8bb786561c713a002",
+ "placeholder": "β",
+ "style": "IPY_MODEL_68de27eb6cda4d2987a080c1f53072a5",
+ "value": "β4.24M/4.24Mβ[00:00<00:00,β43.5MB/s]"
+ }
+ },
+ "4168f8cacfac4125b117e5d8ea1ac2f8": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "42ce8a7b24a847e0bcbf0ae257be355d": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HBoxModel",
+ "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_b6599ff6073b405d8519c79d3fb606e4",
+ "IPY_MODEL_25095892b4e34d4f90ece128162bbf5f",
+ "IPY_MODEL_410bb288b4184674a99d32c70abc363b"
+ ],
+ "layout": "IPY_MODEL_f19e0f590c414fe9b0fb9b663a84175c"
+ }
+ },
+ "44f522242b0c4498b1c6d215d2729f14": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "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_4168f8cacfac4125b117e5d8ea1ac2f8",
+ "placeholder": "β",
+ "style": "IPY_MODEL_551219fa0ea64615a816020543489ee5",
+ "value": "β3.67G/3.67Gβ[02:40<00:00,β23.0MB/s]"
+ }
+ },
+ "4827149734034b16b96bbf8d207732cb": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "48cbb73eed8d4621b5c1446c0f1a7fe9": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "ProgressStyleModel",
+ "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": ""
+ }
+ },
+ "4936e9872dea435392d95ba1bfb57912": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "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_6321877814914b22839afad94092bf59",
+ "placeholder": "β",
+ "style": "IPY_MODEL_ce1582723c79433f8b81668e996bbb78",
+ "value": "model-00001-of-00004.safetensors:β100%"
+ }
+ },
+ "4d20a4b6057a44238f382c015649842b": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "4e3f56e5a77d48829e01536f3ceac42f": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "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_649da1635af043dbae9ee7d9d57998b9",
+ "placeholder": "β",
+ "style": "IPY_MODEL_cb92574b700b4b0eb76b63b14288650e",
+ "value": "β190/190β[00:00<00:00,β16.5kB/s]"
+ }
+ },
+ "52da00f8290c4a449862c64f9c2b71b0": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "551219fa0ea64615a816020543489ee5": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "5ab44d0a65444d10b311bb9905d93bf0": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "5c44c227ee9449ffb035012568fb68b3": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "5ce97812052c4908a309a21490955065": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "ProgressStyleModel",
+ "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": ""
+ }
+ },
+ "5e3be8ddf57942048b0533763319c737": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "5ed7f8c9d2f848299d531dddd70c23a0": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "60ec7eeb0d1a43c1b68223c62d0afc56": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "61f0d8a908d8467a833a01645bf4df93": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "CheckboxModel",
+ "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_4d20a4b6057a44238f382c015649842b",
+ "style": "IPY_MODEL_89aa4177a076483fa584d032251b55ff",
+ "value": true
+ }
+ },
+ "6321877814914b22839afad94092bf59": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "636b613ccc794d388f3b4859e058a39c": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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%"
+ }
+ },
+ "647e744909fd4482b65b00263dc5d79e": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "ProgressStyleModel",
+ "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": ""
+ }
+ },
+ "649da1635af043dbae9ee7d9d57998b9": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "64b42b59dbdf419a811678e0343fa14f": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "PasswordModel",
+ "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_3abc169a4a6546c7b728cea12c6d566e",
+ "placeholder": "β",
+ "style": "IPY_MODEL_09326715e33945359d64e8c981857eea",
+ "value": ""
+ }
+ },
+ "652d12e0cf60479a816d93d0e3c279d9": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "68de27eb6cda4d2987a080c1f53072a5": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "70a1a4af74424990824201047bca0772": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "7281ea0a8ef3454a9a1c6c61e4115f97": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "72b87fa4f1714edbb9785829eb9b6306": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "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_5ed7f8c9d2f848299d531dddd70c23a0",
+ "placeholder": "β",
+ "style": "IPY_MODEL_40a1342f65314d3db775db869ead29a3",
+ "value": "model-00003-of-00004.safetensors:β100%"
+ }
+ },
+ "74ced9d52ff44489bbbd335226bf500f": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "7b7798cf21dd4b61b298d1e7a90d4348": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "7bb90798262f4980bdaa47814fb02e63": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "7d548c1dacb840dcb4bb084727ee888b": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "7da997d0770a449fbe8fee7366eb359c": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HBoxModel",
+ "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_4936e9872dea435392d95ba1bfb57912",
+ "IPY_MODEL_153279dc656a41bdbb122a4854ee57e0",
+ "IPY_MODEL_1f799b16a76141af80fccc6b88826dea"
+ ],
+ "layout": "IPY_MODEL_7e62258760b044648c0fa12e9e7ed272"
+ }
+ },
+ "7e62258760b044648c0fa12e9e7ed272": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "8251b3017d0542febc7e5f40b8efc007": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "84a32373f7004819b0c78660a5011e8f": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "85ab309db4114cb188912ed938f9c64d": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "FloatProgressModel",
+ "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_a2295ea8bc714eba875bee57ff19e6d5",
+ "max": 3670322200,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_da72415268444faeb6295be055c031b8",
+ "value": 3670322200
+ }
+ },
+ "89aa4177a076483fa584d032251b55ff": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "8cf65a2510b54d77b2b36eaebbf8041d": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "8d019370794a47e1a9802e795dd4f9a5": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "8d3b4aae1dc7447589b62f2380313c41": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "9a6932b8b097424885bab2f8e25f9cb9": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "9bd89ecc06214af3a1018701fa3e8758": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "9d7f7e2ef49f443398528e0d38d017a4": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HBoxModel",
+ "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_cdf5c75fa4374715b184f5df2ae13f79",
+ "IPY_MODEL_a6f8346aa094436082345670a526e60a",
+ "IPY_MODEL_ab950c5224374ea98f1eb2b55449ac83"
+ ],
+ "layout": "IPY_MODEL_4827149734034b16b96bbf8d207732cb"
+ }
+ },
+ "9fb90b385a2b42f6ac973a8bcc20f821": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "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_e74b100a0c7b428eacf57c06c687ffb2",
+ "placeholder": "β",
+ "style": "IPY_MODEL_3d47320324f74a01825c44dd749ae993",
+ "value": "Downloadingβshards:β100%"
+ }
+ },
+ "a195da274627424aaaada4cbdc14c746": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "ProgressStyleModel",
+ "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": ""
+ }
+ },
+ "a2295ea8bc714eba875bee57ff19e6d5": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "a2b77cdbf6c84540a2d7a30029e8f9f6": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "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_c107c6048cd74618bd2644ebdb83bd75",
+ "placeholder": "β",
+ "style": "IPY_MODEL_0e15b63d078247018a18c609af24f26f",
+ "value": "β4/4β[11:55<00:00,β178.82s/it]"
+ }
+ },
+ "a4569bde680b4bbdb64b48dd670bfe31": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "a67d624dff604cf8b6c6fed04b750b8b": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "a6f8346aa094436082345670a526e60a": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "FloatProgressModel",
+ "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_7b7798cf21dd4b61b298d1e7a90d4348",
+ "max": 4947570872,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_647e744909fd4482b65b00263dc5d79e",
+ "value": 4947570872
+ }
+ },
+ "a931b15bab1b4dd0a5f3b0da641b5e7b": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "FloatProgressModel",
+ "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_bb5c4be41d114cdea4bea73c39abd1bc",
+ "max": 34362873,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_0b9fcb2b7e82478f8556a9efc41f25d1",
+ "value": 34362873
+ }
+ },
+ "aaf65d8d4f4d4f8a967ef026edcf0570": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "ab1f6fd7b3ae454ebc1f1bba039148fd": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HBoxModel",
+ "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_72b87fa4f1714edbb9785829eb9b6306",
+ "IPY_MODEL_0a5cce1a6f8340ee9ef9c1560d6862a1",
+ "IPY_MODEL_ed77c5a5f462433483425e35d059999d"
+ ],
+ "layout": "IPY_MODEL_d9cfd3c729f24e1c85c9787ecf8cd006"
+ }
+ },
+ "ab6a8171c33345489e0f57c4dbf5fe37": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "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_d35ba0d1406c48f2862b8989c1c3a2a2",
+ "placeholder": "β",
+ "style": "IPY_MODEL_def55d121c2341b789e777d3ee41a65d",
+ "value": "model.safetensors.index.json:β100%"
+ }
+ },
+ "ab950c5224374ea98f1eb2b55449ac83": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "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_84a32373f7004819b0c78660a5011e8f",
+ "placeholder": "β",
+ "style": "IPY_MODEL_19d677b42f0a4f729ef3ba823cdeb4dc",
+ "value": "β4.95G/4.95Gβ[01:57<00:00,β42.0MB/s]"
+ }
+ },
+ "ada70efece51444490ed4e2a82f19c92": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "FloatProgressModel",
+ "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_f7ccf94d50ec44d38ab8f6cdbe610bf9",
+ "max": 636,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_f35ad9d0b27541a991eab1f9a96134c0",
+ "value": 636
+ }
+ },
+ "b0eaa4eebd7647f19f0509e54d1771f5": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HBoxModel",
+ "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_ab6a8171c33345489e0f57c4dbf5fe37",
+ "IPY_MODEL_c1b153e792684badad9088b8d23f0f9f",
+ "IPY_MODEL_e2f0f3c9d0f446ce84bc30f562e63aac"
+ ],
+ "layout": "IPY_MODEL_9bd89ecc06214af3a1018701fa3e8758"
+ }
+ },
+ "b3c7f82cdfe941ddb8a322b519f4f8d7": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "ButtonModel",
+ "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_bcfc20a2d38642ce97393c9d2ec2afbd",
+ "style": "IPY_MODEL_bf696b1bb83f4268a60ebe493f8c820f",
+ "tooltip": ""
+ }
+ },
+ "b6599ff6073b405d8519c79d3fb606e4": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "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_7bb90798262f4980bdaa47814fb02e63",
+ "placeholder": "β",
+ "style": "IPY_MODEL_8251b3017d0542febc7e5f40b8efc007",
+ "value": "tokenizer.model:β100%"
+ }
+ },
+ "b9ef15a980704516b449344ee21f384a": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "bb5c4be41d114cdea4bea73c39abd1bc": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "bcfc20a2d38642ce97393c9d2ec2afbd": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "bd069c0aa8634c48967a76cec5ba73aa": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "bf696b1bb83f4268a60ebe493f8c820f": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "ButtonStyleModel",
+ "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": ""
+ }
+ },
+ "c107c6048cd74618bd2644ebdb83bd75": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "c1b153e792684badad9088b8d23f0f9f": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "FloatProgressModel",
+ "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_3cd55085208f4f09b9442d9cc6635935",
+ "max": 39072,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_1cdec6fd6ccf415888a1cd7275d07e00",
+ "value": 39072
+ }
+ },
+ "c24e7b9712674fb98668c66ec43ca7e6": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "c3cabdc750864c43816fe6a1b01e1dac": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "c436a45ebb964940a65f31c4c032e59a": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "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_193ba6195d6240a2be0ab007d617d7d5",
+ "placeholder": "β",
+ "style": "IPY_MODEL_20d9a5b63fb1497aaab412e7165ed55b",
+ "value": "
Copy a token from your Hugging Face\ntokens page and paste it below.
Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file. "
+ }
+ },
+ "c43792fa6b9b4d51ac11ead6f6f67f47": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "c9096ebfd6784b2487a5043d5effda39": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "ProgressStyleModel",
+ "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": ""
+ }
+ },
+ "c99ac47c21bc463480acf982a2bf7447": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "ProgressStyleModel",
+ "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": ""
+ }
+ },
+ "cb0fbe81482844b69a96edf5b060819d": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "cb92574b700b4b0eb76b63b14288650e": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "cdf5c75fa4374715b184f5df2ae13f79": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "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_bd069c0aa8634c48967a76cec5ba73aa",
+ "placeholder": "β",
+ "style": "IPY_MODEL_29da0c38fded4c3e858fe14e26599db1",
+ "value": "model-00002-of-00004.safetensors:β100%"
+ }
+ },
+ "ce1582723c79433f8b81668e996bbb78": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "ce46f1b18590456d9f49c32b0d8b5404": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "d33d82d85b5f49888434c6d66c55b4a5": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "d35ba0d1406c48f2862b8989c1c3a2a2": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "d4bda3955e894fba86c2de83bd6865fb": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "d59ad8a75d4042db83af02cef430d6ad": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "FloatProgressModel",
+ "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_a4569bde680b4bbdb64b48dd670bfe31",
+ "max": 4,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_36aa16e981fb4eb39f10a959940fd232",
+ "value": 4
+ }
+ },
+ "d68b61cae659412a869d8b180b04bc24": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "FloatProgressModel",
+ "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_652d12e0cf60479a816d93d0e3c279d9",
+ "max": 190,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_e8bd76abbf624531a62d615a892a73ef",
+ "value": 190
+ }
+ },
+ "d971627899ee41d2ac882bf60c97bb6f": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "d9cfd3c729f24e1c85c9787ecf8cd006": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "da72415268444faeb6295be055c031b8": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "ProgressStyleModel",
+ "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": ""
+ }
+ },
+ "dae1b3da597a497e850796ffaedfd53e": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "def55d121c2341b789e777d3ee41a65d": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "e017e6a6d8524089b2dd2ce838373b61": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "FloatProgressModel",
+ "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_18ecac3d03ba440684a0fff2308b0f53",
+ "max": 47025,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_5ce97812052c4908a309a21490955065",
+ "value": 47025
+ }
+ },
+ "e01aa29eaaea49ca8b3ec4c087907df2": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "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_ce46f1b18590456d9f49c32b0d8b5404",
+ "placeholder": "β",
+ "style": "IPY_MODEL_3395a6032b564145a4be7340b61bc3c1",
+ "value": "tokenizer_config.json:β100%"
+ }
+ },
+ "e2f0f3c9d0f446ce84bc30f562e63aac": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "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_c43792fa6b9b4d51ac11ead6f6f67f47",
+ "placeholder": "β",
+ "style": "IPY_MODEL_c24e7b9712674fb98668c66ec43ca7e6",
+ "value": "β39.1k/39.1kβ[00:00<00:00,β3.26MB/s]"
+ }
+ },
+ "e40353e4154e49369fa62666ffdf92ac": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "e74b100a0c7b428eacf57c06c687ffb2": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "e7bc2d94d9834d92ac480e13b7e8afe7": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HBoxModel",
+ "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_f0a136dc3667446b82cbf3d259dd98b6",
+ "IPY_MODEL_1e1a3c7734c64907a6476e8d82f8b2d0",
+ "IPY_MODEL_042772fd617b416892d6266d16d39637"
+ ],
+ "layout": "IPY_MODEL_8d3b4aae1dc7447589b62f2380313c41"
+ }
+ },
+ "e7d1bd4874de49088230cd90e6d3ff51": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "e8bd76abbf624531a62d615a892a73ef": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "ProgressStyleModel",
+ "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": ""
+ }
+ },
+ "ea6fdfeacc7c4e30adc1b951f1edf7d7": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HBoxModel",
+ "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_2148560a3ac2403e83a6e2f48063ae1b",
+ "IPY_MODEL_ada70efece51444490ed4e2a82f19c92",
+ "IPY_MODEL_08b569b28a6c40fa82cf98bef02d0fe4"
+ ],
+ "layout": "IPY_MODEL_2b43651e3a254dbe9953b5675f475863"
+ }
+ },
+ "ed77c5a5f462433483425e35d059999d": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "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_39842768d1274e8899ab932d587752a6",
+ "placeholder": "β",
+ "style": "IPY_MODEL_5ab44d0a65444d10b311bb9905d93bf0",
+ "value": "β4.96G/4.96Gβ[03:55<00:00,β20.8MB/s]"
+ }
+ },
+ "edee9a32368e4df2aa4a5bc87dccaf04": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "efd6fa6da2df4e55ade25161d07b2508": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "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": ""
+ }
+ },
+ "f0a136dc3667446b82cbf3d259dd98b6": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "HTMLModel",
+ "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_7281ea0a8ef3454a9a1c6c61e4115f97",
+ "placeholder": "β",
+ "style": "IPY_MODEL_c3cabdc750864c43816fe6a1b01e1dac",
+ "value": "Loadingβcheckpointβshards:β100%"
+ }
+ },
+ "f19e0f590c414fe9b0fb9b663a84175c": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "f35ad9d0b27541a991eab1f9a96134c0": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "ProgressStyleModel",
+ "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": ""
+ }
+ },
+ "f7ccf94d50ec44d38ab8f6cdbe610bf9": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ },
+ "ffea5b009edb4ee7952a37a849faeefa": {
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "model_name": "LayoutModel",
+ "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
+ }
+ }
+ }
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
\ No newline at end of file