{
  "cells": [
    {
      "cell_type": "code",
      "metadata": {
        "collapsed": false,
        "scrolled": true
      },
      "source": [
        "%uv pip install datasets tokenizers huggingface_hub"
      ],
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[2mUsing Python 3.12.6 environment at: /usr/local\u001b[0m\r\n",
            "\u001b[37m\u280b\u001b[0m \u001b[2mResolving dependencies...                                                     \u001b[0m\r\u001b[2K\u001b[37m\u280b\u001b[0m \u001b[2mResolving dependencies...                                                     \u001b[0m\r\u001b[2K\u001b[37m\u2819\u001b[0m \u001b[2mResolving dependencies...                                                     \u001b[0m\r\u001b[2K\u001b[37m\u2819\u001b[0m \u001b[2mdatasets==5.0.0                                                               \u001b[0m\r\u001b[2K\u001b[37m\u2819\u001b[0m \u001b[2mtokenizers==0.22.0                                                            \u001b[0m\r\u001b[2K\u001b[37m\u2819\u001b[0m \u001b[2mhuggingface-hub==0.34.4                                                       \u001b[0m\r\u001b[2K\u001b[37m\u2839\u001b[0m \u001b[2mhuggingface-hub==0.34.4                                                       \u001b[0m\r\u001b[2K\u001b[37m\u2839\u001b[0m \u001b[2mfilelock==3.13.1                                                              \u001b[0m\r\u001b[2K\u001b[37m\u2839\u001b[0m \u001b[2mnumpy==2.1.2                                                                  \u001b[0m\r\u001b[2K\u001b[37m\u2839\u001b[0m \u001b[2mpyarrow==25.0.0                                                               \u001b[0m\r\u001b[2K\u001b[37m\u2839\u001b[0m \u001b[2mdill==0.4.1                                                                   \u001b[0m\r\u001b[2K\u001b[37m\u2839\u001b[0m \u001b[2mpandas==2.3.2                                                                 \u001b[0m\r\u001b[2K\u001b[37m\u2839\u001b[0m \u001b[2mnumpy==2.1.2                                                                  \u001b[0m\r\u001b[2K\u001b[37m\u2839\u001b[0m \u001b[2mrequests==2.32.5                                                              \u001b[0m\r\u001b[2K\u001b[37m\u2839\u001b[0m \u001b[2mhttpx==0.28.1                                                                 \u001b[0m\r\u001b[2K\u001b[37m\u2839\u001b[0m \u001b[2mtqdm==4.67.1                                                                  \u001b[0m\r\u001b[2K\u001b[37m\u2839\u001b[0m \u001b[2mxxhash==3.8.1                                                                 \u001b[0m\r\u001b[2K\u001b[37m\u2839\u001b[0m \u001b[2mmultiprocess==0.70.19                                                         \u001b[0m\r\u001b[2K\u001b[37m\u2839\u001b[0m \u001b[2mfsspec==2024.6.1                                                              \u001b[0m\r\u001b[2K\u001b[37m\u2839\u001b[0m \u001b[2mfsspec==2024.6.1                                                              \u001b[0m\r\u001b[2K\u001b[37m\u2839\u001b[0m \u001b[2mpackaging==25.0                                                               \u001b[0m\r\u001b[2K\u001b[37m\u2839\u001b[0m \u001b[2mpyyaml==6.0.2                                                                 \u001b[0m\r\u001b[2K\u001b[37m\u2839\u001b[0m \u001b[2mtyping-extensions==4.12.2                                                     \u001b[0m\r\u001b[2K\u001b[37m\u2839\u001b[0m \u001b[2mhf-xet==1.1.9                                                                 \u001b[0m\r\u001b[2K\u001b[37m\u2839\u001b[0m \u001b[2mhf-xet==1.1.9                                                                 \u001b[0m\r\u001b[2K\u001b[37m\u2839\u001b[0m \u001b[2mpython-dateutil==2.9.0.post0                                                  \u001b[0m\r\u001b[2K\u001b[37m\u2839\u001b[0m \u001b[2mpytz==2025.2                                                                  \u001b[0m\r\u001b[2K\u001b[2mResolved \u001b[1m37 packages\u001b[0m \u001b[2min 334ms\u001b[0m\u001b[0m\r\n",
            "\u001b[37m\u280b\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/0)                                                   \r\u001b[2K\u001b[37m\u280b\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/5)                                                   \r\u001b[2K\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/5)                                                   \r\u001b[2K\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/5)\r\n",
            "\u001b[2mdill      \u001b[0m \u001b[32m\u001b[2m------------------------------\u001b[0m\u001b[0m     0 B/117.21 KiB                    \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/5)\r\n",
            "\u001b[2mdill      \u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 14.84 KiB/117.21 KiB                  \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/5)\r\n",
            "\u001b[2mdill      \u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 14.84 KiB/117.21 KiB\r\n",
            "\u001b[2mxxhash    \u001b[0m \u001b[32m\u001b[2m------------------------------\u001b[0m\u001b[0m     0 B/215.30 KiB                    \u001b[2A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[2A\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/5)\r\n",
            "\u001b[2mdill      \u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 14.84 KiB/117.21 KiB\r\n",
            "\u001b[2mxxhash    \u001b[0m \u001b[32m---\u001b[2m---------------------------\u001b[0m\u001b[0m 14.87 KiB/215.30 KiB                  \u001b[2A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[2A\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/5)\r\n",
            "\u001b[2mdill      \u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 14.84 KiB/117.21 KiB\r\n",
            "\u001b[2mmultiprocess\u001b[0m \u001b[32m\u001b[2m------------------------------\u001b[0m\u001b[0m     0 B/146.76 KiB\r\n",
            "\u001b[2mxxhash    \u001b[0m \u001b[32m---\u001b[2m---------------------------\u001b[0m\u001b[0m 14.87 KiB/215.30 KiB                  \u001b[3A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[3A\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/5)\r\n",
            "\u001b[2mdill      \u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 14.84 KiB/117.21 KiB\r\n",
            "\u001b[2mmultiprocess\u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 16.00 KiB/146.76 KiB\r\n",
            "\u001b[2mxxhash    \u001b[0m \u001b[32m---\u001b[2m---------------------------\u001b[0m\u001b[0m 14.87 KiB/215.30 KiB                  \u001b[3A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[3A\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/5)\r\n",
            "\u001b[2mdill      \u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 14.84 KiB/117.21 KiB\r\n",
            "\u001b[2mmultiprocess\u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 16.00 KiB/146.76 KiB\r\n",
            "\u001b[2mxxhash    \u001b[0m \u001b[32m---\u001b[2m---------------------------\u001b[0m\u001b[0m 14.87 KiB/215.30 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m\u001b[2m------------------------------\u001b[0m\u001b[0m     0 B/47.77 MiB                     \u001b[4A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[4A\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/5)\r\n",
            "\u001b[2mdill      \u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 14.84 KiB/117.21 KiB\r\n",
            "\u001b[2mmultiprocess\u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 16.00 KiB/146.76 KiB\r\n",
            "\u001b[2mxxhash    \u001b[0m \u001b[32m---\u001b[2m---------------------------\u001b[0m\u001b[0m 14.87 KiB/215.30 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-\u001b[2m-----------------------------\u001b[0m\u001b[0m 14.83 KiB/47.77 MiB                   \u001b[4A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[4A\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/5)\r\n",
            "\u001b[2mdill      \u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 14.84 KiB/117.21 KiB\r\n",
            "\u001b[2mmultiprocess\u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 16.00 KiB/146.76 KiB\r\n",
            "\u001b[2mxxhash    \u001b[0m \u001b[32m---\u001b[2m---------------------------\u001b[0m\u001b[0m 14.87 KiB/215.30 KiB\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m\u001b[2m------------------------------\u001b[0m\u001b[0m     0 B/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-\u001b[2m-----------------------------\u001b[0m\u001b[0m 14.83 KiB/47.77 MiB                   \u001b[5A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[5A\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/5)\r\n",
            "\u001b[2mdill      \u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 14.84 KiB/117.21 KiB\r\n",
            "\u001b[2mmultiprocess\u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 16.00 KiB/146.76 KiB\r\n",
            "\u001b[2mxxhash    \u001b[0m \u001b[32m---\u001b[2m---------------------------\u001b[0m\u001b[0m 14.87 KiB/215.30 KiB\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m-\u001b[2m-----------------------------\u001b[0m\u001b[0m 14.87 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-\u001b[2m-----------------------------\u001b[0m\u001b[0m 14.83 KiB/47.77 MiB                   \u001b[5A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[5A\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/5)\r\n",
            "\u001b[2mdill      \u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 14.84 KiB/117.21 KiB\r\n",
            "\u001b[2mmultiprocess\u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 16.00 KiB/146.76 KiB\r\n",
            "\u001b[2mxxhash    \u001b[0m \u001b[32m---\u001b[2m---------------------------\u001b[0m\u001b[0m 14.87 KiB/215.30 KiB\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m--\u001b[2m----------------------------\u001b[0m\u001b[0m 30.87 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-\u001b[2m-----------------------------\u001b[0m\u001b[0m 14.83 KiB/47.77 MiB                   \u001b[5A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[5A\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/5)\r\n",
            "\u001b[2mdill      \u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 14.84 KiB/117.21 KiB\r\n",
            "\u001b[2mmultiprocess\u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 16.00 KiB/146.76 KiB\r\n",
            "\u001b[2mxxhash    \u001b[0m \u001b[32m---\u001b[2m---------------------------\u001b[0m\u001b[0m 14.87 KiB/215.30 KiB\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m---\u001b[2m---------------------------\u001b[0m\u001b[0m 46.87 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-\u001b[2m-----------------------------\u001b[0m\u001b[0m 14.83 KiB/47.77 MiB                   \u001b[5A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[5A\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/5)\r\n",
            "\u001b[2mdill      \u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 14.84 KiB/117.21 KiB\r\n",
            "\u001b[2mmultiprocess\u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 16.00 KiB/146.76 KiB\r\n",
            "\u001b[2mxxhash    \u001b[0m \u001b[32m---\u001b[2m---------------------------\u001b[0m\u001b[0m 14.87 KiB/215.30 KiB\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 62.87 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-\u001b[2m-----------------------------\u001b[0m\u001b[0m 14.83 KiB/47.77 MiB                   \u001b[5A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[5A\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/5)\r\n",
            "\u001b[2mdill      \u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 14.84 KiB/117.21 KiB\r\n",
            "\u001b[2mmultiprocess\u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 16.00 KiB/146.76 KiB\r\n",
            "\u001b[2mxxhash    \u001b[0m \u001b[32m---\u001b[2m---------------------------\u001b[0m\u001b[0m 14.87 KiB/215.30 KiB\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m-----\u001b[2m-------------------------\u001b[0m\u001b[0m 78.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-\u001b[2m-----------------------------\u001b[0m\u001b[0m 14.83 KiB/47.77 MiB                   \u001b[5A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[5A\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/5)\r\n",
            "\u001b[2mdill      \u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 14.84 KiB/117.21 KiB\r\n",
            "\u001b[2mmultiprocess\u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 16.00 KiB/146.76 KiB\r\n",
            "\u001b[2mxxhash    \u001b[0m \u001b[32m-----\u001b[2m-------------------------\u001b[0m\u001b[0m 30.87 KiB/215.30 KiB\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m-----\u001b[2m-------------------------\u001b[0m\u001b[0m 78.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-\u001b[2m-----------------------------\u001b[0m\u001b[0m 14.83 KiB/47.77 MiB                   \u001b[5A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[5A\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/5)\r\n",
            "\u001b[2mdill      \u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 14.84 KiB/117.21 KiB\r\n",
            "\u001b[2mmultiprocess\u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 16.00 KiB/146.76 KiB\r\n",
            "\u001b[2mxxhash    \u001b[0m \u001b[32m-------\u001b[2m-----------------------\u001b[0m\u001b[0m 46.87 KiB/215.30 KiB\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m-----\u001b[2m-------------------------\u001b[0m\u001b[0m 78.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-\u001b[2m-----------------------------\u001b[0m\u001b[0m 14.83 KiB/47.77 MiB                   \u001b[5A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[5A\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/5)\r\n",
            "\u001b[2mdill      \u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 14.84 KiB/117.21 KiB\r\n",
            "\u001b[2mmultiprocess\u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 16.00 KiB/146.76 KiB\r\n",
            "\u001b[2mxxhash    \u001b[0m \u001b[32m---------\u001b[2m---------------------\u001b[0m\u001b[0m 62.87 KiB/215.30 KiB\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m-----\u001b[2m-------------------------\u001b[0m\u001b[0m 78.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-\u001b[2m-----------------------------\u001b[0m\u001b[0m 14.83 KiB/47.77 MiB                   \u001b[5A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[5A\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/5)\r\n",
            "\u001b[2mdill      \u001b[0m \u001b[32m--------\u001b[2m----------------------\u001b[0m\u001b[0m 30.84 KiB/117.21 KiB\r\n",
            "\u001b[2mmultiprocess\u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 16.00 KiB/146.76 KiB\r\n",
            "\u001b[2mxxhash    \u001b[0m \u001b[32m---------------------------\u001b[2m---\u001b[0m\u001b[0m 187.97 KiB/215.30 KiB\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m-----\u001b[2m-------------------------\u001b[0m\u001b[0m 78.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-\u001b[2m-----------------------------\u001b[0m\u001b[0m 14.83 KiB/47.77 MiB                   \u001b[5A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[5A\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/5)\r\n",
            "\u001b[2mdill      \u001b[0m \u001b[32m---------------------\u001b[2m---------\u001b[0m\u001b[0m 78.84 KiB/117.21 KiB\r\n",
            "\u001b[2mmultiprocess\u001b[0m \u001b[32m----------\u001b[2m--------------------\u001b[0m\u001b[0m 48.00 KiB/146.76 KiB\r\n",
            "\u001b[2mxxhash    \u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 215.30 KiB/215.30 KiB\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m--------\u001b[2m----------------------\u001b[0m\u001b[0m 142.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-\u001b[2m-----------------------------\u001b[0m\u001b[0m 604.08 KiB/47.77 MiB                  \u001b[5A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[5A\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/5)\r\n",
            "\u001b[2mdill      \u001b[0m \u001b[32m---------------------\u001b[2m---------\u001b[0m\u001b[0m 78.84 KiB/117.21 KiB\r\n",
            "\u001b[2mmultiprocess\u001b[0m \u001b[32m----------\u001b[2m--------------------\u001b[0m\u001b[0m 48.00 KiB/146.76 KiB\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m---------\u001b[2m---------------------\u001b[0m\u001b[0m 158.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-\u001b[2m-----------------------------\u001b[0m\u001b[0m 604.08 KiB/47.77 MiB                  \u001b[4A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[4A\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/5)\r\n",
            "\u001b[2mdill      \u001b[0m \u001b[32m-------------------------\u001b[2m-----\u001b[0m\u001b[0m 94.84 KiB/117.21 KiB\r\n",
            "\u001b[2mmultiprocess\u001b[0m \u001b[32m--------------------\u001b[2m----------\u001b[0m\u001b[0m 93.48 KiB/146.76 KiB\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m---------------\u001b[2m---------------\u001b[0m\u001b[0m 254.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-\u001b[2m-----------------------------\u001b[0m\u001b[0m 1.34 MiB/47.77 MiB                    \u001b[4A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[4A\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (0/5)\r\n",
            "\u001b[2mdill      \u001b[0m \u001b[32m-------------------------\u001b[2m-----\u001b[0m\u001b[0m 94.84 KiB/117.21 KiB\r\n",
            "\u001b[2mmultiprocess\u001b[0m \u001b[32m-----------------------------\u001b[2m-\u001b[0m\u001b[0m 141.48 KiB/146.76 KiB\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m---------------\u001b[2m---------------\u001b[0m\u001b[0m 254.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m--\u001b[2m----------------------------\u001b[0m\u001b[0m 1.97 MiB/47.77 MiB                    \u001b[4A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[4A\u001b[37m\u2839\u001b[0m \u001b[2mPreparing packages...\u001b[0m (1/5)\r\n",
            "\u001b[2mdill      \u001b[0m \u001b[32m-----------------------------\u001b[2m-\u001b[0m\u001b[0m 110.84 KiB/117.21 KiB\r\n",
            "\u001b[2mmultiprocess\u001b[0m \u001b[32m-----------------------------\u001b[2m-\u001b[0m\u001b[0m 141.48 KiB/146.76 KiB\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m-----------------\u001b[2m-------------\u001b[0m\u001b[0m 302.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m--\u001b[2m----------------------------\u001b[0m\u001b[0m 2.23 MiB/47.77 MiB                    \u001b[4A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[4A\u001b[37m\u2839\u001b[0m \u001b[2mPreparing packages...\u001b[0m (1/5)\r\n",
            "\u001b[2mdill      \u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 117.21 KiB/117.21 KiB\r\n",
            "\u001b[2mmultiprocess\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 146.76 KiB/146.76 KiB\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m-------------------\u001b[2m-----------\u001b[0m\u001b[0m 334.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m--\u001b[2m----------------------------\u001b[0m\u001b[0m 2.57 MiB/47.77 MiB                    \u001b[4A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[4A\u001b[37m\u2839\u001b[0m \u001b[2mPreparing packages...\u001b[0m (1/5)\r\n",
            "\u001b[2mmultiprocess\u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 146.76 KiB/146.76 KiB\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m-------------------\u001b[2m-----------\u001b[0m\u001b[0m 334.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m--\u001b[2m----------------------------\u001b[0m\u001b[0m 2.57 MiB/47.77 MiB                    \u001b[3A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[3A\u001b[37m\u2839\u001b[0m \u001b[2mPreparing packages...\u001b[0m (1/5)\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m-------------------\u001b[2m-----------\u001b[0m\u001b[0m 334.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m--\u001b[2m----------------------------\u001b[0m\u001b[0m 2.65 MiB/47.77 MiB                    \u001b[2A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[2A\u001b[37m\u2839\u001b[0m \u001b[2mPreparing packages...\u001b[0m (1/5)\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m---------------------\u001b[2m---------\u001b[0m\u001b[0m 366.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m--\u001b[2m----------------------------\u001b[0m\u001b[0m 2.94 MiB/47.77 MiB                    \u001b[2A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[2A\u001b[37m\u2839\u001b[0m \u001b[2mPreparing packages...\u001b[0m (1/5)\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m---------------------\u001b[2m---------\u001b[0m\u001b[0m 366.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m---\u001b[2m---------------------------\u001b[0m\u001b[0m 4.53 MiB/47.77 MiB                    \u001b[2A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[2A\u001b[37m\u2838\u001b[0m \u001b[2mPreparing packages...\u001b[0m (3/5)\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m---------------------\u001b[2m---------\u001b[0m\u001b[0m 366.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m----\u001b[2m--------------------------\u001b[0m\u001b[0m 5.61 MiB/47.77 MiB                    \u001b[2A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[2A\u001b[37m\u2838\u001b[0m \u001b[2mPreparing packages...\u001b[0m (3/5)\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m---------------------\u001b[2m---------\u001b[0m\u001b[0m 366.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-----\u001b[2m-------------------------\u001b[0m\u001b[0m 6.78 MiB/47.77 MiB                    \u001b[2A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[2A\u001b[37m\u2838\u001b[0m \u001b[2mPreparing packages...\u001b[0m (3/5)\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m-----------------------\u001b[2m-------\u001b[0m\u001b[0m 398.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m------\u001b[2m------------------------\u001b[0m\u001b[0m 8.48 MiB/47.77 MiB                    \u001b[2A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[2A\u001b[37m\u2838\u001b[0m \u001b[2mPreparing packages...\u001b[0m (3/5)\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m-----------------------\u001b[2m-------\u001b[0m\u001b[0m 398.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-------\u001b[2m-----------------------\u001b[0m\u001b[0m 10.33 MiB/47.77 MiB                   \u001b[2A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[2A\u001b[37m\u283c\u001b[0m \u001b[2mPreparing packages...\u001b[0m (3/5)\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m-----------------------\u001b[2m-------\u001b[0m\u001b[0m 414.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m--------\u001b[2m----------------------\u001b[0m\u001b[0m 12.28 MiB/47.77 MiB                   \u001b[2A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[2A\u001b[37m\u283c\u001b[0m \u001b[2mPreparing packages...\u001b[0m (3/5)\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m------------------------\u001b[2m------\u001b[0m\u001b[0m 430.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m--------\u001b[2m----------------------\u001b[0m\u001b[0m 12.56 MiB/47.77 MiB                   \u001b[2A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[2A\u001b[37m\u283c\u001b[0m \u001b[2mPreparing packages...\u001b[0m (3/5)\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m------------------------\u001b[2m------\u001b[0m\u001b[0m 430.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m---------\u001b[2m---------------------\u001b[0m\u001b[0m 14.31 MiB/47.77 MiB                   \u001b[2A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[2A\u001b[37m\u283c\u001b[0m \u001b[2mPreparing packages...\u001b[0m (3/5)\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m-------------------------\u001b[2m-----\u001b[0m\u001b[0m 445.91 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m----------\u001b[2m--------------------\u001b[0m\u001b[0m 14.75 MiB/47.77 MiB                   \u001b[2A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[2A\u001b[37m\u2834\u001b[0m \u001b[2mPreparing packages...\u001b[0m (3/5)\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 526.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-----------\u001b[2m-------------------\u001b[0m\u001b[0m 16.48 MiB/47.77 MiB                   \u001b[2A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[2A\u001b[37m\u2834\u001b[0m \u001b[2mPreparing packages...\u001b[0m (3/5)\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 526.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m------------\u001b[2m------------------\u001b[0m\u001b[0m 18.09 MiB/47.77 MiB                   \u001b[2A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[2A\u001b[37m\u2834\u001b[0m \u001b[2mPreparing packages...\u001b[0m (3/5)\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 526.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m------------\u001b[2m------------------\u001b[0m\u001b[0m 18.59 MiB/47.77 MiB                   \u001b[2A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[2A\u001b[37m\u2834\u001b[0m \u001b[2mPreparing packages...\u001b[0m (3/5)\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 526.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-------------\u001b[2m-----------------\u001b[0m\u001b[0m 19.62 MiB/47.77 MiB                   \u001b[2A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[2A\u001b[37m\u2826\u001b[0m \u001b[2mPreparing packages...\u001b[0m (3/5)\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 526.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-------------\u001b[2m-----------------\u001b[0m\u001b[0m 20.48 MiB/47.77 MiB                   \u001b[2A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[2A\u001b[37m\u2826\u001b[0m \u001b[2mPreparing packages...\u001b[0m (3/5)\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 526.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m--------------\u001b[2m----------------\u001b[0m\u001b[0m 21.61 MiB/47.77 MiB                   \u001b[2A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[2A\u001b[37m\u2826\u001b[0m \u001b[2mPreparing packages...\u001b[0m (3/5)\r\n",
            "\u001b[2mdatasets  \u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 542.02 KiB/542.07 KiB\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m---------------\u001b[2m---------------\u001b[0m\u001b[0m 22.69 MiB/47.77 MiB                   \u001b[2A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[2A\u001b[37m\u2826\u001b[0m \u001b[2mPreparing packages...\u001b[0m (3/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m----------------\u001b[2m--------------\u001b[0m\u001b[0m 24.05 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u2826\u001b[0m \u001b[2mPreparing packages...\u001b[0m (3/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m----------------\u001b[2m--------------\u001b[0m\u001b[0m 24.34 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u2827\u001b[0m \u001b[2mPreparing packages...\u001b[0m (4/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-----------------\u001b[2m-------------\u001b[0m\u001b[0m 25.70 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u2827\u001b[0m \u001b[2mPreparing packages...\u001b[0m (4/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-----------------\u001b[2m-------------\u001b[0m\u001b[0m 26.39 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u2827\u001b[0m \u001b[2mPreparing packages...\u001b[0m (4/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m------------------\u001b[2m------------\u001b[0m\u001b[0m 27.73 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u2827\u001b[0m \u001b[2mPreparing packages...\u001b[0m (4/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-------------------\u001b[2m-----------\u001b[0m\u001b[0m 29.06 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u2807\u001b[0m \u001b[2mPreparing packages...\u001b[0m (4/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-------------------\u001b[2m-----------\u001b[0m\u001b[0m 30.05 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u2807\u001b[0m \u001b[2mPreparing packages...\u001b[0m (4/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m--------------------\u001b[2m----------\u001b[0m\u001b[0m 31.45 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u2807\u001b[0m \u001b[2mPreparing packages...\u001b[0m (4/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m---------------------\u001b[2m---------\u001b[0m\u001b[0m 31.98 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u280b\u001b[0m \u001b[2mPreparing packages...\u001b[0m (4/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m----------------------\u001b[2m--------\u001b[0m\u001b[0m 33.69 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u280b\u001b[0m \u001b[2mPreparing packages...\u001b[0m (4/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m----------------------\u001b[2m--------\u001b[0m\u001b[0m 34.61 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u280b\u001b[0m \u001b[2mPreparing packages...\u001b[0m (4/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-----------------------\u001b[2m-------\u001b[0m\u001b[0m 36.00 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u280b\u001b[0m \u001b[2mPreparing packages...\u001b[0m (4/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m------------------------\u001b[2m------\u001b[0m\u001b[0m 37.70 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u280b\u001b[0m \u001b[2mPreparing packages...\u001b[0m (4/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m------------------------\u001b[2m------\u001b[0m\u001b[0m 37.87 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (4/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-------------------------\u001b[2m-----\u001b[0m\u001b[0m 39.14 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (4/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-------------------------\u001b[2m-----\u001b[0m\u001b[0m 39.75 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (4/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m---------------------------\u001b[2m---\u001b[0m\u001b[0m 41.64 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u2819\u001b[0m \u001b[2mPreparing packages...\u001b[0m (4/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m----------------------------\u001b[2m--\u001b[0m\u001b[0m 43.42 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u2839\u001b[0m \u001b[2mPreparing packages...\u001b[0m (4/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-----------------------------\u001b[2m-\u001b[0m\u001b[0m 44.81 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u2839\u001b[0m \u001b[2mPreparing packages...\u001b[0m (4/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-----------------------------\u001b[2m-\u001b[0m\u001b[0m 45.75 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u2839\u001b[0m \u001b[2mPreparing packages...\u001b[0m (4/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m-----------------------------\u001b[2m-\u001b[0m\u001b[0m 46.17 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u2839\u001b[0m \u001b[2mPreparing packages...\u001b[0m (4/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 46.47 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u2838\u001b[0m \u001b[2mPreparing packages...\u001b[0m (4/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 46.62 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u2838\u001b[0m \u001b[2mPreparing packages...\u001b[0m (4/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 46.87 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u2838\u001b[0m \u001b[2mPreparing packages...\u001b[0m (4/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 47.09 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u2838\u001b[0m \u001b[2mPreparing packages...\u001b[0m (4/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 47.36 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u283c\u001b[0m \u001b[2mPreparing packages...\u001b[0m (4/5)\r\n",
            "\u001b[2mpyarrow   \u001b[0m \u001b[32m------------------------------\u001b[2m\u001b[0m\u001b[0m 47.64 MiB/47.77 MiB                   \u001b[1A\r\u001b[2K\u001b[1B\r\u001b[2K\u001b[1A\u001b[37m\u283c\u001b[0m \u001b[2mPreparing packages...\u001b[0m (4/5)                                                   \r\u001b[2K\u001b[2mPrepared \u001b[1m5 packages\u001b[0m \u001b[2min 2.47s\u001b[0m\u001b[0m\r\n",
            "\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591 [0/0] \u001b[2mInstalling wheels...                                 \u001b[0m\r\u001b[2K\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591 [0/5] \u001b[2mInstalling wheels...                                 \u001b[0m\r\u001b[2K\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591 [0/5] \u001b[2mxxhash==3.8.1                                        \u001b[0m\r\u001b[2K\u2588\u2588\u2588\u2588\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591 [1/5] \u001b[2mxxhash==3.8.1                                        \u001b[0m\r\u001b[2K\u2588\u2588\u2588\u2588\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591 [1/5] \u001b[2mmultiprocess==0.70.19                                \u001b[0m\r\u001b[2K\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591 [2/5] \u001b[2mmultiprocess==0.70.19                                \u001b[0m\r\u001b[2K\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591 [2/5] \u001b[2mdill==0.4.1                                          \u001b[0m\r\u001b[2K\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591 [3/5] \u001b[2mdill==0.4.1                                          \u001b[0m\r\u001b[2K\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2591\u2591\u2591\u2591\u2591\u2591\u2591\u2591 [3/5] \u001b[2mdatasets==5.0.0                                      \u001b[0m\r\u001b[2K\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2591\u2591\u2591\u2591 [4/5] \u001b[2mdatasets==5.0.0                                      \u001b[0m\r\u001b[2K\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2591\u2591\u2591\u2591 [4/5] \u001b[2mpyarrow==25.0.0                                      \u001b[0m\r\u001b[2K\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588 [5/5] \u001b[2mpyarrow==25.0.0                                      \u001b[0m\r\u001b[2K\u001b[2mInstalled \u001b[1m5 packages\u001b[0m \u001b[2min 195ms\u001b[0m\u001b[0m\r\n",
            " \u001b[32m+\u001b[39m \u001b[1mdatasets\u001b[0m\u001b[2m==5.0.0\u001b[0m\r\n",
            " \u001b[32m+\u001b[39m \u001b[1mdill\u001b[0m\u001b[2m==0.4.1\u001b[0m\r\n",
            " \u001b[32m+\u001b[39m \u001b[1mmultiprocess\u001b[0m\u001b[2m==0.70.19\u001b[0m\r\n",
            " \u001b[32m+\u001b[39m \u001b[1mpyarrow\u001b[0m\u001b[2m==25.0.0\u001b[0m\r\n",
            " \u001b[32m+\u001b[39m \u001b[1mxxhash\u001b[0m\u001b[2m==3.8.1\u001b[0m\r\n",
            "Note: you may need to restart the kernel to use updated packages.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "collapsed": false,
        "scrolled": true
      },
      "source": [
        "import torch\n",
        "import torch.nn as nn\n",
        "import torch.optim as optim\n",
        "from datasets import Dataset, load_dataset, concatenate_datasets\n",
        "from tokenizers import Tokenizer\n",
        "from tokenizers.models import WordLevel\n",
        "from tokenizers.pre_tokenizers import Whitespace\n",
        "from tokenizers.trainers import WordLevelTrainer\n",
        "from huggingface_hub import PyTorchModelHubMixin, notebook_login"
      ],
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "collapsed": false,
        "scrolled": true
      },
      "source": [
        "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
        "default_config = dict(\n",
        "\tcontext_window=2,\n",
        "\tx_max=100,\n",
        "\talpha=0.75,\n",
        "\tvocab_size=0,\n",
        "\tembedding_dim=200\n",
        ")"
      ],
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "collapsed": false,
        "scrolled": true
      },
      "source": [
        "# Preparing our dataset\n",
        "ds_train = load_dataset(\"bobox/OpenbookQA-4ST\", data_dir=\"filtered\", split=\"train+validation\", revision=\"refs/convert/parquet\")\n",
        "ds_test = load_dataset(\"bobox/OpenbookQA-4ST\", data_dir=\"filtered\", split=\"test\", revision=\"refs/convert/parquet\")\n",
        "ds = concatenate_datasets([ds_train, ds_test])\n",
        "ds_len = len(ds_train)+len(ds_test)"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "2ee975f77d6b4268bb39cf17905e846d",
              "version_minor": 0.0,
              "version_major": 2.0
            },
            "text/plain": "filtered/train/0000.parquet:   0%|          | 0.00/328k [00:00<?, ?B/s]"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "5c1ffc35e1a8491488a675487cae0ad9",
              "version_minor": 0.0,
              "version_major": 2.0
            },
            "text/plain": "filtered/validation/0000.parquet:   0%|          | 0.00/41.8k [00:00<?, ?B/s]"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "1a6ca3c8fa524677b54ecb88e85c9246",
              "version_minor": 0.0,
              "version_major": 2.0
            },
            "text/plain": "filtered/test/0000.parquet:   0%|          | 0.00/48.2k [00:00<?, ?B/s]"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "297250b3fa9e471fb63d9bb256744153",
              "version_minor": 0.0,
              "version_major": 2.0
            },
            "text/plain": "Generating train split: 0 examples [00:00, ? examples/s]"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "a5eac241d5984633903568fc5cb2bd0c",
              "version_minor": 0.0,
              "version_major": 2.0
            },
            "text/plain": "Generating validation split: 0 examples [00:00, ? examples/s]"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "e6484a18faa14505b25e2174c074fe48",
              "version_minor": 0.0,
              "version_major": 2.0
            },
            "text/plain": "Generating test split: 0 examples [00:00, ? examples/s]"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "collapsed": false,
        "scrolled": true
      },
      "source": [
        "# Preparing tokenizer\n",
        "tokenizer = Tokenizer(WordLevel(unk_token=\"[UNK]\"))\n",
        "tokenizer_trainer = WordLevelTrainer(special_tokens=[\"[UNK]\"])\n",
        "tokenizer.pre_tokenizer = Whitespace()\n",
        "\n",
        "def batcher(n_batch=1000):\n",
        "\tfor i in range(0, ds_len, n_batch):\n",
        "\t\tyield ds[\"fact\"][i : i + n_batch]\n",
        "\n",
        "tokenizer.train_from_iterator(batcher(), trainer=tokenizer_trainer, length=ds_len)\n",
        "\n",
        "tokenizer.save(\"tokenizer.json\")"
      ],
      "execution_count": 5,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "collapsed": false,
        "scrolled": true
      },
      "source": [
        "# Preparing word-to-word co-occurences matrix\n",
        "N = tokenizer.get_vocab_size()\n",
        "X = torch.zeros(N, N)\n",
        "\n",
        "def cooc_gen(batch):\n",
        "\tXp = torch.zeros(N, N)\n",
        "\n",
        "\tfor fact in batch[\"fact\"]:\n",
        "\t\tids = tokenizer.encode(fact).ids\n",
        "\t\tfor idx in range(len(ids)):\n",
        "\t\t\ti = ids[idx]\n",
        "\t\t\tfor d in range(1, default_config[\"context_window\"]+1):\n",
        "\t\t\t\tif idx+d < len(ids):\n",
        "\t\t\t\t\tj = ids[idx+d]\n",
        "\t\t\t\t\tXp[i, j] += 1.0/d\n",
        "\n",
        "\t\t\t\tif idx-d >= 0:\n",
        "\t\t\t\t\tj = ids[idx-d]\n",
        "\t\t\t\t\tXp[i, j] += 1.0/d\n",
        "\n",
        "\treturn dict(Xp=Xp)\n",
        "\n",
        "Xs = ds_train.map(cooc_gen, batched=True, remove_columns=ds_train.column_names)\n",
        "\n",
        "for Xp in Xs[\"Xp\"]:\n",
        "\tX.add_(torch.tensor(Xp))"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "5b09329954f84037afe7587df86bf045",
              "version_minor": 0.0,
              "version_major": 2.0
            },
            "text/plain": "Map:   0%|          | 0/3004 [00:00<?, ? examples/s]"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "collapsed": false,
        "scrolled": true
      },
      "source": [
        "X"
      ],
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 7,
          "data": {
            "text/plain": "tensor([[0.0000e+00, 3.5670e+03, 3.3620e+03,  ..., 3.0000e+00, 3.0000e+00,\n         0.0000e+00],\n        [0.0000e+00, 3.5670e+03, 3.3620e+03,  ..., 3.0000e+00, 3.0000e+00,\n         0.0000e+00],\n        [0.0000e+00, 3.5670e+03, 3.3620e+03,  ..., 3.0000e+00, 3.0000e+00,\n         0.0000e+00],\n        ...,\n        [0.0000e+00, 3.5670e+03, 3.3620e+03,  ..., 3.0000e+00, 3.0000e+00,\n         0.0000e+00],\n        [0.0000e+00, 3.5670e+03, 3.3620e+03,  ..., 3.0000e+00, 3.0000e+00,\n         0.0000e+00],\n        [0.0000e+00, 3.5670e+03, 3.3620e+03,  ..., 3.0000e+00, 3.0000e+00,\n         0.0000e+00]])"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "collapsed": false,
        "scrolled": true
      },
      "source": [
        "# Preparing model\n",
        "class GloVe(nn.Module, PyTorchModelHubMixin):\n",
        "\tdef __init__(self, config):\n",
        "\t\tnn.Module.__init__(self)\n",
        "\n",
        "\t\tself.context_window = config[\"context_window\"]\n",
        "\t\tself.x_max = config[\"x_max\"]\n",
        "\t\tself.alpha = config[\"alpha\"]\n",
        "\t\tself.vocab_size = config[\"vocab_size\"]\n",
        "\t\tself.embedding_dim = config[\"embedding_dim\"]\n",
        "\n",
        "\t\tself.wi = nn.Embedding(self.vocab_size, self.embedding_dim)\n",
        "\t\tself.wj = nn.Embedding(self.vocab_size, self.embedding_dim)\n",
        "\n",
        "\t\tself.bi = nn.Embedding(self.vocab_size, 1)\n",
        "\t\tself.bj = nn.Embedding(self.vocab_size, 1)\n",
        "\n",
        "\tdef f(self, Xij):\n",
        "\t\treturn torch.clamp((Xij / self.x_max) ** self.alpha, max=1)\n",
        "\n",
        "\tdef forward(self, i, j, Xij):\n",
        "\t\twi = self.wi(i)\n",
        "\t\twj = self.wj(j)\n",
        "\n",
        "\t\tbi = self.bi(i).squeeze(-1)\n",
        "\t\tbj = self.bj(j).squeeze(-1)\n",
        "\n",
        "\t\tweighting = self.f(Xij)\n",
        "\n",
        "\t\tdot = (wi * wj).sum(dim=-1)\n",
        "\t\tepsilon = 1e-8\n",
        "\t\tloss = weighting * (dot + bi + bj - torch.log(Xij + epsilon)) ** 2\n",
        "\t\treturn torch.mean(loss)"
      ],
      "execution_count": 8,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "collapsed": false,
        "scrolled": false
      },
      "source": [
        "# Train model\n",
        "default_config[\"vocab_size\"] = N\n",
        "\n",
        "def dsd_gen():\n",
        "\tfor i in range(N):\n",
        "\t\tfor j in range(N):\n",
        "\t\t\tXij = X[i, j]\n",
        "\t\t\tyield dict(i=i, j=j, Xij=Xij)\n",
        "\n",
        "ds_train = Dataset.from_generator(dsd_gen)\n",
        "\n",
        "dl = torch.utils.data.DataLoader(\n",
        "\tds_train.with_format(\"torch\"),\n",
        "\tbatch_size=10240*2, shuffle=True,\n",
        "    num_workers=8, persistent_workers=True, prefetch_factor=2,\n",
        "\tpin_memory=True if device.type == \"cuda\" else False\n",
        ")\n",
        "PurpleGloVe = GloVe(config=default_config).to(device)\n",
        "optimizer = optim.Adam(PurpleGloVe.parameters(), lr=1e-3)\n",
        "\n",
        "for epoch in range(20):\n",
        "\tfor batch in dl:\n",
        "\t\ti = batch[\"i\"].to(device, non_blocking=True)\n",
        "\t\tj = batch[\"j\"].to(device, non_blocking=True)\n",
        "\t\tXij = batch[\"Xij\"].to(device, non_blocking=True)\n",
        "\n",
        "\t\toptimizer.zero_grad()\n",
        "\t\tloss = PurpleGloVe(i, j, Xij)\n",
        "\t\tloss.backward()\n",
        "\t\toptimizer.step()\n",
        "        \n",
        "\tloss = loss.item()\n",
        "\tprint(f\"{epoch = } | {loss = }\")"
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
            "To disable this warning, you can either:\n",
            "\t- Avoid using `tokenizers` before the fork if possible\n",
            "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n",
            "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
            "To disable this warning, you can either:\n",
            "\t- Avoid using `tokenizers` before the fork if possible\n",
            "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n",
            "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
            "To disable this warning, you can either:\n",
            "\t- Avoid using `tokenizers` before the fork if possible\n",
            "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n",
            "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
            "To disable this warning, you can either:\n",
            "\t- Avoid using `tokenizers` before the fork if possible\n",
            "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n",
            "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
            "To disable this warning, you can either:\n",
            "\t- Avoid using `tokenizers` before the fork if possible\n",
            "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n",
            "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
            "To disable this warning, you can either:\n",
            "\t- Avoid using `tokenizers` before the fork if possible\n",
            "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n",
            "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
            "To disable this warning, you can either:\n",
            "\t- Avoid using `tokenizers` before the fork if possible\n",
            "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n",
            "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
            "To disable this warning, you can either:\n",
            "\t- Avoid using `tokenizers` before the fork if possible\n",
            "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "epoch = 0 | loss = 54.24422073364258\n",
            "epoch = 1 | loss = 48.685298919677734\n",
            "epoch = 2 | loss = 40.175540924072266\n",
            "epoch = 3 | loss = 37.30278396606445\n",
            "epoch = 4 | loss = 33.79242706298828\n",
            "epoch = 5 | loss = 28.181514739990234\n",
            "epoch = 6 | loss = 26.533447265625\n",
            "epoch = 7 | loss = 22.93697166442871\n",
            "epoch = 8 | loss = 20.815990447998047\n",
            "epoch = 9 | loss = 18.19524574279785\n",
            "epoch = 10 | loss = 15.720626831054688\n",
            "epoch = 11 | loss = 14.857860565185547\n",
            "epoch = 12 | loss = 12.9190034866333\n",
            "epoch = 13 | loss = 11.276094436645508\n",
            "epoch = 14 | loss = 9.894501686096191\n",
            "epoch = 15 | loss = 8.92365550994873\n",
            "epoch = 16 | loss = 7.816685199737549\n",
            "epoch = 17 | loss = 6.968708038330078\n",
            "epoch = 18 | loss = 6.078571796417236\n",
            "epoch = 19 | loss = 5.477797985076904\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "collapsed": false,
        "scrolled": true
      },
      "source": [
        "notebook_login()"
      ],
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "429339521efd41b7ba3ecf2ea0f157fc",
              "version_minor": 0.0,
              "version_major": 2.0
            },
            "text/plain": "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv\u2026"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "collapsed": false,
        "scrolled": true
      },
      "source": [
        "PurpleGloVe.push_to_hub(\"LocalWisdom/PurpleGloVe\")"
      ],
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "af3acf27a2584986873a24c5196ff6d3",
              "version_minor": 0.0,
              "version_major": 2.0
            },
            "text/plain": "Processing Files (0 / 0)                : |          |  0.00B /  0.00B            "
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "1ce04f8aa27d430394a1ac9c0427671c",
              "version_minor": 0.0,
              "version_major": 2.0
            },
            "text/plain": "New Data Upload                         : |          |  0.00B /  0.00B            "
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "e2deac207e454a72b3ab62eaefc22ee5",
              "version_minor": 0.0,
              "version_major": 2.0
            },
            "text/plain": "  ...isdom/PurpleGloVe/model.safetensors: 100%|##########| 2.80MB / 2.80MB            "
          },
          "metadata": {}
        },
        {
          "output_type": "execute_result",
          "execution_count": 12,
          "data": {
            "text/plain": "CommitInfo(commit_url='https://huggingface.co/LocalWisdom/PurpleGloVe/commit/cbc608291f150e945655a4a8a0ebe089d6f640a7', commit_message='Push model using huggingface_hub.', commit_description='', oid='cbc608291f150e945655a4a8a0ebe089d6f640a7', pr_url=None, repo_url=RepoUrl('https://huggingface.co/LocalWisdom/PurpleGloVe', endpoint='https://huggingface.co', repo_type='model', repo_id='LocalWisdom/PurpleGloVe'), pr_revision=None, pr_num=None)"
          },
          "metadata": {}
        }
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": "Python",
      "language": "python",
      "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"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
}