{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "c0d9dc18aadb485086f5153f9b137368",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from huggingface_hub import notebook_login\n",
    "\n",
    "notebook_login()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "final_model\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/betty/miniconda3/envs/DP/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "from website_script import load\n",
    "tokenizer, model, gazetteers_for_matching = load()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "9e98fea6c2e440f29afb00c0ed5fedff",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "pytorch_model.bin:   0%|          | 0.00/502M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "CommitInfo(commit_url='https://huggingface.co/bettystr/NerRoB-czech/commit/0e6b09c5455288a3305b32e39626d89f7b3937dc', commit_message='Upload ExtendedEmbeddigsRobertaForTokenClassification', commit_description='', oid='0e6b09c5455288a3305b32e39626d89f7b3937dc', pr_url=None, pr_revision=None, pr_num=None)"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.push_to_hub(\"bettystr/NerRoB-czech\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Data from gazetteers.json has been loaded and saved as a pickle file at gazetteers.pkl.\n"
     ]
    }
   ],
   "source": [
    "import json\n",
    "import pickle\n",
    "def load_json_as_pickle(json_path, pickle_path):\n",
    "    \"\"\"\n",
    "    Load data from a JSON file and save it as a pickle file.\n",
    "\n",
    "    Parameters:\n",
    "        json_path (str): Path to the JSON file.\n",
    "        pickle_path (str): Path where the pickle file will be saved.\n",
    "    \"\"\"\n",
    "    # Load data from the JSON file\n",
    "    with open(json_path, 'r') as file:\n",
    "        data = json.load(file)\n",
    "    \n",
    "    # Save data to a pickle file\n",
    "    with open(pickle_path, 'wb') as file:\n",
    "        pickle.dump(data, file)\n",
    "\n",
    "    print(f\"Data from {json_path} has been loaded and saved as a pickle file at {pickle_path}.\")\n",
    "\n",
    "# Example usage\n",
    "json_path = 'gazetteers.json'\n",
    "pickle_path = 'gazetteers.pkl'\n",
    "load_json_as_pickle(json_path, pickle_path)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "DP",
   "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",
   "version": "3.10.14"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}