{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "d:\\FYP\\lilt-app-without-fd\\lilt-env\\lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    }
   ],
   "source": [
    "from transformers import LiltModel, AutoTokenizer, LiltForTokenClassification"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Download tokenizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "('models/lilt-tokenizer\\\\tokenizer_config.json',\n",
       " 'models/lilt-tokenizer\\\\special_tokens_map.json',\n",
       " 'models/lilt-tokenizer\\\\tokenizer.json')"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "TOKENIZER = 'nielsr/lilt-xlm-roberta-base'\n",
    "tokenizer = AutoTokenizer.from_pretrained(TOKENIZER)\n",
    "save_dir = 'models/lilt-tokenizer'\n",
    "tokenizer.save_pretrained(save_dir)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Download and save token classification model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# download the model\n",
    "MODEL = \"pierreguillou/lilt-xlm-roberta-base-finetuned-funsd-iob-original\"\n",
    "model = LiltForTokenClassification.from_pretrained(MODEL)\n",
    "\n",
    "# save the model\n",
    "save_dir = \"models/lilt-ser-iob\"\n",
    "model.save_pretrained(save_dir)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Download and save RE model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Downloading config.json: 100%|██████████| 794/794 [00:00<00:00, 61.2kB/s]\n",
      "d:\\FYP\\lilt-app-without-fd\\lilt-env\\lib\\site-packages\\huggingface_hub\\file_download.py:133: UserWarning: `huggingface_hub` cache-system uses symlinks by default to efficiently store duplicated files but your machine does not support them in C:\\Users\\Gihantha Kavishka\\.cache\\huggingface\\hub. Caching files will still work but in a degraded version that might require more space on your disk. This warning can be disabled by setting the `HF_HUB_DISABLE_SYMLINKS_WARNING` environment variable. For more details, see https://huggingface.co./docs/huggingface_hub/how-to-cache#limitations.\n",
      "To support symlinks on Windows, you either need to activate Developer Mode or to run Python as an administrator. In order to see activate developer mode, see this article: https://docs.microsoft.com/en-us/windows/apps/get-started/enable-your-device-for-development\n",
      "  warnings.warn(message)\n",
      "Downloading pytorch_model.bin: 100%|██████████| 1.15G/1.15G [08:10<00:00, 2.34MB/s]\n",
      "Some weights of the model checkpoint at kavg/layoutxlm-finetuned-xfund-fr-re were not used when initializing LiltModel: ['extractor.rel_classifier.linear.weight', 'extractor.entity_emb.weight', 'extractor.ffnn_tail.0.weight', 'extractor.ffnn_tail.3.bias', 'extractor.ffnn_head.3.weight', 'extractor.ffnn_head.0.weight', 'extractor.ffnn_tail.0.bias', 'extractor.ffnn_head.3.bias', 'extractor.rel_classifier.bilinear.weight', 'extractor.rel_classifier.linear.bias', 'extractor.ffnn_head.0.bias', 'extractor.ffnn_tail.3.weight']\n",
      "- This IS expected if you are initializing LiltModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
      "- This IS NOT expected if you are initializing LiltModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
      "Some weights of LiltModel were not initialized from the model checkpoint at kavg/layoutxlm-finetuned-xfund-fr-re and are newly initialized: ['lilt.pooler.dense.bias', 'lilt.pooler.dense.weight']\n",
      "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
     ]
    }
   ],
   "source": [
    "# download the model\n",
    "MODEL =  'kavg/layoutxlm-finetuned-xfund-fr-re'\n",
    "model = LiltModel.from_pretrained(MODEL)\n",
    "\n",
    "# save the model\n",
    "save_dir = \"models/lilt-re\"\n",
    "model.save_pretrained(save_dir)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "lilt-env",
   "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": "3.7.8"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}