course/videos/model_api_pt.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This notebook regroups the code sample of the video below, which is a part of the [Hugging Face course](https://huggingface.co/course)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "cellView": "form"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<iframe width=\"560\" height=\"315\" src=\"https://www.youtube.com/embed/AhChOFRegn4?rel=0&amp;controls=0&amp;showinfo=0\" frameborder=\"0\" allowfullscreen></iframe>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "execution_count": null,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#@title\n",
    "from IPython.display import HTML\n",
    "\n",
    "HTML('<iframe width=\"560\" height=\"315\" src=\"https://www.youtube.com/embed/AhChOFRegn4?rel=0&amp;controls=0&amp;showinfo=0\" frameborder=\"0\" allowfullscreen></iframe>')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Install the Transformers and Datasets libraries to run this notebook."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "! pip install datasets transformers[sentencepiece]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Some weights of the model checkpoint at bert-base-cased were not used when initializing BertModel: ['cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.seq_relationship.weight', 'cls.predictions.decoder.weight', 'cls.predictions.transform.dense.weight', 'cls.predictions.bias', 'cls.predictions.transform.dense.bias', 'cls.seq_relationship.bias']\n",
      "- This IS expected if you are initializing BertModel 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 BertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'transformers.models.bert.modeling_bert.BertModel'>\n",
      "<class 'transformers.models.gpt2.modeling_gpt2.GPT2Model'>\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Some weights of the model checkpoint at facebook/bart-base were not used when initializing BartModel: ['final_logits_bias']\n",
      "- This IS expected if you are initializing BartModel 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 BartModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'transformers.models.bart.modeling_bart.BartModel'>\n"
     ]
    }
   ],
   "source": [
    "from transformers import AutoModel\n",
    "\n",
    "bert_model = AutoModel.from_pretrained(\"bert-base-cased\")\n",
    "print(type(bert_model))\n",
    "\n",
    "gpt_model = AutoModel.from_pretrained(\"gpt2\")\n",
    "print(type(gpt_model))\n",
    "\n",
    "bart_model = AutoModel.from_pretrained(\"facebook/bart-base\")\n",
    "print(type(bart_model))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'transformers.models.bert.configuration_bert.BertConfig'>\n",
      "<class 'transformers.models.gpt2.configuration_gpt2.GPT2Config'>\n",
      "<class 'transformers.models.bart.configuration_bart.BartConfig'>\n"
     ]
    }
   ],
   "source": [
    "from transformers import AutoConfig\n",
    "\n",
    "bert_config = AutoConfig.from_pretrained(\"bert-base-cased\")\n",
    "print(type(bert_config))\n",
    "\n",
    "gpt_config = AutoConfig.from_pretrained(\"gpt2\")\n",
    "print(type(gpt_config))\n",
    "\n",
    "bart_config = AutoConfig.from_pretrained(\"facebook/bart-base\")\n",
    "print(type(bart_config))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'transformers.models.bert.configuration_bert.BertConfig'>\n"
     ]
    }
   ],
   "source": [
    "from transformers import BertConfig\n",
    "\n",
    "bert_config = BertConfig.from_pretrained(\"bert-base-cased\")\n",
    "print(type(bert_config))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'transformers.models.gpt2.configuration_gpt2.GPT2Config'>\n"
     ]
    }
   ],
   "source": [
    "from transformers import GPT2Config\n",
    "\n",
    "gpt_config = GPT2Config.from_pretrained(\"gpt2\")\n",
    "print(type(gpt_config))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'transformers.models.bart.configuration_bart.BartConfig'>\n"
     ]
    }
   ],
   "source": [
    "from transformers import BartConfig\n",
    "\n",
    "bart_config = BartConfig.from_pretrained(\"facebook/bart-base\")\n",
    "print(type(bart_config))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "BertConfig {\n",
      "  \"architectures\": [\n",
      "    \"BertForMaskedLM\"\n",
      "  ],\n",
      "  \"attention_probs_dropout_prob\": 0.1,\n",
      "  \"gradient_checkpointing\": false,\n",
      "  \"hidden_act\": \"gelu\",\n",
      "  \"hidden_dropout_prob\": 0.1,\n",
      "  \"hidden_size\": 768,\n",
      "  \"initializer_range\": 0.02,\n",
      "  \"intermediate_size\": 3072,\n",
      "  \"layer_norm_eps\": 1e-12,\n",
      "  \"max_position_embeddings\": 512,\n",
      "  \"model_type\": \"bert\",\n",
      "  \"num_attention_heads\": 12,\n",
      "  \"num_hidden_layers\": 12,\n",
      "  \"pad_token_id\": 0,\n",
      "  \"position_embedding_type\": \"absolute\",\n",
      "  \"transformers_version\": \"4.7.0.dev0\",\n",
      "  \"type_vocab_size\": 2,\n",
      "  \"use_cache\": true,\n",
      "  \"vocab_size\": 28996\n",
      "}\n",
      "\n"
     ]
    }
   ],
   "source": [
    "from transformers import BertConfig\n",
    "\n",
    "bert_config = BertConfig.from_pretrained(\"bert-base-cased\")\n",
    "print(bert_config)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import BertConfig, BertModel\n",
    "\n",
    "bert_config = BertConfig.from_pretrained(\"bert-base-cased\")\n",
    "bert_model = BertModel(bert_config)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import BertConfig, BertModel\n",
    "\n",
    "bert_config = BertConfig.from_pretrained(\"bert-base-cased\")\n",
    "bert_model = BertModel(bert_config)\n",
    "\n",
    "# Training code\n",
    "\n",
    "bert_model.save_pretrained(\"my_bert_model\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "name": "Instantiate a Transformers model (PyTorch)",
   "provenance": []
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}