course/videos/sentence_pairs_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/0u3ioSwev3s?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/0u3ioSwev3s?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": [],
   "source": [
    "from transformers import AutoTokenizer\n",
    "\n",
    "checkpoint = \"bert-base-uncased\"\n",
    "tokenizer = AutoTokenizer.from_pretrained(checkpoint)\n",
    "sequences = [\n",
    "    \"I've been waiting for a HuggingFace course my whole life.\",\n",
    "    \"This course is amazing!\",\n",
    "]\n",
    "batch = tokenizer(sequences, padding=True, truncation=True, return_tensors=\"pt\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'input_ids': [101, 2026, 2171, 2003, 25353, 22144, 2378, 1012, 102, 1045, 2147, 2012, 17662, 2227, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]}"
      ]
     },
     "execution_count": null,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from transformers import AutoTokenizer\n",
    "\n",
    "checkpoint = \"bert-base-uncased\"\n",
    "tokenizer = AutoTokenizer.from_pretrained(checkpoint)\n",
    "tokenizer(\"My name is Sylvain.\", \"I work at Hugging Face.\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'input_ids': [[101, 2026, 2171, 2003, 25353, 22144, 2378, 1012, 102, 1045, 2147, 2012, 17662, 2227, 1012, 102], [101, 2183, 2000, 1996, 5988, 1012, 102, 2023, 3185, 2003, 2307, 1012, 102, 0, 0, 0]], 'token_type_ids': [[0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1], [0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0, 0]], 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0]]}"
      ]
     },
     "execution_count": null,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from transformers import AutoTokenizer\n",
    "\n",
    "checkpoint = \"bert-base-uncased\"\n",
    "tokenizer = AutoTokenizer.from_pretrained(checkpoint)\n",
    "tokenizer(\n",
    "    [\"My name is Sylvain.\", \"Going to the cinema.\"],\n",
    "    [\"I work at Hugging Face.\", \"This movie is great.\"],\n",
    "    padding=True\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertForSequenceClassification: ['cls.seq_relationship.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.decoder.weight', 'cls.predictions.transform.LayerNorm.weight', 'cls.seq_relationship.bias', 'cls.predictions.bias']\n",
      "- This IS expected if you are initializing BertForSequenceClassification 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 BertForSequenceClassification 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 BertForSequenceClassification were not initialized from the model checkpoint at bert-base-uncased and are newly initialized: ['classifier.bias', 'classifier.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": [
    "from transformers import AutoModelForSequenceClassification, AutoTokenizer\n",
    "\n",
    "checkpoint = \"bert-base-uncased\"\n",
    "tokenizer = AutoTokenizer.from_pretrained(checkpoint)\n",
    "batch = tokenizer(\n",
    "    [\"My name is Sylvain.\", \"Going to the cinema.\"],\n",
    "    [\"I work at Hugging Face.\", \"This movie is great.\"],\n",
    "    padding=True,\n",
    "    return_tensors=\"pt\",\n",
    ")\n",
    "\n",
    "model = AutoModelForSequenceClassification.from_pretrained(checkpoint)\n",
    "outputs = model(**batch)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "name": "Preprocessing sentence pairs (PyTorch)",
   "provenance": []
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}