text_generation.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Text Generation in English"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import pipeline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "text_generation = pipeline(\"text-generation\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "prefix_text = \"The world is\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Setting `pad_token_id` to `eos_token_id`:50256 for open-end generation.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The world is a better place if you're a good person.\n",
      "\n",
      "I'm not saying that you should be a bad person. I'm saying that you should be a good person.\n",
      "\n",
      "I'm not saying that you should be a bad\n"
     ]
    }
   ],
   "source": [
    "generated_text= text_generation(prefix_text, max_length=50, do_sample=False)[0]\n",
    "print(generated_text['generated_text'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Text Generation in Chinese Example"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import pipeline, BertTokenizerFast, AutoModelWithLMHead"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "tokenizer = BertTokenizerFast.from_pretrained('bert-base-chinese')\n",
    "model = AutoModelWithLMHead.from_pretrained('ckiplab/gpt2-base-chinese')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "text_generation = pipeline(\"text-generation\", model=model, tokenizer=tokenizer)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Setting `pad_token_id` to `eos_token_id`:102 for open-end generation.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "我 想 要 去 看 看 。 」 他 說 : 「 我 們 不 能 說, 我 們 不 能 說, 我 們 不 能 說, 我 們 不 能 說, 我 們 不 能 說, 我 們 不 能 說, 我 們\n"
     ]
    }
   ],
   "source": [
    "prefix_text = \"我 想 要 去\"\n",
    "\n",
    "generated_text= text_generation(prefix_text, max_length=50, do_sample=False)[0]\n",
    "print(generated_text['generated_text'])"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.6.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}