{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import pipeline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "No model was supplied, defaulted to distilbert-base-uncased-finetuned-sst-2-english (https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english)\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "275d80538ffc43b198489f7044e31309",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading:   0%|          | 0.00/629 [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "b3158a617e4940109ab018aa2bfd8a94",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading:   0%|          | 0.00/256M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "All model checkpoint layers were used when initializing TFDistilBertForSequenceClassification.\n",
      "\n",
      "All the layers of TFDistilBertForSequenceClassification were initialized from the model checkpoint at distilbert-base-uncased-finetuned-sst-2-english.\n",
      "If your task is similar to the task the model of the checkpoint was trained on, you can already use TFDistilBertForSequenceClassification for predictions without further training.\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "bfb51231c3ee4b6a9ab5811331baf689",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading:   0%|          | 0.00/48.0 [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "50e43a0ab3154a16ad623cad2c8637d6",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading:   0%|          | 0.00/226k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "[{'label': 'POSITIVE', 'score': 0.9997795224189758}]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "classifier = pipeline(\"sentiment-analysis\")\n",
    "classifier(\"We are very happy to show you the 🤗 Transformers library.\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Take a prompt and generate a line of text"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "6f80cb24ef764bd192e5d3af79f9f5f1",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading:   0%|          | 0.00/665 [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "4e64c3a035b54f0c90ca5cc6e341ad21",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading:   0%|          | 0.00/475M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "All model checkpoint layers were used when initializing TFGPT2LMHeadModel.\n",
      "\n",
      "All the layers of TFGPT2LMHeadModel were initialized from the model checkpoint at gpt2.\n",
      "If your task is similar to the task the model of the checkpoint was trained on, you can already use TFGPT2LMHeadModel for predictions without further training.\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "4f442dd13c5747e1811c2199423de0c9",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading:   0%|          | 0.00/0.99M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "a88572455b744b18b99c5bd775944d77",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading:   0%|          | 0.00/446k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "d31a3e7e53a7422eabfcb61ff5248b8b",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading:   0%|          | 0.00/1.29M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Setting `pad_token_id` to 50256 (first `eos_token_id`) to generate sequence\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[{'generated_text': 'Hello, I\\'m a language model for the world of design,\" explained the senior designer. \"In JavaScript, each line represents a block of code that'},\n",
       " {'generated_text': \"Hello, I'm a language modeler extraordinaire. So if you're looking for an elegant and flexible way to express your language or for an\"},\n",
       " {'generated_text': \"Hello, I'm a language modeler for Ruby using R, and as a newbie to Rails, I've been very interested in these two techniques\"}]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from transformers import pipeline\n",
    "generator = pipeline('text-generation', model = 'gpt2')\n",
    "generator(\"Hello, I'm a language model\", max_length = 30, num_return_sequences=3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "f140e2c426e04c9ea09061a9796baf30",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading:   0%|          | 0.00/29.0 [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "16398286849d4ecaa30d961e2665924a",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading:   0%|          | 0.00/411 [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "91b51416d67b42fda574db1335bb114e",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading:   0%|          | 0.00/208k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "c1a3c1b3cbd24e91b4b455e7bbbcc6d4",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading:   0%|          | 0.00/426k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "ename": "ValueError",
     "evalue": "Unrecognized configuration class <class 'transformers.models.distilbert.configuration_distilbert.DistilBertConfig'> for this kind of AutoModel: AutoModelForCausalLM.\nModel type should be one of GPTJConfig, RemBertConfig, RoFormerConfig, BigBirdPegasusConfig, GPTNeoConfig, BigBirdConfig, Speech2Text2Config, BlenderbotSmallConfig, BertGenerationConfig, CamembertConfig, XLMRobertaConfig, PegasusConfig, MarianConfig, MBartConfig, MegatronBertConfig, BartConfig, BlenderbotConfig, ReformerConfig, RobertaConfig, BertConfig, OpenAIGPTConfig, GPT2Config, TransfoXLConfig, XLNetConfig, XLMProphetNetConfig, ProphetNetConfig, XLMConfig, CTRLConfig.",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "Cell \u001b[0;32mIn [6], line 12\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[38;5;66;03m# tokenizer = AutoTokenizer.from_pretrained(\"BritishLibraryLabs/bl-books-genre\")\u001b[39;00m\n\u001b[1;32m      5\u001b[0m \u001b[38;5;66;03m# model = AutoModelForCausalLM.from_pretrained(\"BritishLibraryLabs/bl-books-genre\")\u001b[39;00m\n\u001b[1;32m      6\u001b[0m \u001b[38;5;66;03m# \"BritishLibraryLabs/bl-books-genre\"\u001b[39;00m\n\u001b[1;32m      7\u001b[0m \n\u001b[1;32m      8\u001b[0m \u001b[38;5;66;03m# tokenizer = AutoTokenizer.from_pretrained(\"gpt2\")\u001b[39;00m\n\u001b[1;32m      9\u001b[0m \u001b[38;5;66;03m# model = AutoModelForCausalLM.from_pretrained(\"gpt2\")\u001b[39;00m\n\u001b[1;32m     11\u001b[0m tokenizer \u001b[38;5;241m=\u001b[39m AutoTokenizer\u001b[38;5;241m.\u001b[39mfrom_pretrained(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdistilbert-base-cased\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m---> 12\u001b[0m model \u001b[38;5;241m=\u001b[39m \u001b[43mAutoModelForCausalLM\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mdistilbert-base-cased\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m     14\u001b[0m \u001b[38;5;66;03m# generator = pipeline('text-generation', model = \"BritishLibraryLabs/bl-books-genre\")\u001b[39;00m\n\u001b[1;32m     15\u001b[0m \u001b[38;5;66;03m# generator(\"Hello, I'm a language model\", max_length = 30, num_return_sequences=3)\u001b[39;00m\n\u001b[1;32m     17\u001b[0m generator \u001b[38;5;241m=\u001b[39m pipeline(task\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtext-generation\u001b[39m\u001b[38;5;124m\"\u001b[39m, model\u001b[38;5;241m=\u001b[39mmodel, tokenizer\u001b[38;5;241m=\u001b[39mtokenizer)\n",
      "File \u001b[0;32m/opt/homebrew/Caskroom/miniforge/base/envs/augmented_poetry/lib/python3.8/site-packages/transformers/models/auto/auto_factory.py:420\u001b[0m, in \u001b[0;36m_BaseAutoModelClass.from_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, *model_args, **kwargs)\u001b[0m\n\u001b[1;32m    418\u001b[0m     model_class \u001b[39m=\u001b[39m _get_model_class(config, \u001b[39mcls\u001b[39m\u001b[39m.\u001b[39m_model_mapping)\n\u001b[1;32m    419\u001b[0m     \u001b[39mreturn\u001b[39;00m model_class\u001b[39m.\u001b[39mfrom_pretrained(pretrained_model_name_or_path, \u001b[39m*\u001b[39mmodel_args, config\u001b[39m=\u001b[39mconfig, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs)\n\u001b[0;32m--> 420\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\n\u001b[1;32m    421\u001b[0m     \u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mUnrecognized configuration class \u001b[39m\u001b[39m{\u001b[39;00mconfig\u001b[39m.\u001b[39m\u001b[39m__class__\u001b[39m\u001b[39m}\u001b[39;00m\u001b[39m for this kind of AutoModel: \u001b[39m\u001b[39m{\u001b[39;00m\u001b[39mcls\u001b[39m\u001b[39m.\u001b[39m\u001b[39m__name__\u001b[39m\u001b[39m}\u001b[39;00m\u001b[39m.\u001b[39m\u001b[39m\\n\u001b[39;00m\u001b[39m\"\u001b[39m\n\u001b[1;32m    422\u001b[0m     \u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mModel type should be one of \u001b[39m\u001b[39m{\u001b[39;00m\u001b[39m'\u001b[39m\u001b[39m, \u001b[39m\u001b[39m'\u001b[39m\u001b[39m.\u001b[39mjoin(c\u001b[39m.\u001b[39m\u001b[39m__name__\u001b[39m \u001b[39mfor\u001b[39;00m c \u001b[39min\u001b[39;00m \u001b[39mcls\u001b[39m\u001b[39m.\u001b[39m_model_mapping\u001b[39m.\u001b[39mkeys())\u001b[39m}\u001b[39;00m\u001b[39m.\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m    423\u001b[0m )\n",
      "\u001b[0;31mValueError\u001b[0m: Unrecognized configuration class <class 'transformers.models.distilbert.configuration_distilbert.DistilBertConfig'> for this kind of AutoModel: AutoModelForCausalLM.\nModel type should be one of GPTJConfig, RemBertConfig, RoFormerConfig, BigBirdPegasusConfig, GPTNeoConfig, BigBirdConfig, Speech2Text2Config, BlenderbotSmallConfig, BertGenerationConfig, CamembertConfig, XLMRobertaConfig, PegasusConfig, MarianConfig, MBartConfig, MegatronBertConfig, BartConfig, BlenderbotConfig, ReformerConfig, RobertaConfig, BertConfig, OpenAIGPTConfig, GPT2Config, TransfoXLConfig, XLNetConfig, XLMProphetNetConfig, ProphetNetConfig, XLMConfig, CTRLConfig."
     ]
    }
   ],
   "source": [
    "from transformers import pipeline\n",
    "from transformers import AutoTokenizer, AutoModelForCausalLM\n",
    "\n",
    "# tokenizer = AutoTokenizer.from_pretrained(\"BritishLibraryLabs/bl-books-genre\")\n",
    "# model = AutoModelForCausalLM.from_pretrained(\"BritishLibraryLabs/bl-books-genre\")\n",
    "# \"BritishLibraryLabs/bl-books-genre\"\n",
    "\n",
    "# tokenizer = AutoTokenizer.from_pretrained(\"gpt2\")\n",
    "# model = AutoModelForCausalLM.from_pretrained(\"gpt2\")\n",
    "\n",
    "tokenizer = AutoTokenizer.from_pretrained(\"distilbert-base-cased\")\n",
    "model = AutoModelForCausalLM.from_pretrained(\"distilbert-base-cased\")\n",
    "\n",
    "# generator = pipeline('text-generation', model = \"BritishLibraryLabs/bl-books-genre\")\n",
    "# generator(\"Hello, I'm a language model\", max_length = 30, num_return_sequences=3)\n",
    "\n",
    "generator = pipeline(task=\"text-generation\", model=model, tokenizer=tokenizer)\n",
    "generator('something to start with', max_length = 30, num_return_sequences=3)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "If you want to use `RobertaLMHeadModel` as a standalone, add `is_decoder=True.`\n"
     ]
    },
    {
     "ename": "ValueError",
     "evalue": "num_return_sequences has to be 1, but is 3 when doing greedy search.",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "Cell \u001b[0;32mIn [11], line 2\u001b[0m\n\u001b[1;32m      1\u001b[0m generator \u001b[38;5;241m=\u001b[39m pipeline(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mtext-generation\u001b[39m\u001b[38;5;124m'\u001b[39m, model \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mroberta-base\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m----> 2\u001b[0m \u001b[43mgenerator\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mHello, I\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mm a language model\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_length\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m30\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mnum_return_sequences\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m3\u001b[39;49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/opt/homebrew/Caskroom/miniforge/base/envs/augmented_poetry/lib/python3.8/site-packages/transformers/pipelines/text_generation.py:150\u001b[0m, in \u001b[0;36mTextGenerationPipeline.__call__\u001b[0;34m(self, text_inputs, **kwargs)\u001b[0m\n\u001b[1;32m    121\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39m__call__\u001b[39m(\u001b[39mself\u001b[39m, text_inputs, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs):\n\u001b[1;32m    122\u001b[0m     \u001b[39m\"\"\"\u001b[39;00m\n\u001b[1;32m    123\u001b[0m \u001b[39m    Complete the prompt(s) given as inputs.\u001b[39;00m\n\u001b[1;32m    124\u001b[0m \n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    148\u001b[0m \u001b[39m          -- The token ids of the generated text.\u001b[39;00m\n\u001b[1;32m    149\u001b[0m \u001b[39m    \"\"\"\u001b[39;00m\n\u001b[0;32m--> 150\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39msuper\u001b[39;49m()\u001b[39m.\u001b[39;49m\u001b[39m__call__\u001b[39;49m(text_inputs, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n",
      "File \u001b[0;32m/opt/homebrew/Caskroom/miniforge/base/envs/augmented_poetry/lib/python3.8/site-packages/transformers/pipelines/base.py:915\u001b[0m, in \u001b[0;36mPipeline.__call__\u001b[0;34m(self, inputs, num_workers, *args, **kwargs)\u001b[0m\n\u001b[1;32m    913\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mget_iterator(inputs, num_workers, preprocess_params, forward_params, postprocess_params)\n\u001b[1;32m    914\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[0;32m--> 915\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mrun_single(inputs, preprocess_params, forward_params, postprocess_params)\n",
      "File \u001b[0;32m/opt/homebrew/Caskroom/miniforge/base/envs/augmented_poetry/lib/python3.8/site-packages/transformers/pipelines/base.py:922\u001b[0m, in \u001b[0;36mPipeline.run_single\u001b[0;34m(self, inputs, preprocess_params, forward_params, postprocess_params)\u001b[0m\n\u001b[1;32m    920\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mrun_single\u001b[39m(\u001b[39mself\u001b[39m, inputs, preprocess_params, forward_params, postprocess_params):\n\u001b[1;32m    921\u001b[0m     model_inputs \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mpreprocess(inputs, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mpreprocess_params)\n\u001b[0;32m--> 922\u001b[0m     model_outputs \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mforward(model_inputs, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mforward_params)\n\u001b[1;32m    923\u001b[0m     outputs \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mpostprocess(model_outputs, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mpostprocess_params)\n\u001b[1;32m    924\u001b[0m     \u001b[39mreturn\u001b[39;00m outputs\n",
      "File \u001b[0;32m/opt/homebrew/Caskroom/miniforge/base/envs/augmented_poetry/lib/python3.8/site-packages/transformers/pipelines/base.py:871\u001b[0m, in \u001b[0;36mPipeline.forward\u001b[0;34m(self, model_inputs, **forward_params)\u001b[0m\n\u001b[1;32m    869\u001b[0m     \u001b[39mwith\u001b[39;00m torch\u001b[39m.\u001b[39mno_grad():\n\u001b[1;32m    870\u001b[0m         model_inputs \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_ensure_tensor_on_device(model_inputs, device\u001b[39m=\u001b[39m\u001b[39mself\u001b[39m\u001b[39m.\u001b[39mdevice)\n\u001b[0;32m--> 871\u001b[0m         model_outputs \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_forward(model_inputs, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mforward_params)\n\u001b[1;32m    872\u001b[0m         model_outputs \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_ensure_tensor_on_device(model_outputs, device\u001b[39m=\u001b[39mtorch\u001b[39m.\u001b[39mdevice(\u001b[39m\"\u001b[39m\u001b[39mcpu\u001b[39m\u001b[39m\"\u001b[39m))\n\u001b[1;32m    873\u001b[0m \u001b[39melse\u001b[39;00m:\n",
      "File \u001b[0;32m/opt/homebrew/Caskroom/miniforge/base/envs/augmented_poetry/lib/python3.8/site-packages/transformers/pipelines/text_generation.py:165\u001b[0m, in \u001b[0;36mTextGenerationPipeline._forward\u001b[0;34m(self, model_inputs, **generate_kwargs)\u001b[0m\n\u001b[1;32m    163\u001b[0m     input_ids \u001b[39m=\u001b[39m \u001b[39mNone\u001b[39;00m\n\u001b[1;32m    164\u001b[0m prompt_text \u001b[39m=\u001b[39m model_inputs\u001b[39m.\u001b[39mpop(\u001b[39m\"\u001b[39m\u001b[39mprompt_text\u001b[39m\u001b[39m\"\u001b[39m)\n\u001b[0;32m--> 165\u001b[0m generated_sequence \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mmodel\u001b[39m.\u001b[39;49mgenerate(input_ids\u001b[39m=\u001b[39;49minput_ids, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mgenerate_kwargs)  \u001b[39m# BS x SL\u001b[39;00m\n\u001b[1;32m    166\u001b[0m \u001b[39mreturn\u001b[39;00m {\u001b[39m\"\u001b[39m\u001b[39mgenerated_sequence\u001b[39m\u001b[39m\"\u001b[39m: generated_sequence, \u001b[39m\"\u001b[39m\u001b[39minput_ids\u001b[39m\u001b[39m\"\u001b[39m: input_ids, \u001b[39m\"\u001b[39m\u001b[39mprompt_text\u001b[39m\u001b[39m\"\u001b[39m: prompt_text}\n",
      "File \u001b[0;32m/opt/homebrew/Caskroom/miniforge/base/envs/augmented_poetry/lib/python3.8/site-packages/torch/autograd/grad_mode.py:27\u001b[0m, in \u001b[0;36m_DecoratorContextManager.__call__.<locals>.decorate_context\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m     24\u001b[0m \u001b[39m@functools\u001b[39m\u001b[39m.\u001b[39mwraps(func)\n\u001b[1;32m     25\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mdecorate_context\u001b[39m(\u001b[39m*\u001b[39margs, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs):\n\u001b[1;32m     26\u001b[0m     \u001b[39mwith\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mclone():\n\u001b[0;32m---> 27\u001b[0m         \u001b[39mreturn\u001b[39;00m func(\u001b[39m*\u001b[39;49margs, \u001b[39m*\u001b[39;49m\u001b[39m*\u001b[39;49mkwargs)\n",
      "File \u001b[0;32m/opt/homebrew/Caskroom/miniforge/base/envs/augmented_poetry/lib/python3.8/site-packages/transformers/generation_utils.py:984\u001b[0m, in \u001b[0;36mGenerationMixin.generate\u001b[0;34m(self, input_ids, max_length, min_length, do_sample, early_stopping, num_beams, temperature, top_k, top_p, repetition_penalty, bad_words_ids, bos_token_id, pad_token_id, eos_token_id, length_penalty, no_repeat_ngram_size, encoder_no_repeat_ngram_size, num_return_sequences, max_time, max_new_tokens, decoder_start_token_id, use_cache, num_beam_groups, diversity_penalty, prefix_allowed_tokens_fn, output_attentions, output_hidden_states, output_scores, return_dict_in_generate, forced_bos_token_id, forced_eos_token_id, remove_invalid_values, synced_gpus, **model_kwargs)\u001b[0m\n\u001b[1;32m    982\u001b[0m \u001b[39mif\u001b[39;00m is_greedy_gen_mode:\n\u001b[1;32m    983\u001b[0m     \u001b[39mif\u001b[39;00m num_return_sequences \u001b[39m>\u001b[39m \u001b[39m1\u001b[39m:\n\u001b[0;32m--> 984\u001b[0m         \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\n\u001b[1;32m    985\u001b[0m             \u001b[39mf\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mnum_return_sequences has to be 1, but is \u001b[39m\u001b[39m{\u001b[39;00mnum_return_sequences\u001b[39m}\u001b[39;00m\u001b[39m when doing greedy search.\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m    986\u001b[0m         )\n\u001b[1;32m    988\u001b[0m     \u001b[39m# greedy search\u001b[39;00m\n\u001b[1;32m    989\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mgreedy_search(\n\u001b[1;32m    990\u001b[0m         input_ids,\n\u001b[1;32m    991\u001b[0m         logits_processor\u001b[39m=\u001b[39mlogits_processor,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    998\u001b[0m         \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mmodel_kwargs,\n\u001b[1;32m    999\u001b[0m     )\n",
      "\u001b[0;31mValueError\u001b[0m: num_return_sequences has to be 1, but is 3 when doing greedy search."
     ]
    }
   ],
   "source": [
    "generator = pipeline('text-generation', model = 'roberta-base')\n",
    "generator(\"Hello, I'm a language model\", max_length = 30, num_return_sequences=3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'[Illustration: \"I saw there something missing from'"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from gutenbergdammit.ziputils import retrieve_one\n",
    "text = retrieve_one(\"gutenberg-dammit-files-v002.zip\", \"123/12345.txt\")\n",
    "# text = retrieve_one(\"gutenberg-dammit-files-v002.zip\", \"123/12345.txt\")\n",
    "text[:50]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'Author': ['Franklin Delano Roosevelt'],\n",
       " 'Author Birth': [1882],\n",
       " 'Author Death': [1945],\n",
       " 'Author Given': ['Franklin Delano'],\n",
       " 'Author Surname': ['Roosevelt'],\n",
       " 'Copyright Status': ['Not copyrighted in the United States.'],\n",
       " 'Language': ['English'],\n",
       " 'LoC Class': ['E740: History: America: Twentieth century'],\n",
       " 'Num': '104',\n",
       " 'Subject': ['New Deal, 1933-1939',\n",
       "  'Presidents -- United States -- Inaugural addresses',\n",
       "  'United States -- Politics and government -- 1933-1945'],\n",
       " 'Title': [\"Franklin Delano Roosevelt's First Inaugural Address\"],\n",
       " 'charset': 'us-ascii',\n",
       " 'gd-num-padded': '00104',\n",
       " 'gd-path': '001/00104.txt',\n",
       " 'href': '/1/0/104/104.zip'}"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from gutenbergdammit.ziputils import loadmetadata\n",
    "metadata = loadmetadata(\"gutenberg-dammit-files-v002.zip\")\n",
    "metadata[101]\n",
    "# ['Essays in the Art of Writing']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Entertaining Made Easy 108314\n",
      "Reading Made Easy for Foreigners - Third Reader 209964\n",
      "The Art of Cookery Made Easy and Refined 262990\n",
      "Shaving Made Easy\tWhat the Man Who Shaves Ought to Know 44982\n",
      "Writing and Drawing Made Easy, Amusing and Instructive\tContaining The Whole Alphabet in all the Characters now\tus'd, Both in Printing and Penmanship 10036\n",
      "Etiquette Made Easy 119372\n"
     ]
    }
   ],
   "source": [
    "from gutenbergdammit.ziputils import searchandretrieve\n",
    "for info, text in searchandretrieve(\"gutenberg-dammit-files-v002.zip\", {'Title': 'Made Easy'}):\n",
    "    print(info['Title'][0], len(text))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# from gutenbergdammit.ziputils import retrieve_one\n",
    "# search and retrieve only poetry text\n",
    "# fine tune with line-by-line"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "False"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# from transformers import AutoModel\n",
    "# model_clpt = \"distilbert-base-uncased\"\n",
    "# device = torch.device(\"cuda\" id tor)\n",
    "import torch\n",
    "torch.cuda.is_available()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING:tensorflow:From /var/folders/vr/wjfjpzn1755bvptln8g22f9r0000gn/T/ipykernel_91499/3763141526.py:2: is_gpu_available (from tensorflow.python.framework.test_util) is deprecated and will be removed in a future version.\n",
      "Instructions for updating:\n",
      "Use `tf.config.list_physical_devices('GPU')` instead.\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "False"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import tensorflow as tf\n",
    "tf.test.is_gpu_available()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[]"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tf.config.list_physical_devices('GPU')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[PhysicalDevice(name='/physical_device:CPU:0', device_type='CPU')]"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tf.config.list_physical_devices('CPU')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Source data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "curl -O http://static.decontextualize.com/gutenberg-poetry-v001.ndjson.gz"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "import gzip, json\n",
    "all_lines = []\n",
    "for line in gzip.open(\"gutenberg-poetry-v001.ndjson.gz\"):\n",
    "    all_lines.append(json.loads(line.strip()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[{'s': 'The Song of Hiawatha is based on the legends and stories of', 'gid': '19'}, {'s': 'many North American Indian tribes, but especially those of the', 'gid': '19'}, {'s': 'Ojibway Indians of northern Michigan, Wisconsin, and Minnesota.', 'gid': '19'}, {'s': 'They were collected by Henry Rowe Schoolcraft, the reknowned', 'gid': '19'}, {'s': 'Schoolcraft married Jane, O-bah-bahm-wawa-ge-zhe-go-qua (The', 'gid': '19'}, {'s': 'fur trader, and O-shau-gus-coday-way-qua (The Woman of the Green', 'gid': '19'}, {'s': 'Prairie), who was a daughter of Waub-o-jeeg (The White Fisher),', 'gid': '19'}, {'s': 'who was Chief of the Ojibway tribe at La Pointe, Wisconsin.', 'gid': '19'}, {'s': 'Jane and her mother are credited with having researched,', 'gid': '19'}, {'s': 'authenticated, and compiled much of the material Schoolcraft', 'gid': '19'}]\n"
     ]
    }
   ],
   "source": [
    "import random\n",
    "random.sample(all_lines, 8)\n",
    "\n",
    "print(all_lines[0:10])\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'Author': ['Henry Rider Haggard'],\n",
       " 'Author Birth': [1856],\n",
       " 'Author Death': [1925],\n",
       " 'Author Given': ['Henry Rider'],\n",
       " 'Author Surname': ['Haggard'],\n",
       " 'Copyright Status': ['Not copyrighted in the United States.'],\n",
       " 'Language': ['English'],\n",
       " 'LoC Class': ['PR: Language and Literatures: English literature'],\n",
       " 'Num': '2721',\n",
       " 'Subject': ['Iceland -- Fiction'],\n",
       " 'Title': ['Eric Brighteyes'],\n",
       " 'charset': 'iso-8859-1',\n",
       " 'gd-num-padded': '02721',\n",
       " 'gd-path': '027/02721.txt',\n",
       " 'href': '/2/7/2/2721/2721_8.zip'}"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from gutenbergdammit.ziputils import loadmetadata\n",
    "metadata = loadmetadata(\"gutenberg-dammit-files-v002.zip\")\n",
    "metadata[2620]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['The Song of Hiawatha is based on the legends and stories of',\n",
       " 'many North American Indian tribes, but especially those of the',\n",
       " 'Ojibway Indians of northern Michigan, Wisconsin, and Minnesota.',\n",
       " 'They were collected by Henry Rowe Schoolcraft, the reknowned',\n",
       " 'Schoolcraft married Jane, O-bah-bahm-wawa-ge-zhe-go-qua (The',\n",
       " 'fur trader, and O-shau-gus-coday-way-qua (The Woman of the Green',\n",
       " 'Prairie), who was a daughter of Waub-o-jeeg (The White Fisher),',\n",
       " 'who was Chief of the Ojibway tribe at La Pointe, Wisconsin.',\n",
       " 'Jane and her mother are credited with having researched,',\n",
       " 'authenticated, and compiled much of the material Schoolcraft']"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "[line['s'] for line in all_lines[0:10]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.10.6 ('augmented_poetry')",
   "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": "3.8.13"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "00664817f4a09ab74dd392ee5a8d12e3606381c26df296db9ea5c334bb5d1b65"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}