{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "_cell_guid": "b1076dfc-b9ad-4769-8c92-a6c4dae69d19",
    "_uuid": "8f2839f25d086af736a60e9eeb907d3b93b6e0e5",
    "execution": {
     "iopub.execute_input": "2025-06-12T17:04:41.889457Z",
     "iopub.status.busy": "2025-06-12T17:04:41.889269Z",
     "iopub.status.idle": "2025-06-12T17:04:43.013740Z",
     "shell.execute_reply": "2025-06-12T17:04:43.012978Z",
     "shell.execute_reply.started": "2025-06-12T17:04:41.889440Z"
    },
    "trusted": true
   },
   "outputs": [],
   "source": [
    "# This Python 3 environment comes with many helpful analytics libraries installed\n",
    "# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n",
    "# For example, here's several helpful packages to load\n",
    "\n",
    "import numpy as np # linear algebra\n",
    "import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n",
    "\n",
    "# Input data files are available in the read-only \"../input/\" directory\n",
    "# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n",
    "\n",
    "import os\n",
    "for dirname, _, filenames in os.walk('/kaggle/input'):\n",
    "    for filename in filenames:\n",
    "        print(os.path.join(dirname, filename))\n",
    "\n",
    "# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n",
    "# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-06-12T17:04:43.015611Z",
     "iopub.status.busy": "2025-06-12T17:04:43.015277Z",
     "iopub.status.idle": "2025-06-12T17:04:47.753149Z",
     "shell.execute_reply": "2025-06-12T17:04:47.752453Z",
     "shell.execute_reply.started": "2025-06-12T17:04:43.015591Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: datasets in /usr/local/lib/python3.11/dist-packages (3.6.0)\n",
      "Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from datasets) (3.18.0)\n",
      "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.11/dist-packages (from datasets) (1.26.4)\n",
      "Requirement already satisfied: pyarrow>=15.0.0 in /usr/local/lib/python3.11/dist-packages (from datasets) (19.0.1)\n",
      "Requirement already satisfied: dill<0.3.9,>=0.3.0 in /usr/local/lib/python3.11/dist-packages (from datasets) (0.3.8)\n",
      "Requirement already satisfied: pandas in /usr/local/lib/python3.11/dist-packages (from datasets) (2.2.3)\n",
      "Requirement already satisfied: requests>=2.32.2 in /usr/local/lib/python3.11/dist-packages (from datasets) (2.32.3)\n",
      "Requirement already satisfied: tqdm>=4.66.3 in /usr/local/lib/python3.11/dist-packages (from datasets) (4.67.1)\n",
      "Requirement already satisfied: xxhash in /usr/local/lib/python3.11/dist-packages (from datasets) (3.5.0)\n",
      "Requirement already satisfied: multiprocess<0.70.17 in /usr/local/lib/python3.11/dist-packages (from datasets) (0.70.16)\n",
      "Collecting fsspec<=2025.3.0,>=2023.1.0 (from fsspec[http]<=2025.3.0,>=2023.1.0->datasets)\n",
      "  Downloading fsspec-2025.3.0-py3-none-any.whl.metadata (11 kB)\n",
      "Requirement already satisfied: huggingface-hub>=0.24.0 in /usr/local/lib/python3.11/dist-packages (from datasets) (0.31.1)\n",
      "Requirement already satisfied: packaging in /usr/local/lib/python3.11/dist-packages (from datasets) (25.0)\n",
      "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.11/dist-packages (from datasets) (6.0.2)\n",
      "Requirement already satisfied: aiohttp!=4.0.0a0,!=4.0.0a1 in /usr/local/lib/python3.11/dist-packages (from fsspec[http]<=2025.3.0,>=2023.1.0->datasets) (3.11.18)\n",
      "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.11/dist-packages (from huggingface-hub>=0.24.0->datasets) (4.13.2)\n",
      "Requirement already satisfied: hf-xet<2.0.0,>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from huggingface-hub>=0.24.0->datasets) (1.1.0)\n",
      "Requirement already satisfied: mkl_fft in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17->datasets) (1.3.8)\n",
      "Requirement already satisfied: mkl_random in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17->datasets) (1.2.4)\n",
      "Requirement already satisfied: mkl_umath in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17->datasets) (0.1.1)\n",
      "Requirement already satisfied: mkl in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17->datasets) (2025.1.0)\n",
      "Requirement already satisfied: tbb4py in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17->datasets) (2022.1.0)\n",
      "Requirement already satisfied: mkl-service in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17->datasets) (2.4.1)\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests>=2.32.2->datasets) (3.4.2)\n",
      "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests>=2.32.2->datasets) (3.10)\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests>=2.32.2->datasets) (2.4.0)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/dist-packages (from requests>=2.32.2->datasets) (2025.4.26)\n",
      "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.11/dist-packages (from pandas->datasets) (2.9.0.post0)\n",
      "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas->datasets) (2025.2)\n",
      "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.11/dist-packages (from pandas->datasets) (2025.2)\n",
      "Requirement already satisfied: aiohappyeyeballs>=2.3.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2025.3.0,>=2023.1.0->datasets) (2.6.1)\n",
      "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2025.3.0,>=2023.1.0->datasets) (1.3.2)\n",
      "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2025.3.0,>=2023.1.0->datasets) (25.3.0)\n",
      "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2025.3.0,>=2023.1.0->datasets) (1.6.0)\n",
      "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2025.3.0,>=2023.1.0->datasets) (6.4.3)\n",
      "Requirement already satisfied: propcache>=0.2.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2025.3.0,>=2023.1.0->datasets) (0.3.1)\n",
      "Requirement already satisfied: yarl<2.0,>=1.17.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2025.3.0,>=2023.1.0->datasets) (1.20.0)\n",
      "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/dist-packages (from python-dateutil>=2.8.2->pandas->datasets) (1.17.0)\n",
      "Requirement already satisfied: intel-openmp<2026,>=2024 in /usr/local/lib/python3.11/dist-packages (from mkl->numpy>=1.17->datasets) (2024.2.0)\n",
      "Requirement already satisfied: tbb==2022.* in /usr/local/lib/python3.11/dist-packages (from mkl->numpy>=1.17->datasets) (2022.1.0)\n",
      "Requirement already satisfied: tcmlib==1.* in /usr/local/lib/python3.11/dist-packages (from tbb==2022.*->mkl->numpy>=1.17->datasets) (1.3.0)\n",
      "Requirement already satisfied: intel-cmplr-lib-rt in /usr/local/lib/python3.11/dist-packages (from mkl_umath->numpy>=1.17->datasets) (2024.2.0)\n",
      "Requirement already satisfied: intel-cmplr-lib-ur==2024.2.0 in /usr/local/lib/python3.11/dist-packages (from intel-openmp<2026,>=2024->mkl->numpy>=1.17->datasets) (2024.2.0)\n",
      "Downloading fsspec-2025.3.0-py3-none-any.whl (193 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m193.6/193.6 kB\u001b[0m \u001b[31m4.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
      "\u001b[?25hInstalling collected packages: fsspec\n",
      "  Attempting uninstall: fsspec\n",
      "    Found existing installation: fsspec 2025.3.2\n",
      "    Uninstalling fsspec-2025.3.2:\n",
      "      Successfully uninstalled fsspec-2025.3.2\n",
      "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
      "cesium 0.12.4 requires numpy<3.0,>=2.0, but you have numpy 1.26.4 which is incompatible.\n",
      "bigframes 1.42.0 requires rich<14,>=12.4.4, but you have rich 14.0.0 which is incompatible.\n",
      "torch 2.6.0+cu124 requires nvidia-cublas-cu12==12.4.5.8; platform_system == \"Linux\" and platform_machine == \"x86_64\", but you have nvidia-cublas-cu12 12.9.0.13 which is incompatible.\n",
      "torch 2.6.0+cu124 requires nvidia-cudnn-cu12==9.1.0.70; platform_system == \"Linux\" and platform_machine == \"x86_64\", but you have nvidia-cudnn-cu12 9.3.0.75 which is incompatible.\n",
      "torch 2.6.0+cu124 requires nvidia-cufft-cu12==11.2.1.3; platform_system == \"Linux\" and platform_machine == \"x86_64\", but you have nvidia-cufft-cu12 11.4.0.6 which is incompatible.\n",
      "torch 2.6.0+cu124 requires nvidia-curand-cu12==10.3.5.147; platform_system == \"Linux\" and platform_machine == \"x86_64\", but you have nvidia-curand-cu12 10.3.10.19 which is incompatible.\n",
      "torch 2.6.0+cu124 requires nvidia-cusolver-cu12==11.6.1.9; platform_system == \"Linux\" and platform_machine == \"x86_64\", but you have nvidia-cusolver-cu12 11.7.4.40 which is incompatible.\n",
      "torch 2.6.0+cu124 requires nvidia-cusparse-cu12==12.3.1.170; platform_system == \"Linux\" and platform_machine == \"x86_64\", but you have nvidia-cusparse-cu12 12.5.9.5 which is incompatible.\n",
      "torch 2.6.0+cu124 requires nvidia-nvjitlink-cu12==12.4.127; platform_system == \"Linux\" and platform_machine == \"x86_64\", but you have nvidia-nvjitlink-cu12 12.9.41 which is incompatible.\n",
      "gcsfs 2025.3.2 requires fsspec==2025.3.2, but you have fsspec 2025.3.0 which is incompatible.\u001b[0m\u001b[31m\n",
      "\u001b[0mSuccessfully installed fsspec-2025.3.0\n"
     ]
    }
   ],
   "source": [
    "!pip install datasets\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-06-12T17:04:47.754432Z",
     "iopub.status.busy": "2025-06-12T17:04:47.754136Z",
     "iopub.status.idle": "2025-06-12T17:04:51.067474Z",
     "shell.execute_reply": "2025-06-12T17:04:51.066953Z",
     "shell.execute_reply.started": "2025-06-12T17:04:47.754407Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "1493ba48468f46648af0bfb811beee06",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "README.md:   0%|          | 0.00/4.65k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "d146713524544f65af5a9c2c7bc33d70",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "train.csv:   0%|          | 0.00/11.3M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "b83b84e119a64c14b78c97549f709b0a",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "validation.csv:   0%|          | 0.00/442k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "bd01c9577b4646d1a16cc3d8f508d610",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "test.csv:   0%|          | 0.00/1.35M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "e486ee8329dc4d29924e3edfb7df2479",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Generating train split:   0%|          | 0/12460 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "366c9a3006034d439092c1a1bc12ace9",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Generating validation split:   0%|          | 0/500 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "70d73fc03dcb446e886abfce07d50b4e",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Generating test split:   0%|          | 0/1500 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from datasets import load_dataset\n",
    "ds = load_dataset(\"knkarthick/dialogsum\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-06-12T17:04:51.068492Z",
     "iopub.status.busy": "2025-06-12T17:04:51.068151Z",
     "iopub.status.idle": "2025-06-12T17:04:52.772955Z",
     "shell.execute_reply": "2025-06-12T17:04:52.772321Z",
     "shell.execute_reply.started": "2025-06-12T17:04:51.068474Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "1814d5ef014147d0ac7e1a9b2ddc6560",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Map:   0%|          | 0/12460 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "ea9b9978b1b24eb188251a9908682166",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Map:   0%|          | 0/500 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "9f0ca8f8df98458381d20cd0908c507f",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Map:   0%|          | 0/1500 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import re\n",
    "def clean_text(text):\n",
    "    text=re.sub(r'\\s+', ' ', text).strip()\n",
    "    return text \n",
    "def preprocess(example):\n",
    "    example[\"dialogue\"] = clean_text(example[\"dialogue\"])\n",
    "    example[\"summary\"] = clean_text(example[\"summary\"])\n",
    "    return example\n",
    "ds[\"train\"] = ds[\"train\"].map(preprocess)\n",
    "ds[\"validation\"] = ds[\"validation\"].map(preprocess)\n",
    "ds[\"test\"] = ds[\"test\"].map(preprocess)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-06-12T17:04:52.774820Z",
     "iopub.status.busy": "2025-06-12T17:04:52.774612Z",
     "iopub.status.idle": "2025-06-12T17:05:15.376798Z",
     "shell.execute_reply": "2025-06-12T17:05:15.375993Z",
     "shell.execute_reply.started": "2025-06-12T17:04:52.774804Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "c9843e22bdeb412f89c8ac4deb2fd6c6",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "tokenizer_config.json:   0%|          | 0.00/26.0 [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "6345b5f45bd245499f288926d631543e",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "config.json:   0%|          | 0.00/1.80k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "c73e268748254c1ab6376245698e649a",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "vocab.json:   0%|          | 0.00/899k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "9deb932fd0c247568e7fa87f909f1413",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "merges.txt:   0%|          | 0.00/456k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "dd000a5f19dd423eb8e3ba0071ee8ed4",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Map:   0%|          | 0/12460 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.11/dist-packages/transformers/tokenization_utils_base.py:3980: UserWarning: `as_target_tokenizer` is deprecated and will be removed in v5 of Transformers. You can tokenize your labels by using the argument `text_target` of the regular `__call__` method (either in the same call as your input texts if you use the same keyword arguments, or in a separate call.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "b50d71bf97ae48e2b6a90a0606380024",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Map:   0%|          | 0/500 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "c3b5f103b9644a1294886e5f32480dc3",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Map:   0%|          | 0/1500 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from transformers import AutoTokenizer\n",
    "\n",
    "# Load the tokenizer\n",
    "tokenizer = AutoTokenizer.from_pretrained(\"sshleifer/distilbart-cnn-12-6\")\n",
    "\n",
    "def tokenize_function(example):\n",
    "    inputs = tokenizer(\n",
    "        example[\"dialogue\"],\n",
    "        max_length=1024,\n",
    "        padding=\"max_length\",\n",
    "        truncation=True\n",
    "    )\n",
    "    with tokenizer.as_target_tokenizer():\n",
    "        labels = tokenizer(\n",
    "            example[\"summary\"],\n",
    "            max_length=128,\n",
    "            padding=\"max_length\",\n",
    "            truncation=True\n",
    "        )\n",
    "    inputs[\"labels\"] = labels[\"input_ids\"]\n",
    "    return inputs\n",
    "tokenized_ds = ds.map(\n",
    "    tokenize_function,\n",
    "    batched=True,\n",
    "    remove_columns=ds[\"train\"].column_names\n",
    ")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-06-12T17:05:15.378134Z",
     "iopub.status.busy": "2025-06-12T17:05:15.377670Z",
     "iopub.status.idle": "2025-06-12T17:05:15.384805Z",
     "shell.execute_reply": "2025-06-12T17:05:15.384102Z",
     "shell.execute_reply.started": "2025-06-12T17:05:15.378114Z"
    },
    "trusted": true
   },
   "outputs": [],
   "source": [
    "import torch \n",
    "from torch.utils.data import DataLoader\n",
    "\n",
    "for split in [\"train\", \"validation\", \"test\"]:\n",
    "    tokenized_ds[split].set_format(type=\"torch\", columns=[\"input_ids\", \"attention_mask\", \"labels\"])\n",
    "train_loader = DataLoader(tokenized_ds[\"train\"], batch_size=8, shuffle=True,num_workers=4)\n",
    "val_loader = DataLoader(tokenized_ds[\"validation\"], batch_size=8,num_workers=4)\n",
    "test_loader = DataLoader(tokenized_ds[\"test\"], batch_size=8,num_workers=4)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-06-12T17:05:15.385961Z",
     "iopub.status.busy": "2025-06-12T17:05:15.385696Z",
     "iopub.status.idle": "2025-06-12T17:05:35.597065Z",
     "shell.execute_reply": "2025-06-12T17:05:35.596176Z",
     "shell.execute_reply.started": "2025-06-12T17:05:15.385922Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2025-06-12 17:05:18.048160: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:477] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
      "WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n",
      "E0000 00:00:1749747918.257111      35 cuda_dnn.cc:8310] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
      "E0000 00:00:1749747918.316434      35 cuda_blas.cc:1418] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "d89f33cc54124a7e9aa9ee425c7a81ac",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "pytorch_model.bin:   0%|          | 0.00/1.22G [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "53e22b661e6a46029ef1f0db2b69d58d",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "model.safetensors:   0%|          | 0.00/1.22G [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Using device: cuda\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "BartForConditionalGeneration(\n",
       "  (model): BartModel(\n",
       "    (shared): BartScaledWordEmbedding(50264, 1024, padding_idx=1)\n",
       "    (encoder): BartEncoder(\n",
       "      (embed_tokens): BartScaledWordEmbedding(50264, 1024, padding_idx=1)\n",
       "      (embed_positions): BartLearnedPositionalEmbedding(1026, 1024)\n",
       "      (layers): ModuleList(\n",
       "        (0-11): 12 x BartEncoderLayer(\n",
       "          (self_attn): BartSdpaAttention(\n",
       "            (k_proj): Linear(in_features=1024, out_features=1024, bias=True)\n",
       "            (v_proj): Linear(in_features=1024, out_features=1024, bias=True)\n",
       "            (q_proj): Linear(in_features=1024, out_features=1024, bias=True)\n",
       "            (out_proj): Linear(in_features=1024, out_features=1024, bias=True)\n",
       "          )\n",
       "          (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)\n",
       "          (activation_fn): GELUActivation()\n",
       "          (fc1): Linear(in_features=1024, out_features=4096, bias=True)\n",
       "          (fc2): Linear(in_features=4096, out_features=1024, bias=True)\n",
       "          (final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)\n",
       "        )\n",
       "      )\n",
       "      (layernorm_embedding): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)\n",
       "    )\n",
       "    (decoder): BartDecoder(\n",
       "      (embed_tokens): BartScaledWordEmbedding(50264, 1024, padding_idx=1)\n",
       "      (embed_positions): BartLearnedPositionalEmbedding(1026, 1024)\n",
       "      (layers): ModuleList(\n",
       "        (0-5): 6 x BartDecoderLayer(\n",
       "          (self_attn): BartSdpaAttention(\n",
       "            (k_proj): Linear(in_features=1024, out_features=1024, bias=True)\n",
       "            (v_proj): Linear(in_features=1024, out_features=1024, bias=True)\n",
       "            (q_proj): Linear(in_features=1024, out_features=1024, bias=True)\n",
       "            (out_proj): Linear(in_features=1024, out_features=1024, bias=True)\n",
       "          )\n",
       "          (activation_fn): GELUActivation()\n",
       "          (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)\n",
       "          (encoder_attn): BartSdpaAttention(\n",
       "            (k_proj): Linear(in_features=1024, out_features=1024, bias=True)\n",
       "            (v_proj): Linear(in_features=1024, out_features=1024, bias=True)\n",
       "            (q_proj): Linear(in_features=1024, out_features=1024, bias=True)\n",
       "            (out_proj): Linear(in_features=1024, out_features=1024, bias=True)\n",
       "          )\n",
       "          (encoder_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)\n",
       "          (fc1): Linear(in_features=1024, out_features=4096, bias=True)\n",
       "          (fc2): Linear(in_features=4096, out_features=1024, bias=True)\n",
       "          (final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)\n",
       "        )\n",
       "      )\n",
       "      (layernorm_embedding): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)\n",
       "    )\n",
       "  )\n",
       "  (lm_head): Linear(in_features=1024, out_features=50264, bias=False)\n",
       ")"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "import torch\n",
    "from transformers import AutoTokenizer, AutoModelForSeq2SeqLM\n",
    "\n",
    "model_name = \"sshleifer/distilbart-cnn-12-6\"\n",
    "\n",
    "tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
    "model = AutoModelForSeq2SeqLM.from_pretrained(model_name)\n",
    "\n",
    "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
    "print(f\"Using device: {device}\")\n",
    "\n",
    "model.to(device)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-06-12T17:05:35.598725Z",
     "iopub.status.busy": "2025-06-12T17:05:35.598092Z",
     "iopub.status.idle": "2025-06-12T17:05:35.634550Z",
     "shell.execute_reply": "2025-06-12T17:05:35.633637Z",
     "shell.execute_reply.started": "2025-06-12T17:05:35.598704Z"
    },
    "trusted": true
   },
   "outputs": [],
   "source": [
    "from torch.optim import AdamW\n",
    "from transformers import get_scheduler\n",
    "\n",
    "optimizer = AdamW(model.parameters(), lr=5e-5, weight_decay=0.01)\n",
    "num_epochs=3\n",
    "\n",
    "num_training_steps = num_epochs * len(train_loader)\n",
    "lr_scheduler = get_scheduler(\n",
    "    name=\"linear\",                 \n",
    "    optimizer=optimizer,\n",
    "    num_warmup_steps=0,                \n",
    "    num_training_steps=num_training_steps,\n",
    ")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-06-12T17:05:35.635812Z",
     "iopub.status.busy": "2025-06-12T17:05:35.635590Z",
     "iopub.status.idle": "2025-06-12T17:05:35.670246Z",
     "shell.execute_reply": "2025-06-12T17:05:35.669407Z",
     "shell.execute_reply.started": "2025-06-12T17:05:35.635795Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CUDA Available: True\n",
      "Device Name: Tesla T4\n",
      "Model is on: cuda:0\n"
     ]
    }
   ],
   "source": [
    "import torch\n",
    "\n",
    "print(\"CUDA Available:\", torch.cuda.is_available())\n",
    "print(\"Device Name:\", torch.cuda.get_device_name(0) if torch.cuda.is_available() else \"CPU only\")\n",
    "print(\"Model is on:\", next(model.parameters()).device)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-06-12T17:05:35.671585Z",
     "iopub.status.busy": "2025-06-12T17:05:35.671257Z",
     "iopub.status.idle": "2025-06-12T17:05:39.563479Z",
     "shell.execute_reply": "2025-06-12T17:05:39.562626Z",
     "shell.execute_reply.started": "2025-06-12T17:05:35.671526Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "--- Dialogue ---\n",
      "\n",
      "#Person1#: Ms. Dawson, I need you to take a dictation for me.\n",
      "#Person2#: Yes, sir...\n",
      "#Person1#: This should go out as an intra-office memorandum to all employees by this afternoon. Are you ready?\n",
      "#Person2#: Yes, sir. Go ahead.\n",
      "#Person1#: Attention all staff... Effective immediately, all office communications are restricted to email correspondence and official memos. The use of Instant Message programs by employees during working hours is strictly prohibited.\n",
      "#Person2#: Sir, does this apply to intra-office communications only? Or will it also restrict external communications?\n",
      "#Person1#: It should apply to all communications, not only in this office between employees, but also any outside communications.\n",
      "#Person2#: But sir, many employees use Instant Messaging to communicate with their clients.\n",
      "#Person1#: They will just have to change their communication methods. I don't want any - one using Instant Messaging in this office. It wastes too much time! Now, please continue with the memo. Where were we?\n",
      "#Person2#: This applies to internal and external communications.\n",
      "#Person1#: Yes. Any employee who persists in using Instant Messaging will first receive a warning and be placed on probation. At second offense, the employee will face termination. Any questions regarding this new policy may be directed to department heads.\n",
      "#Person2#: Is that all?\n",
      "#Person1#: Yes. Please get this memo typed up and distributed to all employees before 4 pm.\n",
      "\n",
      "--- Summary ---\n",
      "\n",
      " The use of Instant Message programs by employees during working hours is strictly prohibited . Any employee who persists in using Instant Messaging will first receive a warning and be placed on probation . At second offense, the employee will face termination . Any questions regarding this new policy may be directed to department heads .\n"
     ]
    }
   ],
   "source": [
    "from transformers import AutoTokenizer, AutoModelForSeq2SeqLM\n",
    "from datasets import load_dataset\n",
    "import torch\n",
    "\n",
    "# 1. Load dataset\n",
    "ds = load_dataset(\"knkarthick/dialogsum\")\n",
    "test_dialogues = ds[\"test\"][\"dialogue\"]\n",
    "\n",
    "# 2. Load a lightweight pretrained summarization model\n",
    "tokenizer = AutoTokenizer.from_pretrained(\"sshleifer/distilbart-cnn-12-6\")\n",
    "model = AutoModelForSeq2SeqLM.from_pretrained(\"sshleifer/distilbart-cnn-12-6\")\n",
    "\n",
    "# 3. Move model to device (GPU if available)\n",
    "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
    "model.to(device)\n",
    "model.eval()\n",
    "\n",
    "# 4. Pick a test example to summarize\n",
    "example_dialogue = test_dialogues[0]\n",
    "\n",
    "# 5. Tokenize and summarize\n",
    "inputs = tokenizer(example_dialogue, return_tensors=\"pt\", max_length=1024, truncation=True).to(device)\n",
    "summary_ids = model.generate(inputs[\"input_ids\"], max_length=128, num_beams=4, early_stopping=True)\n",
    "summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)\n",
    "\n",
    "# 6. Output\n",
    "print(\"\\n--- Dialogue ---\\n\")\n",
    "print(example_dialogue)\n",
    "\n",
    "print(\"\\n--- Summary ---\\n\")\n",
    "print(summary)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-06-12T17:05:39.564906Z",
     "iopub.status.busy": "2025-06-12T17:05:39.564625Z",
     "iopub.status.idle": "2025-06-12T17:05:43.195555Z",
     "shell.execute_reply": "2025-06-12T17:05:43.194726Z",
     "shell.execute_reply.started": "2025-06-12T17:05:39.564883Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
      "To disable this warning, you can either:\n",
      "\t- Avoid using `tokenizers` before the fork if possible\n",
      "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting evaluate\n",
      "  Downloading evaluate-0.4.3-py3-none-any.whl.metadata (9.2 kB)\n",
      "Requirement already satisfied: datasets>=2.0.0 in /usr/local/lib/python3.11/dist-packages (from evaluate) (3.6.0)\n",
      "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.11/dist-packages (from evaluate) (1.26.4)\n",
      "Requirement already satisfied: dill in /usr/local/lib/python3.11/dist-packages (from evaluate) (0.3.8)\n",
      "Requirement already satisfied: pandas in /usr/local/lib/python3.11/dist-packages (from evaluate) (2.2.3)\n",
      "Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.11/dist-packages (from evaluate) (2.32.3)\n",
      "Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.11/dist-packages (from evaluate) (4.67.1)\n",
      "Requirement already satisfied: xxhash in /usr/local/lib/python3.11/dist-packages (from evaluate) (3.5.0)\n",
      "Requirement already satisfied: multiprocess in /usr/local/lib/python3.11/dist-packages (from evaluate) (0.70.16)\n",
      "Requirement already satisfied: fsspec>=2021.05.0 in /usr/local/lib/python3.11/dist-packages (from fsspec[http]>=2021.05.0->evaluate) (2025.3.0)\n",
      "Requirement already satisfied: huggingface-hub>=0.7.0 in /usr/local/lib/python3.11/dist-packages (from evaluate) (0.31.1)\n",
      "Requirement already satisfied: packaging in /usr/local/lib/python3.11/dist-packages (from evaluate) (25.0)\n",
      "Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from datasets>=2.0.0->evaluate) (3.18.0)\n",
      "Requirement already satisfied: pyarrow>=15.0.0 in /usr/local/lib/python3.11/dist-packages (from datasets>=2.0.0->evaluate) (19.0.1)\n",
      "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.11/dist-packages (from datasets>=2.0.0->evaluate) (6.0.2)\n",
      "Requirement already satisfied: aiohttp!=4.0.0a0,!=4.0.0a1 in /usr/local/lib/python3.11/dist-packages (from fsspec[http]>=2021.05.0->evaluate) (3.11.18)\n",
      "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.11/dist-packages (from huggingface-hub>=0.7.0->evaluate) (4.13.2)\n",
      "Requirement already satisfied: hf-xet<2.0.0,>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from huggingface-hub>=0.7.0->evaluate) (1.1.0)\n",
      "Requirement already satisfied: mkl_fft in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17->evaluate) (1.3.8)\n",
      "Requirement already satisfied: mkl_random in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17->evaluate) (1.2.4)\n",
      "Requirement already satisfied: mkl_umath in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17->evaluate) (0.1.1)\n",
      "Requirement already satisfied: mkl in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17->evaluate) (2025.1.0)\n",
      "Requirement already satisfied: tbb4py in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17->evaluate) (2022.1.0)\n",
      "Requirement already satisfied: mkl-service in /usr/local/lib/python3.11/dist-packages (from numpy>=1.17->evaluate) (2.4.1)\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests>=2.19.0->evaluate) (3.4.2)\n",
      "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests>=2.19.0->evaluate) (3.10)\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests>=2.19.0->evaluate) (2.4.0)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/dist-packages (from requests>=2.19.0->evaluate) (2025.4.26)\n",
      "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.11/dist-packages (from pandas->evaluate) (2.9.0.post0)\n",
      "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas->evaluate) (2025.2)\n",
      "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.11/dist-packages (from pandas->evaluate) (2025.2)\n",
      "Requirement already satisfied: aiohappyeyeballs>=2.3.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2021.05.0->evaluate) (2.6.1)\n",
      "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2021.05.0->evaluate) (1.3.2)\n",
      "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2021.05.0->evaluate) (25.3.0)\n",
      "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2021.05.0->evaluate) (1.6.0)\n",
      "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2021.05.0->evaluate) (6.4.3)\n",
      "Requirement already satisfied: propcache>=0.2.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2021.05.0->evaluate) (0.3.1)\n",
      "Requirement already satisfied: yarl<2.0,>=1.17.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2021.05.0->evaluate) (1.20.0)\n",
      "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/dist-packages (from python-dateutil>=2.8.2->pandas->evaluate) (1.17.0)\n",
      "Requirement already satisfied: intel-openmp<2026,>=2024 in /usr/local/lib/python3.11/dist-packages (from mkl->numpy>=1.17->evaluate) (2024.2.0)\n",
      "Requirement already satisfied: tbb==2022.* in /usr/local/lib/python3.11/dist-packages (from mkl->numpy>=1.17->evaluate) (2022.1.0)\n",
      "Requirement already satisfied: tcmlib==1.* in /usr/local/lib/python3.11/dist-packages (from tbb==2022.*->mkl->numpy>=1.17->evaluate) (1.3.0)\n",
      "Requirement already satisfied: intel-cmplr-lib-rt in /usr/local/lib/python3.11/dist-packages (from mkl_umath->numpy>=1.17->evaluate) (2024.2.0)\n",
      "Requirement already satisfied: intel-cmplr-lib-ur==2024.2.0 in /usr/local/lib/python3.11/dist-packages (from intel-openmp<2026,>=2024->mkl->numpy>=1.17->evaluate) (2024.2.0)\n",
      "Downloading evaluate-0.4.3-py3-none-any.whl (84 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m84.0/84.0 kB\u001b[0m \u001b[31m3.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hInstalling collected packages: evaluate\n",
      "Successfully installed evaluate-0.4.3\n"
     ]
    }
   ],
   "source": [
    "!pip install evaluate\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": true,
    "execution": {
     "iopub.execute_input": "2025-06-12T17:05:43.196795Z",
     "iopub.status.busy": "2025-06-12T17:05:43.196573Z",
     "iopub.status.idle": "2025-06-12T17:05:56.234877Z",
     "shell.execute_reply": "2025-06-12T17:05:56.234133Z",
     "shell.execute_reply.started": "2025-06-12T17:05:43.196773Z"
    },
    "jupyter": {
     "outputs_hidden": true
    },
    "trusted": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
      "To disable this warning, you can either:\n",
      "\t- Avoid using `tokenizers` before the fork if possible\n",
      "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting rouge_score\n",
      "  Downloading rouge_score-0.1.2.tar.gz (17 kB)\n",
      "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
      "Requirement already satisfied: absl-py in /usr/local/lib/python3.11/dist-packages (from rouge_score) (1.4.0)\n",
      "Requirement already satisfied: nltk in /usr/local/lib/python3.11/dist-packages (from rouge_score) (3.9.1)\n",
      "Requirement already satisfied: numpy in /usr/local/lib/python3.11/dist-packages (from rouge_score) (1.26.4)\n",
      "Requirement already satisfied: six>=1.14.0 in /usr/local/lib/python3.11/dist-packages (from rouge_score) (1.17.0)\n",
      "Requirement already satisfied: click in /usr/local/lib/python3.11/dist-packages (from nltk->rouge_score) (8.1.8)\n",
      "Requirement already satisfied: joblib in /usr/local/lib/python3.11/dist-packages (from nltk->rouge_score) (1.5.0)\n",
      "Requirement already satisfied: regex>=2021.8.3 in /usr/local/lib/python3.11/dist-packages (from nltk->rouge_score) (2024.11.6)\n",
      "Requirement already satisfied: tqdm in /usr/local/lib/python3.11/dist-packages (from nltk->rouge_score) (4.67.1)\n",
      "Requirement already satisfied: mkl_fft in /usr/local/lib/python3.11/dist-packages (from numpy->rouge_score) (1.3.8)\n",
      "Requirement already satisfied: mkl_random in /usr/local/lib/python3.11/dist-packages (from numpy->rouge_score) (1.2.4)\n",
      "Requirement already satisfied: mkl_umath in /usr/local/lib/python3.11/dist-packages (from numpy->rouge_score) (0.1.1)\n",
      "Requirement already satisfied: mkl in /usr/local/lib/python3.11/dist-packages (from numpy->rouge_score) (2025.1.0)\n",
      "Requirement already satisfied: tbb4py in /usr/local/lib/python3.11/dist-packages (from numpy->rouge_score) (2022.1.0)\n",
      "Requirement already satisfied: mkl-service in /usr/local/lib/python3.11/dist-packages (from numpy->rouge_score) (2.4.1)\n",
      "Requirement already satisfied: intel-openmp<2026,>=2024 in /usr/local/lib/python3.11/dist-packages (from mkl->numpy->rouge_score) (2024.2.0)\n",
      "Requirement already satisfied: tbb==2022.* in /usr/local/lib/python3.11/dist-packages (from mkl->numpy->rouge_score) (2022.1.0)\n",
      "Requirement already satisfied: tcmlib==1.* in /usr/local/lib/python3.11/dist-packages (from tbb==2022.*->mkl->numpy->rouge_score) (1.3.0)\n",
      "Requirement already satisfied: intel-cmplr-lib-rt in /usr/local/lib/python3.11/dist-packages (from mkl_umath->numpy->rouge_score) (2024.2.0)\n",
      "Requirement already satisfied: intel-cmplr-lib-ur==2024.2.0 in /usr/local/lib/python3.11/dist-packages (from intel-openmp<2026,>=2024->mkl->numpy->rouge_score) (2024.2.0)\n",
      "Building wheels for collected packages: rouge_score\n",
      "  Building wheel for rouge_score (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
      "  Created wheel for rouge_score: filename=rouge_score-0.1.2-py3-none-any.whl size=24934 sha256=b66536c4a57b6d602a59f82536abf9cdb3d83ae75b752f815f298def1a2891ee\n",
      "  Stored in directory: /root/.cache/pip/wheels/1e/19/43/8a442dc83660ca25e163e1bd1f89919284ab0d0c1475475148\n",
      "Successfully built rouge_score\n",
      "Installing collected packages: rouge_score\n",
      "Successfully installed rouge_score-0.1.2\n"
     ]
    }
   ],
   "source": [
    "!pip install rouge_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-06-12T17:05:56.236436Z",
     "iopub.status.busy": "2025-06-12T17:05:56.236159Z",
     "iopub.status.idle": "2025-06-12T17:05:57.972541Z",
     "shell.execute_reply": "2025-06-12T17:05:57.971744Z",
     "shell.execute_reply.started": "2025-06-12T17:05:56.236413Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "0a0de9e1e5ee4a9d9c1d705fad7fc03d",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading builder script:   0%|          | 0.00/6.27k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'rouge1': 0.6666666666666666, 'rouge2': 0.42105263157894735, 'rougeL': 0.6666666666666666, 'rougeLsum': 0.6666666666666666}\n"
     ]
    }
   ],
   "source": [
    "import evaluate\n",
    "\n",
    "rouge = evaluate.load(\"rouge\")\n",
    "\n",
    "predictions = [\"The use of Instant Messaging is prohibited...\"]\n",
    "references = [\"The use of Instant Messaging programs by employees during working hours is strictly prohibited...\"]\n",
    "\n",
    "results = rouge.compute(predictions=predictions, references=references)\n",
    "print(results)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-06-12T17:19:07.923722Z",
     "iopub.status.busy": "2025-06-12T17:19:07.922912Z",
     "iopub.status.idle": "2025-06-12T17:19:07.938514Z",
     "shell.execute_reply": "2025-06-12T17:19:07.937755Z",
     "shell.execute_reply.started": "2025-06-12T17:19:07.923698Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "a89c2a8663494ab0a27750205864dc51",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from huggingface_hub import notebook_login\n",
    "notebook_login()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": true,
    "execution": {
     "iopub.execute_input": "2025-06-12T17:23:13.786175Z",
     "iopub.status.busy": "2025-06-12T17:23:13.785509Z",
     "iopub.status.idle": "2025-06-12T17:23:30.231846Z",
     "shell.execute_reply": "2025-06-12T17:23:30.231079Z",
     "shell.execute_reply.started": "2025-06-12T17:23:13.786150Z"
    },
    "jupyter": {
     "outputs_hidden": true
    },
    "trusted": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/lib/python3.11/dist-packages/transformers/modeling_utils.py:3339: UserWarning: Moving the following attributes in the config to the generation config: {'max_length': 142, 'min_length': 56, 'early_stopping': True, 'num_beams': 4, 'length_penalty': 2.0, 'no_repeat_ngram_size': 3, 'forced_bos_token_id': 0}. You are seeing this warning because you've set generation parameters in the model config, as opposed to in the generation config.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "ed9e01e36c42436fb8e4be77e3b51552",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Uploading...:   0%|          | 0.00/1.22G [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "No files have been modified since last commit. Skipping to prevent empty commit.\n",
      "No files have been modified since last commit. Skipping to prevent empty commit.\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "CommitInfo(commit_url='https://huggingface.co/zahraa12355/tiny-distilbart-dialogsum/commit/002c41446a8368246986e3bd3175e7e1f2363e59', commit_message='Upload tokenizer', commit_description='', oid='002c41446a8368246986e3bd3175e7e1f2363e59', pr_url=None, repo_url=RepoUrl('https://huggingface.co/zahraa12355/tiny-distilbart-dialogsum', endpoint='https://huggingface.co', repo_type='model', repo_id='zahraa12355/tiny-distilbart-dialogsum'), pr_revision=None, pr_num=None)"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from transformers import AutoTokenizer, AutoModelForSeq2SeqLM\n",
    "model = AutoModelForSeq2SeqLM.from_pretrained(\"sshleifer/distilbart-cnn-12-6\")\n",
    "tokenizer = AutoTokenizer.from_pretrained(\"sshleifer/distilbart-cnn-12-6\")\n",
    "repo_id = \"zahraa12355/tiny-distilbart-dialogsum\"\n",
    "model.push_to_hub(repo_id)\n",
    "tokenizer.push_to_hub(repo_id)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": true,
    "execution": {
     "iopub.execute_input": "2025-06-12T17:28:01.717930Z",
     "iopub.status.busy": "2025-06-12T17:28:01.717304Z",
     "iopub.status.idle": "2025-06-12T17:28:10.952330Z",
     "shell.execute_reply": "2025-06-12T17:28:10.951482Z",
     "shell.execute_reply.started": "2025-06-12T17:28:01.717908Z"
    },
    "jupyter": {
     "outputs_hidden": true
    },
    "trusted": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...\n",
      "To disable this warning, you can either:\n",
      "\t- Avoid using `tokenizers` before the fork if possible\n",
      "\t- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Collecting gradio\n",
      "  Downloading gradio-5.33.2-py3-none-any.whl.metadata (16 kB)\n",
      "Requirement already satisfied: aiofiles<25.0,>=22.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (22.1.0)\n",
      "Requirement already satisfied: anyio<5.0,>=3.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (4.9.0)\n",
      "Collecting fastapi<1.0,>=0.115.2 (from gradio)\n",
      "  Downloading fastapi-0.115.12-py3-none-any.whl.metadata (27 kB)\n",
      "Collecting ffmpy (from gradio)\n",
      "  Downloading ffmpy-0.6.0-py3-none-any.whl.metadata (2.9 kB)\n",
      "Collecting gradio-client==1.10.3 (from gradio)\n",
      "  Downloading gradio_client-1.10.3-py3-none-any.whl.metadata (7.1 kB)\n",
      "Collecting groovy~=0.1 (from gradio)\n",
      "  Downloading groovy-0.1.2-py3-none-any.whl.metadata (6.1 kB)\n",
      "Requirement already satisfied: httpx>=0.24.1 in /usr/local/lib/python3.11/dist-packages (from gradio) (0.28.1)\n",
      "Requirement already satisfied: huggingface-hub>=0.28.1 in /usr/local/lib/python3.11/dist-packages (from gradio) (0.31.1)\n",
      "Requirement already satisfied: jinja2<4.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (3.1.6)\n",
      "Requirement already satisfied: markupsafe<4.0,>=2.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (3.0.2)\n",
      "Requirement already satisfied: numpy<3.0,>=1.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (1.26.4)\n",
      "Requirement already satisfied: orjson~=3.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (3.10.16)\n",
      "Requirement already satisfied: packaging in /usr/local/lib/python3.11/dist-packages (from gradio) (25.0)\n",
      "Requirement already satisfied: pandas<3.0,>=1.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (2.2.3)\n",
      "Requirement already satisfied: pillow<12.0,>=8.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (11.1.0)\n",
      "Requirement already satisfied: pydantic<2.12,>=2.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (2.11.4)\n",
      "Requirement already satisfied: pydub in /usr/local/lib/python3.11/dist-packages (from gradio) (0.25.1)\n",
      "Collecting python-multipart>=0.0.18 (from gradio)\n",
      "  Downloading python_multipart-0.0.20-py3-none-any.whl.metadata (1.8 kB)\n",
      "Requirement already satisfied: pyyaml<7.0,>=5.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (6.0.2)\n",
      "Collecting ruff>=0.9.3 (from gradio)\n",
      "  Downloading ruff-0.11.13-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (25 kB)\n",
      "Collecting safehttpx<0.2.0,>=0.1.6 (from gradio)\n",
      "  Downloading safehttpx-0.1.6-py3-none-any.whl.metadata (4.2 kB)\n",
      "Collecting semantic-version~=2.0 (from gradio)\n",
      "  Downloading semantic_version-2.10.0-py2.py3-none-any.whl.metadata (9.7 kB)\n",
      "Collecting starlette<1.0,>=0.40.0 (from gradio)\n",
      "  Downloading starlette-0.47.0-py3-none-any.whl.metadata (6.2 kB)\n",
      "Collecting tomlkit<0.14.0,>=0.12.0 (from gradio)\n",
      "  Downloading tomlkit-0.13.3-py3-none-any.whl.metadata (2.8 kB)\n",
      "Requirement already satisfied: typer<1.0,>=0.12 in /usr/local/lib/python3.11/dist-packages (from gradio) (0.15.2)\n",
      "Requirement already satisfied: typing-extensions~=4.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (4.13.2)\n",
      "Collecting uvicorn>=0.14.0 (from gradio)\n",
      "  Downloading uvicorn-0.34.3-py3-none-any.whl.metadata (6.5 kB)\n",
      "Requirement already satisfied: fsspec in /usr/local/lib/python3.11/dist-packages (from gradio-client==1.10.3->gradio) (2025.3.0)\n",
      "Requirement already satisfied: websockets<16.0,>=10.0 in /usr/local/lib/python3.11/dist-packages (from gradio-client==1.10.3->gradio) (15.0.1)\n",
      "Requirement already satisfied: idna>=2.8 in /usr/local/lib/python3.11/dist-packages (from anyio<5.0,>=3.0->gradio) (3.10)\n",
      "Requirement already satisfied: sniffio>=1.1 in /usr/local/lib/python3.11/dist-packages (from anyio<5.0,>=3.0->gradio) (1.3.1)\n",
      "Collecting starlette<1.0,>=0.40.0 (from gradio)\n",
      "  Downloading starlette-0.46.2-py3-none-any.whl.metadata (6.2 kB)\n",
      "Requirement already satisfied: certifi in /usr/local/lib/python3.11/dist-packages (from httpx>=0.24.1->gradio) (2025.4.26)\n",
      "Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.11/dist-packages (from httpx>=0.24.1->gradio) (1.0.7)\n",
      "Requirement already satisfied: h11<0.15,>=0.13 in /usr/local/lib/python3.11/dist-packages (from httpcore==1.*->httpx>=0.24.1->gradio) (0.14.0)\n",
      "Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from huggingface-hub>=0.28.1->gradio) (3.18.0)\n",
      "Requirement already satisfied: requests in /usr/local/lib/python3.11/dist-packages (from huggingface-hub>=0.28.1->gradio) (2.32.3)\n",
      "Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.11/dist-packages (from huggingface-hub>=0.28.1->gradio) (4.67.1)\n",
      "Requirement already satisfied: hf-xet<2.0.0,>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from huggingface-hub>=0.28.1->gradio) (1.1.0)\n",
      "Requirement already satisfied: mkl_fft in /usr/local/lib/python3.11/dist-packages (from numpy<3.0,>=1.0->gradio) (1.3.8)\n",
      "Requirement already satisfied: mkl_random in /usr/local/lib/python3.11/dist-packages (from numpy<3.0,>=1.0->gradio) (1.2.4)\n",
      "Requirement already satisfied: mkl_umath in /usr/local/lib/python3.11/dist-packages (from numpy<3.0,>=1.0->gradio) (0.1.1)\n",
      "Requirement already satisfied: mkl in /usr/local/lib/python3.11/dist-packages (from numpy<3.0,>=1.0->gradio) (2025.1.0)\n",
      "Requirement already satisfied: tbb4py in /usr/local/lib/python3.11/dist-packages (from numpy<3.0,>=1.0->gradio) (2022.1.0)\n",
      "Requirement already satisfied: mkl-service in /usr/local/lib/python3.11/dist-packages (from numpy<3.0,>=1.0->gradio) (2.4.1)\n",
      "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.11/dist-packages (from pandas<3.0,>=1.0->gradio) (2.9.0.post0)\n",
      "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas<3.0,>=1.0->gradio) (2025.2)\n",
      "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.11/dist-packages (from pandas<3.0,>=1.0->gradio) (2025.2)\n",
      "Requirement already satisfied: annotated-types>=0.6.0 in /usr/local/lib/python3.11/dist-packages (from pydantic<2.12,>=2.0->gradio) (0.7.0)\n",
      "Requirement already satisfied: pydantic-core==2.33.2 in /usr/local/lib/python3.11/dist-packages (from pydantic<2.12,>=2.0->gradio) (2.33.2)\n",
      "Requirement already satisfied: typing-inspection>=0.4.0 in /usr/local/lib/python3.11/dist-packages (from pydantic<2.12,>=2.0->gradio) (0.4.0)\n",
      "Requirement already satisfied: click>=8.0.0 in /usr/local/lib/python3.11/dist-packages (from typer<1.0,>=0.12->gradio) (8.1.8)\n",
      "Requirement already satisfied: shellingham>=1.3.0 in /usr/local/lib/python3.11/dist-packages (from typer<1.0,>=0.12->gradio) (1.5.4)\n",
      "Requirement already satisfied: rich>=10.11.0 in /usr/local/lib/python3.11/dist-packages (from typer<1.0,>=0.12->gradio) (14.0.0)\n",
      "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/dist-packages (from python-dateutil>=2.8.2->pandas<3.0,>=1.0->gradio) (1.17.0)\n",
      "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.11/dist-packages (from rich>=10.11.0->typer<1.0,>=0.12->gradio) (3.0.0)\n",
      "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.11/dist-packages (from rich>=10.11.0->typer<1.0,>=0.12->gradio) (2.19.1)\n",
      "Requirement already satisfied: intel-openmp<2026,>=2024 in /usr/local/lib/python3.11/dist-packages (from mkl->numpy<3.0,>=1.0->gradio) (2024.2.0)\n",
      "Requirement already satisfied: tbb==2022.* in /usr/local/lib/python3.11/dist-packages (from mkl->numpy<3.0,>=1.0->gradio) (2022.1.0)\n",
      "Requirement already satisfied: tcmlib==1.* in /usr/local/lib/python3.11/dist-packages (from tbb==2022.*->mkl->numpy<3.0,>=1.0->gradio) (1.3.0)\n",
      "Requirement already satisfied: intel-cmplr-lib-rt in /usr/local/lib/python3.11/dist-packages (from mkl_umath->numpy<3.0,>=1.0->gradio) (2024.2.0)\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests->huggingface-hub>=0.28.1->gradio) (3.4.2)\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests->huggingface-hub>=0.28.1->gradio) (2.4.0)\n",
      "Requirement already satisfied: intel-cmplr-lib-ur==2024.2.0 in /usr/local/lib/python3.11/dist-packages (from intel-openmp<2026,>=2024->mkl->numpy<3.0,>=1.0->gradio) (2024.2.0)\n",
      "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.11/dist-packages (from markdown-it-py>=2.2.0->rich>=10.11.0->typer<1.0,>=0.12->gradio) (0.1.2)\n",
      "Downloading gradio-5.33.2-py3-none-any.whl (54.3 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m54.3/54.3 MB\u001b[0m \u001b[31m33.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m00:01\u001b[0m\n",
      "\u001b[?25hDownloading gradio_client-1.10.3-py3-none-any.whl (323 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m323.6/323.6 kB\u001b[0m \u001b[31m24.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading fastapi-0.115.12-py3-none-any.whl (95 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m95.2/95.2 kB\u001b[0m \u001b[31m9.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading groovy-0.1.2-py3-none-any.whl (14 kB)\n",
      "Downloading python_multipart-0.0.20-py3-none-any.whl (24 kB)\n",
      "Downloading ruff-0.11.13-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (11.6 MB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m11.6/11.6 MB\u001b[0m \u001b[31m101.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m0:01\u001b[0m\n",
      "\u001b[?25hDownloading safehttpx-0.1.6-py3-none-any.whl (8.7 kB)\n",
      "Downloading semantic_version-2.10.0-py2.py3-none-any.whl (15 kB)\n",
      "Downloading starlette-0.46.2-py3-none-any.whl (72 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m72.0/72.0 kB\u001b[0m \u001b[31m6.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading tomlkit-0.13.3-py3-none-any.whl (38 kB)\n",
      "Downloading uvicorn-0.34.3-py3-none-any.whl (62 kB)\n",
      "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.4/62.4 kB\u001b[0m \u001b[31m5.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
      "\u001b[?25hDownloading ffmpy-0.6.0-py3-none-any.whl (5.5 kB)\n",
      "Installing collected packages: uvicorn, tomlkit, semantic-version, ruff, python-multipart, groovy, ffmpy, starlette, safehttpx, gradio-client, fastapi, gradio\n",
      "Successfully installed fastapi-0.115.12 ffmpy-0.6.0 gradio-5.33.2 gradio-client-1.10.3 groovy-0.1.2 python-multipart-0.0.20 ruff-0.11.13 safehttpx-0.1.6 semantic-version-2.10.0 starlette-0.46.2 tomlkit-0.13.3 uvicorn-0.34.3\n"
     ]
    }
   ],
   "source": [
    "!pip install gradio\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-06-12T17:41:26.920321Z",
     "iopub.status.busy": "2025-06-12T17:41:26.919582Z",
     "iopub.status.idle": "2025-06-12T17:41:29.615709Z",
     "shell.execute_reply": "2025-06-12T17:41:29.615166Z",
     "shell.execute_reply.started": "2025-06-12T17:41:26.920296Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "* Running on local URL:  http://127.0.0.1:7862\n",
      "It looks like you are running Gradio on a hosted Jupyter notebook, which requires `share=True`. Automatically setting `share=True` (you can turn this off by setting `share=False` in `launch()` explicitly).\n",
      "\n",
      "* Running on public URL: https://49b0cf98fc551a8610.gradio.live\n",
      "\n",
      "This share link expires in 1 week. For free permanent hosting and GPU upgrades, run `gradio deploy` from the terminal in the working directory to deploy to Hugging Face Spaces (https://huggingface.co/spaces)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div><iframe src=\"https://49b0cf98fc551a8610.gradio.live\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": []
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from transformers import AutoTokenizer, AutoModelForSeq2SeqLM\n",
    "import gradio as gr\n",
    "\n",
    "tokenizer = AutoTokenizer.from_pretrained(\"sshleifer/distilbart-cnn-12-6\")\n",
    "model = AutoModelForSeq2SeqLM.from_pretrained(\"sshleifer/distilbart-cnn-12-6\")\n",
    "\n",
    "def summarize_text(text):\n",
    "    inputs = tokenizer(text, return_tensors=\"pt\", max_length=1024, truncation=True)\n",
    "    summary_ids = model.generate(\n",
    "        inputs[\"input_ids\"],\n",
    "        attention_mask=inputs[\"attention_mask\"],\n",
    "        max_length=100,\n",
    "        min_length=20,\n",
    "        length_penalty=2.0,\n",
    "        num_beams=4,\n",
    "        early_stopping=True,\n",
    "        no_repeat_ngram_size=3\n",
    "    )\n",
    "    summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)\n",
    "    return summary\n",
    "\n",
    "iface = gr.Interface(\n",
    "    fn=summarize_text,\n",
    "    inputs=gr.Textbox(lines=5, label=\"Input Text\"),\n",
    "    outputs=gr.Textbox(label=\"Summary\"),\n",
    "    title=\"DistilBART Summarizer\",\n",
    "    description=\"Summarize any input text using DistilBART fine-tuned model.\"\n",
    ")\n",
    "\n",
    "iface.launch()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-06-12T17:49:48.620290Z",
     "iopub.status.busy": "2025-06-12T17:49:48.620045Z",
     "iopub.status.idle": "2025-06-12T17:49:48.625290Z",
     "shell.execute_reply": "2025-06-12T17:49:48.624563Z",
     "shell.execute_reply.started": "2025-06-12T17:49:48.620275Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "requirements.txt created!\n"
     ]
    }
   ],
   "source": [
    "requirements = \"\"\"\n",
    "transformers\n",
    "torch\n",
    "gradio\n",
    "\"\"\"\n",
    "\n",
    "with open(\"requirements.txt\", \"w\") as f:\n",
    "    f.write(requirements)\n",
    "\n",
    "print(\"requirements.txt created!\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-06-12T17:50:44.573519Z",
     "iopub.status.busy": "2025-06-12T17:50:44.572783Z",
     "iopub.status.idle": "2025-06-12T17:50:44.578702Z",
     "shell.execute_reply": "2025-06-12T17:50:44.577872Z",
     "shell.execute_reply.started": "2025-06-12T17:50:44.573494Z"
    },
    "trusted": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "app.py created!\n"
     ]
    }
   ],
   "source": [
    "code = '''\n",
    "import gradio as gr\n",
    "from transformers import AutoTokenizer, AutoModelForSeq2SeqLM\n",
    "\n",
    "tokenizer = AutoTokenizer.from_pretrained(\"sshleifer/distilbart-cnn-12-6\")\n",
    "model = AutoModelForSeq2SeqLM.from_pretrained(\"sshleifer/distilbart-cnn-12-6\")\n",
    "\n",
    "def summarize_text(text):\n",
    "    inputs = tokenizer(text, return_tensors=\"pt\", max_length=1024, truncation=True)\n",
    "    summary_ids = model.generate(\n",
    "        inputs[\"input_ids\"],\n",
    "        attention_mask=inputs[\"attention_mask\"],\n",
    "        max_length=100,\n",
    "        min_length=20,\n",
    "        length_penalty=2.0,\n",
    "        num_beams=4,\n",
    "        early_stopping=True,\n",
    "        no_repeat_ngram_size=3\n",
    "    )\n",
    "    summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)\n",
    "    return summary\n",
    "\n",
    "iface = gr.Interface(\n",
    "    fn=summarize_text,\n",
    "    inputs=gr.Textbox(lines=5, label=\"Input Text\"),\n",
    "    outputs=gr.Textbox(label=\"Summary\"),\n",
    "    title=\"DistilBART Summarizer\",\n",
    "    description=\"Summarize any input text using DistilBART fine-tuned model.\"\n",
    ")\n",
    "\n",
    "iface.launch()\n",
    "'''\n",
    "\n",
    "with open(\"app.py\", \"w\") as f:\n",
    "    f.write(code)\n",
    "\n",
    "print(\"app.py created!\")\n"
   ]
  }
 ],
 "metadata": {
  "kaggle": {
   "accelerator": "nvidiaTeslaT4",
   "dataSources": [],
   "dockerImageVersionId": 31040,
   "isGpuEnabled": true,
   "isInternetEnabled": true,
   "language": "python",
   "sourceType": "notebook"
  },
  "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": "3.11.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}