llama2_7b_ft.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4",
      "machine_shape": "hm"
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU",
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "26c603e6f8ec4ef8a3efbc21ae719ed2": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_45572f3563db467aa34602372c0be409",
              "IPY_MODEL_6ec4eb0517554fc2b50ff082af9edca9",
              "IPY_MODEL_8f6ad07eafff4f86ad80ed5cbb191d03"
            ],
            "layout": "IPY_MODEL_7be482eeda3547d3948701ace7277bb3"
          }
        },
        "45572f3563db467aa34602372c0be409": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_e83ca5bce91641fdb5c852df465cf1b6",
            "placeholder": "​",
            "style": "IPY_MODEL_826026a9e4e14b66a1717dfaca61b8a7",
            "value": "Loading checkpoint shards: 100%"
          }
        },
        "6ec4eb0517554fc2b50ff082af9edca9": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_299c18e228ec45deb04e6161534a7ee1",
            "max": 2,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_7c2ea4d6ae2041d3a4e716cdb1718e58",
            "value": 2
          }
        },
        "8f6ad07eafff4f86ad80ed5cbb191d03": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_d81d246e68f84080aa67525c3058040c",
            "placeholder": "​",
            "style": "IPY_MODEL_5145823c7f5e4fa3a553c0c42982a2e4",
            "value": " 2/2 [00:04&lt;00:00,  2.27s/it]"
          }
        },
        "7be482eeda3547d3948701ace7277bb3": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "e83ca5bce91641fdb5c852df465cf1b6": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "826026a9e4e14b66a1717dfaca61b8a7": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "299c18e228ec45deb04e6161534a7ee1": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "7c2ea4d6ae2041d3a4e716cdb1718e58": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "d81d246e68f84080aa67525c3058040c": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "5145823c7f5e4fa3a553c0c42982a2e4": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "518c2a00450f46f782daae2a7757fe2a": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_2092e9dae7664b6c9251badf72da6dd2",
              "IPY_MODEL_49c3c6105e0d47d8b4ac508f61ac2f93",
              "IPY_MODEL_f73d89a632b74e588f3444663db18c71"
            ],
            "layout": "IPY_MODEL_ee2d3c528c22481dbe30074bf6475a50"
          }
        },
        "2092e9dae7664b6c9251badf72da6dd2": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_58efb4ffee8b4d94941f8bf35043ea9a",
            "placeholder": "​",
            "style": "IPY_MODEL_61af3afe3fa6408b842a77646672eae8",
            "value": "Downloading (…)lve/main/config.json: 100%"
          }
        },
        "49c3c6105e0d47d8b4ac508f61ac2f93": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_3b25cd12e0824ec580df1d616d4ebdb2",
            "max": 583,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_281142a746cb4cdebf78f7eccfc7acb2",
            "value": 583
          }
        },
        "f73d89a632b74e588f3444663db18c71": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_d4fd64c0826646508993a9402c41e04f",
            "placeholder": "​",
            "style": "IPY_MODEL_ebc1fc5defa049699ab19e79b3caabaa",
            "value": " 583/583 [00:00&lt;00:00, 57.7kB/s]"
          }
        },
        "ee2d3c528c22481dbe30074bf6475a50": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "58efb4ffee8b4d94941f8bf35043ea9a": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "61af3afe3fa6408b842a77646672eae8": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "3b25cd12e0824ec580df1d616d4ebdb2": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "281142a746cb4cdebf78f7eccfc7acb2": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "d4fd64c0826646508993a9402c41e04f": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "ebc1fc5defa049699ab19e79b3caabaa": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "9a3d344182fb4c6cb351ac0b0978c0cf": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_7bfe60ec0dfe473bbdf9c36988bf4829",
              "IPY_MODEL_03e72f11a4324523866bb4d8944a22d6",
              "IPY_MODEL_834ffe46ea2f43feab88d5905133e712"
            ],
            "layout": "IPY_MODEL_ebb0e0fce7ff45289bf15dc40aa55d1a"
          }
        },
        "7bfe60ec0dfe473bbdf9c36988bf4829": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_0d0d9072dc2e42cbb8704dc239756c8a",
            "placeholder": "​",
            "style": "IPY_MODEL_fe9f31a56f5f4b009796e691bb2b635a",
            "value": "Downloading (…)fetensors.index.json: 100%"
          }
        },
        "03e72f11a4324523866bb4d8944a22d6": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_53187a779b9a456db8ebef9f112a104c",
            "max": 26788,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_376075ad007f4aa98530c1847e14e10c",
            "value": 26788
          }
        },
        "834ffe46ea2f43feab88d5905133e712": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_1ca5d78c7b0d4957931fa22d1dd90dce",
            "placeholder": "​",
            "style": "IPY_MODEL_d1b29e0b943d4e40ba07dbba502ac424",
            "value": " 26.8k/26.8k [00:00&lt;00:00, 2.52MB/s]"
          }
        },
        "ebb0e0fce7ff45289bf15dc40aa55d1a": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "0d0d9072dc2e42cbb8704dc239756c8a": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "fe9f31a56f5f4b009796e691bb2b635a": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "53187a779b9a456db8ebef9f112a104c": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "376075ad007f4aa98530c1847e14e10c": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "1ca5d78c7b0d4957931fa22d1dd90dce": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "d1b29e0b943d4e40ba07dbba502ac424": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "71f94fcfff1c42f3bd47949d7b3232a0": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_8f1ee3b4aa7c4586a7a5c98faa18ac47",
              "IPY_MODEL_1c44539ef9614cca95d1d2d414c3b280",
              "IPY_MODEL_a192f87c278b43fcac8dcdbb722c100d"
            ],
            "layout": "IPY_MODEL_8186e4b9f21446c1a2c518ded94c9e21"
          }
        },
        "8f1ee3b4aa7c4586a7a5c98faa18ac47": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_393f1f2d38ca48d1beeaf3caa340a166",
            "placeholder": "​",
            "style": "IPY_MODEL_879c35ad45864adeab33da232ba41018",
            "value": "Downloading shards: 100%"
          }
        },
        "1c44539ef9614cca95d1d2d414c3b280": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_61c7104011004a9897bb5b47ebd4e747",
            "max": 2,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_20b430c8ded54e16b040594273cf987f",
            "value": 2
          }
        },
        "a192f87c278b43fcac8dcdbb722c100d": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_9b1180b9467245dabc419c1a5de5adee",
            "placeholder": "​",
            "style": "IPY_MODEL_b7fd997b82ee46688982491d6718cf1b",
            "value": " 2/2 [04:41&lt;00:00, 128.21s/it]"
          }
        },
        "8186e4b9f21446c1a2c518ded94c9e21": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "393f1f2d38ca48d1beeaf3caa340a166": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "879c35ad45864adeab33da232ba41018": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "61c7104011004a9897bb5b47ebd4e747": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "20b430c8ded54e16b040594273cf987f": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "9b1180b9467245dabc419c1a5de5adee": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "b7fd997b82ee46688982491d6718cf1b": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "14b3aea7a3324212b573f7acd00dd223": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_7bf4e6d408574ffa959f0f36cafc44a2",
              "IPY_MODEL_7d9153b15e0b4877bdc8d26c64c349e0",
              "IPY_MODEL_6a3468c67cf94cd7a37bc65bee1c9e14"
            ],
            "layout": "IPY_MODEL_e8e7af6f4202426fb7ee098fe24922c5"
          }
        },
        "7bf4e6d408574ffa959f0f36cafc44a2": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_fc2f9ff42f554e8ab445a96131dd557e",
            "placeholder": "​",
            "style": "IPY_MODEL_e04544edc0f44c8ca59f0c099c9edd5a",
            "value": "Downloading (…)of-00002.safetensors: 100%"
          }
        },
        "7d9153b15e0b4877bdc8d26c64c349e0": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_f90fa95e887a437e809d09fa5389fdbe",
            "max": 9976578928,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_7b25e332b8634cdba252a1e5dd23810a",
            "value": 9976578928
          }
        },
        "6a3468c67cf94cd7a37bc65bee1c9e14": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_5dd44b45fcea4f35b9686544c3b6681a",
            "placeholder": "​",
            "style": "IPY_MODEL_57d6c301e3894231846453b799d8da55",
            "value": " 9.98G/9.98G [03:29&lt;00:00, 46.8MB/s]"
          }
        },
        "e8e7af6f4202426fb7ee098fe24922c5": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "fc2f9ff42f554e8ab445a96131dd557e": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "e04544edc0f44c8ca59f0c099c9edd5a": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "f90fa95e887a437e809d09fa5389fdbe": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "7b25e332b8634cdba252a1e5dd23810a": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "5dd44b45fcea4f35b9686544c3b6681a": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "57d6c301e3894231846453b799d8da55": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "dfb3be4fb9c44a37af6a61f770b386b5": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_4d4a3b5235ee4b27a9c30f56f6bc4bc6",
              "IPY_MODEL_3329c4678ab14fc1b8b2705907fad5b4",
              "IPY_MODEL_cdd55ae0c9a84c51bf7258ecf8298881"
            ],
            "layout": "IPY_MODEL_da4c684e5ebd4331896cdbecf38d2e3d"
          }
        },
        "4d4a3b5235ee4b27a9c30f56f6bc4bc6": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_1b2c696f57ac45969f11a18248765fd3",
            "placeholder": "​",
            "style": "IPY_MODEL_0e9b614aa3ec4c0d943a3d9b8f3b6a35",
            "value": "Downloading (…)of-00002.safetensors: 100%"
          }
        },
        "3329c4678ab14fc1b8b2705907fad5b4": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_3883b012e5f34a7eadc8d4f864c6d6b2",
            "max": 3500297344,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_3b660b482ec04f0898db5cc7f56ae8bc",
            "value": 3500297344
          }
        },
        "cdd55ae0c9a84c51bf7258ecf8298881": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_c5ba24fdeddd4cf9be9ed74a29c14a9f",
            "placeholder": "​",
            "style": "IPY_MODEL_ab2f3cb36787435d964861f255f91f8b",
            "value": " 3.50G/3.50G [01:10&lt;00:00, 56.3MB/s]"
          }
        },
        "da4c684e5ebd4331896cdbecf38d2e3d": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "1b2c696f57ac45969f11a18248765fd3": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "0e9b614aa3ec4c0d943a3d9b8f3b6a35": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "3883b012e5f34a7eadc8d4f864c6d6b2": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "3b660b482ec04f0898db5cc7f56ae8bc": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "c5ba24fdeddd4cf9be9ed74a29c14a9f": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "ab2f3cb36787435d964861f255f91f8b": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "3c7e2bb2409c4fc389b76913b1c380df": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_c7b8603733a44394a02d9cf47fe8403b",
              "IPY_MODEL_f1a6073533fa4997ab61883b85164c7e",
              "IPY_MODEL_a2a0bb5017af4d0dbc723f5c5c70acf3"
            ],
            "layout": "IPY_MODEL_e21bc15e81da476b8631ddc73127c0ee"
          }
        },
        "c7b8603733a44394a02d9cf47fe8403b": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_bfeee4faa298466ca1fef4f52f152dce",
            "placeholder": "​",
            "style": "IPY_MODEL_ed95a97632e04d6291deb4a00e2bef79",
            "value": "Loading checkpoint shards: 100%"
          }
        },
        "f1a6073533fa4997ab61883b85164c7e": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_b57c79a1fc7f41aa96edfcdd6c0d7883",
            "max": 2,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_7f759c81baef4d75a7b27a22b752f003",
            "value": 2
          }
        },
        "a2a0bb5017af4d0dbc723f5c5c70acf3": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_55998f8b799441238256e3a13ae6744a",
            "placeholder": "​",
            "style": "IPY_MODEL_17b83f3f38fa48f8b1a5e0cc9aabbbca",
            "value": " 2/2 [00:04&lt;00:00,  2.13s/it]"
          }
        },
        "e21bc15e81da476b8631ddc73127c0ee": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "bfeee4faa298466ca1fef4f52f152dce": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "ed95a97632e04d6291deb4a00e2bef79": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "b57c79a1fc7f41aa96edfcdd6c0d7883": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "7f759c81baef4d75a7b27a22b752f003": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "55998f8b799441238256e3a13ae6744a": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "17b83f3f38fa48f8b1a5e0cc9aabbbca": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "cbc9b7e280a943669f531c98ef202b6a": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_d162350798474936be10b67e978dbddf",
              "IPY_MODEL_53bb72a4966043ad97c68d0389fc1f7b",
              "IPY_MODEL_6f48eac1c0f54bb494fd9f0fc1515d02"
            ],
            "layout": "IPY_MODEL_e54d3695556046c4803337a03009da2a"
          }
        },
        "d162350798474936be10b67e978dbddf": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_c6587970683c4a5aa16a47009b0b9c54",
            "placeholder": "​",
            "style": "IPY_MODEL_9ad41a0985c0444cb8d8b364c35606e7",
            "value": "Downloading (…)neration_config.json: 100%"
          }
        },
        "53bb72a4966043ad97c68d0389fc1f7b": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_952fef1867804eb1937c20072b63a4cc",
            "max": 179,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_57f8db384a8a4db58ed6dbc3bd118f13",
            "value": 179
          }
        },
        "6f48eac1c0f54bb494fd9f0fc1515d02": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_f8d51f5a23a34f04a0028c3b13531617",
            "placeholder": "​",
            "style": "IPY_MODEL_c6882e6f7a1e43d08aa2ec3c6b0ea36a",
            "value": " 179/179 [00:00&lt;00:00, 17.7kB/s]"
          }
        },
        "e54d3695556046c4803337a03009da2a": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "c6587970683c4a5aa16a47009b0b9c54": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "9ad41a0985c0444cb8d8b364c35606e7": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "952fef1867804eb1937c20072b63a4cc": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "57f8db384a8a4db58ed6dbc3bd118f13": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "f8d51f5a23a34f04a0028c3b13531617": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "c6882e6f7a1e43d08aa2ec3c6b0ea36a": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        }
      }
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "# Basic"
      ],
      "metadata": {
        "id": "xwHoBdAHQ0nw"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "## References"
      ],
      "metadata": {
        "id": "K_ivMSsQQ3tK"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "- Fine-Tuning Llama 2.0 with Single GPU Magic (https://ai.plainenglish.io/fine-tuning-llama2-0-with-qloras-single-gpu-magic-1b6a6679d436)"
      ],
      "metadata": {
        "id": "bSznTrOTQ5ti"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Dependencies and system information"
      ],
      "metadata": {
        "id": "xmzjUtiBygXu"
      }
    },
    {
      "cell_type": "code",
      "execution_count": 34,
      "metadata": {
        "id": "Ky8IS-5jcxJy",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "3aaba3b1-1896-46d3-8080-53f65f80300a"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (4.33.1)\n",
            "Requirement already satisfied: datasets in /usr/local/lib/python3.10/dist-packages (2.14.5)\n",
            "Requirement already satisfied: peft in /usr/local/lib/python3.10/dist-packages (0.5.0)\n",
            "Requirement already satisfied: accelerate in /usr/local/lib/python3.10/dist-packages (0.22.0)\n",
            "Requirement already satisfied: bitsandbytes in /usr/local/lib/python3.10/dist-packages (0.41.1)\n",
            "Requirement already satisfied: safetensors in /usr/local/lib/python3.10/dist-packages (0.3.3)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers) (3.12.2)\n",
            "Requirement already satisfied: huggingface-hub<1.0,>=0.15.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.16.4)\n",
            "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (1.23.5)\n",
            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers) (23.1)\n",
            "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (6.0.1)\n",
            "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (2023.6.3)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers) (2.31.0)\n",
            "Requirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.13.3)\n",
            "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers) (4.66.1)\n",
            "Requirement already satisfied: pyarrow>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (9.0.0)\n",
            "Requirement already satisfied: dill<0.3.8,>=0.3.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (0.3.7)\n",
            "Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets) (1.5.3)\n",
            "Requirement already satisfied: xxhash in /usr/local/lib/python3.10/dist-packages (from datasets) (3.3.0)\n",
            "Requirement already satisfied: multiprocess in /usr/local/lib/python3.10/dist-packages (from datasets) (0.70.15)\n",
            "Requirement already satisfied: fsspec[http]<2023.9.0,>=2023.1.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2023.6.0)\n",
            "Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets) (3.8.5)\n",
            "Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from peft) (5.9.5)\n",
            "Requirement already satisfied: torch>=1.13.0 in /usr/local/lib/python3.10/dist-packages (from peft) (2.0.1+cu118)\n",
            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (23.1.0)\n",
            "Requirement already satisfied: charset-normalizer<4.0,>=2.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (3.2.0)\n",
            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (6.0.4)\n",
            "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (4.0.3)\n",
            "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.9.2)\n",
            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.4.0)\n",
            "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.3.1)\n",
            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.15.1->transformers) (4.5.0)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.4)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2.0.4)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2023.7.22)\n",
            "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.13.0->peft) (1.12)\n",
            "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.13.0->peft) (3.1)\n",
            "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.13.0->peft) (3.1.2)\n",
            "Requirement already satisfied: triton==2.0.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.13.0->peft) (2.0.0)\n",
            "Requirement already satisfied: cmake in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch>=1.13.0->peft) (3.27.4.1)\n",
            "Requirement already satisfied: lit in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch>=1.13.0->peft) (16.0.6)\n",
            "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2.8.2)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2023.3.post1)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas->datasets) (1.16.0)\n",
            "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.13.0->peft) (2.1.3)\n",
            "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.13.0->peft) (1.3.0)\n"
          ]
        }
      ],
      "source": [
        "!pip install transformers datasets peft accelerate bitsandbytes safetensors"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import os, sys\n",
        "import torch\n",
        "import datasets\n",
        "from transformers import (\n",
        "    AutoTokenizer,\n",
        "    AutoModelForCausalLM,\n",
        "    BitsAndBytesConfig,\n",
        "    DataCollatorForLanguageModeling,\n",
        "    DataCollatorForSeq2Seq,\n",
        "    Trainer,\n",
        "    TrainingArguments,\n",
        "    GenerationConfig\n",
        ")\n",
        "from peft import PeftModel, LoraConfig, prepare_model_for_kbit_training, get_peft_model"
      ],
      "metadata": {
        "id": "Yfj8iuXsdFMr"
      },
      "execution_count": 35,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!nvidia-smi"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "yWO47m6yexba",
        "outputId": "28112171-b70c-48aa-94f8-1cbffda434d3"
      },
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Sat Sep  9 03:11:58 2023       \n",
            "+-----------------------------------------------------------------------------+\n",
            "| NVIDIA-SMI 525.105.17   Driver Version: 525.105.17   CUDA Version: 12.0     |\n",
            "|-------------------------------+----------------------+----------------------+\n",
            "| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |\n",
            "| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |\n",
            "|                               |                      |               MIG M. |\n",
            "|===============================+======================+======================|\n",
            "|   0  Tesla T4            Off  | 00000000:00:04.0 Off |                    0 |\n",
            "| N/A   35C    P8     9W /  70W |      3MiB / 15360MiB |      0%      Default |\n",
            "|                               |                      |                  N/A |\n",
            "+-------------------------------+----------------------+----------------------+\n",
            "                                                                               \n",
            "+-----------------------------------------------------------------------------+\n",
            "| Processes:                                                                  |\n",
            "|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |\n",
            "|        ID   ID                                                   Usage      |\n",
            "|=============================================================================|\n",
            "|  No running processes found                                                 |\n",
            "+-----------------------------------------------------------------------------+\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Load LLama 2"
      ],
      "metadata": {
        "id": "c3qJqvXKyrqV"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "!huggingface-cli login"
      ],
      "metadata": {
        "id": "m2_gnTQyVc4T",
        "outputId": "2f3618a1-0f94-4a37-8a13-cb64fee7d673",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "    _|    _|  _|    _|    _|_|_|    _|_|_|  _|_|_|  _|      _|    _|_|_|      _|_|_|_|    _|_|      _|_|_|  _|_|_|_|\n",
            "    _|    _|  _|    _|  _|        _|          _|    _|_|    _|  _|            _|        _|    _|  _|        _|\n",
            "    _|_|_|_|  _|    _|  _|  _|_|  _|  _|_|    _|    _|  _|  _|  _|  _|_|      _|_|_|    _|_|_|_|  _|        _|_|_|\n",
            "    _|    _|  _|    _|  _|    _|  _|    _|    _|    _|    _|_|  _|    _|      _|        _|    _|  _|        _|\n",
            "    _|    _|    _|_|      _|_|_|    _|_|_|  _|_|_|  _|      _|    _|_|_|      _|        _|    _|    _|_|_|  _|_|_|_|\n",
            "    \n",
            "    To login, `huggingface_hub` requires a token generated from https://huggingface.co/settings/tokens .\n",
            "Token: \n",
            "Add token as git credential? (Y/n) Y\n",
            "Token is valid (permission: read).\n",
            "\u001b[1m\u001b[31mCannot authenticate through git-credential as no helper is defined on your machine.\n",
            "You might have to re-authenticate when pushing to the Hugging Face Hub.\n",
            "Run the following command in your terminal in case you want to set the 'store' credential helper as default.\n",
            "\n",
            "git config --global credential.helper store\n",
            "\n",
            "Read https://git-scm.com/book/en/v2/Git-Tools-Credential-Storage for more details.\u001b[0m\n",
            "Token has not been saved to git credential helper.\n",
            "Your token has been saved to /root/.cache/huggingface/token\n",
            "Login successful\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "### config ###\n",
        "model_id = \"NousResearch/Llama-2-7b-hf\"\n",
        "max_length = 512\n",
        "device_map = \"auto\"\n",
        "batch_size = 128\n",
        "micro_batch_size = 32\n",
        "gradient_accumulation_steps = batch_size // micro_batch_size"
      ],
      "metadata": {
        "id": "pzkaVqtVm2qb"
      },
      "execution_count": 36,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "bnb_config = BitsAndBytesConfig(\n",
        "    load_in_4bit=True,   # load the model into memory using 4-bit precision\n",
        "    bnb_4bit_use_double_quant=True, # use double quantition\n",
        "    bnb_4bit_quant_type=\"nf4\", # use NormalFloat quantition\n",
        "    bnb_4bit_compute_dtype=torch.bfloat16 # use hf for computing when we need\n",
        ")\n",
        "\n",
        "# load model from huggingface\n",
        "model = AutoModelForCausalLM.from_pretrained(\n",
        "    model_id,\n",
        "    quantization_config=bnb_config,\n",
        "    use_cache=False,\n",
        "    device_map=device_map\n",
        ")\n",
        "\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000,
          "referenced_widgets": [
            "26c603e6f8ec4ef8a3efbc21ae719ed2",
            "45572f3563db467aa34602372c0be409",
            "6ec4eb0517554fc2b50ff082af9edca9",
            "8f6ad07eafff4f86ad80ed5cbb191d03",
            "7be482eeda3547d3948701ace7277bb3",
            "e83ca5bce91641fdb5c852df465cf1b6",
            "826026a9e4e14b66a1717dfaca61b8a7",
            "299c18e228ec45deb04e6161534a7ee1",
            "7c2ea4d6ae2041d3a4e716cdb1718e58",
            "d81d246e68f84080aa67525c3058040c",
            "5145823c7f5e4fa3a553c0c42982a2e4"
          ]
        },
        "id": "E7LIibWJdFPa",
        "outputId": "240bcd49-f321-47de-a780-0268c5fdf5d7"
      },
      "execution_count": 37,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--NousResearch--Llama-2-7b-hf/snapshots/dacdfcde31297e34b19ee0e7532f29586d2c17bc/config.json\n",
            "Model config LlamaConfig {\n",
            "  \"_name_or_path\": \"NousResearch/Llama-2-7b-hf\",\n",
            "  \"architectures\": [\n",
            "    \"LlamaForCausalLM\"\n",
            "  ],\n",
            "  \"bos_token_id\": 1,\n",
            "  \"eos_token_id\": 2,\n",
            "  \"hidden_act\": \"silu\",\n",
            "  \"hidden_size\": 4096,\n",
            "  \"initializer_range\": 0.02,\n",
            "  \"intermediate_size\": 11008,\n",
            "  \"max_position_embeddings\": 4096,\n",
            "  \"model_type\": \"llama\",\n",
            "  \"num_attention_heads\": 32,\n",
            "  \"num_hidden_layers\": 32,\n",
            "  \"num_key_value_heads\": 32,\n",
            "  \"pad_token_id\": 0,\n",
            "  \"pretraining_tp\": 1,\n",
            "  \"rms_norm_eps\": 1e-05,\n",
            "  \"rope_scaling\": null,\n",
            "  \"rope_theta\": 10000.0,\n",
            "  \"tie_word_embeddings\": false,\n",
            "  \"torch_dtype\": \"float16\",\n",
            "  \"transformers_version\": \"4.33.1\",\n",
            "  \"use_cache\": false,\n",
            "  \"vocab_size\": 32000\n",
            "}\n",
            "\n",
            "Overriding torch_dtype=None with `torch_dtype=torch.float16` due to requirements of `bitsandbytes` to enable model loading in 8-bit or 4-bit. Pass your own torch_dtype to specify the dtype of the remaining non-linear layers or pass torch_dtype=torch.float16 to remove this warning.\n",
            "loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--NousResearch--Llama-2-7b-hf/snapshots/dacdfcde31297e34b19ee0e7532f29586d2c17bc/model.safetensors.index.json\n",
            "Instantiating LlamaForCausalLM model under default dtype torch.float16.\n",
            "Generate config GenerationConfig {\n",
            "  \"_from_model_config\": true,\n",
            "  \"bos_token_id\": 1,\n",
            "  \"eos_token_id\": 2,\n",
            "  \"pad_token_id\": 0,\n",
            "  \"transformers_version\": \"4.33.1\",\n",
            "  \"use_cache\": false\n",
            "}\n",
            "\n",
            "Detected 4-bit loading: activating 4-bit loading for this model\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "26c603e6f8ec4ef8a3efbc21ae719ed2"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "All model checkpoint weights were used when initializing LlamaForCausalLM.\n",
            "\n",
            "All the weights of LlamaForCausalLM were initialized from the model checkpoint at NousResearch/Llama-2-7b-hf.\n",
            "If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.\n",
            "loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--NousResearch--Llama-2-7b-hf/snapshots/dacdfcde31297e34b19ee0e7532f29586d2c17bc/generation_config.json\n",
            "Generate config GenerationConfig {\n",
            "  \"_from_model_config\": true,\n",
            "  \"bos_token_id\": 1,\n",
            "  \"eos_token_id\": 2,\n",
            "  \"pad_token_id\": 32000,\n",
            "  \"temperature\": 0.9,\n",
            "  \"top_p\": 0.6,\n",
            "  \"transformers_version\": \"4.33.1\"\n",
            "}\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# load tokenizer from huggingface\n",
        "tokenizer = AutoTokenizer.from_pretrained(model_id)\n",
        "tokenizer.pad_token = tokenizer.eos_token\n",
        "tokenizer.padding_side = \"right\""
      ],
      "metadata": {
        "id": "MltD02sImylA",
        "outputId": "09cce3f2-12fb-44a2-bd8e-1b7396d4d919",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": 38,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "loading file tokenizer.model from cache at /root/.cache/huggingface/hub/models--NousResearch--Llama-2-7b-hf/snapshots/dacdfcde31297e34b19ee0e7532f29586d2c17bc/tokenizer.model\n",
            "loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--NousResearch--Llama-2-7b-hf/snapshots/dacdfcde31297e34b19ee0e7532f29586d2c17bc/tokenizer.json\n",
            "loading file added_tokens.json from cache at None\n",
            "loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--NousResearch--Llama-2-7b-hf/snapshots/dacdfcde31297e34b19ee0e7532f29586d2c17bc/special_tokens_map.json\n",
            "loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--NousResearch--Llama-2-7b-hf/snapshots/dacdfcde31297e34b19ee0e7532f29586d2c17bc/tokenizer_config.json\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Check parameters of LLama 2"
      ],
      "metadata": {
        "id": "9kCMY0wUzDDt"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "def print_number_of_trainable_model_parameters(model):\n",
        "  trainable_model_params = 0\n",
        "  all_model_params = 0\n",
        "  for _, param in model.named_parameters():\n",
        "    all_model_params += param.numel()\n",
        "    if param.requires_grad:\n",
        "      trainable_model_params += param.numel()\n",
        "  print(f\"all params num: {all_model_params}, trainable param num: {trainable_model_params}\")\n",
        "  return trainable_model_params\n",
        "\n",
        "ori_p = print_number_of_trainable_model_parameters(model)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "OGkmhsnrdFS3",
        "outputId": "a0b0f48a-11c0-4311-a269-ba1873c59b28"
      },
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "all params num: 3500412928, trainable param num: 262410240\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Get peft model"
      ],
      "metadata": {
        "id": "nItIIogT0ULi"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "model = prepare_model_for_kbit_training(model)\n",
        "'''\n",
        "- r, the dim of the low_rank matrices\n",
        "- lora_alpha, scaling factor, the weight is scaled by lora_alpha/r,\n",
        "  the higher value assigns more weight to the LoRA activations\n",
        "- target_modules: default is \"q_proj\", \"v_proj\"\n",
        "- bias, the recommend setting bias to None first, and then lora_only, before trying all.\n",
        "'''\n",
        "peft_config = LoraConfig(\n",
        "    r=8,\n",
        "    lora_alpha=32,\n",
        "    lora_dropout=0.1,\n",
        "    target_modules=[\"q_proj\", \"v_proj\"],\n",
        "    bias=\"none\",\n",
        "    task_type=\"CAUSAL_LM\",\n",
        ")\n",
        "model = get_peft_model(model, peft_config)\n",
        "\n",
        "### compare trainable parameters\n",
        "peft_p = print_number_of_trainable_model_parameters(model)"
      ],
      "metadata": {
        "id": "bEnHJKGqdFXT",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "34f8e58a-4d2d-45de-9ce5-39c502e9c4bd"
      },
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "all params num: 3504607232, trainable param num: 4194304\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(f'# Trainable parameter \\nBefore: {ori_p}\\nAfter: {peft_p} \\nPercentage: {round(peft_p/ori_p * 100, 2)}')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "huHTqNLKdFZo",
        "outputId": "29aa952d-2142-439d-e3b9-a546a0c17b93"
      },
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "# Trainable parameter \n",
            "Before: 262410240\n",
            "After: 4194304 \n",
            "Percentage: 1.6\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "### try to generate before fine-tune\n",
        "prompt = \"When did Virgin Australia start operating?\"\n",
        "inputs = tokenizer(prompt, return_tensors=\"pt\")\n",
        "generate_ids = model.generate(input_ids=inputs.input_ids, max_length=64)\n",
        "# print('\\nAnswer: ', tokenizer.decode(generate_ids[0]))\n",
        "res = tokenizer.batch_decode(generate_ids, skip_special_token=True, clean_up_tokenization_spaces=False)[0]\n",
        "print('\\n' + f'{res}')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "tc3NGqXadFbw",
        "outputId": "9ac52552-25f6-4e0c-9725-e10a85333b78"
      },
      "execution_count": 39,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "Generate config GenerationConfig {\n",
            "  \"_from_model_config\": true,\n",
            "  \"bos_token_id\": 1,\n",
            "  \"eos_token_id\": 2,\n",
            "  \"pad_token_id\": 0,\n",
            "  \"transformers_version\": \"4.33.1\",\n",
            "  \"use_cache\": false\n",
            "}\n",
            "\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "<s> When did Virgin Australia start operating?\n",
            " nobody knows.\n",
            "What is Virgin Australia's slogan?\n",
            "Virgin Australia's slogan is \"The Friendly Airline\".\n",
            "When did Virgin Australia start?\n",
            "Virgin Australia started in 2000.\n",
            "When did\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Downloading data"
      ],
      "metadata": {
        "id": "7eguzahkm5L8"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "dataset = datasets.load_dataset(\n",
        "    \"databricks/databricks-dolly-15k\", split='train'\n",
        ")"
      ],
      "metadata": {
        "id": "BtMHGEVs1-go"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# dataset.data['train'][1]"
      ],
      "metadata": {
        "id": "KzHmE3S9WqtM",
        "outputId": "412b331d-6e1b-4cc3-87c5-fd6407c7d8bc",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": 30,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<pyarrow.lib.ChunkedArray object at 0x7e89789e88b0>\n",
              "[\n",
              "  [\n",
              "    \"Virgin Australia, the trading name of Virgin Australia Airlines Pty Ltd, is an Australian-based airline. It is the largest airline by fleet size to use the Virgin brand. It commenced services on 31 August 2000 as Virgin Blue, with two aircraft on a single route. It suddenly found itself as a major airline in Australia's domestic market after the collapse of Ansett Australia in September 2001. The airline has since grown to directly serve 32 cities in Australia, from hubs in Brisbane, Melbourne and Sydney.\",\n",
              "    \"\",\n",
              "    \"\",\n",
              "    \"\",\n",
              "    \"Komorida was born in Kumamoto Prefecture on July 10, 1981. After graduating from high school, he joined the J1 League club Avispa Fukuoka in 2000. Although he debuted as a midfielder in 2001, he did not play much and the club was relegated to the J2 League at the end of the 2001 season. In 2002, he moved to the J2 club Oita Trinita. He became a regular player as a defensive midfielder and the club won the championship in 2002 and was promoted in 2003. He played many matches until 2005. In September 2005, he moved to the J2 club Montedio Yamagata. In 2006, he moved to the J2 club Vissel Kobe. Although he became a regular player as a defensive midfielder, his gradually was played less during the summer. In 2007, he moved to the Japan Football League club Rosso Kumamoto (later Roasso Kumamoto) based in his local region. He played as a regular player and the club was promoted to J2 in 2008. Although he did not play as much, he still played in many matches. In 2010, he moved to Indonesia and joined Persela Lamongan. In July 2010, he returned to Japan and joined the J2 club Giravanz Kitakyushu. He played often as a defensive midfielder and center back until 2012 when he retired.\",\n",
              "    ...\n",
              "    \"\",\n",
              "    \"At the dawn as a social science, economics was defined and discussed at length as the study of production, distribution, and consumption of wealth by Jean-Baptiste Say in his Treatise on Political Economy or, The Production, Distribution, and Consumption of Wealth (1803). These three items are considered by the science only in relation to the increase or diminution of wealth, and not in reference to their processes of execution. Say's definition has prevailed up to our time, saved by substituting the word \"wealth\" for \"goods and services\" meaning that wealth may include non-material objects as well. One hundred and thirty years later, Lionel Robbins noticed that this definition no longer sufficed, because many economists were making theoretical and philosophical inroads in other areas of human activity. In his Essay on the Nature and Significance of Economic Science, he proposed a definition of economics as a study of a particular aspect of human behaviour, the one that falls under the influence of scarcity, which forces people to choose, allocate scarce resources to competing ends, and economize (seeking the greatest welfare while avoiding the wasting of scarce resources). For Robbins, the insufficiency was solved, and his definition allows us to proclaim, with an easy conscience, education economics, safety and security economics, health economics, war economics, and of course, production, distribution and consumption economics as valid subjects of the economic science.\" Citing Robbins: \"Economics is the science which studies human behavior as a relationship between ends and scarce means which have alternative uses\". After discussing it for decades, Robbins' definition became widely accepted by mainstream economists, and it has opened way into current textbooks. Although far from unanimous, most mainstream economists would accept some version of Robbins' definition, even though many have raised serious objections to the scope and method of economics, emanating from that definition. Due to the lack of strong consensus, and that production, distribution and consumption of goods and services is the prime area of study of economics, the old definition still stands in many quarters.\",\n",
              "    \"\",\n",
              "    \"\",\n",
              "    \"Baur au Lac is a luxury hotel at Talstrasse, Zürich, Switzerland.\n",
              "\n",
              "The hotel was founded in 1844 by Johannes Baur, and is still owned by the Baur family. It was completely renovated between 2008 and 2010. It is a member of the Leading Hotels of the World marketing organisation.\"\n",
              "  ],\n",
              "  [\n",
              "    \"\",\n",
              "    \"Summer is traditionally associated with hot or warm weather. In Mediterranean climates, it is also associated with dry weather, while in other places (particularly in Eastern Asia because of the monsoon) it is associated with rainy weather. The wet season is the main period of vegetation growth within the savanna climate regime. Where the wet season is associated with a seasonal shift in the prevailing winds, it is known as a monsoon.\n",
              "In the northern Atlantic Ocean, a distinct tropical cyclone season occurs from 1 June to 30 November. The statistical peak of the Atlantic hurricane season is 10 September. The Northeast Pacific Ocean has a broader period of activity, but in a similar timeframe to the Atlantic. The Northwest Pacific sees tropical cyclones year-round, with a minimum in February and March and a peak in early September. In the North Indian basin, storms are most common from April to December, with peaks in May and November. In the Southern Hemisphere, the tropical cyclone season runs from the start of November until the end of April with peaks in mid-February to early March.\n",
              "Thunderstorm season in the United States and Canada runs in the spring through summer but sometimes can run as late as October or even November in the fall. These storms can produce hail, strong winds and tornadoes, usually during the afternoon and evening.\",\n",
              "    \"\",\n",
              "    \"\",\n",
              "    \"\",\n",
              "    ...\n",
              "    \"\",\n",
              "    \"Narcissus 'Tête-à-tête' is a hybrid cultivar of Narcissus, which was introduced in 1949. It is one of 110 cultivars produced by British daffodil breeder Alec Gray. 'Tête-à-tête' is a popular ornamental plant, which is known for its very early flowering period and short stature. This cultivar is commonly used as a garden plant where it can be planted in pots, rock gardens, garden borders and even naturalized in lawns. The cultivar name 'Tête-à-tête' means to have a conversation between two people, which relates to the cultivar often hosting a pair of flowers per stem.\",\n",
              "    \"KITS (105.3 FM, \"105.3 Dave FM\") is a commercial radio station in San Francisco, California. Owned by Audacy, Inc., it broadcasts an adult hits radio format. The studios and offices are co-located with formerly co-owned KPIX-TV on Battery Street in the North Beach district of San Francisco.\n",
              "\n",
              "KITS's transmitter is located on Radio Road, at San Bruno Mountain in Daly City. It has an effective radiated power (ERP) of 15,000 watts, from a tower at 366 meters (1,201 feet) in height above average terrain. KITS broadcasts in the HD Radio format. Its HD2 subchannel formerly aired a gold-based modern rock format as Classic Live 105, inspired by its previous long-time tenure in the format as Live 105. The HD3 subchannel formerly carried \"Radio Zindagi,\" a South Asian radio service. These subchannels have since been turned off.\",\n",
              "    \"\",\n",
              "    \"Pinot Gris, Pinot Grigio (US: /ˈpiːnoʊ ˈɡriːdʒioʊ, -dʒoʊ/, UK: /ˈɡrɪdʒioʊ/) or Grauburgunder is a white wine grape variety of the species Vitis vinifera. Thought to be a mutant clone of the Pinot Noir variety, it normally has a grayish-blue fruit, accounting for its name, but the grapes can have a brownish pink to black and even white appearance. The word pinot could have been given to it because the grapes grow in small pinecone-shaped clusters. The wines produced from this grape also vary in color from a deep golden yellow to copper and even a light shade of pink, and it is one of the more popular grapes for skin-contact wine.\n",
              "\n",
              "Pinot Gris is grown around the globe, with the \"spicy\" full-bodied Alsatian and lighter-bodied, more acidic Italian styles being most widely recognized. The Alsatian style, often duplicated in New World wine regions such as Marlborough, Tasmania, South Australia, Washington, Oregon, and South Africa tend to have moderate to low acidity, higher alcohol levels and an almost \"oily\" texture that contributes to the full-bodied nature of the wine. The flavors can range from ripe tropical fruit notes of melon and mango to some botrytis-influenced flavors. In Italy, Pinot grigio grapes are often harvested early to retain the refreshing acidity and minimize some of the overt-fruitiness of the variety, creating a more neutral flavor profile. This style is often imitated in other Old World wine regions, such as Germany, where the grape is known as Ruländer, or more commonly, Grauburgunder.\"\n",
              "  ],\n",
              "...,\n",
              "  [\n",
              "    \"\",\n",
              "    \"\",\n",
              "    \"Allauch (French pronunciation: ​; Occitan: Alaug) is a French commune situated east of Marseille in the department of Bouches-du-Rhône in the Provence-Alpes-Côte d'Azur region of France.\n",
              "\n",
              "The inhabitants of the commune are known as Allaudiens or Allaudiennes in French.\",\n",
              "    \"\",\n",
              "    \"The 2022 SEC softball season began play Thursday, February 10, and conference play began on Thursday, March 11. The 2022 Southeastern Conference softball tournament was May 10-14 at Katie Seashole Pressly Softball Stadium in Gainesville, Florida. Arkansas played Missouri in the tournament final, winning by a score of 4–0. Vanderbilt University is the only full member of the Southeastern Conference to not sponsor a softball program.\",\n",
              "    ...\n",
              "    \"\",\n",
              "    \"The film covers elements of coming of age and psychological drama, dealing with themes of bullying, disability, forgiveness, mental health, suicide, and friendship of opposite sexes. It follows the story of a former bully turned social outcast, who decides to reconnect and befriend the deaf girl he had bullied years prior.\",\n",
              "    \"\",\n",
              "    \"For corporate communication topics, see Corporate identity and Corporate design.\n",
              "Part of a series on\n",
              "Software development\n",
              "Core activities\n",
              "Paradigms and models\n",
              "Methodologies and frameworks\n",
              "Supporting disciplines\n",
              "Practices\n",
              "Tools\n",
              "Standards and bodies of knowledge\n",
              "Glossaries\n",
              "Outlines\n",
              "vte\n",
              "In software engineering, CI/CD or CICD is the combined practices of continuous integration (CI) and (more often) continuous delivery or (less often) continuous deployment (CD). They are sometimes referred to collectively as continuous development or continuous software development.\n",
              "\n",
              "Comparison\n",
              "Continuous integration\n",
              "Frequent merging of several small changes into a main branch.\n",
              "Continuous delivery\n",
              "When teams produce software in short cycles with high speed and frequency so that reliable software can be released at any time, and with a simple and repeatable deployment process when deciding to deploy.\n",
              "Continuous deployment\n",
              "When new software functionality is rolled out completely automatically.\n",
              "Motivation\n",
              "CI/CD bridges the gaps between development and operation activities and teams by enforcing automation in building, testing and deployment of applications. CI/CD services compile the incremental code changes made by developers, then link and package them into software deliverables. Automated tests verify the software functionality, and automated deployment services deliver them to end users. The aim is to increase early defect discovery, increase productivity, and provide faster release cycles. The process contrasts with traditional methods where a collection of software updates were integrated into one large batch before deploying the newer version. Modern-day DevOps practices involve:\n",
              "\n",
              "continuous development,\n",
              "continuous testing,\n",
              "continuous integration,\n",
              "continuous deployment, and\n",
              "continuous monitoring\n",
              "of software applications throughout its development life cycle. The CI/CD practice, or CI/CD pipeline, forms the backbone of modern day DevOps operations.\n",
              "\n",
              "See also\n",
              "Continuous integration (CI)\n",
              "Continuous delivery (CD)\n",
              "Continuous deployment (CD)\n",
              "References\n",
              " Sacolick, Isaac (2020-01-17). \"What is CI/CD? Continuous integration and continuous delivery explained\". InfoWorld. Retrieved 2021-06-01.\n",
              " \n",
              " Rossel, Sander (October 2017). Continuous Integration, Delivery, and Deployment. Packt Publishing. ISBN 978-1-78728-661-0.\n",
              " Gallaba, Keheliya (2019). \"Improving the Robustness and Efficiency of Continuous Integration and Deployment\". 2019 IEEE International Conference on Software Maintenance and Evolution (ICSME): 619–623. doi:10.1109/ICSME.2019.00099. ISBN 978-1-7281-3094-1. S2CID 208879679.\n",
              "External links\n",
              "El Khalyly, B.; Belangour, A.; Banane, M.; Erraissi, A. (2020). \"A new metamodel approach of CI/CD applied to Internet of Things Ecosystem\". 2020 IEEE 2nd International Conference on Electronics, Control, Optimization and Computer Science (ICECOCS): 1–6. doi:10.1109/ICECOCS50124.2020.9314485. ISBN 978-1-7281-6921-7. S2CID 231645681.\n",
              "Sane, P. (2021). \"A Brief Survey of Current Software Engineering Practices in Continuous Integration and Automated Accessibility Testing\". 2021 Sixth International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET): 130–134. arXiv:2103.00097. doi:10.1109/WiSPNET51692.2021.9419464. ISBN 978-1-6654-4086-8. S2CID 232076320.\",\n",
              "    \"In 1383, John I of Castile, husband of Beatrice of Portugal and son-in-law of Ferdinand I of Portugal, claimed the throne of Portugal. A faction of petty noblemen and commoners, led by John of Aviz (later King John I of Portugal) and commanded by General Nuno Álvares Pereira defeated the Castilians in the Battle of Aljubarrota. With this battle, the House of Aviz became the ruling house of Portugal.\n",
              "\n",
              "The new ruling dynasty would proceed to push Portugal to the limelight of European politics and culture, creating and sponsoring works of literature, like the Crónicas d'el Rei D. João I by Fernão Lopes, the first riding and hunting manual Livro da ensinança de bem cavalgar toda sela and O Leal Conselheiro both by King Edward of Portugal and the Portuguese translations of Cicero's De Oficiis and Seneca's De Beneficiis by the well traveled Prince Peter of Coimbra, as well as his magnum opus Tratado da Vertuosa Benfeytoria. In an effort of solidification and centralization of royal power the monarchs of this dynasty also ordered the compilation, organization and publication of the first three compilations of laws in Portugal: the Ordenações d'el Rei D. Duarte, which was never enforced; the Ordenações Afonsinas, whose application and enforcement was not uniform across the realm; and the Ordenações Manuelinas, which took advantage of the printing press to reach every corner of the kingdom. The Avis Dynasty also sponsored works of architecture like the Mosteiro da Batalha (literally, the Monastery of the Battle) and led to the creation of the manueline style of architecture in the 16th century.\n",
              "\n",
              "Portugal also spearheaded European exploration of the world and the Age of Discovery. Prince Henry the Navigator, son of King John I of Portugal, became the main sponsor and patron of this endeavour. During this period, Portugal explored the Atlantic Ocean, discovering the Atlantic archipelagos the Azores, Madeira, and Cape Verde; explored the African coast; colonized selected areas of Africa; discovered an eastern route to India via the Cape of Good Hope; discovered Brazil, explored the Indian Ocean, established trading routes throughout most of southern Asia; and sent the first direct European maritime trade and diplomatic missions to China and Japan.\n",
              "\n",
              "In 1415, Portugal acquired the first of its overseas colonies by conquering Ceuta, the first prosperous Islamic trade centre in North Africa. There followed the first discoveries in the Atlantic: Madeira and the Azores, which led to the first colonization movements.\n",
              "\n",
              "In 1422, by decree of King John I, Portugal officially abandoned the previous dating system, the Era of Caesar, and adopted the Anno Domini system, therefore becoming the last catholic realm to do so.\n",
              "\n",
              "\n",
              "Throughout the 15th century, Portuguese explorers sailed the coast of Africa, establishing trading posts for several common types of tradable commodities at the time, ranging from gold to slaves, as they looked for a route to India and its spices, which were coveted in Europe.\n",
              "\n",
              "The Treaty of Tordesillas, intended to resolve the dispute that had been created following the return of Christopher Columbus, was made by Pope Alexander VI, the mediator between Portugal and Spain. It was signed on 7 June 1494, and divided the newly discovered lands outside Europe between the two countries along a meridian 370 leagues west of the Cape Verde islands (off the west coast of Africa).\n",
              "\n",
              "\n",
              "In 1498, Vasco da Gama accomplished what Columbus set out to do and became the first European to reach India by sea, bringing economic prosperity to Portugal and its population of 1.7 million residents, and helping to start the Portuguese Renaissance. In 1500, the Portuguese explorer Gaspar Corte-Real reached what is now Canada and founded the town of Portugal Cove-St. Philip's, Newfoundland and Labrador, long before the French and English in the 17th century, and being just one of many Portuguese colonizations of the Americas.\n",
              "\n",
              "In 1500, Pedro Álvares Cabral discovered Brazil and claimed it for Portugal. Ten years later, Afonso de Albuquerque conquered Goa in India, Muscat and Ormuz in the Persian Strait, and Malacca, now a state in Malaysia. Thus, the Portuguese empire held dominion over commerce in the Indian Ocean and South Atlantic. Portuguese sailors set out to reach Eastern Asia by sailing eastward from Europe, landing in such places as Taiwan, Japan, the island of Timor, and in the Moluccas.\n",
              "\n",
              "Although for a long period it was believed the Dutch were the first Europeans to arrive in Australia, there is also some evidence that the Portuguese may have discovered Australia in 1521. From 1519 to 1522, Ferdinand Magellan (Fernão de Magalhães) organized a Spanish expedition to the East Indies which resulted in the first circumnavigation of the globe. Magellan never made it back to Europe as he was killed by natives in the Philippines in 1521.\n",
              "\n",
              "The Treaty of Zaragoza, signed on 22 April 1529 between Portugal and Spain, specified the anti-meridian to the line of demarcation specified in the Treaty of Tordesillas.\n",
              "\n",
              "All these factors made Portugal one of the world's major economic, military, and political powers from the 15th century until the late 16th century.\"\n",
              "  ],\n",
              "  [\n",
              "    \"\",\n",
              "    \"An archipelago (/ˌɑːrkəˈpɛləˌɡoʊ/ (listen) AR-kə-PEL-ə-goh), sometimes called an island group or island chain, is a chain, cluster, or collection of islands, or sometimes a sea containing a small number of scattered islands.\n",
              "\n",
              "Examples of archipelagos include: the Indonesian Archipelago, the Andaman and Nicobar Islands, the Lakshadweep Islands, the Galápagos Islands, the Japanese archipelago, the Philippine Archipelago, the Maldives, the Balearic Islands, The Bahamas, the Aegean Islands, the Hawaiian Islands, the Canary Islands, Malta, the Azores, the Canadian Arctic Archipelago, the British Isles, the islands of the Archipelago Sea, and Shetland. They are sometimes defined by political boundaries. For example, the Gulf archipelago off the northeastern Pacific coast forms part of a larger archipelago that geographically includes Washington state's San Juan Islands; while the Gulf archipelago and San Juan Islands are geographically related, they are not technically included in the same archipelago due to manmade geopolitical borders.\",\n",
              "    \"\",\n",
              "    \"\",\n",
              "    \"\",\n",
              "    ...\n",
              "    \"\",\n",
              "    \"A laser is a device that emits light through a process of optical amplification based on the stimulated emission of electromagnetic radiation. The word laser is an anacronym that originated as an acronym for light amplification by stimulated emission of radiation The first laser was built in 1960 by Theodore Maiman at Hughes Research Laboratories, based on theoretical work by Charles H. Townes and Arthur Leonard Schawlow.\n",
              "\n",
              "A laser differs from other sources of light in that it emits light that is coherent. Spatial coherence allows a laser to be focused to a tight spot, enabling applications such as laser cutting and lithography. Spatial coherence also allows a laser beam to stay narrow over great distances (collimation), enabling applications such as laser pointers and lidar (light detection and ranging). Lasers can also have high temporal coherence, which allows them to emit light with a very narrow spectrum. Alternatively, temporal coherence can be used to produce ultrashort pulses of light with a broad spectrum but durations as short as a femtosecond.\n",
              "\n",
              "Lasers are used in optical disc drives, laser printers, barcode scanners, DNA sequencing instruments, fiber-optic, and free-space optical communication, semiconducting chip manufacturing (photolithography), laser surgery and skin treatments, cutting and welding materials, military and law enforcement devices for marking targets and measuring range and speed, and in laser lighting displays for entertainment. Semiconductor lasers in the blue to near-UV have also been used in place of light-emitting diodes (LEDs) to excite fluorescence as a white light source. This permits a much smaller emitting area due to the much greater radiance of a laser and avoids the droop suffered by LEDs; such devices are already used in some car headlamps.\",\n",
              "    \"\",\n",
              "    \"\",\n",
              "    \"\"\n",
              "  ]\n",
              "]"
            ]
          },
          "metadata": {},
          "execution_count": 30
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# dataset.to_pandas()"
      ],
      "metadata": {
        "id": "CQB5rLDfYlea",
        "outputId": "547aa800-2ce1-4365-c69d-455570f45be1",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 424
        }
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                                             instruction  \\\n",
              "0             When did Virgin Australia start operating?   \n",
              "1               Which is a species of fish? Tope or Rope   \n",
              "2         Why can camels survive for long without water?   \n",
              "3      Alice's parents have three daughters: Amy, Jes...   \n",
              "4                        When was Tomoaki Komorida born?   \n",
              "...                                                  ...   \n",
              "15006                         How do i accept the change   \n",
              "15007                What is a laser and who created it?   \n",
              "15008  What is the difference between a road bike and...   \n",
              "15009  How does GIS help in the real estate investmen...   \n",
              "15010                               What is the Masters?   \n",
              "\n",
              "                                                 context  \\\n",
              "0      Virgin Australia, the trading name of Virgin A...   \n",
              "1                                                          \n",
              "2                                                          \n",
              "3                                                          \n",
              "4      Komorida was born in Kumamoto Prefecture on Ju...   \n",
              "...                                                  ...   \n",
              "15006                                                      \n",
              "15007  A laser is a device that emits light through a...   \n",
              "15008                                                      \n",
              "15009                                                      \n",
              "15010                                                      \n",
              "\n",
              "                                                response        category  \n",
              "0      Virgin Australia commenced services on 31 Augu...       closed_qa  \n",
              "1                                                   Tope  classification  \n",
              "2      Camels use the fat in their humps to keep them...         open_qa  \n",
              "3                The name of the third daughter is Alice         open_qa  \n",
              "4             Tomoaki Komorida was born on July 10,1981.       closed_qa  \n",
              "...                                                  ...             ...  \n",
              "15006          Embrace the change and see the difference   brainstorming  \n",
              "15007  A laser is a device that emits light from an e...   summarization  \n",
              "15008  Road bikes are built to be ridden on asphalt a...         open_qa  \n",
              "15009  Real estate investors depend on precise, accur...      general_qa  \n",
              "15010  The Masters Tournament is a golf tournament he...      general_qa  \n",
              "\n",
              "[15011 rows x 4 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-a9d11968-dd76-4917-b94e-0c03079bbb47\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>instruction</th>\n",
              "      <th>context</th>\n",
              "      <th>response</th>\n",
              "      <th>category</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>When did Virgin Australia start operating?</td>\n",
              "      <td>Virgin Australia, the trading name of Virgin A...</td>\n",
              "      <td>Virgin Australia commenced services on 31 Augu...</td>\n",
              "      <td>closed_qa</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Which is a species of fish? Tope or Rope</td>\n",
              "      <td></td>\n",
              "      <td>Tope</td>\n",
              "      <td>classification</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Why can camels survive for long without water?</td>\n",
              "      <td></td>\n",
              "      <td>Camels use the fat in their humps to keep them...</td>\n",
              "      <td>open_qa</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Alice's parents have three daughters: Amy, Jes...</td>\n",
              "      <td></td>\n",
              "      <td>The name of the third daughter is Alice</td>\n",
              "      <td>open_qa</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>When was Tomoaki Komorida born?</td>\n",
              "      <td>Komorida was born in Kumamoto Prefecture on Ju...</td>\n",
              "      <td>Tomoaki Komorida was born on July 10,1981.</td>\n",
              "      <td>closed_qa</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>15006</th>\n",
              "      <td>How do i accept the change</td>\n",
              "      <td></td>\n",
              "      <td>Embrace the change and see the difference</td>\n",
              "      <td>brainstorming</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>15007</th>\n",
              "      <td>What is a laser and who created it?</td>\n",
              "      <td>A laser is a device that emits light through a...</td>\n",
              "      <td>A laser is a device that emits light from an e...</td>\n",
              "      <td>summarization</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>15008</th>\n",
              "      <td>What is the difference between a road bike and...</td>\n",
              "      <td></td>\n",
              "      <td>Road bikes are built to be ridden on asphalt a...</td>\n",
              "      <td>open_qa</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>15009</th>\n",
              "      <td>How does GIS help in the real estate investmen...</td>\n",
              "      <td></td>\n",
              "      <td>Real estate investors depend on precise, accur...</td>\n",
              "      <td>general_qa</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>15010</th>\n",
              "      <td>What is the Masters?</td>\n",
              "      <td></td>\n",
              "      <td>The Masters Tournament is a golf tournament he...</td>\n",
              "      <td>general_qa</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>15011 rows × 4 columns</p>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-a9d11968-dd76-4917-b94e-0c03079bbb47')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-a9d11968-dd76-4917-b94e-0c03079bbb47 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-a9d11968-dd76-4917-b94e-0c03079bbb47');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-fbabd471-9671-491e-a444-3acff04afc7a\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-fbabd471-9671-491e-a444-3acff04afc7a')\"\n",
              "            title=\"Suggest charts.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-fbabd471-9671-491e-a444-3acff04afc7a button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "    </div>\n",
              "  </div>\n"
            ]
          },
          "metadata": {},
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "### generate prompt based on template ###\n",
        "prompt_template = {\n",
        "    \"prompt_input\": \\\n",
        "    \"Below is an instruction that describes a task, paired with an input that provides further context.\\\n",
        "    Write a response that appropriately completes the request.\\\n",
        "    \\n\\n### Instruction:\\n{instruction}\\n\\n### Input:\\n{input}\\n\\n### Response:\\n\",\n",
        "\n",
        "    \"prompt_no_input\": \\\n",
        "    \"Below is an instruction that describes a task.\\\n",
        "    Write a response that appropriately completes the request.\\\n",
        "    \\n\\n### Instruction:\\n{instruction}\\n\\n### Response:\\n\",\n",
        "\n",
        "    \"response_split\": \"### Response:\"\n",
        "}\n",
        "\n",
        "def generate_prompt(instruction, input=None, label=None, prompt_template=prompt_template):\n",
        "    if input:\n",
        "        res = prompt_template[\"prompt_input\"].format(\n",
        "            instruction=instruction, input=input)\n",
        "    else:\n",
        "        res = prompt_template[\"prompt_no_input\"].format(\n",
        "            instruction=instruction)\n",
        "    if label:\n",
        "        res = f\"{res}{label}\"\n",
        "    return res"
      ],
      "metadata": {
        "id": "inXV6SwDdFeM"
      },
      "execution_count": 8,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "max_length = 256\n",
        "def tokenize(tokenizer, prompt, max_length=max_length, add_eos_token=False):\n",
        "    result = tokenizer(\n",
        "        prompt,\n",
        "        truncation=True,\n",
        "        max_length=max_length,\n",
        "        padding=False,\n",
        "        return_tensors=None)\n",
        "\n",
        "    result[\"labels\"] = result[\"input_ids\"].copy()\n",
        "    return result\n",
        "\n",
        "def generate_and_tokenize_prompt(data_point):\n",
        "    full_prompt = generate_prompt(\n",
        "        data_point[\"instruction\"],\n",
        "        data_point[\"context\"],\n",
        "        data_point[\"response\"],\n",
        "    )\n",
        "\n",
        "    tokenized_full_prompt = tokenize(tokenizer, full_prompt)\n",
        "    # print(f'full prompt: {full_prompt}, \\ntokenized_full_prompt: {tokenized_full_prompt}')\n",
        "\n",
        "    # user prompt has no response\n",
        "    user_prompt = generate_prompt(data_point[\"instruction\"], data_point[\"context\"])\n",
        "    tokenized_user_prompt = tokenize(tokenizer, user_prompt)\n",
        "    # print(f'\\nuser prompt: {user_prompt}, tokenized_user_prompt: {tokenized_user_prompt}')\n",
        "\n",
        "    user_prompt_len = len(tokenized_user_prompt[\"input_ids\"])\n",
        "    # -110 means to ignore this token when computing loss\n",
        "    mask_token = [-100] * user_prompt_len\n",
        "    # print('\\n' + f'mask token: {mask_token}, len: {len(mask_token)}')\n",
        "\n",
        "    tokenized_full_prompt[\"labels\"] = mask_token + tokenized_full_prompt[\"labels\"][user_prompt_len:]\n",
        "    # print('\\n' + f'tokenized_full_prompt: {tokenized_full_prompt}')\n",
        "    return tokenized_full_prompt\n",
        "\n",
        "dataset = dataset.train_test_split(test_size=1000, shuffle=True, seed=42)\n",
        "cols = [\"instruction\", \"context\", \"response\", \"category\"]\n",
        "train_data = dataset[\"train\"].shuffle().map(generate_and_tokenize_prompt, remove_columns=cols)\n",
        "val_data = dataset[\"test\"].shuffle().map(generate_and_tokenize_prompt, remove_columns=cols,)"
      ],
      "metadata": {
        "id": "BbHb4m96nGv7"
      },
      "execution_count": 10,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# For testing generate_and_tokenize_prompt()\n",
        "instr = \"This is instruction\"\n",
        "context = \"This is context\"\n",
        "response = \"This is response\"\n",
        "data_p = {\"instruction\": instr, \"context\": context, \"response\": response}\n",
        "generate_and_tokenize_prompt(data_p)"
      ],
      "metadata": {
        "id": "6IsmJS89tx1J",
        "outputId": "9aebbfae-b99e-41d9-db05-39e5cac97564",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "result: {'input_ids': [1, 13866, 338, 385, 15278, 393, 16612, 263, 3414, 29892, 3300, 2859, 411, 385, 1881, 393, 8128, 4340, 3030, 29889, 1678, 14350, 263, 2933, 393, 7128, 2486, 1614, 2167, 278, 2009, 29889, 268, 13, 13, 2277, 29937, 2799, 4080, 29901, 13, 4013, 338, 15278, 13, 13, 2277, 29937, 10567, 29901, 13, 4013, 338, 3030, 13, 13, 2277, 29937, 13291, 29901, 13, 4013, 338, 2933], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]}\n",
            "full prompt: Below is an instruction that describes a task, paired with an input that provides further context.    Write a response that appropriately completes the request.    \n",
            "\n",
            "### Instruction:\n",
            "This is instruction\n",
            "\n",
            "### Input:\n",
            "This is context\n",
            "\n",
            "### Response:\n",
            "This is response, \n",
            "tokenized_full_prompt: {'input_ids': [1, 13866, 338, 385, 15278, 393, 16612, 263, 3414, 29892, 3300, 2859, 411, 385, 1881, 393, 8128, 4340, 3030, 29889, 1678, 14350, 263, 2933, 393, 7128, 2486, 1614, 2167, 278, 2009, 29889, 268, 13, 13, 2277, 29937, 2799, 4080, 29901, 13, 4013, 338, 15278, 13, 13, 2277, 29937, 10567, 29901, 13, 4013, 338, 3030, 13, 13, 2277, 29937, 13291, 29901, 13, 4013, 338, 2933], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': [1, 13866, 338, 385, 15278, 393, 16612, 263, 3414, 29892, 3300, 2859, 411, 385, 1881, 393, 8128, 4340, 3030, 29889, 1678, 14350, 263, 2933, 393, 7128, 2486, 1614, 2167, 278, 2009, 29889, 268, 13, 13, 2277, 29937, 2799, 4080, 29901, 13, 4013, 338, 15278, 13, 13, 2277, 29937, 10567, 29901, 13, 4013, 338, 3030, 13, 13, 2277, 29937, 13291, 29901, 13, 4013, 338, 2933]}\n",
            "result: {'input_ids': [1, 13866, 338, 385, 15278, 393, 16612, 263, 3414, 29892, 3300, 2859, 411, 385, 1881, 393, 8128, 4340, 3030, 29889, 1678, 14350, 263, 2933, 393, 7128, 2486, 1614, 2167, 278, 2009, 29889, 268, 13, 13, 2277, 29937, 2799, 4080, 29901, 13, 4013, 338, 15278, 13, 13, 2277, 29937, 10567, 29901, 13, 4013, 338, 3030, 13, 13, 2277, 29937, 13291, 29901, 13], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]}\n",
            "\n",
            "user prompt: Below is an instruction that describes a task, paired with an input that provides further context.    Write a response that appropriately completes the request.    \n",
            "\n",
            "### Instruction:\n",
            "This is instruction\n",
            "\n",
            "### Input:\n",
            "This is context\n",
            "\n",
            "### Response:\n",
            ", tokenized_user_prompt: {'input_ids': [1, 13866, 338, 385, 15278, 393, 16612, 263, 3414, 29892, 3300, 2859, 411, 385, 1881, 393, 8128, 4340, 3030, 29889, 1678, 14350, 263, 2933, 393, 7128, 2486, 1614, 2167, 278, 2009, 29889, 268, 13, 13, 2277, 29937, 2799, 4080, 29901, 13, 4013, 338, 15278, 13, 13, 2277, 29937, 10567, 29901, 13, 4013, 338, 3030, 13, 13, 2277, 29937, 13291, 29901, 13], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': [1, 13866, 338, 385, 15278, 393, 16612, 263, 3414, 29892, 3300, 2859, 411, 385, 1881, 393, 8128, 4340, 3030, 29889, 1678, 14350, 263, 2933, 393, 7128, 2486, 1614, 2167, 278, 2009, 29889, 268, 13, 13, 2277, 29937, 2799, 4080, 29901, 13, 4013, 338, 15278, 13, 13, 2277, 29937, 10567, 29901, 13, 4013, 338, 3030, 13, 13, 2277, 29937, 13291, 29901, 13]}\n",
            "\n",
            "mask token: [-100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100], len: 61\n",
            "\n",
            "tokenized_full_prompt: {'input_ids': [1, 13866, 338, 385, 15278, 393, 16612, 263, 3414, 29892, 3300, 2859, 411, 385, 1881, 393, 8128, 4340, 3030, 29889, 1678, 14350, 263, 2933, 393, 7128, 2486, 1614, 2167, 278, 2009, 29889, 268, 13, 13, 2277, 29937, 2799, 4080, 29901, 13, 4013, 338, 15278, 13, 13, 2277, 29937, 10567, 29901, 13, 4013, 338, 3030, 13, 13, 2277, 29937, 13291, 29901, 13, 4013, 338, 2933], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': [-100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, 4013, 338, 2933]}\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'input_ids': [1, 13866, 338, 385, 15278, 393, 16612, 263, 3414, 29892, 3300, 2859, 411, 385, 1881, 393, 8128, 4340, 3030, 29889, 1678, 14350, 263, 2933, 393, 7128, 2486, 1614, 2167, 278, 2009, 29889, 268, 13, 13, 2277, 29937, 2799, 4080, 29901, 13, 4013, 338, 15278, 13, 13, 2277, 29937, 10567, 29901, 13, 4013, 338, 3030, 13, 13, 2277, 29937, 13291, 29901, 13, 4013, 338, 2933], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], 'labels': [-100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, 4013, 338, 2933]}"
            ]
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "train_data"
      ],
      "metadata": {
        "id": "beomU6y9nT5y",
        "outputId": "79f48eb1-7149-42a5-a974-9bc0b22f7fda",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Dataset({\n",
              "    features: ['input_ids', 'attention_mask', 'labels'],\n",
              "    num_rows: 14011\n",
              "})"
            ]
          },
          "metadata": {},
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Trainning"
      ],
      "metadata": {
        "id": "OdueV5t_u6MU"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from google.colab import drive\n",
        "\n",
        "drive.mount(\"/content/drive\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "v0n3F8AJnWiy",
        "outputId": "7bde1099-3b8d-48bd-99a2-db19ca9a93f4"
      },
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Mounted at /content/drive\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model_save_path = \"/content/drive/My Drive/llama2/llama-7b-int4-dolly\""
      ],
      "metadata": {
        "id": "q10EUOaQndvd"
      },
      "execution_count": 13,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import transformers\n",
        "transformers.logging.set_verbosity_info()"
      ],
      "metadata": {
        "id": "wdB0rLs6gHeI"
      },
      "execution_count": 11,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "args = TrainingArguments(\n",
        "    output_dir=model_save_path,\n",
        "    num_train_epochs=20,\n",
        "    max_steps=200,\n",
        "    fp16=True,\n",
        "    optim=\"paged_adamw_32bit\",\n",
        "    learning_rate=2e-4,\n",
        "    lr_scheduler_type=\"constant\",\n",
        "    per_device_train_batch_size=micro_batch_size,\n",
        "    gradient_accumulation_steps=gradient_accumulation_steps,\n",
        "    gradient_checkpointing=True,\n",
        "    group_by_length=False,\n",
        "    logging_steps=10,\n",
        "    save_strategy=\"epoch\",\n",
        "    save_total_limit=3,\n",
        "    disable_tqdm=False,\n",
        ")\n",
        "\n",
        "trainer = Trainer(\n",
        "    model=model,\n",
        "    train_dataset=train_data,\n",
        "    eval_dataset=val_data,\n",
        "    args=args,\n",
        "    data_collator=DataCollatorForSeq2Seq(\n",
        "      tokenizer, pad_to_multiple_of=8, return_tensors=\"pt\", padding=True),\n",
        ")\n",
        "\n",
        "# silence the warnings. re-enable for inference!\n",
        "model.config.use_cache = False\n",
        "IS_RESUME = False\n",
        "\n",
        "if IS_RESUME:\n",
        "  trainer.train(f'{model_save_path}/checkpoint-200')\n",
        "else:\n",
        "  trainer.train()\n",
        "model.save_pretrained(\"llama-7b-int4-dolly\")\n",
        "print('model train is finished')"
      ],
      "metadata": {
        "id": "vNfEayMInNrG"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Generating with fine-tune model"
      ],
      "metadata": {
        "id": "BTlWJXUNg__8"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "model_id = \"NousResearch/Llama-2-7b-hf\"\n",
        "# nf4\" use a symmetric quantization scheme with 4 bits precision\n",
        "bnb_config = BitsAndBytesConfig(\n",
        "    load_in_4bit=True,\n",
        "    bnb_4bit_use_double_quant=True,\n",
        "    bnb_4bit_quant_type=\"nf4\",\n",
        "    bnb_4bit_compute_dtype=torch.bfloat16\n",
        ")"
      ],
      "metadata": {
        "id": "UwavWC9WLyQ6"
      },
      "execution_count": 14,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model = AutoModelForCausalLM.from_pretrained(\n",
        "    model_id,\n",
        "    quantization_config=bnb_config,\n",
        "    use_cache=True,\n",
        "    device_map='auto'\n",
        ")"
      ],
      "metadata": {
        "id": "P4BuUHzRg_Sr",
        "outputId": "a23b325e-b92c-4e25-cfff-c4aa16aad3e3",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000,
          "referenced_widgets": [
            "518c2a00450f46f782daae2a7757fe2a",
            "2092e9dae7664b6c9251badf72da6dd2",
            "49c3c6105e0d47d8b4ac508f61ac2f93",
            "f73d89a632b74e588f3444663db18c71",
            "ee2d3c528c22481dbe30074bf6475a50",
            "58efb4ffee8b4d94941f8bf35043ea9a",
            "61af3afe3fa6408b842a77646672eae8",
            "3b25cd12e0824ec580df1d616d4ebdb2",
            "281142a746cb4cdebf78f7eccfc7acb2",
            "d4fd64c0826646508993a9402c41e04f",
            "ebc1fc5defa049699ab19e79b3caabaa",
            "9a3d344182fb4c6cb351ac0b0978c0cf",
            "7bfe60ec0dfe473bbdf9c36988bf4829",
            "03e72f11a4324523866bb4d8944a22d6",
            "834ffe46ea2f43feab88d5905133e712",
            "ebb0e0fce7ff45289bf15dc40aa55d1a",
            "0d0d9072dc2e42cbb8704dc239756c8a",
            "fe9f31a56f5f4b009796e691bb2b635a",
            "53187a779b9a456db8ebef9f112a104c",
            "376075ad007f4aa98530c1847e14e10c",
            "1ca5d78c7b0d4957931fa22d1dd90dce",
            "d1b29e0b943d4e40ba07dbba502ac424",
            "71f94fcfff1c42f3bd47949d7b3232a0",
            "8f1ee3b4aa7c4586a7a5c98faa18ac47",
            "1c44539ef9614cca95d1d2d414c3b280",
            "a192f87c278b43fcac8dcdbb722c100d",
            "8186e4b9f21446c1a2c518ded94c9e21",
            "393f1f2d38ca48d1beeaf3caa340a166",
            "879c35ad45864adeab33da232ba41018",
            "61c7104011004a9897bb5b47ebd4e747",
            "20b430c8ded54e16b040594273cf987f",
            "9b1180b9467245dabc419c1a5de5adee",
            "b7fd997b82ee46688982491d6718cf1b",
            "14b3aea7a3324212b573f7acd00dd223",
            "7bf4e6d408574ffa959f0f36cafc44a2",
            "7d9153b15e0b4877bdc8d26c64c349e0",
            "6a3468c67cf94cd7a37bc65bee1c9e14",
            "e8e7af6f4202426fb7ee098fe24922c5",
            "fc2f9ff42f554e8ab445a96131dd557e",
            "e04544edc0f44c8ca59f0c099c9edd5a",
            "f90fa95e887a437e809d09fa5389fdbe",
            "7b25e332b8634cdba252a1e5dd23810a",
            "5dd44b45fcea4f35b9686544c3b6681a",
            "57d6c301e3894231846453b799d8da55",
            "dfb3be4fb9c44a37af6a61f770b386b5",
            "4d4a3b5235ee4b27a9c30f56f6bc4bc6",
            "3329c4678ab14fc1b8b2705907fad5b4",
            "cdd55ae0c9a84c51bf7258ecf8298881",
            "da4c684e5ebd4331896cdbecf38d2e3d",
            "1b2c696f57ac45969f11a18248765fd3",
            "0e9b614aa3ec4c0d943a3d9b8f3b6a35",
            "3883b012e5f34a7eadc8d4f864c6d6b2",
            "3b660b482ec04f0898db5cc7f56ae8bc",
            "c5ba24fdeddd4cf9be9ed74a29c14a9f",
            "ab2f3cb36787435d964861f255f91f8b",
            "3c7e2bb2409c4fc389b76913b1c380df",
            "c7b8603733a44394a02d9cf47fe8403b",
            "f1a6073533fa4997ab61883b85164c7e",
            "a2a0bb5017af4d0dbc723f5c5c70acf3",
            "e21bc15e81da476b8631ddc73127c0ee",
            "bfeee4faa298466ca1fef4f52f152dce",
            "ed95a97632e04d6291deb4a00e2bef79",
            "b57c79a1fc7f41aa96edfcdd6c0d7883",
            "7f759c81baef4d75a7b27a22b752f003",
            "55998f8b799441238256e3a13ae6744a",
            "17b83f3f38fa48f8b1a5e0cc9aabbbca",
            "cbc9b7e280a943669f531c98ef202b6a",
            "d162350798474936be10b67e978dbddf",
            "53bb72a4966043ad97c68d0389fc1f7b",
            "6f48eac1c0f54bb494fd9f0fc1515d02",
            "e54d3695556046c4803337a03009da2a",
            "c6587970683c4a5aa16a47009b0b9c54",
            "9ad41a0985c0444cb8d8b364c35606e7",
            "952fef1867804eb1937c20072b63a4cc",
            "57f8db384a8a4db58ed6dbc3bd118f13",
            "f8d51f5a23a34f04a0028c3b13531617",
            "c6882e6f7a1e43d08aa2ec3c6b0ea36a"
          ]
        }
      },
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Downloading (…)lve/main/config.json:   0%|          | 0.00/583 [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "518c2a00450f46f782daae2a7757fe2a"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--NousResearch--Llama-2-7b-hf/snapshots/dacdfcde31297e34b19ee0e7532f29586d2c17bc/config.json\n",
            "Model config LlamaConfig {\n",
            "  \"_name_or_path\": \"NousResearch/Llama-2-7b-hf\",\n",
            "  \"architectures\": [\n",
            "    \"LlamaForCausalLM\"\n",
            "  ],\n",
            "  \"bos_token_id\": 1,\n",
            "  \"eos_token_id\": 2,\n",
            "  \"hidden_act\": \"silu\",\n",
            "  \"hidden_size\": 4096,\n",
            "  \"initializer_range\": 0.02,\n",
            "  \"intermediate_size\": 11008,\n",
            "  \"max_position_embeddings\": 4096,\n",
            "  \"model_type\": \"llama\",\n",
            "  \"num_attention_heads\": 32,\n",
            "  \"num_hidden_layers\": 32,\n",
            "  \"num_key_value_heads\": 32,\n",
            "  \"pad_token_id\": 0,\n",
            "  \"pretraining_tp\": 1,\n",
            "  \"rms_norm_eps\": 1e-05,\n",
            "  \"rope_scaling\": null,\n",
            "  \"rope_theta\": 10000.0,\n",
            "  \"tie_word_embeddings\": false,\n",
            "  \"torch_dtype\": \"float16\",\n",
            "  \"transformers_version\": \"4.33.1\",\n",
            "  \"use_cache\": true,\n",
            "  \"vocab_size\": 32000\n",
            "}\n",
            "\n",
            "Overriding torch_dtype=None with `torch_dtype=torch.float16` due to requirements of `bitsandbytes` to enable model loading in 8-bit or 4-bit. Pass your own torch_dtype to specify the dtype of the remaining non-linear layers or pass torch_dtype=torch.float16 to remove this warning.\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Downloading (…)fetensors.index.json:   0%|          | 0.00/26.8k [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "9a3d344182fb4c6cb351ac0b0978c0cf"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--NousResearch--Llama-2-7b-hf/snapshots/dacdfcde31297e34b19ee0e7532f29586d2c17bc/model.safetensors.index.json\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Downloading shards:   0%|          | 0/2 [00:00<?, ?it/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "71f94fcfff1c42f3bd47949d7b3232a0"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Downloading (…)of-00002.safetensors:   0%|          | 0.00/9.98G [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "14b3aea7a3324212b573f7acd00dd223"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Downloading (…)of-00002.safetensors:   0%|          | 0.00/3.50G [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "dfb3be4fb9c44a37af6a61f770b386b5"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "Instantiating LlamaForCausalLM model under default dtype torch.float16.\n",
            "Generate config GenerationConfig {\n",
            "  \"_from_model_config\": true,\n",
            "  \"bos_token_id\": 1,\n",
            "  \"eos_token_id\": 2,\n",
            "  \"pad_token_id\": 0,\n",
            "  \"transformers_version\": \"4.33.1\"\n",
            "}\n",
            "\n",
            "Detected 4-bit loading: activating 4-bit loading for this model\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "3c7e2bb2409c4fc389b76913b1c380df"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "All model checkpoint weights were used when initializing LlamaForCausalLM.\n",
            "\n",
            "All the weights of LlamaForCausalLM were initialized from the model checkpoint at NousResearch/Llama-2-7b-hf.\n",
            "If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Downloading (…)neration_config.json:   0%|          | 0.00/179 [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "cbc9b7e280a943669f531c98ef202b6a"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--NousResearch--Llama-2-7b-hf/snapshots/dacdfcde31297e34b19ee0e7532f29586d2c17bc/generation_config.json\n",
            "/usr/local/lib/python3.10/dist-packages/transformers/generation/configuration_utils.py:362: UserWarning: `do_sample` is set to `False`. However, `temperature` is set to `0.9` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `temperature`. This was detected when initializing the generation config instance, which means the corresponding file may hold incorrect parameterization and should be fixed.\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.10/dist-packages/transformers/generation/configuration_utils.py:367: UserWarning: `do_sample` is set to `False`. However, `top_p` is set to `0.6` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `top_p`. This was detected when initializing the generation config instance, which means the corresponding file may hold incorrect parameterization and should be fixed.\n",
            "  warnings.warn(\n",
            "Generate config GenerationConfig {\n",
            "  \"_from_model_config\": true,\n",
            "  \"bos_token_id\": 1,\n",
            "  \"eos_token_id\": 2,\n",
            "  \"pad_token_id\": 32000,\n",
            "  \"temperature\": 0.9,\n",
            "  \"top_p\": 0.6,\n",
            "  \"transformers_version\": \"4.33.1\"\n",
            "}\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "peft_path = f'{model_save_path}/checkpoint-201'\n",
        "model = PeftModel.from_pretrained(\n",
        "    model,\n",
        "    peft_path,\n",
        "    torch_dtype=torch.float16,\n",
        ")\n",
        "model.eval()"
      ],
      "metadata": {
        "id": "VzMXAZU1h-3D",
        "outputId": "21dd0981-8b75-4159-a396-f4bf1341e51d",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "PeftModelForCausalLM(\n",
              "  (base_model): LoraModel(\n",
              "    (model): LlamaForCausalLM(\n",
              "      (model): LlamaModel(\n",
              "        (embed_tokens): Embedding(32000, 4096, padding_idx=0)\n",
              "        (layers): ModuleList(\n",
              "          (0-31): 32 x LlamaDecoderLayer(\n",
              "            (self_attn): LlamaAttention(\n",
              "              (q_proj): Linear4bit(\n",
              "                in_features=4096, out_features=4096, bias=False\n",
              "                (lora_dropout): ModuleDict(\n",
              "                  (default): Dropout(p=0.1, inplace=False)\n",
              "                )\n",
              "                (lora_A): ModuleDict(\n",
              "                  (default): Linear(in_features=4096, out_features=8, bias=False)\n",
              "                )\n",
              "                (lora_B): ModuleDict(\n",
              "                  (default): Linear(in_features=8, out_features=4096, bias=False)\n",
              "                )\n",
              "                (lora_embedding_A): ParameterDict()\n",
              "                (lora_embedding_B): ParameterDict()\n",
              "              )\n",
              "              (k_proj): Linear4bit(in_features=4096, out_features=4096, bias=False)\n",
              "              (v_proj): Linear4bit(\n",
              "                in_features=4096, out_features=4096, bias=False\n",
              "                (lora_dropout): ModuleDict(\n",
              "                  (default): Dropout(p=0.1, inplace=False)\n",
              "                )\n",
              "                (lora_A): ModuleDict(\n",
              "                  (default): Linear(in_features=4096, out_features=8, bias=False)\n",
              "                )\n",
              "                (lora_B): ModuleDict(\n",
              "                  (default): Linear(in_features=8, out_features=4096, bias=False)\n",
              "                )\n",
              "                (lora_embedding_A): ParameterDict()\n",
              "                (lora_embedding_B): ParameterDict()\n",
              "              )\n",
              "              (o_proj): Linear4bit(in_features=4096, out_features=4096, bias=False)\n",
              "              (rotary_emb): LlamaRotaryEmbedding()\n",
              "            )\n",
              "            (mlp): LlamaMLP(\n",
              "              (gate_proj): Linear4bit(in_features=4096, out_features=11008, bias=False)\n",
              "              (up_proj): Linear4bit(in_features=4096, out_features=11008, bias=False)\n",
              "              (down_proj): Linear4bit(in_features=11008, out_features=4096, bias=False)\n",
              "              (act_fn): SiLUActivation()\n",
              "            )\n",
              "            (input_layernorm): LlamaRMSNorm()\n",
              "            (post_attention_layernorm): LlamaRMSNorm()\n",
              "          )\n",
              "        )\n",
              "        (norm): LlamaRMSNorm()\n",
              "      )\n",
              "      (lm_head): Linear(in_features=4096, out_features=32000, bias=False)\n",
              "    )\n",
              "  )\n",
              ")"
            ]
          },
          "metadata": {},
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "generation_config = GenerationConfig(\n",
        "    do_sample=True,\n",
        "    temperature=0.9,\n",
        "    # top_p=0.92,\n",
        "    # top_k=100,\n",
        "    num_beams=4, # beam search\n",
        "    # no_repeat_ngram_size=2\n",
        ")"
      ],
      "metadata": {
        "id": "b77aqg7aimxb"
      },
      "execution_count": 29,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "with torch.no_grad():\n",
        "  prompt = \"When did Virgin Australia start operating?\"\n",
        "  inputs = tokenizer(prompt, return_tensors=\"pt\")\n",
        "  generation_output = model.generate(\n",
        "      input_ids=inputs.input_ids,\n",
        "      generation_config=generation_config,\n",
        "      return_dict_in_generate=True,\n",
        "      max_new_tokens=100,\n",
        "  )\n",
        "  print('\\nAnswer: ', tokenizer.decode(generation_output.sequences[0]))"
      ],
      "metadata": {
        "id": "9oPvN-K7jGy5",
        "outputId": "90c15530-f614-4614-9e46-b5278e70fae9",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": 31,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "Answer:  <s> When did Virgin Australia start operating?\n",
            " everybody knows that Virgin Australia started operating in 2000.\n",
            "Virgin Australia is an Australian airline with its head office in Sydney, New South Wales. It is the largest airline in Australia by fleet size, and the second-largest airline in Australia by number of passengers carried, behind Qantas. Virgin Australia operates a domestic and international network that spans across Australia, Asia, New Zealand, North America and the South Pacific.\n",
            "Virgin\n"
          ]
        }
      ]
    }
  ]
}