{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [] }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" }, "widgets": { "application/vnd.jupyter.widget-state+json": { "a2e4e425b0bb46998b2217c709868715": { "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_5a99e443c2d94bb5b4bd5d54df31e016", "IPY_MODEL_cc26a4b380624f3faefe4b64da40179d", "IPY_MODEL_1f2554e855314b3c851e3ed69cc0239e" ], "layout": "IPY_MODEL_c39241d7b86f4c80ade8c77a52d0a65e" } }, "5a99e443c2d94bb5b4bd5d54df31e016": { "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_7480fe53b29e4116a6dc1dea890f17f5", "placeholder": "​", "style": "IPY_MODEL_a5dd56d18157419da45ad543c9ad632c", "value": "Downloading https://raw.githubusercontent.com/stanfordnlp/stanza-resources/main/resources_1.12.0.json: " } }, "cc26a4b380624f3faefe4b64da40179d": { "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_603aeb6d85664679b1234e4b1f926cc6", "max": 55072, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_bdf917e0d0f044dea02b13eb113ae706", "value": 55072 } }, "1f2554e855314b3c851e3ed69cc0239e": { "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_d9484af31d6c4a89b1b661f880051b31", "placeholder": "​", "style": "IPY_MODEL_d129a841bd0b4525afd37816b058611d", "value": " 450k/? [00:00<00:00, 14.8MB/s]" } }, "c39241d7b86f4c80ade8c77a52d0a65e": { "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 } }, "7480fe53b29e4116a6dc1dea890f17f5": { "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 } }, "a5dd56d18157419da45ad543c9ad632c": { "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": "" } }, "603aeb6d85664679b1234e4b1f926cc6": { "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 } }, "bdf917e0d0f044dea02b13eb113ae706": { "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": "" } }, "d9484af31d6c4a89b1b661f880051b31": { "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 } }, "d129a841bd0b4525afd37816b058611d": { "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": "" } }, "302c4b8434b44ae683c85179e1116605": { "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_e66fbdb6943349aab2e904f397f8fdf8", "IPY_MODEL_0fb00d473dbf49e5aa694c3cf2863cc7", "IPY_MODEL_cd55b5c0c5b34646b4efc8d0a7e5d647" ], "layout": "IPY_MODEL_301ed4f4acff4033be3926625a50967d" } }, "e66fbdb6943349aab2e904f397f8fdf8": { "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_8170acc142d8416c9c5a864c294fdd8f", "placeholder": "​", "style": "IPY_MODEL_5004f01629284671898849c697c14589", "value": "Downloading https://huggingface.co/stanfordnlp/stanza-en/resolve/v1.12.0/models/default.zip: 100%" } }, "0fb00d473dbf49e5aa694c3cf2863cc7": { "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_58bcc346996f427d96f664156a9c29e1", "max": 525960813, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_8179634b95404d44ba01887aa8c9fdd6", "value": 525960813 } }, "cd55b5c0c5b34646b4efc8d0a7e5d647": { "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_087e4264ebe34c2fa4ba8c245ca83fbe", "placeholder": "​", "style": "IPY_MODEL_d56a291b948c4f0b92ee38eb6d3749f3", "value": " 526M/526M [00:03<00:00, 125MB/s]" } }, "301ed4f4acff4033be3926625a50967d": { "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 } }, "8170acc142d8416c9c5a864c294fdd8f": { "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 } }, "5004f01629284671898849c697c14589": { "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": "" } }, "58bcc346996f427d96f664156a9c29e1": { "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 } }, "8179634b95404d44ba01887aa8c9fdd6": { "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": "" } }, "087e4264ebe34c2fa4ba8c245ca83fbe": { "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 } }, "d56a291b948c4f0b92ee38eb6d3749f3": { "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": "" } }, "4ac57be03fd24e488019495bb98e9d14": { "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_09a8483aa6e1436095cbe2fa4c2d45b9", "IPY_MODEL_8b381df3167748f08329afafee5e91b1", "IPY_MODEL_8a167cf8e34f4038b0e0d5a8a1dcbe07" ], "layout": "IPY_MODEL_c8ddccf7da5b49ad94b0b783ffe59f8d" } }, "09a8483aa6e1436095cbe2fa4c2d45b9": { "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_b81230c212214ba581803577437d1e1d", "placeholder": "​", "style": "IPY_MODEL_1e9d15e2d1dd435d9bde9f36f7f07736", "value": "Downloading https://raw.githubusercontent.com/stanfordnlp/stanza-resources/main/resources_1.12.0.json: " } }, "8b381df3167748f08329afafee5e91b1": { "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_68eebe3b39164a1bbfc4a33cb151efdd", "max": 55072, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_d85af3826fa44b538f09d8e866bc3324", "value": 55072 } }, "8a167cf8e34f4038b0e0d5a8a1dcbe07": { "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_b338e0c52c04433684390b8a14104420", "placeholder": "​", "style": "IPY_MODEL_fdf2702a60064fd2ad428801bae3d05d", "value": " 450k/? [00:00<00:00, 24.5MB/s]" } }, "c8ddccf7da5b49ad94b0b783ffe59f8d": { "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 } }, "b81230c212214ba581803577437d1e1d": { "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 } }, "1e9d15e2d1dd435d9bde9f36f7f07736": { "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": "" } }, "68eebe3b39164a1bbfc4a33cb151efdd": { "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 } }, "d85af3826fa44b538f09d8e866bc3324": { "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": "" } }, "b338e0c52c04433684390b8a14104420": { "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 } }, "fdf2702a60064fd2ad428801bae3d05d": { "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": "" } }, "e67e1a68554a449788670206a6131995": { "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_412953d259cc4d4dab07dcc029f077ba", "IPY_MODEL_4f9d38bd58ec465fa85a6ffd1a98ccb4", "IPY_MODEL_8503c97f61ec4cfeb319ce91ab775604" ], "layout": "IPY_MODEL_12efd716a5444d7f8f0ad5adcf379869" } }, "412953d259cc4d4dab07dcc029f077ba": { "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_2f0f9249e2914e94a8349838293af13a", "placeholder": "​", "style": "IPY_MODEL_adb5340729354cf6a7ee85b0dc5b1741", "value": "config.json: 100%" } }, "4f9d38bd58ec465fa85a6ffd1a98ccb4": { "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_aae88b0bff3d4a6c9f85cacee3ea32a4", "max": 665, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_f50eb13981ac4f9c91a4c735171b3cd5", "value": 665 } }, "8503c97f61ec4cfeb319ce91ab775604": { "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_2a68d8bb04cc42288fd8771e2a3e6c63", "placeholder": "​", "style": "IPY_MODEL_46d301645e724b989cc0f2cab057b51e", "value": " 665/665 [00:00<00:00, 12.9kB/s]" } }, "12efd716a5444d7f8f0ad5adcf379869": { "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 } }, "2f0f9249e2914e94a8349838293af13a": { "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 } }, "adb5340729354cf6a7ee85b0dc5b1741": { "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": "" } }, "aae88b0bff3d4a6c9f85cacee3ea32a4": { "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 } }, "f50eb13981ac4f9c91a4c735171b3cd5": { "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": "" } }, "2a68d8bb04cc42288fd8771e2a3e6c63": { "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 } }, "46d301645e724b989cc0f2cab057b51e": { "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": "" } }, "867bd34ec2a244699d921396ccd41c45": { "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_d3db2a7e95704a9bb63cfd6b53345417", "IPY_MODEL_3efe319801b94b5f85ccc4485ff33eb0", "IPY_MODEL_86a3fc73cb7049f3872e004a4cbe34eb" ], "layout": "IPY_MODEL_38cc6aeb9c264376a7677804e638ef0e" } }, "d3db2a7e95704a9bb63cfd6b53345417": { "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_a55a3c7f0f734e9cbb231b4627ecb051", "placeholder": "​", "style": "IPY_MODEL_6702e1ef46994164808296f8b1d3ef54", "value": "model.safetensors: 100%" } }, "3efe319801b94b5f85ccc4485ff33eb0": { "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_cddb35edcd0c4ed6a33488a7af89acee", "max": 548105171, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_5cba8f200b794ce7835978ccf212c21b", "value": 548105171 } }, "86a3fc73cb7049f3872e004a4cbe34eb": { "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_b79004450c4045d5bfab80f04ae6efa3", "placeholder": "​", "style": "IPY_MODEL_2687a0d8cba14b3bb456bd92bf471aa2", "value": " 548M/548M [00:09<00:00, 87.3MB/s]" } }, "38cc6aeb9c264376a7677804e638ef0e": { "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 } }, "a55a3c7f0f734e9cbb231b4627ecb051": { "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 } }, "6702e1ef46994164808296f8b1d3ef54": { "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": "" } }, "cddb35edcd0c4ed6a33488a7af89acee": { "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 } }, "5cba8f200b794ce7835978ccf212c21b": { "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": "" } }, "b79004450c4045d5bfab80f04ae6efa3": { "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 } }, "2687a0d8cba14b3bb456bd92bf471aa2": { "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": "" } }, "9e90fb34cf034b3b954a1562fa6d318c": { "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_931324c3ba814c35a4bcdcb188a60851", "IPY_MODEL_614f1cb0b77b4f84bc64218a6384f592", "IPY_MODEL_71c9518e37ab4c06bb434e91023e38f8" ], "layout": "IPY_MODEL_66aa0550932c4a38a6bc548bcaf77761" } }, "931324c3ba814c35a4bcdcb188a60851": { "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_f65e007e5fe54f9b97e1628fbedb55f5", "placeholder": "​", "style": "IPY_MODEL_876d3eafd002467f82f9d091058ae0a0", "value": "Loading weights: 100%" } }, "614f1cb0b77b4f84bc64218a6384f592": { "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_7463d336c8cb468bb9dbcaf8994150c1", "max": 148, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_c4642347a5a442ebba609363c6d40087", "value": 148 } }, "71c9518e37ab4c06bb434e91023e38f8": { "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_bc7f3a490d394a1ca139f11a4b7499fe", "placeholder": "​", "style": "IPY_MODEL_717210576269425f9d440bbd65b3d9c4", "value": " 148/148 [00:00<00:00, 229.41it/s, Materializing param=transformer.wte.weight]" } }, "66aa0550932c4a38a6bc548bcaf77761": { "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 } }, "f65e007e5fe54f9b97e1628fbedb55f5": { "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 } }, "876d3eafd002467f82f9d091058ae0a0": { "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": "" } }, "7463d336c8cb468bb9dbcaf8994150c1": { "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 } }, "c4642347a5a442ebba609363c6d40087": { "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": "" } }, "bc7f3a490d394a1ca139f11a4b7499fe": { "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 } }, "717210576269425f9d440bbd65b3d9c4": { "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": "" } }, "461de7b2813c41e99b3c75df6e08f9d2": { "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_8d3559ba307f418ca31e1fab0dc375fb", "IPY_MODEL_803277b13e3d4c7faeb9dc9eabec19f3", "IPY_MODEL_99825624e7854b2397897f58beb27f46" ], "layout": "IPY_MODEL_f2fc29e957e64cc1aadc920a34c9ef16" } }, "8d3559ba307f418ca31e1fab0dc375fb": { "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_6f0eb2d6318642a1bee2bb19bb311d6c", "placeholder": "​", "style": "IPY_MODEL_56f92edca1a949c7b8642f5261b49606", "value": "generation_config.json: 100%" } }, "803277b13e3d4c7faeb9dc9eabec19f3": { "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_3c724f88bf76402f90fcd7700b842076", "max": 124, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_1f938382ba5947229d8aff0b8c761e76", "value": 124 } }, "99825624e7854b2397897f58beb27f46": { "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_0393e5f2538e48c884d4956a3f794466", "placeholder": "​", "style": "IPY_MODEL_34457c79fdf446ad80b1528bfc0121a7", "value": " 124/124 [00:00<00:00, 3.57kB/s]" } }, "f2fc29e957e64cc1aadc920a34c9ef16": { "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 } }, "6f0eb2d6318642a1bee2bb19bb311d6c": { "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 } }, "56f92edca1a949c7b8642f5261b49606": { "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": "" } }, "3c724f88bf76402f90fcd7700b842076": { "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 } }, "1f938382ba5947229d8aff0b8c761e76": { "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": "" } }, "0393e5f2538e48c884d4956a3f794466": { "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 } }, "34457c79fdf446ad80b1528bfc0121a7": { "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": "" } }, "cdfa8da7c61c4f5d90669527dc70a9ec": { "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_6f5fadd3214348598a55ab98eb3a646c", "IPY_MODEL_4703cfae59914a72bd611d7f136a2d89", "IPY_MODEL_ad6b5eafeed94f9aa0cea14a8024496c" ], "layout": "IPY_MODEL_c141c9defb224413a23a0c84d654148c" } }, "6f5fadd3214348598a55ab98eb3a646c": { "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_98370eb0e5604b7e85fe78513d94b563", "placeholder": "​", "style": "IPY_MODEL_40684bdeab80474f80e925ef7ce1aa79", "value": "tokenizer_config.json: 100%" } }, "4703cfae59914a72bd611d7f136a2d89": { "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_e2814cec6023419785982d0de99926d8", "max": 26, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_2d8804ed08bf451f95c1bc1d6e18788d", "value": 26 } }, "ad6b5eafeed94f9aa0cea14a8024496c": { "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_bd9796366d554e5ba6ea17b516a8fd4d", "placeholder": "​", "style": "IPY_MODEL_916126700c544f2a9e45fe5cdf3f1f09", "value": " 26.0/26.0 [00:00<00:00, 701B/s]" } }, "c141c9defb224413a23a0c84d654148c": { "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 } }, "98370eb0e5604b7e85fe78513d94b563": { "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 } }, "40684bdeab80474f80e925ef7ce1aa79": { "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": "" } }, "e2814cec6023419785982d0de99926d8": { "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 } }, "2d8804ed08bf451f95c1bc1d6e18788d": { "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": "" } }, "bd9796366d554e5ba6ea17b516a8fd4d": { "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 } }, "916126700c544f2a9e45fe5cdf3f1f09": { "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": "" } }, "c41480f5234f4d3a99ced15985df0ab6": { "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_50f648f766354ccbb1a784301828efa6", "IPY_MODEL_162f618178ff4077893800b2660bd0c9", "IPY_MODEL_5ffb99cdafa54bc79fb0136931b42d65" ], "layout": "IPY_MODEL_7e8bf24baba7495dab6248cdceb0800e" } }, "50f648f766354ccbb1a784301828efa6": { "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_573333d43b0e4dd8af5b84de26e78daf", "placeholder": "​", "style": "IPY_MODEL_2fcf4de90b5844c4bc0ad1942a3a46db", "value": "vocab.json: " } }, "162f618178ff4077893800b2660bd0c9": { "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_a245a953c0b24c909cb28e1fba5536e3", "max": 1, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_7ba77611d63c400db1b2ba4f421d3023", "value": 1 } }, "5ffb99cdafa54bc79fb0136931b42d65": { "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_67087dd536dc447592d440a7c46eb923", "placeholder": "​", "style": "IPY_MODEL_2bbb3a79ef9b4e96adb82609519eaef3", "value": " 1.04M/? [00:00<00:00, 9.80MB/s]" } }, "7e8bf24baba7495dab6248cdceb0800e": { "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 } }, "573333d43b0e4dd8af5b84de26e78daf": { "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 } }, "2fcf4de90b5844c4bc0ad1942a3a46db": { "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": "" } }, "a245a953c0b24c909cb28e1fba5536e3": { "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": "20px" } }, "7ba77611d63c400db1b2ba4f421d3023": { "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": "" } }, "67087dd536dc447592d440a7c46eb923": { "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 } }, "2bbb3a79ef9b4e96adb82609519eaef3": { "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": "" } }, "6c94a5c9986c4df69a0ee4f04870ce84": { "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_d081b39bf3c642e0b2078c84d146d012", "IPY_MODEL_8b5bbf96e25542dcbb59e4562a86dc84", "IPY_MODEL_94194591ce60466b8426a8b54f6b26e1" ], "layout": "IPY_MODEL_be57b859dd604189b778e07bfe719036" } }, "d081b39bf3c642e0b2078c84d146d012": { "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_2d1d60a49bdb420e8ceb05e528a103b4", "placeholder": "​", "style": "IPY_MODEL_d9ca1d21fe924f7c923d06b3c8fcb148", "value": "merges.txt: " } }, "8b5bbf96e25542dcbb59e4562a86dc84": { "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_f61ddc9b376c4caa8fedbe6c1fbb7619", "max": 1, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_1e8c6345bcd547158f340bc972075068", "value": 1 } }, "94194591ce60466b8426a8b54f6b26e1": { "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_485369b459c5479d93f9f7c474a62241", "placeholder": "​", "style": "IPY_MODEL_7c05b6397c5245598009e3c0c570d894", "value": " 456k/? [00:00<00:00, 6.49MB/s]" } }, "be57b859dd604189b778e07bfe719036": { "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 } }, "2d1d60a49bdb420e8ceb05e528a103b4": { "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 } }, "d9ca1d21fe924f7c923d06b3c8fcb148": { "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": "" } }, "f61ddc9b376c4caa8fedbe6c1fbb7619": { "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": "20px" } }, "1e8c6345bcd547158f340bc972075068": { "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": "" } }, "485369b459c5479d93f9f7c474a62241": { "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 } }, "7c05b6397c5245598009e3c0c570d894": { "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": "" } }, "da714638921c4ebd81358734c9548a8c": { "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_fb56be9ad309449e8ccae9c948826aef", "IPY_MODEL_36395a5ff64c4151aa0d3d428ca540a3", "IPY_MODEL_fbd05bc8225a489c9ba3163e10f80d9f" ], "layout": "IPY_MODEL_4ae36d16f1744ac9a2a2442704163c2f" } }, "fb56be9ad309449e8ccae9c948826aef": { "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_673a95d4b0274b859d25c540aead7a57", "placeholder": "​", "style": "IPY_MODEL_e518b690f7f74b739cf563cbd0ae53e9", "value": "tokenizer.json: " } }, "36395a5ff64c4151aa0d3d428ca540a3": { "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_4f0eaa172c384160807ee5e715c2b287", "max": 1, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_1db87e4363744b88b611804f9195d196", "value": 1 } }, "fbd05bc8225a489c9ba3163e10f80d9f": { "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_b917740795d14855b4d6b713e25546ae", "placeholder": "​", "style": "IPY_MODEL_02a76e30345d4ce9b23c6b84d5432adf", "value": " 1.36M/? [00:00<00:00, 14.0MB/s]" } }, "4ae36d16f1744ac9a2a2442704163c2f": { "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 } }, "673a95d4b0274b859d25c540aead7a57": { "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 } }, "e518b690f7f74b739cf563cbd0ae53e9": { "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": "" } }, "4f0eaa172c384160807ee5e715c2b287": { "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": "20px" } }, "1db87e4363744b88b611804f9195d196": { "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": "" } }, "b917740795d14855b4d6b713e25546ae": { "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 } }, "02a76e30345d4ce9b23c6b84d5432adf": { "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": "" } }, "455c1f40f89046269f1dea71badb8e8d": { "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_5728f6a9104048b292194d98d4155fa2", "IPY_MODEL_8afc623afea042c3a01f96115a5ee2ff", "IPY_MODEL_226dc758713d4df7b4dfc5b7419ca332" ], "layout": "IPY_MODEL_7910fe4089544a168e86fcc446fa39b3" } }, "5728f6a9104048b292194d98d4155fa2": { "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_e942fc441ba64496933a2930f2f19f25", "placeholder": "​", "style": "IPY_MODEL_a4f3b70cbaee43869ae62f3cf23f4e87", "value": "pytorch_model.bin: 100%" } }, "8afc623afea042c3a01f96115a5ee2ff": { "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_34700d9e05514fb8a7e80d5527331f12", "max": 419080819, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_81cfea069dfd495bbeb34890c1c08fff", "value": 419080819 } }, "226dc758713d4df7b4dfc5b7419ca332": { "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_7fe4cb82aa524c76a5827877c58e3581", "placeholder": "​", "style": "IPY_MODEL_2fe509a615104032ba39330f4057ec20", "value": " 419M/419M [00:06<00:00, 105MB/s]" } }, "7910fe4089544a168e86fcc446fa39b3": { "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 } }, "e942fc441ba64496933a2930f2f19f25": { "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 } }, "a4f3b70cbaee43869ae62f3cf23f4e87": { "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": "" } }, "34700d9e05514fb8a7e80d5527331f12": { "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 } }, "81cfea069dfd495bbeb34890c1c08fff": { "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": "" } }, "7fe4cb82aa524c76a5827877c58e3581": { "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 } }, "2fe509a615104032ba39330f4057ec20": { "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": [ "##**Regular Expressions**" ], "metadata": { "id": "QHtN2aSlepdv" } }, { "cell_type": "code", "source": [ "import re\n", "\n", "text = \"\"\"\n", "Contact us at support@gmail.com or call 9876543210\n", "\"\"\"\n", "\n", "email = re.findall(r'\\S+@\\S+', text)\n", "\n", "phone = re.findall(r'\\d{10}', text)\n", "\n", "print(\"Email:\", email)\n", "print(\"Phone:\", phone)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "wuYZ9WvreZMm", "outputId": "8476def1-780f-4111-a6a7-87fa1f7945d9" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Email: ['support@gmail.com']\n", "Phone: ['9876543210']\n" ] } ] }, { "cell_type": "markdown", "source": [ "##**NLTK**" ], "metadata": { "id": "yVutCQwIf65g" } }, { "cell_type": "code", "source": [ "!pip install nltk" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "iUFii7oqgKCo", "outputId": "42f4b225-0131-4e85-a6fc-c633a4afa3ce" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Requirement already satisfied: nltk in /usr/local/lib/python3.12/dist-packages (3.9.1)\n", "Requirement already satisfied: click in /usr/local/lib/python3.12/dist-packages (from nltk) (8.3.3)\n", "Requirement already satisfied: joblib in /usr/local/lib/python3.12/dist-packages (from nltk) (1.5.3)\n", "Requirement already satisfied: regex>=2021.8.3 in /usr/local/lib/python3.12/dist-packages (from nltk) (2025.11.3)\n", "Requirement already satisfied: tqdm in /usr/local/lib/python3.12/dist-packages (from nltk) (4.67.3)\n" ] } ] }, { "cell_type": "code", "source": [ "import nltk\n", "nltk.download('punkt_tab')\n", "from nltk.tokenize import word_tokenize\n", "\n", "text = \"Natural Language Processing is interesting.\"\n", "\n", "tokens = word_tokenize(text)\n", "\n", "print(tokens)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "Whmb9K9CeZPC", "outputId": "44ac55ee-85f5-4484-debe-5998cf398c0c" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "[nltk_data] Downloading package punkt_tab to /root/nltk_data...\n", "[nltk_data] Unzipping tokenizers/punkt_tab.zip.\n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "['Natural', 'Language', 'Processing', 'is', 'interesting', '.']\n" ] } ] }, { "cell_type": "markdown", "source": [ "##**Spacy**" ], "metadata": { "id": "DCxcqyXkkln9" } }, { "cell_type": "code", "source": [ "import spacy\n", "\n", "nlp = spacy.load(\"en_core_web_sm\")\n", "\n", "text = \"Apple opened a new office in California.\"\n", "\n", "doc = nlp(text)\n", "\n", "for ent in doc.ents:\n", " print(ent.text, ent.label_)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "Olb8dHk3eZRq", "outputId": "3ea593f1-77f2-4293-cf8c-fcc3fc29609e" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Apple ORG\n", "California GPE\n" ] } ] }, { "cell_type": "markdown", "source": [ "##**TextBlob**" ], "metadata": { "id": "KlJH3sRHl7fl" } }, { "cell_type": "code", "source": [ "from textblob import TextBlob\n", "\n", "text = TextBlob(\"I love learning NLP with Python.\")\n", "\n", "print(text.sentiment)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "7L3gsQFdeZUK", "outputId": "0ee1b553-4bfd-4ebc-fc9e-807e1e70db60" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Sentiment(polarity=0.5, subjectivity=0.6)\n" ] } ] }, { "cell_type": "markdown", "source": [ "##**TextAcy**" ], "metadata": { "id": "PflMJT7GmgVe" } }, { "cell_type": "code", "source": [ "!pip install textacy" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "collapsed": true, "id": "bSNGYy52ms_G", "outputId": "bffedeeb-a11d-44de-d8a2-6aa1ff9ac846" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Collecting textacy\n", " Downloading textacy-0.13.0-py3-none-any.whl.metadata (5.3 kB)\n", "Requirement already satisfied: cachetools>=4.0.0 in /usr/local/lib/python3.12/dist-packages (from textacy) (6.2.6)\n", "Requirement already satisfied: catalogue~=2.0 in /usr/local/lib/python3.12/dist-packages (from textacy) (2.0.10)\n", "Collecting cytoolz>=0.10.1 (from textacy)\n", " Downloading cytoolz-1.1.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl.metadata (5.2 kB)\n", "Collecting floret~=0.10.0 (from textacy)\n", " Downloading floret-0.10.5-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.1 kB)\n", "Collecting jellyfish>=0.8.0 (from textacy)\n", " Downloading jellyfish-1.2.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (642 bytes)\n", "Requirement already satisfied: joblib>=0.13.0 in /usr/local/lib/python3.12/dist-packages (from textacy) (1.5.3)\n", "Requirement already satisfied: networkx>=2.7 in /usr/local/lib/python3.12/dist-packages (from textacy) (3.6.1)\n", "Requirement already satisfied: numpy>=1.17.0 in /usr/local/lib/python3.12/dist-packages (from textacy) (2.0.2)\n", "Collecting pyphen>=0.10.0 (from textacy)\n", " Downloading pyphen-0.17.2-py3-none-any.whl.metadata (3.2 kB)\n", "Requirement already satisfied: requests>=2.10.0 in /usr/local/lib/python3.12/dist-packages (from textacy) (2.32.4)\n", "Requirement already satisfied: scipy>=1.8.0 in /usr/local/lib/python3.12/dist-packages (from textacy) (1.16.3)\n", "Requirement already satisfied: scikit-learn>=1.0 in /usr/local/lib/python3.12/dist-packages (from textacy) (1.6.1)\n", "Requirement already satisfied: spacy~=3.0 in /usr/local/lib/python3.12/dist-packages (from textacy) (3.8.14)\n", "Requirement already satisfied: tqdm>=4.19.6 in /usr/local/lib/python3.12/dist-packages (from textacy) (4.67.3)\n", "Requirement already satisfied: toolz>=0.8.0 in /usr/local/lib/python3.12/dist-packages (from cytoolz>=0.10.1->textacy) (0.12.1)\n", "Requirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests>=2.10.0->textacy) (3.4.7)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests>=2.10.0->textacy) (3.13)\n", "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests>=2.10.0->textacy) (2.5.0)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests>=2.10.0->textacy) (2026.4.22)\n", "Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn>=1.0->textacy) (3.6.0)\n", "Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.11 in /usr/local/lib/python3.12/dist-packages (from spacy~=3.0->textacy) (3.0.12)\n", "Requirement already satisfied: spacy-loggers<2.0.0,>=1.0.0 in /usr/local/lib/python3.12/dist-packages (from spacy~=3.0->textacy) (1.0.5)\n", "Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in /usr/local/lib/python3.12/dist-packages (from spacy~=3.0->textacy) (1.0.15)\n", "Requirement already satisfied: cymem<2.1.0,>=2.0.2 in /usr/local/lib/python3.12/dist-packages (from spacy~=3.0->textacy) (2.0.13)\n", "Requirement already satisfied: preshed<3.1.0,>=3.0.2 in /usr/local/lib/python3.12/dist-packages (from spacy~=3.0->textacy) (3.0.13)\n", "Requirement already satisfied: thinc<8.4.0,>=8.3.12 in /usr/local/lib/python3.12/dist-packages (from spacy~=3.0->textacy) (8.3.13)\n", "Requirement already satisfied: wasabi<1.2.0,>=0.9.1 in /usr/local/lib/python3.12/dist-packages (from spacy~=3.0->textacy) (1.1.3)\n", "Requirement already satisfied: srsly<3.0.0,>=2.5.3 in /usr/local/lib/python3.12/dist-packages (from spacy~=3.0->textacy) (2.5.3)\n", "Requirement already satisfied: weasel<2.0.0,>=1.0.0 in /usr/local/lib/python3.12/dist-packages (from spacy~=3.0->textacy) (1.0.0)\n", "Requirement already satisfied: confection<2.0.0,>=1.3.2 in /usr/local/lib/python3.12/dist-packages (from spacy~=3.0->textacy) (1.3.3)\n", "Requirement already satisfied: typer<1.0.0,>=0.3.0 in /usr/local/lib/python3.12/dist-packages (from spacy~=3.0->textacy) (0.24.2)\n", "Requirement already satisfied: pydantic<3.0.0,>=2.0.0 in /usr/local/lib/python3.12/dist-packages (from spacy~=3.0->textacy) (2.12.3)\n", "Requirement already satisfied: jinja2 in /usr/local/lib/python3.12/dist-packages (from spacy~=3.0->textacy) (3.1.6)\n", "Requirement already satisfied: setuptools in /usr/local/lib/python3.12/dist-packages (from spacy~=3.0->textacy) (75.2.0)\n", "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.12/dist-packages (from spacy~=3.0->textacy) (26.1)\n", "Requirement already satisfied: annotated-types>=0.6.0 in /usr/local/lib/python3.12/dist-packages (from pydantic<3.0.0,>=2.0.0->spacy~=3.0->textacy) (0.7.0)\n", "Requirement already satisfied: pydantic-core==2.41.4 in /usr/local/lib/python3.12/dist-packages (from pydantic<3.0.0,>=2.0.0->spacy~=3.0->textacy) (2.41.4)\n", "Requirement already satisfied: typing-extensions>=4.14.1 in /usr/local/lib/python3.12/dist-packages (from pydantic<3.0.0,>=2.0.0->spacy~=3.0->textacy) (4.15.0)\n", "Requirement already satisfied: typing-inspection>=0.4.2 in /usr/local/lib/python3.12/dist-packages (from pydantic<3.0.0,>=2.0.0->spacy~=3.0->textacy) (0.4.2)\n", "Requirement already satisfied: blis<1.4.0,>=1.3.0 in /usr/local/lib/python3.12/dist-packages (from thinc<8.4.0,>=8.3.12->spacy~=3.0->textacy) (1.3.3)\n", "Requirement already satisfied: click>=8.2.1 in /usr/local/lib/python3.12/dist-packages (from typer<1.0.0,>=0.3.0->spacy~=3.0->textacy) (8.3.3)\n", "Requirement already satisfied: shellingham>=1.3.0 in /usr/local/lib/python3.12/dist-packages (from typer<1.0.0,>=0.3.0->spacy~=3.0->textacy) (1.5.4)\n", "Requirement already satisfied: rich>=12.3.0 in /usr/local/lib/python3.12/dist-packages (from typer<1.0.0,>=0.3.0->spacy~=3.0->textacy) (13.9.4)\n", "Requirement already satisfied: annotated-doc>=0.0.2 in /usr/local/lib/python3.12/dist-packages (from typer<1.0.0,>=0.3.0->spacy~=3.0->textacy) (0.0.4)\n", "Requirement already satisfied: cloudpathlib>=0.7.0 in /usr/local/lib/python3.12/dist-packages (from weasel<2.0.0,>=1.0.0->spacy~=3.0->textacy) (0.23.0)\n", "Requirement already satisfied: smart-open>=5.2.1 in /usr/local/lib/python3.12/dist-packages (from weasel<2.0.0,>=1.0.0->spacy~=3.0->textacy) (7.6.0)\n", "Requirement already satisfied: httpx>=0.24.0 in /usr/local/lib/python3.12/dist-packages (from weasel<2.0.0,>=1.0.0->spacy~=3.0->textacy) (0.28.1)\n", "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.12/dist-packages (from jinja2->spacy~=3.0->textacy) (3.0.3)\n", "Requirement already satisfied: anyio in /usr/local/lib/python3.12/dist-packages (from httpx>=0.24.0->weasel<2.0.0,>=1.0.0->spacy~=3.0->textacy) (4.13.0)\n", "Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.12/dist-packages (from httpx>=0.24.0->weasel<2.0.0,>=1.0.0->spacy~=3.0->textacy) (1.0.9)\n", "Requirement already satisfied: h11>=0.16 in /usr/local/lib/python3.12/dist-packages (from httpcore==1.*->httpx>=0.24.0->weasel<2.0.0,>=1.0.0->spacy~=3.0->textacy) (0.16.0)\n", "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.12/dist-packages (from rich>=12.3.0->typer<1.0.0,>=0.3.0->spacy~=3.0->textacy) (4.0.0)\n", "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.12/dist-packages (from rich>=12.3.0->typer<1.0.0,>=0.3.0->spacy~=3.0->textacy) (2.20.0)\n", "Requirement already satisfied: wrapt in /usr/local/lib/python3.12/dist-packages (from smart-open>=5.2.1->weasel<2.0.0,>=1.0.0->spacy~=3.0->textacy) (2.1.2)\n", "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.12/dist-packages (from markdown-it-py>=2.2.0->rich>=12.3.0->typer<1.0.0,>=0.3.0->spacy~=3.0->textacy) (0.1.2)\n", "Downloading textacy-0.13.0-py3-none-any.whl (210 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m210.7/210.7 kB\u001b[0m \u001b[31m9.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading cytoolz-1.1.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl (2.9 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.9/2.9 MB\u001b[0m \u001b[31m63.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading floret-0.10.5-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (321 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m321.6/321.6 kB\u001b[0m \u001b[31m20.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading jellyfish-1.2.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (360 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m360.5/360.5 kB\u001b[0m \u001b[31m22.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading pyphen-0.17.2-py3-none-any.whl (2.1 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.1/2.1 MB\u001b[0m \u001b[31m78.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hInstalling collected packages: pyphen, jellyfish, floret, cytoolz, textacy\n", "Successfully installed cytoolz-1.1.0 floret-0.10.5 jellyfish-1.2.1 pyphen-0.17.2 textacy-0.13.0\n" ] } ] }, { "cell_type": "code", "source": [ "import textacy.preprocessing as preprocessing\n", "\n", "text = \"Hello!!! Welcome to NLP with Textacy.\"\n", "\n", "clean_text = preprocessing.remove.punctuation(text)\n", "\n", "print(clean_text)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "xhFmMqOSeZW6", "outputId": "d94f6e03-c944-497f-b310-a6570642ab7a" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Hello Welcome to NLP with Textacy \n" ] } ] }, { "cell_type": "markdown", "source": [ "##**VADER**" ], "metadata": { "id": "6BY_OhJZnWaA" } }, { "cell_type": "code", "source": [ "!pip install vaderSentiment" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "collapsed": true, "id": "GfHiL1c8necy", "outputId": "09dbe245-64c9-41c0-9947-8a9fb583a938" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Collecting vaderSentiment\n", " Downloading vaderSentiment-3.3.2-py2.py3-none-any.whl.metadata (572 bytes)\n", "Requirement already satisfied: requests in /usr/local/lib/python3.12/dist-packages (from vaderSentiment) (2.32.4)\n", "Requirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests->vaderSentiment) (3.4.7)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests->vaderSentiment) (3.13)\n", "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests->vaderSentiment) (2.5.0)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests->vaderSentiment) (2026.4.22)\n", "Downloading vaderSentiment-3.3.2-py2.py3-none-any.whl (125 kB)\n", "\u001b[?25l \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/126.0 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m126.0/126.0 kB\u001b[0m \u001b[31m5.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hInstalling collected packages: vaderSentiment\n", "Successfully installed vaderSentiment-3.3.2\n" ] } ] }, { "cell_type": "code", "source": [ "from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer\n", "\n", "analyzer = SentimentIntensityAnalyzer()\n", "\n", "text = \"This movie was amazing! 😍\"\n", "\n", "scores = analyzer.polarity_scores(text)\n", "\n", "print(scores)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "-SKrNd7xeZZC", "outputId": "a8d06169-0730-42ae-aad7-5292086850d5" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "{'neg': 0.0, 'neu': 0.458, 'pos': 0.542, 'compound': 0.7959}\n" ] } ] }, { "cell_type": "markdown", "source": [ "##**Gensim**" ], "metadata": { "id": "eexV1Dixobd3" } }, { "cell_type": "code", "source": [ "!pip install gensim" ], "metadata": { "collapsed": true, "colab": { "base_uri": "https://localhost:8080/" }, "id": "qnhX6BM1okdR", "outputId": "b6541a39-c08e-43f4-9d36-32ecc7576596" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Collecting gensim\n", " Downloading gensim-4.4.0-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl.metadata (8.4 kB)\n", "Requirement already satisfied: numpy>=1.18.5 in /usr/local/lib/python3.12/dist-packages (from gensim) (2.0.2)\n", "Requirement already satisfied: scipy>=1.7.0 in /usr/local/lib/python3.12/dist-packages (from gensim) (1.16.3)\n", "Requirement already satisfied: smart_open>=1.8.1 in /usr/local/lib/python3.12/dist-packages (from gensim) (7.6.0)\n", "Requirement already satisfied: wrapt in /usr/local/lib/python3.12/dist-packages (from smart_open>=1.8.1->gensim) (2.1.2)\n", "Downloading gensim-4.4.0-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl (27.9 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m27.9/27.9 MB\u001b[0m \u001b[31m61.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hInstalling collected packages: gensim\n", "Successfully installed gensim-4.4.0\n" ] } ] }, { "cell_type": "code", "source": [ "from gensim.utils import simple_preprocess\n", "\n", "text = \"Gensim is useful for topic modeling and NLP.\"\n", "\n", "tokens = simple_preprocess(text)\n", "\n", "print(tokens)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "R-GlMSjreZba", "outputId": "fe516290-8293-4a36-aae9-77533e8d0d29" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "['gensim', 'is', 'useful', 'for', 'topic', 'modeling', 'and', 'nlp']\n" ] } ] }, { "cell_type": "markdown", "source": [ "##**Stanza**" ], "metadata": { "id": "qpZWzKohu4Ht" } }, { "cell_type": "code", "source": [ "!pip install stanza" ], "metadata": { "collapsed": true, "colab": { "base_uri": "https://localhost:8080/" }, "id": "iJfl5_7xu8_x", "outputId": "e192e3c8-0482-4720-c9b4-2000dc63abbc" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Collecting stanza\n", " Downloading stanza-1.12.0-py3-none-any.whl.metadata (14 kB)\n", "Collecting emoji (from stanza)\n", " Downloading emoji-2.15.0-py3-none-any.whl.metadata (5.7 kB)\n", "Requirement already satisfied: numpy in /usr/local/lib/python3.12/dist-packages (from stanza) (2.0.2)\n", "Requirement already satisfied: platformdirs in /usr/local/lib/python3.12/dist-packages (from stanza) (4.9.6)\n", "Requirement already satisfied: protobuf>=3.15.0 in /usr/local/lib/python3.12/dist-packages (from stanza) (5.29.6)\n", "Requirement already satisfied: requests in /usr/local/lib/python3.12/dist-packages (from stanza) (2.32.4)\n", "Requirement already satisfied: networkx in /usr/local/lib/python3.12/dist-packages (from stanza) (3.6.1)\n", "Requirement already satisfied: torch>=1.13.0 in /usr/local/lib/python3.12/dist-packages (from stanza) (2.10.0+cpu)\n", "Requirement already satisfied: tqdm in /usr/local/lib/python3.12/dist-packages (from stanza) (4.67.3)\n", "Collecting udtools>=0.2.4 (from stanza)\n", " Downloading udtools-0.2.7-py3-none-any.whl.metadata (13 kB)\n", "Requirement already satisfied: filelock in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.0->stanza) (3.29.0)\n", "Requirement already satisfied: typing-extensions>=4.10.0 in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.0->stanza) (4.15.0)\n", "Requirement already satisfied: setuptools in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.0->stanza) (75.2.0)\n", "Requirement already satisfied: sympy>=1.13.3 in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.0->stanza) (1.14.0)\n", "Requirement already satisfied: jinja2 in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.0->stanza) (3.1.6)\n", "Requirement already satisfied: fsspec>=0.8.5 in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.0->stanza) (2025.3.0)\n", "Collecting udapi>=0.5.0 (from udtools>=0.2.4->stanza)\n", " Downloading udapi-0.5.2-py3-none-any.whl.metadata (2.0 kB)\n", "Requirement already satisfied: regex>=2020.09.27 in /usr/local/lib/python3.12/dist-packages (from udtools>=0.2.4->stanza) (2025.11.3)\n", "Requirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests->stanza) (3.4.7)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests->stanza) (3.13)\n", "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests->stanza) (2.5.0)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests->stanza) (2026.4.22)\n", "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from sympy>=1.13.3->torch>=1.13.0->stanza) (1.3.0)\n", "Collecting colorama (from udapi>=0.5.0->udtools>=0.2.4->stanza)\n", " Downloading colorama-0.4.6-py2.py3-none-any.whl.metadata (17 kB)\n", "Requirement already satisfied: termcolor in /usr/local/lib/python3.12/dist-packages (from udapi>=0.5.0->udtools>=0.2.4->stanza) (3.3.0)\n", "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.12/dist-packages (from jinja2->torch>=1.13.0->stanza) (3.0.3)\n", "Downloading stanza-1.12.0-py3-none-any.whl (1.8 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.8/1.8 MB\u001b[0m \u001b[31m32.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading udtools-0.2.7-py3-none-any.whl (773 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m773.7/773.7 kB\u001b[0m \u001b[31m38.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading emoji-2.15.0-py3-none-any.whl (608 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m608.4/608.4 kB\u001b[0m \u001b[31m32.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading udapi-0.5.2-py3-none-any.whl (418 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m418.7/418.7 kB\u001b[0m \u001b[31m25.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading colorama-0.4.6-py2.py3-none-any.whl (25 kB)\n", "Installing collected packages: emoji, colorama, udapi, udtools, stanza\n", "Successfully installed colorama-0.4.6 emoji-2.15.0 stanza-1.12.0 udapi-0.5.2 udtools-0.2.7\n" ] } ] }, { "cell_type": "code", "source": [ "import stanza\n", "\n", "stanza.download('en')\n", "\n", "nlp = stanza.Pipeline('en')\n", "\n", "doc = nlp(\"Natural Language Processing is powerful.\")\n", "\n", "for sentence in doc.sentences:\n", " for word in sentence.words:\n", " print(word.text, word.upos)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 737, "referenced_widgets": [ "a2e4e425b0bb46998b2217c709868715", "5a99e443c2d94bb5b4bd5d54df31e016", "cc26a4b380624f3faefe4b64da40179d", "1f2554e855314b3c851e3ed69cc0239e", "c39241d7b86f4c80ade8c77a52d0a65e", "7480fe53b29e4116a6dc1dea890f17f5", "a5dd56d18157419da45ad543c9ad632c", "603aeb6d85664679b1234e4b1f926cc6", "bdf917e0d0f044dea02b13eb113ae706", "d9484af31d6c4a89b1b661f880051b31", "d129a841bd0b4525afd37816b058611d", "302c4b8434b44ae683c85179e1116605", "e66fbdb6943349aab2e904f397f8fdf8", "0fb00d473dbf49e5aa694c3cf2863cc7", "cd55b5c0c5b34646b4efc8d0a7e5d647", "301ed4f4acff4033be3926625a50967d", "8170acc142d8416c9c5a864c294fdd8f", "5004f01629284671898849c697c14589", "58bcc346996f427d96f664156a9c29e1", "8179634b95404d44ba01887aa8c9fdd6", "087e4264ebe34c2fa4ba8c245ca83fbe", "d56a291b948c4f0b92ee38eb6d3749f3", "4ac57be03fd24e488019495bb98e9d14", "09a8483aa6e1436095cbe2fa4c2d45b9", "8b381df3167748f08329afafee5e91b1", "8a167cf8e34f4038b0e0d5a8a1dcbe07", "c8ddccf7da5b49ad94b0b783ffe59f8d", "b81230c212214ba581803577437d1e1d", "1e9d15e2d1dd435d9bde9f36f7f07736", "68eebe3b39164a1bbfc4a33cb151efdd", "d85af3826fa44b538f09d8e866bc3324", "b338e0c52c04433684390b8a14104420", "fdf2702a60064fd2ad428801bae3d05d" ] }, "id": "l8EjrY2GeZeK", "outputId": "f5227c67-6c21-4a71-a6b6-61d470008719" }, "execution_count": null, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "Downloading https://raw.githubusercontent.com/stanfordnlp/stanza-resources/main/resources_1.12.0.json: 0%| …" ], "application/vnd.jupyter.widget-view+json": { "version_major": 2, "version_minor": 0, "model_id": "a2e4e425b0bb46998b2217c709868715" } }, "metadata": {} }, { "output_type": "stream", "name": "stderr", "text": [ "INFO:stanza:Downloaded file to /root/.cache/stanza/1.12.0/resources/resources.json\n", "INFO:stanza:Downloading default packages for language: en (English) ...\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "Downloading https://huggingface.co/stanfordnlp/stanza-en/resolve/v1.12.0/models/default.zip: 0%| | …" ], "application/vnd.jupyter.widget-view+json": { "version_major": 2, "version_minor": 0, "model_id": "302c4b8434b44ae683c85179e1116605" } }, "metadata": {} }, { "output_type": "stream", "name": "stderr", "text": [ "INFO:stanza:Downloaded file to /root/.cache/stanza/1.12.0/resources/en/default.zip\n", "INFO:stanza:Finished downloading models and saved to /root/.cache/stanza/1.12.0/resources\n", "INFO:stanza:Checking for updates to resources.json in case models have been updated. Note: this behavior can be turned off with download_method=None or download_method=DownloadMethod.REUSE_RESOURCES\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "Downloading https://raw.githubusercontent.com/stanfordnlp/stanza-resources/main/resources_1.12.0.json: 0%| …" ], "application/vnd.jupyter.widget-view+json": { "version_major": 2, "version_minor": 0, "model_id": "4ac57be03fd24e488019495bb98e9d14" } }, "metadata": {} }, { "output_type": "stream", "name": "stderr", "text": [ "INFO:stanza:Downloaded file to /root/.cache/stanza/1.12.0/resources/resources.json\n", "INFO:stanza:Loading these models for language: en (English):\n", "============================================\n", "| Processor | Package |\n", "--------------------------------------------\n", "| tokenize | combined |\n", "| mwt | combined |\n", "| pos | combined_charlm |\n", "| lemma | combined_nocharlm |\n", "| constituency | ptb3-revised_charlm |\n", "| depparse | combined_charlm |\n", "| sentiment | sstplus_charlm |\n", "| ner | ontonotes-ww-multi_charlm |\n", "============================================\n", "\n", "INFO:stanza:Using device: cpu\n", "INFO:stanza:Loading: tokenize\n", "INFO:stanza:Loading: mwt\n", "INFO:stanza:Loading: pos\n", "INFO:stanza:Loading: lemma\n", "INFO:stanza:Loading: constituency\n", "INFO:stanza:Loading: depparse\n", "INFO:stanza:Loading: sentiment\n", "INFO:stanza:Loading: ner\n", "INFO:stanza:Done loading processors!\n" ] }, { "output_type": "stream", "name": "stdout", "text": [ "Natural ADJ\n", "Language NOUN\n", "Processing NOUN\n", "is AUX\n", "powerful ADJ\n", ". PUNCT\n" ] } ] }, { "cell_type": "markdown", "source": [ "##**PyNLPL**" ], "metadata": { "id": "HSUJYN9UybLR" } }, { "cell_type": "code", "source": [ "!pip install pynlpl" ], "metadata": { "collapsed": true, "colab": { "base_uri": "https://localhost:8080/" }, "id": "qghKMNT9x9nJ", "outputId": "c4431a19-c3c2-4a3d-8d5f-e71ccbf67491" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Collecting pynlpl\n", " Downloading PyNLPl-1.2.9.tar.gz (277 kB)\n", "\u001b[?25l \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/277.9 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K \u001b[91m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[91m╸\u001b[0m \u001b[32m276.5/277.9 kB\u001b[0m \u001b[31m11.8 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m277.9/277.9 kB\u001b[0m \u001b[31m6.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", "Requirement already satisfied: lxml>=2.2 in /usr/local/lib/python3.12/dist-packages (from pynlpl) (6.1.0)\n", "Requirement already satisfied: httplib2>=0.6 in /usr/local/lib/python3.12/dist-packages (from pynlpl) (0.31.2)\n", "Collecting rdflib (from pynlpl)\n", " Downloading rdflib-7.6.0-py3-none-any.whl.metadata (12 kB)\n", "Requirement already satisfied: pyparsing<4,>=3.1 in /usr/local/lib/python3.12/dist-packages (from httplib2>=0.6->pynlpl) (3.3.2)\n", "Downloading rdflib-7.6.0-py3-none-any.whl (615 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m615.4/615.4 kB\u001b[0m \u001b[31m31.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hBuilding wheels for collected packages: pynlpl\n", " Building wheel for pynlpl (setup.py) ... \u001b[?25l\u001b[?25hdone\n", " Created wheel for pynlpl: filename=PyNLPl-1.2.9-py3-none-any.whl size=328340 sha256=f87a33b3e7735335c0f2693576b06e29921afaae455692ab392a68224c3834d7\n", " Stored in directory: /root/.cache/pip/wheels/7a/ac/17/a16bf1864592379291c0aa21a491207a16e87873a794a8a136\n", "Successfully built pynlpl\n", "Installing collected packages: rdflib, pynlpl\n", "Successfully installed pynlpl-1.2.9 rdflib-7.6.0\n" ] } ] }, { "cell_type": "code", "source": [ "from pynlpl.textprocessors import tokenize\n", "\n", "text = \"Natural Language Processing is interesting.\"\n", "\n", "tokens = list(tokenize(text))\n", "\n", "print(tokens)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "lv1QzK-Ywsj_", "outputId": "bab98bde-2eab-47e3-beb5-47d09f80c8ba" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "['Natural', 'Language', 'Processing', 'is', 'interesting', '.']\n" ] } ] }, { "cell_type": "markdown", "source": [ "##**Hugging Face transformer**" ], "metadata": { "id": "crRe0dxEyi76" } }, { "cell_type": "code", "source": [ "from transformers import pipeline\n", "\n", "generator = pipeline(\"text-generation\")\n", "\n", "result = generator(\n", " \"Artificial Intelligence is\",\n", " max_length=20\n", ")\n", "\n", "print(result)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 657, "referenced_widgets": [ "e67e1a68554a449788670206a6131995", "412953d259cc4d4dab07dcc029f077ba", "4f9d38bd58ec465fa85a6ffd1a98ccb4", "8503c97f61ec4cfeb319ce91ab775604", "12efd716a5444d7f8f0ad5adcf379869", "2f0f9249e2914e94a8349838293af13a", "adb5340729354cf6a7ee85b0dc5b1741", "aae88b0bff3d4a6c9f85cacee3ea32a4", "f50eb13981ac4f9c91a4c735171b3cd5", "2a68d8bb04cc42288fd8771e2a3e6c63", "46d301645e724b989cc0f2cab057b51e", "867bd34ec2a244699d921396ccd41c45", "d3db2a7e95704a9bb63cfd6b53345417", "3efe319801b94b5f85ccc4485ff33eb0", "86a3fc73cb7049f3872e004a4cbe34eb", "38cc6aeb9c264376a7677804e638ef0e", "a55a3c7f0f734e9cbb231b4627ecb051", "6702e1ef46994164808296f8b1d3ef54", "cddb35edcd0c4ed6a33488a7af89acee", "5cba8f200b794ce7835978ccf212c21b", "b79004450c4045d5bfab80f04ae6efa3", "2687a0d8cba14b3bb456bd92bf471aa2", "9e90fb34cf034b3b954a1562fa6d318c", "931324c3ba814c35a4bcdcb188a60851", "614f1cb0b77b4f84bc64218a6384f592", "71c9518e37ab4c06bb434e91023e38f8", "66aa0550932c4a38a6bc548bcaf77761", "f65e007e5fe54f9b97e1628fbedb55f5", "876d3eafd002467f82f9d091058ae0a0", "7463d336c8cb468bb9dbcaf8994150c1", "c4642347a5a442ebba609363c6d40087", "bc7f3a490d394a1ca139f11a4b7499fe", "717210576269425f9d440bbd65b3d9c4", "461de7b2813c41e99b3c75df6e08f9d2", "8d3559ba307f418ca31e1fab0dc375fb", "803277b13e3d4c7faeb9dc9eabec19f3", "99825624e7854b2397897f58beb27f46", "f2fc29e957e64cc1aadc920a34c9ef16", "6f0eb2d6318642a1bee2bb19bb311d6c", "56f92edca1a949c7b8642f5261b49606", "3c724f88bf76402f90fcd7700b842076", "1f938382ba5947229d8aff0b8c761e76", "0393e5f2538e48c884d4956a3f794466", "34457c79fdf446ad80b1528bfc0121a7", "cdfa8da7c61c4f5d90669527dc70a9ec", "6f5fadd3214348598a55ab98eb3a646c", "4703cfae59914a72bd611d7f136a2d89", "ad6b5eafeed94f9aa0cea14a8024496c", "c141c9defb224413a23a0c84d654148c", "98370eb0e5604b7e85fe78513d94b563", "40684bdeab80474f80e925ef7ce1aa79", "e2814cec6023419785982d0de99926d8", "2d8804ed08bf451f95c1bc1d6e18788d", "bd9796366d554e5ba6ea17b516a8fd4d", "916126700c544f2a9e45fe5cdf3f1f09", "c41480f5234f4d3a99ced15985df0ab6", "50f648f766354ccbb1a784301828efa6", "162f618178ff4077893800b2660bd0c9", "5ffb99cdafa54bc79fb0136931b42d65", "7e8bf24baba7495dab6248cdceb0800e", "573333d43b0e4dd8af5b84de26e78daf", "2fcf4de90b5844c4bc0ad1942a3a46db", "a245a953c0b24c909cb28e1fba5536e3", "7ba77611d63c400db1b2ba4f421d3023", "67087dd536dc447592d440a7c46eb923", "2bbb3a79ef9b4e96adb82609519eaef3", "6c94a5c9986c4df69a0ee4f04870ce84", "d081b39bf3c642e0b2078c84d146d012", "8b5bbf96e25542dcbb59e4562a86dc84", "94194591ce60466b8426a8b54f6b26e1", "be57b859dd604189b778e07bfe719036", "2d1d60a49bdb420e8ceb05e528a103b4", "d9ca1d21fe924f7c923d06b3c8fcb148", "f61ddc9b376c4caa8fedbe6c1fbb7619", "1e8c6345bcd547158f340bc972075068", "485369b459c5479d93f9f7c474a62241", "7c05b6397c5245598009e3c0c570d894", "da714638921c4ebd81358734c9548a8c", "fb56be9ad309449e8ccae9c948826aef", "36395a5ff64c4151aa0d3d428ca540a3", "fbd05bc8225a489c9ba3163e10f80d9f", "4ae36d16f1744ac9a2a2442704163c2f", "673a95d4b0274b859d25c540aead7a57", "e518b690f7f74b739cf563cbd0ae53e9", "4f0eaa172c384160807ee5e715c2b287", "1db87e4363744b88b611804f9195d196", "b917740795d14855b4d6b713e25546ae", "02a76e30345d4ce9b23c6b84d5432adf" ] }, "id": "DdkEEW-7wsmX", "outputId": "1428caf0-66e1-4f8e-b06d-862b7e8cfe1b" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "No model was supplied, defaulted to openai-community/gpt2 and revision 607a30d.\n", "Using a pipeline without specifying a model name and revision in production is not recommended.\n", "/usr/local/lib/python3.12/dist-packages/huggingface_hub/utils/_auth.py:93: UserWarning: \n", "The secret `HF_TOKEN` does not exist in your Colab secrets.\n", "To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.\n", "You will be able to reuse this secret in all of your notebooks.\n", "Please note that authentication is recommended but still optional to access public models or datasets.\n", " warnings.warn(\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "config.json: 0%| | 0.00/665 [00:00=1.20.27 (from flair)\n", " Downloading boto3-1.43.9-py3-none-any.whl.metadata (6.6 kB)\n", "Collecting conllu<5.0.0,>=4.0 (from flair)\n", " Downloading conllu-4.5.3-py2.py3-none-any.whl.metadata (19 kB)\n", "Collecting deprecated>=1.2.13 (from flair)\n", " Downloading deprecated-1.3.1-py2.py3-none-any.whl.metadata (5.9 kB)\n", "Collecting ftfy>=6.1.0 (from flair)\n", " Using cached ftfy-6.3.1-py3-none-any.whl.metadata (7.3 kB)\n", "Requirement already satisfied: gdown>=4.4.0 in /usr/local/lib/python3.12/dist-packages (from flair) (5.2.2)\n", "Requirement already satisfied: huggingface-hub>=0.10.0 in /usr/local/lib/python3.12/dist-packages (from flair) (1.11.0)\n", "Collecting langdetect>=1.0.9 (from flair)\n", " Downloading langdetect-1.0.9.tar.gz (981 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m981.5/981.5 kB\u001b[0m \u001b[31m19.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", "Requirement already satisfied: lxml>=4.8.0 in /usr/local/lib/python3.12/dist-packages (from flair) (6.1.0)\n", "Requirement already satisfied: matplotlib>=2.2.3 in /usr/local/lib/python3.12/dist-packages (from flair) (3.10.0)\n", "Requirement already satisfied: more-itertools>=8.13.0 in /usr/local/lib/python3.12/dist-packages (from flair) (10.8.0)\n", "Collecting mpld3>=0.3 (from flair)\n", " Downloading mpld3-0.5.12-py3-none-any.whl.metadata (5.3 kB)\n", "Collecting pptree>=3.1 (from flair)\n", " Downloading pptree-3.1.tar.gz (3.0 kB)\n", " Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.12/dist-packages (from flair) (2.9.0.post0)\n", "Collecting pytorch-revgrad>=0.2.0 (from flair)\n", " Downloading pytorch_revgrad-0.2.0-py3-none-any.whl.metadata (1.7 kB)\n", "Requirement already satisfied: regex>=2022.1.18 in /usr/local/lib/python3.12/dist-packages (from flair) (2025.11.3)\n", "Requirement already satisfied: scikit-learn>=1.0.2 in /usr/local/lib/python3.12/dist-packages (from flair) (1.6.1)\n", "Collecting segtok>=1.5.11 (from flair)\n", " Downloading segtok-1.5.11-py3-none-any.whl.metadata (9.0 kB)\n", "Collecting sqlitedict>=2.0.0 (from flair)\n", " Downloading sqlitedict-2.1.0.tar.gz (21 kB)\n", " Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", "Requirement already satisfied: tabulate>=0.8.10 in /usr/local/lib/python3.12/dist-packages (from flair) (0.9.0)\n", "Requirement already satisfied: torch>=1.13.1 in /usr/local/lib/python3.12/dist-packages (from flair) (2.10.0+cpu)\n", "Requirement already satisfied: tqdm>=4.63.0 in /usr/local/lib/python3.12/dist-packages (from flair) (4.67.3)\n", "Collecting transformer-smaller-training-vocab>=0.2.3 (from flair)\n", " Downloading transformer_smaller_training_vocab-0.4.2-py3-none-any.whl.metadata (7.9 kB)\n", "Collecting transformers<5.0.0,>=4.25.0 (from transformers[sentencepiece]<5.0.0,>=4.25.0->flair)\n", " Downloading transformers-4.57.6-py3-none-any.whl.metadata (43 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m44.0/44.0 kB\u001b[0m \u001b[31m3.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting wikipedia-api>=0.5.7 (from flair)\n", " Downloading wikipedia_api-0.14.1-py3-none-any.whl.metadata (43 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m43.6/43.6 kB\u001b[0m \u001b[31m2.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting bioc<3.0.0,>=2.0.0 (from flair)\n", " Downloading bioc-2.1-py3-none-any.whl.metadata (4.6 kB)\n", "Collecting jsonlines>=1.2.0 (from bioc<3.0.0,>=2.0.0->flair)\n", " Downloading jsonlines-4.0.0-py3-none-any.whl.metadata (1.6 kB)\n", "Collecting intervaltree (from bioc<3.0.0,>=2.0.0->flair)\n", " Downloading intervaltree-3.2.1-py2.py3-none-any.whl.metadata (12 kB)\n", "Collecting docopt (from bioc<3.0.0,>=2.0.0->flair)\n", " Downloading docopt-0.6.2.tar.gz (25 kB)\n", " Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", "Collecting botocore<1.44.0,>=1.43.9 (from boto3>=1.20.27->flair)\n", " Downloading botocore-1.43.9-py3-none-any.whl.metadata (5.6 kB)\n", "Collecting jmespath<2.0.0,>=0.7.1 (from boto3>=1.20.27->flair)\n", " Downloading jmespath-1.1.0-py3-none-any.whl.metadata (7.6 kB)\n", "Collecting s3transfer<0.18.0,>=0.17.0 (from boto3>=1.20.27->flair)\n", " Downloading s3transfer-0.17.0-py3-none-any.whl.metadata (1.7 kB)\n", "Requirement already satisfied: wrapt<3,>=1.10 in /usr/local/lib/python3.12/dist-packages (from deprecated>=1.2.13->flair) (2.1.2)\n", "Requirement already satisfied: wcwidth in /usr/local/lib/python3.12/dist-packages (from ftfy>=6.1.0->flair) (0.6.0)\n", "Requirement already satisfied: beautifulsoup4 in /usr/local/lib/python3.12/dist-packages (from gdown>=4.4.0->flair) (4.13.5)\n", "Requirement already satisfied: filelock in /usr/local/lib/python3.12/dist-packages (from gdown>=4.4.0->flair) (3.29.0)\n", "Requirement already satisfied: requests[socks] in /usr/local/lib/python3.12/dist-packages (from gdown>=4.4.0->flair) (2.32.4)\n", "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub>=0.10.0->flair) (2025.3.0)\n", "Requirement already satisfied: hf-xet<2.0.0,>=1.4.3 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub>=0.10.0->flair) (1.4.3)\n", "Requirement already satisfied: httpx<1,>=0.23.0 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub>=0.10.0->flair) (0.28.1)\n", "Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub>=0.10.0->flair) (26.1)\n", "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub>=0.10.0->flair) (6.0.3)\n", "Requirement already satisfied: typer in /usr/local/lib/python3.12/dist-packages (from huggingface-hub>=0.10.0->flair) (0.24.2)\n", "Requirement already satisfied: typing-extensions>=4.1.0 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub>=0.10.0->flair) (4.15.0)\n", "Requirement already satisfied: six in /usr/local/lib/python3.12/dist-packages (from langdetect>=1.0.9->flair) (1.17.0)\n", "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=2.2.3->flair) (1.3.3)\n", "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=2.2.3->flair) (0.12.1)\n", "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=2.2.3->flair) (4.62.1)\n", "Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=2.2.3->flair) (1.5.0)\n", "Requirement already satisfied: numpy>=1.23 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=2.2.3->flair) (2.0.2)\n", "Requirement already satisfied: pillow>=8 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=2.2.3->flair) (11.3.0)\n", "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=2.2.3->flair) (3.3.2)\n", "Requirement already satisfied: jinja2 in /usr/local/lib/python3.12/dist-packages (from mpld3>=0.3->flair) (3.1.6)\n", "Requirement already satisfied: scipy>=1.6.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn>=1.0.2->flair) (1.16.3)\n", "Requirement already satisfied: joblib>=1.2.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn>=1.0.2->flair) (1.5.3)\n", "Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn>=1.0.2->flair) (3.6.0)\n", "Requirement already satisfied: setuptools in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.1->flair) (75.2.0)\n", "Requirement already satisfied: sympy>=1.13.3 in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.1->flair) (1.14.0)\n", "Requirement already satisfied: networkx>=2.5.1 in /usr/local/lib/python3.12/dist-packages (from torch>=1.13.1->flair) (3.6.1)\n", "Collecting huggingface-hub>=0.10.0 (from flair)\n", " Downloading huggingface_hub-0.36.2-py3-none-any.whl.metadata (15 kB)\n", "Requirement already satisfied: tokenizers<=0.23.0,>=0.22.0 in /usr/local/lib/python3.12/dist-packages (from transformers<5.0.0,>=4.25.0->transformers[sentencepiece]<5.0.0,>=4.25.0->flair) (0.22.2)\n", "Requirement already satisfied: safetensors>=0.4.3 in /usr/local/lib/python3.12/dist-packages (from transformers<5.0.0,>=4.25.0->transformers[sentencepiece]<5.0.0,>=4.25.0->flair) (0.7.0)\n", "Requirement already satisfied: sentencepiece!=0.1.92,>=0.1.91 in /usr/local/lib/python3.12/dist-packages (from transformers[sentencepiece]<5.0.0,>=4.25.0->flair) (0.2.1)\n", "Requirement already satisfied: protobuf in /usr/local/lib/python3.12/dist-packages (from transformers[sentencepiece]<5.0.0,>=4.25.0->flair) (5.29.6)\n", "Collecting click==8.3.2 (from wikipedia-api>=0.5.7->flair)\n", " Downloading click-8.3.2-py3-none-any.whl.metadata (2.6 kB)\n", "Requirement already satisfied: tenacity==9.1.4 in /usr/local/lib/python3.12/dist-packages (from wikipedia-api>=0.5.7->flair) (9.1.4)\n", "Requirement already satisfied: anyio in /usr/local/lib/python3.12/dist-packages (from httpx<1,>=0.23.0->huggingface-hub>=0.10.0->flair) (4.13.0)\n", "Requirement already satisfied: certifi in /usr/local/lib/python3.12/dist-packages (from httpx<1,>=0.23.0->huggingface-hub>=0.10.0->flair) (2026.4.22)\n", "Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.12/dist-packages (from httpx<1,>=0.23.0->huggingface-hub>=0.10.0->flair) (1.0.9)\n", "Requirement already satisfied: idna in /usr/local/lib/python3.12/dist-packages (from httpx<1,>=0.23.0->huggingface-hub>=0.10.0->flair) (3.13)\n", "Requirement already satisfied: h11>=0.16 in /usr/local/lib/python3.12/dist-packages (from httpcore==1.*->httpx<1,>=0.23.0->huggingface-hub>=0.10.0->flair) (0.16.0)\n", "Requirement already satisfied: urllib3!=2.2.0,<3,>=1.25.4 in /usr/local/lib/python3.12/dist-packages (from botocore<1.44.0,>=1.43.9->boto3>=1.20.27->flair) (2.5.0)\n", "Requirement already satisfied: attrs>=19.2.0 in /usr/local/lib/python3.12/dist-packages (from jsonlines>=1.2.0->bioc<3.0.0,>=2.0.0->flair) (26.1.0)\n", "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from sympy>=1.13.3->torch>=1.13.1->flair) (1.3.0)\n", "Requirement already satisfied: accelerate>=0.26.0 in /usr/local/lib/python3.12/dist-packages (from transformers[sentencepiece,torch]<5.0,>=4.1->transformer-smaller-training-vocab>=0.2.3->flair) (1.13.0)\n", "Requirement already satisfied: soupsieve>1.2 in /usr/local/lib/python3.12/dist-packages (from beautifulsoup4->gdown>=4.4.0->flair) (2.8.3)\n", "Collecting sortedcontainers (from intervaltree->bioc<3.0.0,>=2.0.0->flair)\n", " Downloading sortedcontainers-2.4.0-py2.py3-none-any.whl.metadata (10 kB)\n", "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.12/dist-packages (from jinja2->mpld3>=0.3->flair) (3.0.3)\n", "Requirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests[socks]->gdown>=4.4.0->flair) (3.4.7)\n", "Requirement already satisfied: PySocks!=1.5.7,>=1.5.6 in /usr/local/lib/python3.12/dist-packages (from requests[socks]->gdown>=4.4.0->flair) (1.7.1)\n", "Requirement already satisfied: psutil in /usr/local/lib/python3.12/dist-packages (from accelerate>=0.26.0->transformers[sentencepiece,torch]<5.0,>=4.1->transformer-smaller-training-vocab>=0.2.3->flair) (5.9.5)\n", "Requirement already satisfied: shellingham>=1.3.0 in /usr/local/lib/python3.12/dist-packages (from typer->huggingface-hub>=0.10.0->flair) (1.5.4)\n", "Requirement already satisfied: rich>=12.3.0 in /usr/local/lib/python3.12/dist-packages (from typer->huggingface-hub>=0.10.0->flair) (13.9.4)\n", "Requirement already satisfied: annotated-doc>=0.0.2 in /usr/local/lib/python3.12/dist-packages (from typer->huggingface-hub>=0.10.0->flair) (0.0.4)\n", "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.12/dist-packages (from rich>=12.3.0->typer->huggingface-hub>=0.10.0->flair) (4.0.0)\n", "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.12/dist-packages (from rich>=12.3.0->typer->huggingface-hub>=0.10.0->flair) (2.20.0)\n", "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.12/dist-packages (from markdown-it-py>=2.2.0->rich>=12.3.0->typer->huggingface-hub>=0.10.0->flair) (0.1.2)\n", "Downloading flair-0.15.1-py3-none-any.whl (1.2 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m48.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading bioc-2.1-py3-none-any.whl (33 kB)\n", "Downloading boto3-1.43.9-py3-none-any.whl (140 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m140.5/140.5 kB\u001b[0m \u001b[31m10.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading conllu-4.5.3-py2.py3-none-any.whl (16 kB)\n", "Downloading deprecated-1.3.1-py2.py3-none-any.whl (11 kB)\n", "Downloading ftfy-6.3.1-py3-none-any.whl (44 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m44.8/44.8 kB\u001b[0m \u001b[31m3.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading mpld3-0.5.12-py3-none-any.whl (203 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m203.1/203.1 kB\u001b[0m \u001b[31m14.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading pytorch_revgrad-0.2.0-py3-none-any.whl (4.6 kB)\n", "Downloading segtok-1.5.11-py3-none-any.whl (24 kB)\n", "Downloading transformer_smaller_training_vocab-0.4.2-py3-none-any.whl (14 kB)\n", "Downloading transformers-4.57.6-py3-none-any.whl (12.0 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m12.0/12.0 MB\u001b[0m \u001b[31m97.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading huggingface_hub-0.36.2-py3-none-any.whl (566 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m566.4/566.4 kB\u001b[0m \u001b[31m30.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading wikipedia_api-0.14.1-py3-none-any.whl (129 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m129.1/129.1 kB\u001b[0m \u001b[31m8.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading click-8.3.2-py3-none-any.whl (108 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m108.4/108.4 kB\u001b[0m \u001b[31m7.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading botocore-1.43.9-py3-none-any.whl (15.0 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m15.0/15.0 MB\u001b[0m \u001b[31m76.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading jmespath-1.1.0-py3-none-any.whl (20 kB)\n", "Downloading jsonlines-4.0.0-py3-none-any.whl (8.7 kB)\n", "Downloading s3transfer-0.17.0-py3-none-any.whl (86 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m86.8/86.8 kB\u001b[0m \u001b[31m5.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading intervaltree-3.2.1-py2.py3-none-any.whl (25 kB)\n", "Downloading sortedcontainers-2.4.0-py2.py3-none-any.whl (29 kB)\n", "Building wheels for collected packages: langdetect, pptree, sqlitedict, docopt\n", " Building wheel for langdetect (setup.py) ... \u001b[?25l\u001b[?25hdone\n", " Created wheel for langdetect: filename=langdetect-1.0.9-py3-none-any.whl size=993223 sha256=7ce37d7d500c3b9998f455cf59a3bb7032f772a7118c83292737d595ca1631e8\n", " Stored in directory: /root/.cache/pip/wheels/c1/67/88/e844b5b022812e15a52e4eaa38a1e709e99f06f6639d7e3ba7\n", " Building wheel for pptree (setup.py) ... \u001b[?25l\u001b[?25hdone\n", " Created wheel for pptree: filename=pptree-3.1-py3-none-any.whl size=4609 sha256=a421975306e0e5717d27fdfe09380f67a4b4994071963ed96aa765f63d36052a\n", " Stored in directory: /root/.cache/pip/wheels/b0/2d/de/37058114a8f07cfec75747cb46b864bc5c71b0e9e0e4cd0acd\n", " Building wheel for sqlitedict (setup.py) ... \u001b[?25l\u001b[?25hdone\n", " Created wheel for sqlitedict: filename=sqlitedict-2.1.0-py3-none-any.whl size=16862 sha256=150331e76273a45150259a264a80184aab53c792e4a7af7120e7c904bcf02ba5\n", " Stored in directory: /root/.cache/pip/wheels/7a/6f/21/fc016aef45ffcabe27129a2252f061387cbf278d2086225a64\n", " Building wheel for docopt (setup.py) ... \u001b[?25l\u001b[?25hdone\n", " Created wheel for docopt: filename=docopt-0.6.2-py2.py3-none-any.whl size=13706 sha256=3655d293c2112682e2353623d0fe30e8338f675ee78959f7f3ba299735edf646\n", " Stored in directory: /root/.cache/pip/wheels/1a/bf/a1/4cee4f7678c68c5875ca89eaccf460593539805c3906722228\n", "Successfully built langdetect pptree sqlitedict docopt\n", "Installing collected packages: sqlitedict, sortedcontainers, pptree, docopt, segtok, langdetect, jsonlines, jmespath, intervaltree, ftfy, deprecated, conllu, click, huggingface-hub, botocore, bioc, wikipedia-api, s3transfer, pytorch-revgrad, mpld3, transformers, boto3, transformer-smaller-training-vocab, flair\n", " Attempting uninstall: click\n", " Found existing installation: click 8.3.3\n", " Uninstalling click-8.3.3:\n", " Successfully uninstalled click-8.3.3\n", " Attempting uninstall: huggingface-hub\n", " Found existing installation: huggingface_hub 1.11.0\n", " Uninstalling huggingface_hub-1.11.0:\n", " Successfully uninstalled huggingface_hub-1.11.0\n", " Attempting uninstall: transformers\n", " Found existing installation: transformers 5.0.0\n", " Uninstalling transformers-5.0.0:\n", " Successfully uninstalled transformers-5.0.0\n", "Successfully installed bioc-2.1 boto3-1.43.9 botocore-1.43.9 click-8.3.2 conllu-4.5.3 deprecated-1.3.1 docopt-0.6.2 flair-0.15.1 ftfy-6.3.1 huggingface-hub-0.36.2 intervaltree-3.2.1 jmespath-1.1.0 jsonlines-4.0.0 langdetect-1.0.9 mpld3-0.5.12 pptree-3.1 pytorch-revgrad-0.2.0 s3transfer-0.17.0 segtok-1.5.11 sortedcontainers-2.4.0 sqlitedict-2.1.0 transformer-smaller-training-vocab-0.4.2 transformers-4.57.6 wikipedia-api-0.14.1\n" ] }, { "output_type": "display_data", "data": { "application/vnd.colab-display-data+json": { "pip_warning": { "packages": [ "click", "transformers" ] }, "id": "71f963a6665e4c57ab8f5f3a91dd019b" } }, "metadata": {} } ] }, { "cell_type": "code", "source": [ "from flair.data import Sentence\n", "from flair.models import SequenceTagger\n", "\n", "tagger = SequenceTagger.load(\"ner\")\n", "\n", "sentence = Sentence(\"Apple is opening a new office in London.\")\n", "\n", "tagger.predict(sentence)\n", "\n", "print(sentence.get_spans('ner'))" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 205, "referenced_widgets": [ "455c1f40f89046269f1dea71badb8e8d", "5728f6a9104048b292194d98d4155fa2", "8afc623afea042c3a01f96115a5ee2ff", "226dc758713d4df7b4dfc5b7419ca332", "7910fe4089544a168e86fcc446fa39b3", "e942fc441ba64496933a2930f2f19f25", "a4f3b70cbaee43869ae62f3cf23f4e87", "34700d9e05514fb8a7e80d5527331f12", "81cfea069dfd495bbeb34890c1c08fff", "7fe4cb82aa524c76a5827877c58e3581", "2fe509a615104032ba39330f4057ec20" ] }, "id": "8XsC0UEhwssf", "outputId": "c5eba9d5-c4f0-4ef8-c195-9debdc791f3f" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "WARNING:torchao.kernel.intmm:Warning: Detected no triton, on systems without Triton certain kernels will not work\n", "/usr/local/lib/python3.12/dist-packages/huggingface_hub/utils/_auth.py:94: UserWarning: \n", "The secret `HF_TOKEN` does not exist in your Colab secrets.\n", "To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.\n", "You will be able to reuse this secret in all of your notebooks.\n", "Please note that authentication is recommended but still optional to access public models or datasets.\n", " warnings.warn(\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "pytorch_model.bin: 0%| | 0.00/419M [00:00, O, S-ORG, S-MISC, B-PER, E-PER, S-LOC, B-ORG, E-ORG, I-PER, S-PER, B-MISC, I-MISC, E-MISC, I-ORG, B-LOC, E-LOC, I-LOC, , \n", "[Span[0:1]: \"Apple\" → ORG (0.9991), Span[7:8]: \"London\" → LOC (0.9999)]\n" ] } ] }, { "cell_type": "markdown", "source": [ "##**FastText**" ], "metadata": { "id": "NKr6xiGGyOyM" } }, { "cell_type": "code", "source": [ "!pip install FastText" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "RKBZfg0ozUGb", "outputId": "265b36fb-ab9a-435d-c450-ce9365aaae45" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Collecting FastText\n", " Downloading fasttext-0.9.3.tar.gz (73 kB)\n", "\u001b[?25l \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/73.4 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m73.4/73.4 kB\u001b[0m \u001b[31m3.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25h Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n", " Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n", " Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", "Collecting pybind11>=2.2 (from FastText)\n", " Using cached pybind11-3.0.4-py3-none-any.whl.metadata (10 kB)\n", "Requirement already satisfied: setuptools>=0.7.0 in /usr/local/lib/python3.12/dist-packages (from FastText) (75.2.0)\n", "Requirement already satisfied: numpy in /usr/local/lib/python3.12/dist-packages (from FastText) (2.0.2)\n", "Using cached pybind11-3.0.4-py3-none-any.whl (314 kB)\n", "Building wheels for collected packages: FastText\n", " Building wheel for FastText (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", " Created wheel for FastText: filename=fasttext-0.9.3-cp312-cp312-linux_x86_64.whl size=4653907 sha256=5210b1325c08f86ab9272f83ce2adb47a4d5151d78fe5933c5de5cf9dd2575ae\n", " Stored in directory: /root/.cache/pip/wheels/20/27/95/a7baf1b435f1cbde017cabdf1e9688526d2b0e929255a359c6\n", "Successfully built FastText\n", "Installing collected packages: pybind11, FastText\n", "Successfully installed FastText-0.9.3 pybind11-3.0.4\n" ] } ] }, { "cell_type": "code", "source": [ "from gensim.models import FastText\n", "\n", "sentences = [\n", " [\"I\", \"love\", \"NLP\"],\n", " [\"FastText\", \"is\", \"efficient\"]\n", "]\n", "\n", "model = FastText(\n", " sentences,\n", " vector_size=10,\n", " min_count=1\n", ")\n", "\n", "print(model.wv['NLP'])" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "mqgS9p_JzUIr", "outputId": "a2851097-2c23-43a0-e063-396ce29e92a1" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "[-0.01986931 0.00510041 -0.00597237 0.03512271 0.00647743 -0.00812644\n", " 0.01452924 0.00778776 0.00406258 0.01224898]\n" ] } ] }, { "cell_type": "markdown", "source": [ "##**polyglot**" ], "metadata": { "id": "kK0tWu_LyKC8" } }, { "cell_type": "code", "source": [ "!pip install pyicu\n", "!pip install pycld2\n", "!pip install polyglot" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 461 }, "collapsed": true, "id": "Z6X7Bh8FeZjL", "outputId": "66ff078a-9c46-48ec-f7f9-98464c1d9390" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Collecting pyicu\n", " Downloading pyicu-2.16.2.tar.gz (268 kB)\n", "\u001b[?25l \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/268.2 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K \u001b[91m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[91m╸\u001b[0m \u001b[32m266.2/268.2 kB\u001b[0m \u001b[31m12.7 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m268.2/268.2 kB\u001b[0m \u001b[31m5.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25h Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n", " Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n", " Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", "Building wheels for collected packages: pyicu\n", " Building wheel for pyicu (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", " Created wheel for pyicu: filename=pyicu-2.16.2-cp312-cp312-linux_x86_64.whl size=2720235 sha256=a178f3e1767af94d258bf2be57d6356ecd96558322e6df02ada000447536a7cb\n", " Stored in directory: /root/.cache/pip/wheels/25/f3/cd/4923c874cedf8cdb8608035f48bb726fa040a98a66e2b13cea\n", "Successfully built pyicu\n", "Installing collected packages: pyicu\n", "Successfully installed pyicu-2.16.2\n" ] }, { "output_type": "display_data", "data": { "application/vnd.colab-display-data+json": { "pip_warning": { "packages": [ "icu" ] }, "id": "3d6915693c394a2fbf260741d79212d9" } }, "metadata": {} }, { "output_type": "stream", "name": "stdout", "text": [ "Collecting pycld2\n", " Downloading pycld2-0.42-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (7.5 kB)\n", "Downloading pycld2-0.42-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (9.9 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m9.9/9.9 MB\u001b[0m \u001b[31m78.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hInstalling collected packages: pycld2\n", "Successfully installed pycld2-0.42\n", "Requirement already satisfied: polyglot in /usr/local/lib/python3.12/dist-packages (16.7.4)\n" ] } ] }, { "cell_type": "code", "source": [ "from polyglot.detect import Detector\n", "\n", "text = \"Bonjour tout le monde\"\n", "\n", "detector = Detector(text)\n", "\n", "print(detector.language)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "-7mZUGW9zr0G", "outputId": "09d9c997-c37b-4d3c-938a-2a5cba4385d9" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "name: French code: fr confidence: 95.0 read bytes: 1070\n" ] } ] }, { "cell_type": "markdown", "source": [ "##**Keras-NLP**" ], "metadata": { "id": "AlKA6V97yCAW" } }, { "cell_type": "code", "source": [ "import keras_nlp\n", "\n", "preprocessor = keras_nlp.models.BertPreprocessor.from_preset(\n", " \"bert_tiny_en_uncased\"\n", ")\n", "\n", "classifier = keras_nlp.models.BertClassifier.from_preset(\n", " \"bert_tiny_en_uncased\",\n", " num_classes=2,\n", " preprocessor=preprocessor\n", ")\n", "\n", "prediction = classifier.predict(\n", " [\"KerasNLP makes NLP easy\"]\n", ")\n", "\n", "print(prediction)" ], "metadata": { "id": "gVLAUSnwzr6a", "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "476d09f0-265e-414d-8b2d-11bc6ac55d9a" }, "execution_count": 2, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 2s/step\n", "[[-0.10305174 -0.23531248]]\n" ] } ] }, { "cell_type": "markdown", "source": [ "##**Pytorch-NLP**" ], "metadata": { "id": "apYbg5fnx_N-" } }, { "cell_type": "code", "source": [ "!pip install pytorch-nlp" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "rQ1BTREfudI7", "outputId": "5cfa4cf4-3a9f-4891-a2f1-bcdb4aeb66b0" }, "execution_count": 6, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Collecting pytorch-nlp\n", " Downloading pytorch_nlp-0.5.0-py3-none-any.whl.metadata (9.0 kB)\n", "Requirement already satisfied: numpy in /usr/local/lib/python3.12/dist-packages (from pytorch-nlp) (2.0.2)\n", "Requirement already satisfied: tqdm in /usr/local/lib/python3.12/dist-packages (from pytorch-nlp) (4.67.3)\n", "Downloading pytorch_nlp-0.5.0-py3-none-any.whl (90 kB)\n", "\u001b[?25l \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/90.1 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m90.1/90.1 kB\u001b[0m \u001b[31m5.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hInstalling collected packages: pytorch-nlp\n", "Successfully installed pytorch-nlp-0.5.0\n" ] } ] }, { "cell_type": "code", "source": [ "from torchnlp.encoders.text import WhitespaceEncoder\n", "\n", "texts = [\"PyTorch NLP is powerful\"]\n", "\n", "encoder = WhitespaceEncoder(texts)\n", "\n", "encoded = encoder.encode(texts[0])\n", "\n", "print(encoded)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "t5Graw0Mt6Mj", "outputId": "de4c47b2-6675-42c3-be98-fb474454a675" }, "execution_count": 7, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "tensor([5, 6, 7, 8])\n" ] } ] }, { "cell_type": "code", "source": [], "metadata": { "id": "02muxvGUt3cn" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [], "metadata": { "id": "rYXpbszBt3fB" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [], "metadata": { "id": "KikZOHynzr9y" }, "execution_count": null, "outputs": [] } ] }