{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [], "gpuType": "T4" }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" }, "accelerator": "GPU", "widgets": { "application/vnd.jupyter.widget-state+json": { "e45db4f1c73b4aee997f477171a9f9ab": { "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_7973d006c6164a548823b8a560ab9cb5", "IPY_MODEL_c3013b5ba38241a594ae22207e56bfdf", "IPY_MODEL_458a54da8b37496eb76e60658a3f0dd2" ], "layout": "IPY_MODEL_1b616d26fb5347e5b46a881aece70ca4" } }, "7973d006c6164a548823b8a560ab9cb5": { "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_30058fe6d884408aaf183d896aeadbce", "placeholder": "​", "style": "IPY_MODEL_eba48ad1b56b43bcbeb4c6b02862d9ec", "value": "tokenizer_config.json: 100%" } }, "c3013b5ba38241a594ae22207e56bfdf": { "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_103b5789787f4ff8abf086fba2c1755a", "max": 50570, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_937f9f0710334d3c93a6ea56f65ce0ac", "value": 50570 } }, "458a54da8b37496eb76e60658a3f0dd2": { "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_9997c2b2d2a94505a1969bb1e1cc8fc8", "placeholder": "​", "style": "IPY_MODEL_0e5c424ab95e4ed6987a4d21aeac9f7a", "value": " 50.6k/50.6k [00:00<00:00, 1.77MB/s]" } }, "1b616d26fb5347e5b46a881aece70ca4": { "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 } }, "30058fe6d884408aaf183d896aeadbce": { "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 } }, "eba48ad1b56b43bcbeb4c6b02862d9ec": { "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": "" } }, "103b5789787f4ff8abf086fba2c1755a": { "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 } }, "937f9f0710334d3c93a6ea56f65ce0ac": { "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": "" } }, "9997c2b2d2a94505a1969bb1e1cc8fc8": { "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 } }, "0e5c424ab95e4ed6987a4d21aeac9f7a": { "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": "" } }, "e9830a7c444d4435960dda28ac469940": { "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_545e4cdea8334d938af708fc76108b44", "IPY_MODEL_08fced61286c4fb89f165f8c88d43bde", "IPY_MODEL_b9902e87b182484aafe4bc0633d70c9b" ], "layout": "IPY_MODEL_f956da2df1c34297b646656a68f531cc" } }, "545e4cdea8334d938af708fc76108b44": { "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_4bf6f18e6aef4a038ac3d1886f4d36ff", "placeholder": "​", "style": "IPY_MODEL_1d85969bfb404a3881262159e98c0667", "value": "tokenizer.json: 100%" } }, "08fced61286c4fb89f165f8c88d43bde": { "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_1ca38146638d48609e872be9bde06287", "max": 9085657, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_311d8f3f80f6424ebbf3624c5fde5f13", "value": 9085657 } }, "b9902e87b182484aafe4bc0633d70c9b": { "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_c838a8b476a94924874098de3f745182", "placeholder": "​", "style": "IPY_MODEL_82571a30ed394868a2443a22d91d1e9e", "value": " 9.09M/9.09M [00:00<00:00, 10.5MB/s]" } }, "f956da2df1c34297b646656a68f531cc": { "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 } }, "4bf6f18e6aef4a038ac3d1886f4d36ff": { "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 } }, "1d85969bfb404a3881262159e98c0667": { "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": "" } }, "1ca38146638d48609e872be9bde06287": { "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 } }, "311d8f3f80f6424ebbf3624c5fde5f13": { "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": "" } }, "c838a8b476a94924874098de3f745182": { "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 } }, "82571a30ed394868a2443a22d91d1e9e": { "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": "" } }, "86d7ac3240fa4e8cab5ad0239c4f176f": { "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_39e0544e05d6456bbe9f5c38835ad885", "IPY_MODEL_e83d44b0c8c54702971b23826d60c38e", "IPY_MODEL_f5979989e2ec4ddcb26a2e16d07b8465" ], "layout": "IPY_MODEL_f5b98b635e39477398f37c502145f563" } }, "39e0544e05d6456bbe9f5c38835ad885": { "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_e76b86249e1f48cd9fc919b687efb172", "placeholder": "​", "style": "IPY_MODEL_e002387841b540b3a76b2ccf70a64d30", "value": "special_tokens_map.json: 100%" } }, "e83d44b0c8c54702971b23826d60c38e": { "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_8a86e5a47b464ca7a2752c46f530a8f6", "max": 345, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_4c6bc029c4ef4bf7af2d3f9e3c3feb09", "value": 345 } }, "f5979989e2ec4ddcb26a2e16d07b8465": { "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_403ec0c98dcd45848ed6fd8c094262af", "placeholder": "​", "style": "IPY_MODEL_cb678d26b9294b11946248dc7d0548af", "value": " 345/345 [00:00<00:00, 13.2kB/s]" } }, "f5b98b635e39477398f37c502145f563": { "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 } }, "e76b86249e1f48cd9fc919b687efb172": { "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 } }, "e002387841b540b3a76b2ccf70a64d30": { "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": "" } }, "8a86e5a47b464ca7a2752c46f530a8f6": { "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 } }, "4c6bc029c4ef4bf7af2d3f9e3c3feb09": { "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": "" } }, "403ec0c98dcd45848ed6fd8c094262af": { "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 } }, "cb678d26b9294b11946248dc7d0548af": { "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": "" } }, "686b8e0a01d248b3b9fe789537d453ec": { "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_2b50ce4f6a054166a40d8abe5971e6cb", "IPY_MODEL_a94eba73ef3146c48e6d08d720368761", "IPY_MODEL_5c7ccad6f1514905b0a1f4e95bc56d46" ], "layout": "IPY_MODEL_7a065e03af8b403a89f4bc08dd3e3d35" } }, "2b50ce4f6a054166a40d8abe5971e6cb": { "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_72bf22ff09fa4d0d967c30fdcab3d230", "placeholder": "​", "style": "IPY_MODEL_083cb42029d646f1acf2294857f78961", "value": "config.json: 100%" } }, "a94eba73ef3146c48e6d08d720368761": { "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_591d588586974cfba3027922a36e0973", "max": 1407, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_6d7fcabfaa7f45299985b82710aebaa6", "value": 1407 } }, "5c7ccad6f1514905b0a1f4e95bc56d46": { "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_ad742d69b4b34bb5902dc425a809d869", "placeholder": "​", "style": "IPY_MODEL_e9191ac0dcf44aee83bb56772cffba90", "value": " 1.41k/1.41k [00:00<00:00, 30.6kB/s]" } }, "7a065e03af8b403a89f4bc08dd3e3d35": { "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 } }, "72bf22ff09fa4d0d967c30fdcab3d230": { "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 } }, "083cb42029d646f1acf2294857f78961": { "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": "" } }, "591d588586974cfba3027922a36e0973": { "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 } }, "6d7fcabfaa7f45299985b82710aebaa6": { "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": "" } }, "ad742d69b4b34bb5902dc425a809d869": { "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 } }, "e9191ac0dcf44aee83bb56772cffba90": { "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": "" } }, "99d76bcbf8ad47bb8d7123e86b70efc8": { "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_26362990544241bda00991ee4ed7051d", "IPY_MODEL_d3f2087627134a0581d0ce6057455285", "IPY_MODEL_9bdcde73e8ca40068b166473a8facd5b" ], "layout": "IPY_MODEL_f180bb9528fa44aeacc5e908bca6c3ab" } }, "26362990544241bda00991ee4ed7051d": { "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_eca52880436c4f5a91aa6f260ee295a8", "placeholder": "​", "style": "IPY_MODEL_c611aba7174e45dca124e43f83b8069b", "value": "model.safetensors: 100%" } }, "d3f2087627134a0581d0ce6057455285": { "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_5291c2d7470048f5ac0153eadebd2a90", "max": 5702746390, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_bf375989f44c492ab4c5ddf3c3637394", "value": 5702746390 } }, "9bdcde73e8ca40068b166473a8facd5b": { "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_e34a5c3098164350a9c47d3585919252", "placeholder": "​", "style": "IPY_MODEL_dddba27214a2412a8c604940bb29b7ec", "value": " 5.70G/5.70G [00:33<00:00, 45.2MB/s]" } }, "f180bb9528fa44aeacc5e908bca6c3ab": { "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 } }, "eca52880436c4f5a91aa6f260ee295a8": { "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 } }, "c611aba7174e45dca124e43f83b8069b": { "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": "" } }, "5291c2d7470048f5ac0153eadebd2a90": { "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 } }, "bf375989f44c492ab4c5ddf3c3637394": { "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": "" } }, "e34a5c3098164350a9c47d3585919252": { "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 } }, "dddba27214a2412a8c604940bb29b7ec": { "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": "" } }, "4bfc1142ebdc428395b6357a58f9eb7c": { "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_31a695d8984d45e8bc73a457e3f06c29", "IPY_MODEL_664af58fe08d442a9a4f7bea43fe18a1", "IPY_MODEL_705af834674e4f709be01ab098f8744d" ], "layout": "IPY_MODEL_87881a974fe44497939f447a23236496" } }, "31a695d8984d45e8bc73a457e3f06c29": { "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_ab94352c01d64e9b9ef320c90752c27d", "placeholder": "​", "style": "IPY_MODEL_52e258b99a764817be02ea9b3da456a4", "value": "generation_config.json: 100%" } }, "664af58fe08d442a9a4f7bea43fe18a1": { "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_e454b9d65c194bc684f11706887836fe", "max": 230, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_e83c8c58697c4f85b6bc8269a07b1083", "value": 230 } }, "705af834674e4f709be01ab098f8744d": { "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_e6b79b6ac3a1425db870ef4ee17bbc2a", "placeholder": "​", "style": "IPY_MODEL_5663b1338dc144178ed05aa79d43957f", "value": " 230/230 [00:00<00:00, 14.2kB/s]" } }, "87881a974fe44497939f447a23236496": { "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 } }, "ab94352c01d64e9b9ef320c90752c27d": { "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 } }, "52e258b99a764817be02ea9b3da456a4": { "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": "" } }, "e454b9d65c194bc684f11706887836fe": { "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 } }, "e83c8c58697c4f85b6bc8269a07b1083": { "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": "" } }, "e6b79b6ac3a1425db870ef4ee17bbc2a": { "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 } }, "5663b1338dc144178ed05aa79d43957f": { "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": [ "# Задание 4.11.1 📚 Литературный RAG из pdf 🤖" ], "metadata": { "id": "19NO_x3c5gd8" } }, { "cell_type": "code", "source": [ "!pip install openai langchain tiktoken langchain-openai langchain-community sentence_transformers faiss-cpu pypdf -q" ], "metadata": { "id": "t1euoXtz5its" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "import pandas as pd\n", "from tqdm import tqdm\n", "\n", "df = pd.read_csv('https://stepik.org/media/attachments/lesson/1084288/pushkin_questions.csv')\n", "print(df.shape)\n", "df.head()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 223 }, "id": "279PAALH5leL", "outputId": "8daae516-a260-4373-8377-2f61326a5504" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "(15, 1)\n" ] }, { "output_type": "execute_result", "data": { "text/plain": [ " question\n", "0 Кого убили раздетой на крыльце?\n", "1 Где Маша остановилась в Петербурге?\n", "2 Почему Гринев и Савельич сбились с дороги?\n", "3 Кто издевался над Машей и морил ее голодом?\n", "4 Куда приговорили отправить Гринева в ссылку?" ], "text/html": [ "\n", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
question
0Кого убили раздетой на крыльце?
1Где Маша остановилась в Петербурге?
2Почему Гринев и Савельич сбились с дороги?
3Кто издевался над Машей и морил ее голодом?
4Куда приговорили отправить Гринева в ссылку?
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "\n", "
\n", "
\n" ], "application/vnd.google.colaboratory.intrinsic+json": { "type": "dataframe", "variable_name": "df", "summary": "{\n \"name\": \"df\",\n \"rows\": 15,\n \"fields\": [\n {\n \"column\": \"question\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 15,\n \"samples\": [\n \"\\u041a\\u0430\\u043a \\u0437\\u0432\\u0430\\u043b\\u0438 \\u0434\\u043e\\u0447\\u043a\\u0443 \\u043a\\u043e\\u043c\\u0435\\u043d\\u0434\\u0430\\u043d\\u0442\\u0430?\",\n \"\\u041a\\u0430\\u043a\\u043e\\u0435 \\u043d\\u0430\\u043f\\u0443\\u0442\\u0441\\u0442\\u0432\\u0438\\u0435 \\u0434\\u0430\\u043b \\u041f\\u0435\\u0442\\u0440\\u0443 \\u043e\\u0442\\u0435\\u0446?\",\n \"\\u041a\\u043e\\u0433\\u043e \\u0443\\u0431\\u0438\\u043b\\u0438 \\u0440\\u0430\\u0437\\u0434\\u0435\\u0442\\u043e\\u0439 \\u043d\\u0430 \\u043a\\u0440\\u044b\\u043b\\u044c\\u0446\\u0435?\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" } }, "metadata": {}, "execution_count": 2 } ] }, { "cell_type": "code", "source": [ "import pandas as pd\n", "from tqdm import tqdm\n", "from langchain.schema import StrOutputParser\n", "from langchain_core.prompts import ChatPromptTemplate\n", "from langchain_core.runnables import RunnablePassthrough\n", "\n", "from langchain.text_splitter import RecursiveCharacterTextSplitter\n", "from langchain.vectorstores import FAISS\n", "from langchain.embeddings import HuggingFaceEmbeddings\n", "from langchain.llms import HuggingFacePipeline\n", "from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM\n", "\n", "import re\n", "from langchain.document_loaders import PyPDFLoader\n", "from langchain.text_splitter import CharacterTextSplitter\n", "from langchain.schema import Document\n", "\n", "import torch\n", "torch.cuda.empty_cache()\n", "\n", "\n", "# Загрузка документа\n", "loader = PyPDFLoader(\"The_Daughter_of_The_Commandant.pdf\")\n", "documents = loader.load()\n", "\n", "# Соединяем весь текст в одну строку для поиска по регулярному выражению\n", "full_text = \"\\n\".join([doc.page_content for doc in documents])\n", "# Очистка от всех ссылок\n", "full_text = re.sub(r'http[s]?://\\S+', '', full_text)\n", "# Удаление ненужных заголовков и лишней информации\n", "full_text = re.sub(r'(www\\.\\S+|Краткое содержание|М.: АСТ|И\\.О\\. Родин|Т\\.М\\. Пименова)', '', full_text)\n", "# Удаление лишних пробелов и переносов строк\n", "full_text = re.sub(r'\\s+', ' ', full_text).strip()\n", "# Разделение на главы с учетом возможных вариантов пробелов\n", "chapters = re.split(r'(Глава\\s*\\d+)', full_text)\n", "# Преобразуем разделенные главы в формат Document и проверяем, чтобы они не были пустыми\n", "splitted_data = []\n", "for i in range(1, len(chapters), 2):\n", " chapter_title = chapters[i].strip() # Убираем пробелы по краям в названии главы\n", " chapter_content = chapters[i+1].strip() # Убираем пробелы по краям в содержании главы\n", " if chapter_content: # Проверяем, что контент не пустой\n", " full_chapter = chapter_title + \" \" + chapter_content # Объединяем заголовок и содержимое\n", " splitted_data.append(Document(page_content=full_chapter))\n", "\n", "# Проверяем, что список не пустой\n", "if len(splitted_data) == 0:\n", " raise ValueError(\"Ошибка: список 'splitted_data' пуст. Проверьте корректность загрузки и разделения текста.\")\n", "\n", "\n", "# Теперь можно создать эмбеддинги и векторное хранилище\n", "model_name = \"bert-base-uncased\"\n", "# model_name = \"mistralai/Mixtral-8x7B-Instruct-v0.1\"\n", "embeddings = HuggingFaceEmbeddings(model_name=model_name)\n", "\n", "# Создание и сохранение векторного хранилища\n", "db = FAISS.from_documents(splitted_data, embeddings)\n", "db.save_local(\"pushkin_db\")\n", "\n", "\n", "# Настройка retriever'а\n", "retriever = db.as_retriever(\n", " search_type=\"similarity\",\n", " k=10,\n", " score_threshold=None,\n", ")\n", "\n", "# Название модели\n", "# gen_model_name = \"IlyaGusev/saiga_mistral_7b\"\n", "# gen_model_name = \"IlyaGusev/saiga_llama3_8b\"\n", "gen_model_name = \"ai-forever/rugpt3small_based_on_gpt2\"\n", "# gen_model_name = \"ruslandev/llama-3-8b-gpt-4o\"\n", "# gen_model_name = \"ruslandev/llama-3-8b-gpt-4o-ru1.0\"\n", "gen_model_name = \"unsloth/Meta-Llama-3.1-8B-bnb-4bit\"\n", "\n", "# Загрузка токенизатора и модели\n", "tokenizer = AutoTokenizer.from_pretrained(gen_model_name)\n", "model = AutoModelForCausalLM.from_pretrained(gen_model_name)\n", "\n", "# Настройка параметров генерации\n", "generation_config = {\n", " \"max_new_tokens\": 50, # Ограничиваем до 10 токенов\n", " \"do_sample\": False, # Отключаем семплирование для более детерминированных ответов\n", " \"temperature\": 0.1, # Снижаем температуру для более консервативных ответов\n", " \"num_beams\": 1 # Используем жадный поиск\n", "}\n", "\n", "\n", "hf_pipeline = pipeline(\n", " \"text-generation\",\n", " model=model,\n", " tokenizer=tokenizer,\n", " **generation_config\n", ")\n", "\n", "llm = HuggingFacePipeline(pipeline=hf_pipeline)\n", "\n", "# Настройка шаблона промпта\n", "template = \"\"\"\n", "Ответь на вопрос, основываясь только на следующем контексте:\n", "{context}\n", "Если ты не уверен в ответе исходя из контекста, то напиши \"не знаю\".\n", "Ответ должен быть максимально кратким, не более 5 слов.\n", "Вопрос: {question}\n", "Краткий ответ:\"\"\"\n", "\n", "\n", "prompt = ChatPromptTemplate.from_template(template)\n", "\n", "def format_docs(docs):\n", " return \"\\n\\n\".join([d.page_content for d in docs])\n", "\n", "# Создание цепочки обработки\n", "chain = (\n", " {\"context\": retriever | format_docs, \"question\": RunnablePassthrough()}\n", " | prompt\n", " | llm\n", " | StrOutputParser()\n", ")\n", "\n", "df = pd.read_csv('https://stepik.org/media/attachments/lesson/1084288/pushkin_questions.csv')\n", "\n", "def extract_answer(text):\n", " for line in text.split('\\n'):\n", " if 'Краткий ответ:' in line:\n", " # Извлекаем ответ и удаляем слово 'bot', если оно есть\n", " answer = line.split('Краткий ответ:')[1].strip()\n", " return answer.replace('bot', '').strip() # Удаляем 'bot' и лишние пробелы\n", " return \"\" # Возвращаем пустую строку, если ответ не найден\n", "\n", "# Обработка вопросов и получение ответов\n", "answers = []\n", "for text_input in tqdm(df['question']):\n", " answer = chain.invoke(text_input)\n", " answers.append(extract_answer(answer))\n", "\n", "df['answer'] = answers\n", "df.to_csv('4_1_11_solution.csv', index=False)\n", "\n", "print(\"Обработка завершена. Результаты сохранены в '4_1_11_solution.csv'.\")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 1000, "referenced_widgets": [ "e45db4f1c73b4aee997f477171a9f9ab", "7973d006c6164a548823b8a560ab9cb5", "c3013b5ba38241a594ae22207e56bfdf", "458a54da8b37496eb76e60658a3f0dd2", "1b616d26fb5347e5b46a881aece70ca4", "30058fe6d884408aaf183d896aeadbce", "eba48ad1b56b43bcbeb4c6b02862d9ec", "103b5789787f4ff8abf086fba2c1755a", "937f9f0710334d3c93a6ea56f65ce0ac", "9997c2b2d2a94505a1969bb1e1cc8fc8", "0e5c424ab95e4ed6987a4d21aeac9f7a", "e9830a7c444d4435960dda28ac469940", "545e4cdea8334d938af708fc76108b44", "08fced61286c4fb89f165f8c88d43bde", "b9902e87b182484aafe4bc0633d70c9b", "f956da2df1c34297b646656a68f531cc", "4bf6f18e6aef4a038ac3d1886f4d36ff", "1d85969bfb404a3881262159e98c0667", "1ca38146638d48609e872be9bde06287", "311d8f3f80f6424ebbf3624c5fde5f13", "c838a8b476a94924874098de3f745182", "82571a30ed394868a2443a22d91d1e9e", "86d7ac3240fa4e8cab5ad0239c4f176f", "39e0544e05d6456bbe9f5c38835ad885", "e83d44b0c8c54702971b23826d60c38e", "f5979989e2ec4ddcb26a2e16d07b8465", "f5b98b635e39477398f37c502145f563", "e76b86249e1f48cd9fc919b687efb172", "e002387841b540b3a76b2ccf70a64d30", "8a86e5a47b464ca7a2752c46f530a8f6", "4c6bc029c4ef4bf7af2d3f9e3c3feb09", "403ec0c98dcd45848ed6fd8c094262af", "cb678d26b9294b11946248dc7d0548af", "686b8e0a01d248b3b9fe789537d453ec", "2b50ce4f6a054166a40d8abe5971e6cb", "a94eba73ef3146c48e6d08d720368761", "5c7ccad6f1514905b0a1f4e95bc56d46", "7a065e03af8b403a89f4bc08dd3e3d35", "72bf22ff09fa4d0d967c30fdcab3d230", "083cb42029d646f1acf2294857f78961", "591d588586974cfba3027922a36e0973", "6d7fcabfaa7f45299985b82710aebaa6", "ad742d69b4b34bb5902dc425a809d869", "e9191ac0dcf44aee83bb56772cffba90", "99d76bcbf8ad47bb8d7123e86b70efc8", "26362990544241bda00991ee4ed7051d", "d3f2087627134a0581d0ce6057455285", "9bdcde73e8ca40068b166473a8facd5b", "f180bb9528fa44aeacc5e908bca6c3ab", "eca52880436c4f5a91aa6f260ee295a8", "c611aba7174e45dca124e43f83b8069b", "5291c2d7470048f5ac0153eadebd2a90", "bf375989f44c492ab4c5ddf3c3637394", "e34a5c3098164350a9c47d3585919252", "dddba27214a2412a8c604940bb29b7ec", "4bfc1142ebdc428395b6357a58f9eb7c", "31a695d8984d45e8bc73a457e3f06c29", "664af58fe08d442a9a4f7bea43fe18a1", "705af834674e4f709be01ab098f8744d", "87881a974fe44497939f447a23236496", "ab94352c01d64e9b9ef320c90752c27d", "52e258b99a764817be02ea9b3da456a4", "e454b9d65c194bc684f11706887836fe", "e83c8c58697c4f85b6bc8269a07b1083", "e6b79b6ac3a1425db870ef4ee17bbc2a", "5663b1338dc144178ed05aa79d43957f" ] }, "id": "Wx3g35Lr5lbr", "outputId": "d6e0e856-90f2-4623-aaab-032524c50285" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "/usr/local/lib/python3.10/dist-packages/pydantic/_internal/_fields.py:132: UserWarning: Field \"model_name\" in HuggingFaceInferenceAPIEmbeddings has conflict with protected namespace \"model_\".\n", "\n", "You may be able to resolve this warning by setting `model_config['protected_namespaces'] = ()`.\n", " warnings.warn(\n", ":53: LangChainDeprecationWarning: The class `HuggingFaceEmbeddings` was deprecated in LangChain 0.2.2 and will be removed in 1.0. An updated version of the class exists in the langchain-huggingface package and should be used instead. To use it run `pip install -U langchain-huggingface` and import as `from langchain_huggingface import HuggingFaceEmbeddings`.\n", " embeddings = HuggingFaceEmbeddings(model_name=model_name)\n", "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_token.py:89: 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", "WARNING:sentence_transformers.SentenceTransformer:No sentence-transformers model found with name bert-base-uncased. Creating a new one with mean pooling.\n", "/usr/local/lib/python3.10/dist-packages/transformers/tokenization_utils_base.py:1601: FutureWarning: `clean_up_tokenization_spaces` was not set. It will be set to `True` by default. This behavior will be depracted in transformers v4.45, and will be then set to `False` by default. For more details check this issue: https://github.com/huggingface/transformers/issues/31884\n", " warnings.warn(\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "tokenizer_config.json: 0%| | 0.00/50.6k [00:00.\n", "`low_cpu_mem_usage` was None, now set to True since model is quantized.\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "model.safetensors: 0%| | 0.00/5.70G [00:00:95: LangChainDeprecationWarning: The class `HuggingFacePipeline` was deprecated in LangChain 0.0.37 and will be removed in 1.0. An updated version of the class exists in the langchain-huggingface package and should be used instead. To use it run `pip install -U langchain-huggingface` and import as `from langchain_huggingface import HuggingFacePipeline`.\n", " llm = HuggingFacePipeline(pipeline=hf_pipeline)\n", " 0%| | 0/15 [00:00\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
questionanswer
0Кого убили раздетой на крыльце?Савельича.
1Где Маша остановилась в Петербурге?в доме Гринева.
2Почему Гринев и Савельич сбились с дороги?Гринев и Савельич сбились с дороги, потому что...
3Кто издевался над Машей и морил ее голодом?Швабрин.
4Куда приговорили отправить Гринева в ссылку?в Казань.
5Сколько детей было в семье Петра Гринева?2
6Кто воспитывал Петра Гринева?Швабрин
7Сколько казаков попросил Гринев, чтобы очистит...1000
8Как далеко находилась от города Белогорская кр...20 верст.
9Как звали дочку коменданта?Маша
10Что Петя подарил вожатому?лошадь и шубу со своего плеча.
11Какое напутствие дал Петру отец?\"Казнить, так казнить, жаловать, так жаловать\".
12Кого Пугачев оставил комендантом Белогорской к...Швабрина.
13Почему Швабрина перевели в крепость?Пугачев перевел Швабрина в крепость, чтобы тот...
14Кого просил пощадить Савельич у Пугачева?Машу.
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "\n", "
\n", " \n", " \n", " \n", "
\n", "\n", "
\n", " \n" ], "application/vnd.google.colaboratory.intrinsic+json": { "type": "dataframe", "variable_name": "df", "summary": "{\n \"name\": \"df\",\n \"rows\": 15,\n \"fields\": [\n {\n \"column\": \"question\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 15,\n \"samples\": [\n \"\\u041a\\u0430\\u043a \\u0437\\u0432\\u0430\\u043b\\u0438 \\u0434\\u043e\\u0447\\u043a\\u0443 \\u043a\\u043e\\u043c\\u0435\\u043d\\u0434\\u0430\\u043d\\u0442\\u0430?\",\n \"\\u041a\\u0430\\u043a\\u043e\\u0435 \\u043d\\u0430\\u043f\\u0443\\u0442\\u0441\\u0442\\u0432\\u0438\\u0435 \\u0434\\u0430\\u043b \\u041f\\u0435\\u0442\\u0440\\u0443 \\u043e\\u0442\\u0435\\u0446?\",\n \"\\u041a\\u043e\\u0433\\u043e \\u0443\\u0431\\u0438\\u043b\\u0438 \\u0440\\u0430\\u0437\\u0434\\u0435\\u0442\\u043e\\u0439 \\u043d\\u0430 \\u043a\\u0440\\u044b\\u043b\\u044c\\u0446\\u0435?\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"answer\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 15,\n \"samples\": [\n \"\\u041c\\u0430\\u0448\\u0430\",\n \"\\\"\\u041a\\u0430\\u0437\\u043d\\u0438\\u0442\\u044c, \\u0442\\u0430\\u043a \\u043a\\u0430\\u0437\\u043d\\u0438\\u0442\\u044c, \\u0436\\u0430\\u043b\\u043e\\u0432\\u0430\\u0442\\u044c, \\u0442\\u0430\\u043a \\u0436\\u0430\\u043b\\u043e\\u0432\\u0430\\u0442\\u044c\\\".\",\n \"\\u0421\\u0430\\u0432\\u0435\\u043b\\u044c\\u0438\\u0447\\u0430.\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" } }, "metadata": {}, "execution_count": 5 } ] }, { "cell_type": "markdown", "source": [ "# Правильные ответы" ], "metadata": { "id": "NYY7ddzj6Pcu" } }, { "cell_type": "code", "source": [ "true_df = pd.read_csv('4.1_semantic_text_splitter.csv')\n", "print(true_df.shape)\n", "true_df" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 537 }, "id": "h9-Ww8Wb6QLm", "outputId": "c1969f63-8f5d-4d7f-fa65-38987a3c59d6" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "(15, 2)\n" ] }, { "output_type": "execute_result", "data": { "text/plain": [ " question \\\n", "0 Кого убили раздетой на крыльце? \n", "1 Где Маша остановилась в Петербурге? \n", "2 Почему Гринев и Савельич сбились с дороги? \n", "3 Кто издевался над Машей и морил ее голодом? \n", "4 Куда приговорили отправить Гринева в ссылку? \n", "5 Сколько детей было в семье Петра Гринева? \n", "6 Кто воспитывал Петра Гринева? \n", "7 Сколько казаков попросил Гринев, чтобы очистит... \n", "8 Как далеко находилась от города Белогорская кр... \n", "9 Как звали дочку коменданта? \n", "10 Что Петя подарил вожатому? \n", "11 Какое напутствие дал Петру отец? \n", "12 Кого Пугачев оставил комендантом Белогорской к... \n", "13 Почему Швабрина перевели в крепость? \n", "14 Кого просил пощадить Савельич у Пугачева? \n", "\n", " answer \n", "0 Василису Егоровну \n", "1 Царском Селе \n", "2 буран \n", "3 Швабрин \n", "4 Сибирь \n", "5 девять \n", "6 Савельич \n", "7 роту солдат и полсотни казаков \n", "8 40 верст \n", "9 Маша Миронова \n", "10 заячий тулупчик \n", "11 платье снову, а честь смолоду \n", "12 Швабрина \n", "13 за дуэль \n", "14 барского дитятю " ], "text/html": [ "\n", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
questionanswer
0Кого убили раздетой на крыльце?Василису Егоровну
1Где Маша остановилась в Петербурге?Царском Селе
2Почему Гринев и Савельич сбились с дороги?буран
3Кто издевался над Машей и морил ее голодом?Швабрин
4Куда приговорили отправить Гринева в ссылку?Сибирь
5Сколько детей было в семье Петра Гринева?девять
6Кто воспитывал Петра Гринева?Савельич
7Сколько казаков попросил Гринев, чтобы очистит...роту солдат и полсотни казаков
8Как далеко находилась от города Белогорская кр...40 верст
9Как звали дочку коменданта?Маша Миронова
10Что Петя подарил вожатому?заячий тулупчик
11Какое напутствие дал Петру отец?платье снову, а честь смолоду
12Кого Пугачев оставил комендантом Белогорской к...Швабрина
13Почему Швабрина перевели в крепость?за дуэль
14Кого просил пощадить Савельич у Пугачева?барского дитятю
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "\n", "
\n", " \n", " \n", " \n", "
\n", "\n", "
\n", "
\n" ], "application/vnd.google.colaboratory.intrinsic+json": { "type": "dataframe", "variable_name": "true_df", "summary": "{\n \"name\": \"true_df\",\n \"rows\": 15,\n \"fields\": [\n {\n \"column\": \"question\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 15,\n \"samples\": [\n \"\\u041a\\u0430\\u043a \\u0437\\u0432\\u0430\\u043b\\u0438 \\u0434\\u043e\\u0447\\u043a\\u0443 \\u043a\\u043e\\u043c\\u0435\\u043d\\u0434\\u0430\\u043d\\u0442\\u0430?\",\n \"\\u041a\\u0430\\u043a\\u043e\\u0435 \\u043d\\u0430\\u043f\\u0443\\u0442\\u0441\\u0442\\u0432\\u0438\\u0435 \\u0434\\u0430\\u043b \\u041f\\u0435\\u0442\\u0440\\u0443 \\u043e\\u0442\\u0435\\u0446?\",\n \"\\u041a\\u043e\\u0433\\u043e \\u0443\\u0431\\u0438\\u043b\\u0438 \\u0440\\u0430\\u0437\\u0434\\u0435\\u0442\\u043e\\u0439 \\u043d\\u0430 \\u043a\\u0440\\u044b\\u043b\\u044c\\u0446\\u0435?\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"answer\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 15,\n \"samples\": [\n \"\\u041c\\u0430\\u0448\\u0430 \\u041c\\u0438\\u0440\\u043e\\u043d\\u043e\\u0432\\u0430\",\n \"\\u043f\\u043b\\u0430\\u0442\\u044c\\u0435 \\u0441\\u043d\\u043e\\u0432\\u0443, \\u0430 \\u0447\\u0435\\u0441\\u0442\\u044c \\u0441\\u043c\\u043e\\u043b\\u043e\\u0434\\u0443\",\n \"\\u0412\\u0430\\u0441\\u0438\\u043b\\u0438\\u0441\\u0443 \\u0415\\u0433\\u043e\\u0440\\u043e\\u0432\\u043d\\u0443\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" } }, "metadata": {}, "execution_count": 6 } ] } ] }