{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"collapsed_sections":["pUAhWWcTAQAH","QvL1duYFDRZY","aBW3QmrxDq72","1R-V0UuTGvZn","QgtJTyELEDRg","C05ODEnFHZXF","o8fXqz3DXukk","TOCspcgXNOav"]},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"},"widgets":{"application/vnd.jupyter.widget-state+json":{"bec0bc6d2ddf4279afe39be57f2a7078":{"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_77e5b95f38b14ff6a0fcddcd2c9f63ff","IPY_MODEL_1efe64f4294c4f8cb86f14dfbeae466e","IPY_MODEL_f35ce532c3024c0ab8ed5e77ffad0b15"],"layout":"IPY_MODEL_d6ebe833fca3454796271cf0f90843ba"}},"77e5b95f38b14ff6a0fcddcd2c9f63ff":{"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_fc199b9f3b2246be86528d5ee27ec7aa","placeholder":"​","style":"IPY_MODEL_4e636e88bcf04737b6a5a5553164e29d","value":"Uploading the dataset shards: 100%"}},"1efe64f4294c4f8cb86f14dfbeae466e":{"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_ee60ebaf2654483fab92f264cb67b0bb","max":1,"min":0,"orientation":"horizontal","style":"IPY_MODEL_0eff8d93269146ea887f0b70198ac7b1","value":1}},"f35ce532c3024c0ab8ed5e77ffad0b15":{"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_c7d221edccf644e8bc566ed168f9be0b","placeholder":"​","style":"IPY_MODEL_4ca842a0d1414d6f8d2bc88d51350372","value":" 1/1 [00:00&lt;00:00,  1.26it/s]"}},"d6ebe833fca3454796271cf0f90843ba":{"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}},"fc199b9f3b2246be86528d5ee27ec7aa":{"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}},"4e636e88bcf04737b6a5a5553164e29d":{"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":""}},"ee60ebaf2654483fab92f264cb67b0bb":{"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}},"0eff8d93269146ea887f0b70198ac7b1":{"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":""}},"c7d221edccf644e8bc566ed168f9be0b":{"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}},"4ca842a0d1414d6f8d2bc88d51350372":{"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":""}},"6f39a20e7d394bc3a31a5371a715e2c6":{"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_439be3c81e744204ad7ffb35f6c2edc8","IPY_MODEL_2d401141021e45e1b57228f2a301810c","IPY_MODEL_625c8adb770f44f482c42e07c75bc3b8"],"layout":"IPY_MODEL_3bf5ed3bacad49b3914a3c3b2442833f"}},"439be3c81e744204ad7ffb35f6c2edc8":{"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_c62266e4ee56414c95eabcee2a517613","placeholder":"​","style":"IPY_MODEL_32206221acca4304b3db8a6d1c9cbdf8","value":"Creating parquet from Arrow format: 100%"}},"2d401141021e45e1b57228f2a301810c":{"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_5edbb6b742ea4895ba6cbd54d3d7bafc","max":1,"min":0,"orientation":"horizontal","style":"IPY_MODEL_e35e27bb30424f3fb2128b76d482ef61","value":1}},"625c8adb770f44f482c42e07c75bc3b8":{"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_e402634acd784e08839808e210c9b986","placeholder":"​","style":"IPY_MODEL_db4ec493d9344451ac78a9be25fa0305","value":" 1/1 [00:00&lt;00:00, 28.34ba/s]"}},"3bf5ed3bacad49b3914a3c3b2442833f":{"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}},"c62266e4ee56414c95eabcee2a517613":{"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}},"32206221acca4304b3db8a6d1c9cbdf8":{"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":""}},"5edbb6b742ea4895ba6cbd54d3d7bafc":{"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}},"e35e27bb30424f3fb2128b76d482ef61":{"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":""}},"e402634acd784e08839808e210c9b986":{"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}},"db4ec493d9344451ac78a9be25fa0305":{"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":""}},"fe8d245fe09e4852b7f3e37a6505d641":{"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_0bbc237ce4ed42caacd2548706421462","IPY_MODEL_d0adaa2d18f34821972a4c7da8ad00a5","IPY_MODEL_4491d84c927648f2a12232281f8f432f"],"layout":"IPY_MODEL_5e90a10d9bbc4f81bfed78be6095c0c9"}},"0bbc237ce4ed42caacd2548706421462":{"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_cc33318e90a7419e902d5e0bb7f1631c","placeholder":"​","style":"IPY_MODEL_3f39e3abed3a4404a1238c42e5b92a83","value":"Uploading the dataset shards: 100%"}},"d0adaa2d18f34821972a4c7da8ad00a5":{"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_4c71d238b8bd4932be832e763b18b7c9","max":1,"min":0,"orientation":"horizontal","style":"IPY_MODEL_71d2d8a378fb405690004360dfd8369b","value":1}},"4491d84c927648f2a12232281f8f432f":{"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_8b9cf44aa9504ae8b3797d5838737410","placeholder":"​","style":"IPY_MODEL_defb1059cc2f44d8812be091633096e5","value":" 1/1 [00:00&lt;00:00,  1.56it/s]"}},"5e90a10d9bbc4f81bfed78be6095c0c9":{"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}},"cc33318e90a7419e902d5e0bb7f1631c":{"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}},"3f39e3abed3a4404a1238c42e5b92a83":{"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":""}},"4c71d238b8bd4932be832e763b18b7c9":{"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}},"71d2d8a378fb405690004360dfd8369b":{"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":""}},"8b9cf44aa9504ae8b3797d5838737410":{"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}},"defb1059cc2f44d8812be091633096e5":{"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":""}},"bd4395a4f8df4770b8ede90cc6946977":{"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_589485d7544e446483fc1a3c00808c6a","IPY_MODEL_96335e11b8e94a228af6fa0378b0f880","IPY_MODEL_553d03197e9a49c2b3babd8b07b88d3a"],"layout":"IPY_MODEL_127f503e2064434a80c45ee5c4964c8d"}},"589485d7544e446483fc1a3c00808c6a":{"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_3bcf945f384349cf99fa3f84993c7134","placeholder":"​","style":"IPY_MODEL_a817e862a2e240a29000852e29bebd4c","value":"Creating parquet from Arrow format: 100%"}},"96335e11b8e94a228af6fa0378b0f880":{"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_c173273f98e9469398b676f0830fe4ba","max":1,"min":0,"orientation":"horizontal","style":"IPY_MODEL_3aa832fb797842bd9be70bcd39160c90","value":1}},"553d03197e9a49c2b3babd8b07b88d3a":{"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_74640336853b4bb2b2cff91be9407b52","placeholder":"​","style":"IPY_MODEL_b1bd126a1c814111a032ba1752109f6c","value":" 1/1 [00:00&lt;00:00, 23.27ba/s]"}},"127f503e2064434a80c45ee5c4964c8d":{"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}},"3bcf945f384349cf99fa3f84993c7134":{"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}},"a817e862a2e240a29000852e29bebd4c":{"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":""}},"c173273f98e9469398b676f0830fe4ba":{"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}},"3aa832fb797842bd9be70bcd39160c90":{"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":""}},"74640336853b4bb2b2cff91be9407b52":{"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}},"b1bd126a1c814111a032ba1752109f6c":{"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":""}},"a8b93bb62eca4fe8844ff032c9dd0122":{"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_6a935756eee44fbe9aa17f65e5932da5","IPY_MODEL_9323f202e7d0437394e16150e5fbb140","IPY_MODEL_08284f96f55649b2b0bef2721d0bfbd1"],"layout":"IPY_MODEL_97364153a4734cff90126d8ab36ba8a9"}},"6a935756eee44fbe9aa17f65e5932da5":{"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_902a4c7ef4f445db9d90b29a60ac9fba","placeholder":"​","style":"IPY_MODEL_6694ed93dbde4ce6a6bdfd8dd2f511f7","value":"Uploading the dataset shards: 100%"}},"9323f202e7d0437394e16150e5fbb140":{"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_33d44efe248a4ba99f263ebb356f2abc","max":1,"min":0,"orientation":"horizontal","style":"IPY_MODEL_ba817a16d01b402a9ee8e65f1f2ecf1d","value":1}},"08284f96f55649b2b0bef2721d0bfbd1":{"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_2bba8e0b3d03450d9ba2b26d45a02f8f","placeholder":"​","style":"IPY_MODEL_4f46ba538cec4f87a96fab111688f506","value":" 1/1 [00:00&lt;00:00,  2.03it/s]"}},"97364153a4734cff90126d8ab36ba8a9":{"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}},"902a4c7ef4f445db9d90b29a60ac9fba":{"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}},"6694ed93dbde4ce6a6bdfd8dd2f511f7":{"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":""}},"33d44efe248a4ba99f263ebb356f2abc":{"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}},"ba817a16d01b402a9ee8e65f1f2ecf1d":{"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":""}},"2bba8e0b3d03450d9ba2b26d45a02f8f":{"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}},"4f46ba538cec4f87a96fab111688f506":{"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":""}},"2f52827a49594608a33418a9ea8683b2":{"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_ff361df3397d485abde40d86c098b50f","IPY_MODEL_cb0b4f712ef44d0f9ce301a949eacc6a","IPY_MODEL_83db66d1fa1d43f782896143dc8fbfa0"],"layout":"IPY_MODEL_393f21ef86d24e4a9211437ba48c8fac"}},"ff361df3397d485abde40d86c098b50f":{"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_cfd10f20005a483fa879bf391229c454","placeholder":"​","style":"IPY_MODEL_e48482ff80454cae80f6197184fb133d","value":"Creating parquet from Arrow format: 100%"}},"cb0b4f712ef44d0f9ce301a949eacc6a":{"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_9f857551fd0c4429baee3c8b32dbd8ac","max":1,"min":0,"orientation":"horizontal","style":"IPY_MODEL_9f9a7778f213478f9229501d28865939","value":1}},"83db66d1fa1d43f782896143dc8fbfa0":{"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_da6b7edafc154ebc80b13dea1d6b195a","placeholder":"​","style":"IPY_MODEL_8e76ecf38de340cfb341581b14f9eb37","value":" 1/1 [00:00&lt;00:00, 37.77ba/s]"}},"393f21ef86d24e4a9211437ba48c8fac":{"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}},"cfd10f20005a483fa879bf391229c454":{"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}},"e48482ff80454cae80f6197184fb133d":{"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":""}},"9f857551fd0c4429baee3c8b32dbd8ac":{"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}},"9f9a7778f213478f9229501d28865939":{"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":""}},"da6b7edafc154ebc80b13dea1d6b195a":{"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}},"8e76ecf38de340cfb341581b14f9eb37":{"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":""}},"14bba26a25c5422eb1e5ab40eedc1039":{"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_5b0f1caa88194e8fa43cf7a5fe9ba506","IPY_MODEL_c5898b1e695e4781a76fc712d2fe50ba","IPY_MODEL_b238516174704559b71d21ee507edf18"],"layout":"IPY_MODEL_a42fb59ce2cd453dbb2adacefb987b37"}},"5b0f1caa88194e8fa43cf7a5fe9ba506":{"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_42b55aa5f28e4d2e8781e9a3c6bf7998","placeholder":"​","style":"IPY_MODEL_9a1a12c269a1408bbe21f8fbbb771664","value":"Uploading the dataset shards: 100%"}},"c5898b1e695e4781a76fc712d2fe50ba":{"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_d51f1b853c9747a0a64dc55e8a1e4b1b","max":1,"min":0,"orientation":"horizontal","style":"IPY_MODEL_4b49bea5b3cd42c78119fcc1ee8faa5f","value":1}},"b238516174704559b71d21ee507edf18":{"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_a8a41dfed7df484fafc10b0f184f2342","placeholder":"​","style":"IPY_MODEL_b0d36dfde6e44c29baedf730a76111b2","value":" 1/1 [00:00&lt;00:00,  2.39it/s]"}},"a42fb59ce2cd453dbb2adacefb987b37":{"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}},"42b55aa5f28e4d2e8781e9a3c6bf7998":{"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}},"9a1a12c269a1408bbe21f8fbbb771664":{"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":""}},"d51f1b853c9747a0a64dc55e8a1e4b1b":{"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}},"4b49bea5b3cd42c78119fcc1ee8faa5f":{"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":""}},"a8a41dfed7df484fafc10b0f184f2342":{"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}},"b0d36dfde6e44c29baedf730a76111b2":{"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":""}},"697095894b0746c19cac9c84ee1299a5":{"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_6958b08b55cf4803841921a3a58a25bb","IPY_MODEL_9d5d957377a5447fb2918b977332bb09","IPY_MODEL_b4b38b9be896405ebbc4cfacc8a13c6b"],"layout":"IPY_MODEL_95845f3081e3446dbda4d1ebae411e1e"}},"6958b08b55cf4803841921a3a58a25bb":{"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_239d99c569664efa89d9e2c101d9595e","placeholder":"​","style":"IPY_MODEL_c8b2a0c6fcc8424490580b2ad0d0c55e","value":"Creating parquet from Arrow format: 100%"}},"9d5d957377a5447fb2918b977332bb09":{"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_449721872331456f8efc6695d81b8e2b","max":1,"min":0,"orientation":"horizontal","style":"IPY_MODEL_2673cfa4debe4d5aac87e2020944cfb9","value":1}},"b4b38b9be896405ebbc4cfacc8a13c6b":{"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_368f4b55d6b745f5b8ae735eb1407a20","placeholder":"​","style":"IPY_MODEL_e0eca158cdfb459fab7c6cb2949a8174","value":" 1/1 [00:00&lt;00:00, 28.18ba/s]"}},"95845f3081e3446dbda4d1ebae411e1e":{"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}},"239d99c569664efa89d9e2c101d9595e":{"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}},"c8b2a0c6fcc8424490580b2ad0d0c55e":{"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":""}},"449721872331456f8efc6695d81b8e2b":{"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}},"2673cfa4debe4d5aac87e2020944cfb9":{"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":""}},"368f4b55d6b745f5b8ae735eb1407a20":{"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}},"e0eca158cdfb459fab7c6cb2949a8174":{"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":""}},"aad9177750614696ae2cbc05084ca901":{"model_module":"@jupyter-widgets/controls","model_name":"VBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"VBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"VBoxView","box_style":"","children":["IPY_MODEL_bea3753676194ce199cbac34437fe02c","IPY_MODEL_63ac6dcce5ad41eab94c677e4ced1739","IPY_MODEL_96c1efa0809e4e5dbf4e01459ad9874d","IPY_MODEL_30485ee212864fe8bf4df32915d9bd05"],"layout":"IPY_MODEL_5d0bf9b3947640c6abf6a9bbef95d444"}},"683e84ac0d30498680a705564f1b8fd0":{"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_6dee3243999141efabfbe3adaf9037b6","placeholder":"​","style":"IPY_MODEL_b1c3daa957c84294bae86e4ad6706756","value":"<center> <img\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.svg\nalt='Hugging Face'> <br> Copy a token from <a\nhref=\"https://huggingface.co/settings/tokens\" target=\"_blank\">your Hugging Face\ntokens page</a> and paste it below. <br> Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file. </center>"}},"5d28187910324c76b603f28caeac8834":{"model_module":"@jupyter-widgets/controls","model_name":"PasswordModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"PasswordModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"PasswordView","continuous_update":true,"description":"Token:","description_tooltip":null,"disabled":false,"layout":"IPY_MODEL_204fed5d2e954d1482303016792791a2","placeholder":"​","style":"IPY_MODEL_7879690e674d4d92bc2391571fa57868","value":""}},"a7794614c3aa4b10a468437e265b7a87":{"model_module":"@jupyter-widgets/controls","model_name":"CheckboxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"CheckboxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"CheckboxView","description":"Add token as git credential?","description_tooltip":null,"disabled":false,"indent":true,"layout":"IPY_MODEL_2e38bdd8bd1a4d1f83a69f59d4072f6e","style":"IPY_MODEL_c1e7fe0e092e4b4db19d322f5a338cc3","value":true}},"a23d8258a10141889cf520ae33e9a5a6":{"model_module":"@jupyter-widgets/controls","model_name":"ButtonModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ButtonModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ButtonView","button_style":"","description":"Login","disabled":false,"icon":"","layout":"IPY_MODEL_dc129a2f7bf14b34bb24b121f1f88a76","style":"IPY_MODEL_214dbc6b261b4c3fa9d19228dce132ce","tooltip":""}},"6a0cac18ca21476991c265ef20a32edb":{"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_7c0a38bb3bd64ed38831141661ebea1c","placeholder":"​","style":"IPY_MODEL_464829ba3cdb469a95a0f4a9089d75bf","value":"\n<b>Pro Tip:</b> If you don't already have one, you can create a dedicated\n'notebooks' token with 'write' access, that you can then easily reuse for all\nnotebooks. </center>"}},"5d0bf9b3947640c6abf6a9bbef95d444":{"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":"center","align_self":null,"border":null,"bottom":null,"display":"flex","flex":null,"flex_flow":"column","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":"50%"}},"6dee3243999141efabfbe3adaf9037b6":{"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}},"b1c3daa957c84294bae86e4ad6706756":{"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":""}},"204fed5d2e954d1482303016792791a2":{"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}},"7879690e674d4d92bc2391571fa57868":{"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":""}},"2e38bdd8bd1a4d1f83a69f59d4072f6e":{"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}},"c1e7fe0e092e4b4db19d322f5a338cc3":{"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":""}},"dc129a2f7bf14b34bb24b121f1f88a76":{"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}},"214dbc6b261b4c3fa9d19228dce132ce":{"model_module":"@jupyter-widgets/controls","model_name":"ButtonStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ButtonStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","button_color":null,"font_weight":""}},"7c0a38bb3bd64ed38831141661ebea1c":{"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}},"464829ba3cdb469a95a0f4a9089d75bf":{"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":""}},"2db0f2ff3d484d778c397625e60b23a5":{"model_module":"@jupyter-widgets/controls","model_name":"LabelModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"LabelModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"LabelView","description":"","description_tooltip":null,"layout":"IPY_MODEL_fa4c40830976491fa9d3175617e296b5","placeholder":"​","style":"IPY_MODEL_096c770097c147f2b989e300327fcf35","value":"Connecting..."}},"fa4c40830976491fa9d3175617e296b5":{"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}},"096c770097c147f2b989e300327fcf35":{"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":""}},"bea3753676194ce199cbac34437fe02c":{"model_module":"@jupyter-widgets/controls","model_name":"LabelModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"LabelModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"LabelView","description":"","description_tooltip":null,"layout":"IPY_MODEL_0ac44a37168b4130bab4438776df3e97","placeholder":"​","style":"IPY_MODEL_747988d1b2244e9496e9e2565d6e98c6","value":"Token is valid (permission: write)."}},"63ac6dcce5ad41eab94c677e4ced1739":{"model_module":"@jupyter-widgets/controls","model_name":"LabelModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"LabelModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"LabelView","description":"","description_tooltip":null,"layout":"IPY_MODEL_c99133095ad544a891d3f1f26c21870a","placeholder":"​","style":"IPY_MODEL_2bb9477a98c347e8830827ef6a39b9b4","value":"Your token has been saved in your configured git credential helpers (store)."}},"96c1efa0809e4e5dbf4e01459ad9874d":{"model_module":"@jupyter-widgets/controls","model_name":"LabelModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"LabelModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"LabelView","description":"","description_tooltip":null,"layout":"IPY_MODEL_65bfc48f5abe4f94aab1b833f0381b8b","placeholder":"​","style":"IPY_MODEL_24628bf215594e24a22364137a0ed28b","value":"Your token has been saved to /root/.cache/huggingface/token"}},"30485ee212864fe8bf4df32915d9bd05":{"model_module":"@jupyter-widgets/controls","model_name":"LabelModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"LabelModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"LabelView","description":"","description_tooltip":null,"layout":"IPY_MODEL_06e9ba8e64704c1abbcfd34230e77eea","placeholder":"​","style":"IPY_MODEL_4ba8236cc5834185a2c652472b3a8abc","value":"Login successful"}},"0ac44a37168b4130bab4438776df3e97":{"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}},"747988d1b2244e9496e9e2565d6e98c6":{"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":""}},"c99133095ad544a891d3f1f26c21870a":{"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}},"2bb9477a98c347e8830827ef6a39b9b4":{"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":""}},"65bfc48f5abe4f94aab1b833f0381b8b":{"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}},"24628bf215594e24a22364137a0ed28b":{"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":""}},"06e9ba8e64704c1abbcfd34230e77eea":{"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}},"4ba8236cc5834185a2c652472b3a8abc":{"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":["#Create instructions fine-tuning dataset for LLAMA 2 lora tuning\n","\n","we will use machine learning topics available in PDF for context.\n","utilize openai 3.5 turbo to generate json records for 2 instructions fine-tuning tasks\n","\n","1.   summarization\n","2.   creating multiple choice questions (MCQ)\n","\n","\n","final dataset is stored in hugging face.\n","\n","MCQ only in nested dictionary format. see MCQ expected output json format sample below\n","[apailang/dataset_mcq_table](https://huggingface.co/datasets/apailang/dataset_mcq_table)\n","\n","and\n","\n","summarization and mcq in dinctionary string format. see Summarization expected output json format sample below\n","[bitbasher/mini-dataset-978](https://huggingface.co/datasets/BitBasher/mini-dataset-978)\n","---\n","\n","\n","\n","####Summarization expected output json format.\n","\n","\n","```\n","\n","\n","[{\n","        \"instruction\": \"Summarize the concept and applications of AI\",\n","\n","        \"input_content\": \"AI refers to the development of computer systems that can perform tasks that would normally require human intelligence. Some examples of AI applications .....\",\n","\n","        \"expected_output\": \"AI, or artificial intelligence, involves the creation of computer systems capable of performing tasks that typically require human intelligence. Examples of AI applications include speech recognition systems used in self-driving cars, security systems, and medical imaging. AI algorithms are also used for personalized recommendations on e-commerce sites and streaming services, predictive maintenance in various industries, medical diagnosis systems, autonomous vehicles, fraud detection in financial institutions, image recognition in photo organization and security systems, natural language processing in chatbots and language translation systems, and predictive analytics in healthcare and marketing.\"\n","    }]\n","```\n","\n","\n","####MCQ expected output json format.\n","\n","\n","\n","```\n","[\n","    {\n","        \"instruction\": \"Create an MCQ on the structure of artificial neural networks\",\n","        \"input_content\": \"Artificial neural networks are built on the principles of the structure and operation of human neurons.......\",\n","\n","        \"expected_output\": {\n","            \"question\": \"What is the structure of an artificial neural network?\",\n","            \"options\": {\n","                \"A\": \"It consists of input layers and hidden layers only\",\n","                \"B\": \"It consists of input layers, hidden layers, and output layers\",\n","                \"C\": \"It consists of input layers, hidden layers, output layers, and artificial neurons\",\n","                \"D\": \"It consists of input layers, hidden layers, output layers, artificial neurons, and weighted connections\"\n","            },\n","            \"correct_answer\": \"C\",\n","            \"explanation\": \"An artificial neural network consists of input layers, hidden layers, output layers, and artificial neurons. The input layer receives data from the outside world, the hidden layers process and compute the weighted total, and the output layer provides the final response. Artificial neurons are the units within the network, and the connections between neurons are weighted to optimize the impact of inputs from the preceding layer.\"\n","        }\n","    }\n","]\n","```\n","\n","\n","\n","\n","---\n","\n"],"metadata":{"id":"iYeJEWUdAsVk"}},{"cell_type":"code","source":["!pip install openai==0.28\n","!pip install PyPDF2\n","!pip install --upgrade tiktoken\n","!pip install -q datasets transformers sentence_transformers faiss-gpu huggingface_hub"],"metadata":{"id":"9s76sLpIfeUK"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":["###import libraries"],"metadata":{"id":"_SZpV4KiAMd8"}},{"cell_type":"code","source":["# Import the required libraries\n","import openai\n","import PyPDF2\n","\n","import json\n","import pandas as pd\n","from datasets import Dataset, DatasetDict, concatenate_datasets, load_dataset\n","\n","from transformers import AutoTokenizer\n","import matplotlib.pyplot as plt\n","import seaborn as sns\n","\n","from sentence_transformers import SentenceTransformer\n","import faiss\n","from tqdm.autonotebook import tqdm\n","import numpy as np"],"metadata":{"id":"m8Du-508eujO"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["from huggingface_hub import notebook_login\n","notebook_login()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":145,"referenced_widgets":["aad9177750614696ae2cbc05084ca901","683e84ac0d30498680a705564f1b8fd0","5d28187910324c76b603f28caeac8834","a7794614c3aa4b10a468437e265b7a87","a23d8258a10141889cf520ae33e9a5a6","6a0cac18ca21476991c265ef20a32edb","5d0bf9b3947640c6abf6a9bbef95d444","6dee3243999141efabfbe3adaf9037b6","b1c3daa957c84294bae86e4ad6706756","204fed5d2e954d1482303016792791a2","7879690e674d4d92bc2391571fa57868","2e38bdd8bd1a4d1f83a69f59d4072f6e","c1e7fe0e092e4b4db19d322f5a338cc3","dc129a2f7bf14b34bb24b121f1f88a76","214dbc6b261b4c3fa9d19228dce132ce","7c0a38bb3bd64ed38831141661ebea1c","464829ba3cdb469a95a0f4a9089d75bf","2db0f2ff3d484d778c397625e60b23a5","fa4c40830976491fa9d3175617e296b5","096c770097c147f2b989e300327fcf35","bea3753676194ce199cbac34437fe02c","63ac6dcce5ad41eab94c677e4ced1739","96c1efa0809e4e5dbf4e01459ad9874d","30485ee212864fe8bf4df32915d9bd05","0ac44a37168b4130bab4438776df3e97","747988d1b2244e9496e9e2565d6e98c6","c99133095ad544a891d3f1f26c21870a","2bb9477a98c347e8830827ef6a39b9b4","65bfc48f5abe4f94aab1b833f0381b8b","24628bf215594e24a22364137a0ed28b","06e9ba8e64704c1abbcfd34230e77eea","4ba8236cc5834185a2c652472b3a8abc"]},"id":"W2AwoT_mWCT0","outputId":"6c3b17bf-214f-484c-c83a-c6009f677efd"},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":["VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"aad9177750614696ae2cbc05084ca901"}},"metadata":{}}]},{"cell_type":"markdown","source":["### helper functions\n","\n","\n","1.   convert pdfs to json\n","2.   append generate output json records\n","\n"],"metadata":{"id":"pUAhWWcTAQAH"}},{"cell_type":"code","source":["def pdf_to_json(pdf_path, replace_newlines=True, indentation=4):\n","    \"\"\"Converts a PDF document to JSON format, ensuring proper text formatting and\n","    optional newline replacement with spaces.\n","\n","    Args:\n","        pdf_path (str): The path to the PDF file.\n","        replace_newlines (bool, optional): Whether to replace newlines with spaces.\n","                                          Defaults to True.\n","        indentation (int, optional): The level of indentation for JSON output.\n","                                      Defaults to 4.\n","\n","    Returns:\n","        str: The JSON-formatted string representation of the PDF content.\n","    \"\"\"\n","\n","    with open(pdf_path, 'rb') as pdf_file:\n","        pdf_reader = PyPDF2.PdfReader(pdf_file)\n","\n","        text_content = \"\"\n","        for page_num in range(len(pdf_reader.pages)):\n","            page = pdf_reader.pages[page_num]\n","            text_content += page.extract_text().strip() + \"\\n\"\n","\n","        # Preprocess text to remove unnecessary characters and spacing\n","        processed_text = text_content.replace('\\r', '')  # Remove carriage returns\n","        if replace_newlines:\n","            processed_text = processed_text.replace('\\n', ' ')  # Replace newlines with spaces\n","        else:\n","            # Preserve newlines if explicitly requested\n","            processed_text = processed_text.strip()\n","\n","        # Create a JSON object with a single key \"text\" containing the processed text\n","        json_data = {\"text\": processed_text}\n","\n","        # Return the JSON-formatted string with indentation for readability\n","        return json.dumps(json_data, indent=indentation)\n","\n","# test usage:\n","pdf_path = \"geeksforgeeks4.pdf\"\n","json_string = pdf_to_json(pdf_path)\n","print(json_string)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"k_pHqiBmPHTM","outputId":"0b6a506d-cba5-4801-84bb-7a13b96f7407"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["{\n","    \"text\": \"AI vs. Machine Learning vs. Deep Learning Examples: Arti\\ufb01cial Intelligence (AI) refers to the development of computer systems that can perform tasks that would normally require human intelligence. Some examples of AI include: There are numerous examples of AI applications across various industries. Here are some common examples: \\u25cf Speech recognition: speech recognition systems use deep learning algorithms to recognize and classify images and speech. These systems are used in a variety of applications, such as self-driving cars, security systems, and medical imaging. \\u25cf Personalized recommendations: E-commerce sites and streaming services like Amazon and Net\\ufb02ix use AI algorithms to analyze users\\u2019 browsing and viewing history to recommend products and content that they are likely to be interested in. \\u25cf Predictive maintenance: AI-powered predictive maintenance systems analyze data from sensors and other sources to predict when equipment is likely to fail, helping to reduce downtime and maintenance costs. \\u25cf Medical diagnosis: AI-powered medical diagnosis systems analyze medical images and other patient data to help doctors make more accurate diagnoses and treatment plans. \\u25cf Autonomous vehicles: Self-driving cars and other autonomous vehicles use AI algorithms and sensors to analyze their environment and make decisions about speed, direction, and other factors. \\u25cf Virtual Personal Assistants (VPA) like Siri or Alexa \\u2013 these use natural language processing to understand and respond to user requests, such as playing music, setting reminders, and answering questions. \\u25cf Autonomous vehicles \\u2013 self-driving cars use AI to analyze sensor data, such as cameras and lidar, to make decisions about navigation, obstacle avoidance, and route planning. \\u25cf Fraud detection \\u2013 \\ufb01nancial institutions use AI to analyze transactions and detect patterns that are indicative of fraud, such as unusual spending patterns or transactions from unfamiliar locations. \\u25cf Image recognition \\u2013 AI is used in applications such as photo organization, security systems, and autonomous robots to identify objects, people, and scenes in images. \\u25cf Natural language processing \\u2013 AI is used in chatbots and language translation systems to understand and generate human-like text. \\u25cf Predictive analytics \\u2013 AI is used in industries such as healthcare and marketing to analyze large amounts of data and make predictions about future events, such as disease outbreaks or consumer behavior. \\u25cf Game-playing AI \\u2013 AI algorithms have been developed to play games such as chess, Go, and poker at a superhuman level, by analyzing game data and making predictions about the outcomes of moves. \"\n","}\n"]}]},{"cell_type":"code","source":["# openai.api_key = \"your secret API Key\" mr mar key\n","openai.api_key = \"sk-xxxxx\""],"metadata":{"id":"mab6clp-feo3"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["model_engine =\"gpt-3.5-turbo\"\n","data=json_string\n"],"metadata":{"id":"J24FJ42hgV5f"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["#append json records\n","def append_to_json(file_path, new_records):\n","    \"\"\"Appends new records to an existing JSON file.\n","\n","    Args:\n","        file_path (str): The path to the existing JSON file.\n","        new_records (list): A list of new records to append, each record as a dictionary.\n","    \"\"\"\n","\n","    try:\n","        with open(file_path, \"r\") as f:\n","            existing_data = json.load(f)\n","    except FileNotFoundError:\n","        existing_data = []\n","\n","    # Combine existing data with new records\n","    all_data = existing_data + new_records\n","\n","    with open(file_path, \"w\") as f:\n","        json.dump(all_data, f, indent=4)  # Indent for readability\n","\n","    print(f\"New records appended to {file_path}\")"],"metadata":{"id":"8WpY-cl-qBpw"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":["###start of Summarization instrucions dataset generation"],"metadata":{"id":"QvL1duYFDRZY"}},{"cell_type":"code","source":["def get_completion(prompt):\n","  messages=[{'role':'system', 'content':r\"\"\"\n","  As a machine learning education specialist, your expertise is pivotal in deepening the comprehension of complex machine learning concepts for both educators and students.\n","\n","  Your role entails:\n","\n","  Crafting Insightful Questions: Develop thought-provoking questions that explore the intricacies of machine learning topics.\n","  Providing Detailed Explanations: Deliver comprehensive answers to these questions, elucidating the underlying technical principles.\n","  Assisting in Exam Preparation: Support educators in formulating sophisticated exam and quiz questions, including MCQs, accompanied by thorough explanations.\n","  Summarizing Course Material: Distill key information from course materials, articulating complex ideas within the context of advanced machine learning practices.\n","  Generating MCQs: Create MCQs for each machine learning topic, comprising a question, four choices (A-D), and the correct answer, along with a rationale explaining the answer.\n","\n","  Objective:\n","  Your primary goal is to compile an Instruction Dataset in a structured JSON format. This dataset should integrate specific instructions, relevant content on various machine learning topics, expected outputs with expert-level explanations, and summaries for student comprehension.\n","\n","  Dataset Structure:\n","  Instruction: Specifies the task, such as summarizing, explaining, or creating MCQs.\n","  Input Content: Provides brief summary of context or inputs for the task.\n","  Expected Output: The detailed outcome produced by the model, potentially an explanation, summary.\n","\n","  2 sample output JSON format:\n","  [\n","    {\n","        \"instruction\": \"Summarize the concept and applications of AI\",\n","        \"input_content\": \"AI refers to the development of computer systems that can perform tasks that would normally require human intelligence. Some examples of AI applications include:\",\n","        \"expected_output\": \"AI, or artificial intelligence, involves the creation of computer systems capable of performing tasks that typically require human intelligence. Examples of AI applications include speech recognition systems used in self-driving cars, security systems, and medical imaging. AI algorithms are also used for personalized recommendations on e-commerce sites and streaming services, predictive maintenance in various industries, medical diagnosis systems, autonomous vehicles, fraud detection in financial institutions, image recognition in photo organization and security systems, natural language processing in chatbots and language translation systems, and predictive analytics in healthcare and marketing.\"\n","    },\n","    {\n","        \"instruction\": \"Summarize the concept and applications of Machine Learning\",\n","        \"input_content\": \"Machine Learning is a subset of AI that focuses on enabling computer systems to learn from data and improve their performance without being explicitly programmed. Some examples of Machine Learning applications include:\",\n","        \"expected_output\": \"Machine Learning is a branch of AI that enables computer systems to learn from data and improve their performance without explicit programming. Examples of Machine Learning applications include speech recognition systems, personalized recommendations on e-commerce sites and streaming services, predictive maintenance systems, medical diagnosis systems, autonomous vehicles, fraud detection systems, image recognition applications, natural language processing systems, and predictive analytics in various industries.\"\n","    }\n","  ]\n","\n","  \"\"\"}]\n","\n","  messages = messages+ prompt\n","  reponse = openai.ChatCompletion.create(\n","    model=model_engine,\n","    messages=messages,\n","    temperature=0.5)\n","  response = reponse['choices'][0]['message']['content']\n","\n","  return response"],"metadata":{"id":"D-rO-eNNgWAB"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["#mass query for summary\n","\n","# List of file paths. #\n","file_paths = [\"geeksforgeeks0.pdf\",\"geeksforgeeks1.pdf\", \"geeksforgeeks2.pdf\",\"geeksforgeeks3.pdf\", \"geeksforgeeks4.pdf\",\"geeksforgeeks5.pdf\",\"geeksforgeeks6.pdf\",\"geeksforgeeks7.pdf\",\"geeksforgeeks8.pdf\",\"geeksforgeeks9.pdf\",\"geeksforgeeks10.pdf\",\"geeksforgeeks11.pdf\",\"geeksforgeeks12.pdf\"]  # Replace with your actual file paths\n","\n","# Initialize an empty list to store all query data\n","all_query_data = []\n","\n","# Iterate through each file path\n","for file_path in file_paths:\n","    # Initialize an empty list to store query data for the current file\n","    query_data = []\n","    print(file_path)\n","    #convert pdf to json\n","    json_data = pdf_to_json(file_path)\n","\n","    # Loop 10 times to generate 10 summarization records for each file\n","    for i in range(1):\n","        i+1\n","        prompt_template= f\"\"\"\n","        For given {json_data}, create 4 subject summary to aid examination prepration.\n","        \"\"\"\n","        query = get_completion([{'role':'user', 'content':prompt_template}] )\n","        print(query)\n","\n","        # Append the query to the query_data list for the current file\n","        new_records = json.loads(query)\n","        append_to_json(\"my_data.json\", new_records)\n","\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"tQEys_dOfpfT","outputId":"9e0e4c87-9990-4dd9-c6ab-903c8cbc4bec"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["geeksforgeeks0.pdf\n","[\n","  {\n","    \"instruction\": \"Summarize the concept of artificial neural networks\",\n","    \"input_content\": \"Artificial neural networks are built on the principles of the structure and operation of human neurons. They consist of input layers, hidden layers, and output layers. Neurons in the hidden layer receive information from the previous layer, compute a weighted total, and pass it on to the next layer. The weights of the connections between neurons are adjusted during training to improve the model's performance.\",\n","    \"expected_output\": \"Artificial neural networks are modeled after human neurons and consist of input, hidden, and output layers. Neurons in the hidden layer receive input from the previous layer, calculate a weighted total, and pass it to the next layer. The weights of the connections between neurons are adjusted during training to enhance the model's performance.\"\n","  },\n","  {\n","    \"instruction\": \"Explain the structure of an artificial neural network\",\n","    \"input_content\": \"An artificial neural network is composed of artificial neurons arranged in layers. It typically has an input layer, one or more hidden layers, and an output layer. Each neuron receives input from the previous layer or the input layer, and its output becomes the input for neurons in the next layer. The final layer produces the network's output.\",\n","    \"expected_output\": \"An artificial neural network consists of layers of artificial neurons. It usually includes an input layer, hidden layers, and an output layer. Neurons in each layer receive input from the previous layer or the input layer, and their outputs become inputs for neurons in the next layer. The final layer produces the network's output.\"\n","  },\n","  {\n","    \"instruction\": \"Differentiate between Machine Learning and Deep Learning\",\n","    \"input_content\": \"Machine Learning and Deep Learning are both subsets of artificial intelligence. They have similarities and differences. Machine Learning applies statistical algorithms to learn patterns and relationships in a dataset, while Deep Learning uses artificial neural network architecture for the same purpose. Machine Learning can work with smaller datasets, while Deep Learning requires larger volumes of data. Machine Learning is better for low-label tasks, while Deep Learning excels in complex tasks like image processing and natural language processing.\",\n","    \"expected_output\": \"Machine Learning and Deep Learning are subsets of artificial intelligence. Machine Learning uses statistical algorithms to learn patterns and relationships in data, while Deep Learning utilizes artificial neural networks. Machine Learning can operate with smaller datasets, while Deep Learning requires larger volumes of data. Machine Learning is suitable for low-label tasks, while Deep Learning is more effective for complex tasks such as image processing and natural language processing.\"\n","  },\n","  {\n","    \"instruction\": \"Discuss the differences between Machine Learning and Deep Learning\",\n","    \"input_content\": \"Machine Learning and Deep Learning have differences in terms of dataset size, task suitability, training time, feature extraction, complexity, and computing power requirements. Machine Learning can work with smaller datasets, while Deep Learning requires larger volumes of data. Machine Learning is better for low-label tasks, while Deep Learning excels in complex tasks like image processing. Machine Learning takes less time to train models, while Deep Learning requires more time. Machine Learning relies on manually extracted features, while Deep Learning automatically extracts relevant features. Machine Learning models are less complex and easier to interpret, while Deep Learning models are more complex and their interpretations are not straightforward. Machine Learning can work on CPUs or with less computing power, while Deep Learning requires high-performance computers with GPUs.\",\n","    \"expected_output\": \"Machine Learning and Deep Learning differ in terms of dataset size, task suitability, training time, feature extraction, complexity, and computing power requirements. Machine Learning can handle smaller datasets, while Deep Learning requires larger volumes of data. Machine Learning is suitable for low-label tasks, while Deep Learning is particularly effective for complex tasks like image processing. Machine Learning models have shorter training times compared to Deep Learning models. Machine Learning relies on manual feature extraction, whereas Deep Learning automatically extracts relevant features. Machine Learning models are less complex and easier to interpret, while Deep Learning models are more complex and their interpretations are not as straightforward. Machine Learning can work on CPUs or with lower computing power, while Deep Learning requires high-performance computers with GPUs.\"\n","  }\n","]\n","New records appended to my_data.json\n","geeksforgeeks1.pdf\n","[\n","  {\n","    \"instruction\": \"Summarize the concept of Deep Learning\",\n","    \"input_content\": \"Deep learning is a branch of machine learning that is based on artificial neural networks. It involves the use of deep neural networks to model and solve complex problems. Deep learning algorithms can automatically learn and improve from data without the need for manual feature engineering.\",\n","    \"expected_output\": \"Deep learning is a subfield of machine learning that utilizes artificial neural networks to model and solve intricate problems. It is characterized by the use of deep neural networks, which can learn complex representations of data by discovering hierarchical patterns and features. Deep learning algorithms have the advantage of automatically learning and improving from data, eliminating the need for manual feature engineering.\"\n","  },\n","  {\n","    \"instruction\": \"Explain the architecture and functioning of artificial neural networks\",\n","    \"input_content\": \"Artificial neural networks (ANNs) are the building blocks of deep learning. They consist of layers of interconnected nodes called neurons that process and learn from input data. Each neuron receives input from the previous layer or the input layer and produces output that becomes the input for the next layer.\",\n","    \"expected_output\": \"Artificial neural networks (ANNs) form the foundation of deep learning. They are composed of interconnected nodes, known as neurons, organized into layers. Neurons receive input from the previous layer or the input layer and generate output that serves as input for the subsequent layer. This process continues until the final layer produces the network's output. The layers of an ANN transform input data through nonlinear transformations, enabling the network to learn complex representations of the input data.\"\n","  },\n","  {\n","    \"instruction\": \"Discuss the applications of Deep Learning\",\n","    \"input_content\": \"Deep learning has achieved significant success in various fields, including image recognition, natural language processing, speech recognition, and recommendation systems. It is widely used in applications such as computer vision, language translation, sentiment analysis, and robotics.\",\n","    \"expected_output\": \"Deep learning has made remarkable advancements in diverse domains, such as image recognition, natural language processing, speech recognition, and recommendation systems. It finds extensive applications in computer vision tasks, language translation systems, sentiment analysis, and robotics. Deep learning algorithms like Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Deep Belief Networks (DBNs) are commonly employed in these applications.\"\n","  },\n","  {\n","    \"instruction\": \"Describe the different types of machine learning techniques used in Deep Learning\",\n","    \"input_content\": \"Deep learning incorporates various machine learning techniques, including supervised learning, unsupervised learning, and reinforcement learning. Each technique serves different purposes, such as prediction and classification, pattern discovery and clustering, and decision-making in an environment.\",\n","    \"expected_output\": \"Deep learning encompasses multiple machine learning techniques, namely supervised learning, unsupervised learning, and reinforcement learning. Supervised learning involves predicting or classifying data based on labeled datasets, while unsupervised learning focuses on discovering patterns or clustering unlabeled datasets. Reinforcement learning enables an agent to make decisions in an environment to maximize a reward signal. Deep learning algorithms like convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are utilized for supervised tasks, autoencoders and generative models for unsupervised tasks, and deep Q networks and deep deterministic policy gradient (DDPG) for reinforcement learning tasks.\"\n","  }\n","]\n","New records appended to my_data.json\n","geeksforgeeks2.pdf\n","[\n","  {\n","    \"instruction\": \"Summarize the types of neural networks in deep learning\",\n","    \"input_content\": \"Deep learning models are able to automatically learn features from the data, which makes them well-suited for tasks such as image recognition, speech recognition, and natural language processing. The most widely used architectures in deep learning are feedforward neural networks, convolutional neural networks (CNNs), and recurrent neural networks (RNNs).\",\n","    \"expected_output\": \"Deep learning models, such as feedforward neural networks, convolutional neural networks (CNNs), and recurrent neural networks (RNNs), are widely used for tasks like image recognition, speech recognition, and natural language processing. These networks enable automatic feature learning from data.\"\n","  },\n","  {\n","    \"instruction\": \"Summarize the applications of deep learning in computer vision\",\n","    \"input_content\": \"Deep learning models can enable machines to identify and understand visual data in computer vision tasks. Some of the main applications of deep learning in computer vision include object detection and recognition, image classification, and image segmentation.\",\n","    \"expected_output\": \"Deep learning models in computer vision enable machines to perform tasks like object detection and recognition, image classification, and image segmentation. These applications find use in self-driving cars, surveillance, robotics, medical imaging, quality control, and image retrieval.\"\n","  },\n","  {\n","    \"instruction\": \"Summarize the applications of deep learning in natural language processing (NLP)\",\n","    \"input_content\": \"Deep learning models can enable machines to understand and generate human language in NLP tasks. Some of the main applications of deep learning in NLP include automatic text generation, language translation, sentiment analysis, and speech recognition.\",\n","    \"expected_output\": \"Deep learning models in NLP enable machines to perform tasks like automatic text generation, language translation, sentiment analysis, and speech recognition. These applications have uses in areas such as text summarization, language translation, customer service, social media monitoring, and voice-controlled devices.\"\n","  },\n","  {\n","    \"instruction\": \"Summarize the applications of deep learning in reinforcement learning\",\n","    \"input_content\": \"Deep learning models can be used in reinforcement learning to train agents to take actions in an environment to maximize a reward. Some of the main applications of deep learning in reinforcement learning include game playing, robotics, and control systems.\",\n","    \"expected_output\": \"Deep learning models in reinforcement learning are used to train agents to maximize rewards by taking actions in an environment. Applications include game playing (e.g., beating human experts at games like Go and Chess), robotics (e.g., complex task performance), and control systems (e.g., power grids, traffic management, and supply chain optimization).\"\n","  }\n","]\n","New records appended to my_data.json\n","geeksforgeeks3.pdf\n","[\n","  {\n","    \"instruction\": \"Summarize the concept of Artificial Intelligence\",\n","    \"input_content\": \"Artificial Intelligence (AI) is the incorporation of human intelligence into machines through a set of rules or algorithms. AI focuses on learning, reasoning, and self-correction to achieve maximum efficiency.\",\n","    \"expected_output\": \"Artificial Intelligence (AI) is the study of training machines to mimic human brain and thinking capabilities. It involves the development of algorithms that enable machines to learn, reason, and correct themselves. AI aims to incorporate human-like intelligence into machines.\"\n","  },\n","  {\n","    \"instruction\": \"Summarize the concept of Machine Learning\",\n","    \"input_content\": \"Machine Learning (ML) is a subset of AI that allows systems to learn automatically from experiences and improve without explicit programming. ML focuses on accessing and analyzing data to identify patterns and make better decisions.\",\n","    \"expected_output\": \"Machine Learning (ML) is a branch of AI that enables systems to learn from data without being explicitly programmed. It involves the development of algorithms that analyze data and identify patterns. ML aims to improve system performance through experience and pattern recognition.\"\n","  },\n","  {\n","    \"instruction\": \"Summarize the concept of Deep Learning\",\n","    \"input_content\": \"Deep Learning (DL) is a sub-part of Machine Learning that uses neural networks to mimic human brain behavior. DL works with larger datasets and focuses on information processing patterns to classify data.\",\n","    \"expected_output\": \"Deep Learning (DL) is a subset of Machine Learning that utilizes neural networks to imitate human brain functionality. DL algorithms analyze data using deep neural networks and classify information based on patterns. DL is particularly effective with large datasets.\"\n","  },\n","  {\n","    \"instruction\": \"Summarize the differences between Artificial Intelligence, Machine Learning, and Deep Learning\",\n","    \"input_content\": \"Artificial Intelligence (AI) encompasses both Machine Learning (ML) and Deep Learning (DL). AI is the broader family, ML is a subset of AI, and DL is a subset of ML. AI focuses on decision making, ML allows systems to learn from data, and DL uses deep neural networks for data analysis.\",\n","    \"expected_output\": \"Artificial Intelligence (AI) is the overall concept that includes both Machine Learning (ML) and Deep Learning (DL). ML is a subset of AI that enables systems to learn from data, while DL is a subset of ML that utilizes deep neural networks for data analysis. AI focuses on decision making, ML focuses on learning from data, and DL focuses on analyzing data using deep neural networks.\"\n","  }\n","]\n","New records appended to my_data.json\n","geeksforgeeks4.pdf\n","[\n","    {\n","        \"instruction\": \"Summarize the concept of Artificial Intelligence (AI)\",\n","        \"input_content\": \"AI refers to the development of computer systems that can perform tasks that would normally require human intelligence. Some examples of AI include:\",\n","        \"expected_output\": \"Artificial Intelligence (AI) involves the development of computer systems capable of performing tasks that typically require human intelligence. Examples of AI applications include speech recognition systems used in self-driving cars, security systems, and medical imaging. AI algorithms are also used for personalized recommendations on e-commerce sites and streaming services, predictive maintenance in various industries, medical diagnosis systems, autonomous vehicles, fraud detection in financial institutions, image recognition in photo organization and security systems, natural language processing in chatbots and language translation systems, and predictive analytics in healthcare and marketing.\"\n","    },\n","    {\n","        \"instruction\": \"Summarize the concept of Machine Learning\",\n","        \"input_content\": \"Machine Learning is a subset of AI that focuses on enabling computer systems to learn from data and improve their performance without being explicitly programmed. Some examples of Machine Learning applications include:\",\n","        \"expected_output\": \"Machine Learning is a branch of AI that enables computer systems to learn from data and improve their performance without explicit programming. Examples of Machine Learning applications include speech recognition systems, personalized recommendations on e-commerce sites and streaming services, predictive maintenance systems, medical diagnosis systems, autonomous vehicles, fraud detection systems, image recognition applications, natural language processing systems, and predictive analytics in various industries.\"\n","    },\n","    {\n","        \"instruction\": \"Summarize the concept of Deep Learning\",\n","        \"input_content\": \"Deep Learning is a subfield of Machine Learning that focuses on training artificial neural networks with multiple layers to learn and make predictions. Some examples of Deep Learning applications include:\",\n","        \"expected_output\": \"Deep Learning is a subfield of Machine Learning that involves training artificial neural networks with multiple layers to learn and make predictions. Examples of Deep Learning applications include speech recognition systems, image and video classification, natural language processing, autonomous vehicles, and medical diagnosis systems.\"\n","    },\n","    {\n","        \"instruction\": \"Summarize the applications of AI, Machine Learning, and Deep Learning across various industries\",\n","        \"input_content\": \"AI, Machine Learning, and Deep Learning have numerous applications across various industries. Some common examples include:\",\n","        \"expected_output\": \"AI, Machine Learning, and Deep Learning have wide-ranging applications across industries. Examples include speech recognition systems used in self-driving cars, security systems, and medical imaging, personalized recommendations on e-commerce sites and streaming services, predictive maintenance systems, medical diagnosis systems, autonomous vehicles, fraud detection in financial institutions, image recognition in photo organization and security systems, natural language processing in chatbots and language translation systems, predictive analytics in healthcare and marketing, and deep learning applications such as speech recognition, image and video classification, natural language processing, autonomous vehicles, and medical diagnosis systems.\"\n","    }\n","]\n","New records appended to my_data.json\n","geeksforgeeks5.pdf\n","[\n","    {\n","        \"instruction\": \"Summarize the role and responsibilities of an AI Engineer\",\n","        \"input_content\": \"AI Engineers design, develop, and implement artificial intelligence (AI) systems and solutions. They are responsible for tasks such as designing and developing AI algorithms, analyzing and interpreting data, training and evaluating AI models, deploying and maintaining AI models, collaborating with stakeholders, conducting research and innovation, and communicating the results of their work.\",\n","        \"expected_output\": \"AI Engineers are professionals who design, develop, and implement AI systems and solutions. They are responsible for tasks such as designing and developing AI algorithms, analyzing and interpreting data, training and evaluating AI models, deploying and maintaining AI models, collaborating with stakeholders, conducting research and innovation, and communicating the results of their work.\"\n","    },\n","    {\n","        \"instruction\": \"Summarize the role and responsibilities of a Machine Learning Engineer\",\n","        \"input_content\": \"Machine Learning Engineers design, develop, and implement machine learning (ML) systems and solutions. They are responsible for tasks such as designing and developing ML algorithms, analyzing and interpreting data, training and evaluating ML models, deploying and maintaining ML models, collaborating with stakeholders, conducting research and innovation, and communicating the results of their work.\",\n","        \"expected_output\": \"Machine Learning Engineers are professionals who design, develop, and implement ML systems and solutions. They are responsible for tasks such as designing and developing ML algorithms, analyzing and interpreting data, training and evaluating ML models, deploying and maintaining ML models, collaborating with stakeholders, conducting research and innovation, and communicating the results of their work.\"\n","    },\n","    {\n","        \"instruction\": \"Summarize the role and responsibilities of a Deep Learning Engineer\",\n","        \"input_content\": \"Deep Learning Engineers design, develop, and implement deep learning (DL) systems and solutions. They are responsible for tasks such as designing and developing DL algorithms, analyzing and interpreting data, training and evaluating DL models, deploying and maintaining DL models, collaborating with stakeholders, conducting research and innovation, and communicating the results of their work.\",\n","        \"expected_output\": \"Deep Learning Engineers are professionals who design, develop, and implement DL systems and solutions. They are responsible for tasks such as designing and developing DL algorithms, analyzing and interpreting data, training and evaluating DL models, deploying and maintaining DL models, collaborating with stakeholders, conducting research and innovation, and communicating the results of their work.\"\n","    },\n","    {\n","        \"instruction\": \"Differentiate between the roles of AI Engineer, Machine Learning Engineer, and Deep Learning Engineer\",\n","        \"input_content\": \"AI Engineers, Machine Learning Engineers, and Deep Learning Engineers have overlapping roles and responsibilities, but there are some key differences. AI Engineers focus on designing and implementing AI systems and solutions, while Machine Learning Engineers specifically work with ML systems and solutions. Deep Learning Engineers specialize in deep learning algorithms and systems. Additionally, the level of complexity and scale of the models and algorithms they work with may vary.\",\n","        \"expected_output\": \"AI Engineers, Machine Learning Engineers, and Deep Learning Engineers have overlapping roles and responsibilities, but there are some key differences. AI Engineers focus on designing and implementing AI systems and solutions, while Machine Learning Engineers specifically work with ML systems and solutions. Deep Learning Engineers specialize in deep learning algorithms and systems. Additionally, the level of complexity and scale of the models and algorithms they work with may vary.\"\n","    }\n","]\n","New records appended to my_data.json\n","geeksforgeeks6.pdf\n","[\n","  {\n","    \"instruction\": \"Summarize the concept of Artificial Neural Networks (ANN)\",\n","    \"input_content\": \"Artificial Neural Networks (ANN) are a type of neural network based on a Feed-Forward strategy. They pass information through nodes continuously until it reaches the output node. ANN has the ability to learn irrespective of the type of data and is commonly used in financial time series forecasting.\",\n","    \"expected_output\": \"Artificial Neural Networks (ANN) are a type of neural network that uses a Feed-Forward strategy to pass information through nodes until it reaches the output node. ANN has the advantage of being able to learn from different types of data, whether linear or non-linear. It is particularly useful in financial time series forecasting.\"\n","  },\n","  {\n","    \"instruction\": \"Summarize the concept of Biological Neural Networks (BNN)\",\n","    \"input_content\": \"Biological Neural Networks (BNN) are structures that consist of synapses, dendrites, cell bodies, and axons. Processing in BNN is carried out by neurons. Dendrites receive signals from other neurons, the cell body sums all incoming signals, and the axon transmits signals to other cells.\",\n","    \"expected_output\": \"Biological Neural Networks (BNN) are structures composed of synapses, dendrites, cell bodies, and axons. Neurons in BNN receive signals through dendrites, sum them in the cell body, and transmit signals through the axon to other cells. BNN is capable of processing highly complex parallel inputs.\"\n","  },\n","  {\n","    \"instruction\": \"Explain the differences between Artificial Neural Networks (ANN) and Biological Neural Networks (BNN)\",\n","    \"input_content\": \"Artificial Neural Networks (ANNs) and Biological Neural Networks (BNNs) share similar basic components but have some differences. Neurons in BNNs are more complex and diverse than ANNs. BNNs have flexible connections between neurons, while ANNs have fixed connections determined by weights. Neural pathways in BNNs are highly modifiable, while in ANNs, they are predetermined by the network architecture.\",\n","    \"expected_output\": \"Artificial Neural Networks (ANNs) and Biological Neural Networks (BNNs) have similarities in their basic components, but there are significant differences. BNN neurons are more complex and diverse compared to ANNs. Connections between BNN neurons are flexible, while ANNs have fixed connections determined by weights. Neural pathways in BNNs are highly modifiable based on experience and learning, whereas ANNs have predetermined pathways based on network architecture.\"\n","  },\n","  {\n","    \"instruction\": \"Summarize the differences in parameters, computing, reliability, expertise, operating environment, and fault tolerance between ANN and BNN\",\n","    \"input_content\": \"ANN and BNN differ in parameters, computing, reliability, expertise, operating environment, and fault tolerance. ANN processes very precise structures and formatted data, while BNN can tolerate ambiguity. ANN has a complex processor with high-speed computing, while BNN has a few simple processors with low-speed computing. ANN has separate memory from the processor, while BNN has integrated memory. ANN is suitable for numerical and symbolic manipulations, while BNN is suited for perceptual problems. ANN operates in well-defined environments, while BNN operates in poorly defined environments. ANN has potential fault tolerance, while BNN's performance is degraded even on partial damage.\",\n","    \"expected_output\": \"Artificial Neural Networks (ANN) and Biological Neural Networks (BNN) differ in parameters, computing, reliability, expertise, operating environment, and fault tolerance. ANN processes very precise structures and formatted data, while BNN can tolerate ambiguity. ANN has a complex processor with high-speed computing, while BNN has a few simple processors with low-speed computing. ANN has separate memory from the processor, while BNN has integrated memory. ANN is suitable for numerical and symbolic manipulations, while BNN is suited for perceptual problems. ANN operates in well-defined environments, while BNN operates in poorly defined environments. ANN has potential fault tolerance, while BNN's performance is degraded even on partial damage.\"\n","  }\n","]\n","New records appended to my_data.json\n","geeksforgeeks7.pdf\n","[\n","    {\n","        \"instruction\": \"Summarize the concept of hyperparameter tuning\",\n","        \"input_content\": \"Hyperparameter tuning is the process of selecting the optimal values for a machine learning model's hyperparameters. These hyperparameters control the learning process of the model, such as the learning rate, the number of neurons in a neural network, or the kernel size in a support vector machine.\",\n","        \"expected_output\": \"Hyperparameter tuning involves finding the best values for a machine learning model's hyperparameters. These parameters, like learning rate and number of neurons, affect how the model learns. By selecting the right hyperparameter values, we can optimize the model's performance on a given task.\"\n","    },\n","    {\n","        \"instruction\": \"Summarize the importance of hyperparameters in machine learning models\",\n","        \"input_content\": \"Hyperparameters are configuration variables that control the learning process of a machine learning model. They have a significant impact on the model's accuracy, generalization, and other metrics.\",\n","        \"expected_output\": \"Hyperparameters play a crucial role in machine learning models. They control how the model learns and can greatly influence its accuracy, generalization, and overall performance. Selecting the right hyperparameter values is essential for achieving optimal results.\"\n","    },\n","    {\n","        \"instruction\": \"Summarize the different types of hyperparameters in neural networks\",\n","        \"input_content\": \"Neural networks have several essential hyperparameters that need to be adjusted, including learning rate, epochs, number of layers, number of nodes per layer, architecture, and activation function.\",\n","        \"expected_output\": \"In neural networks, there are various hyperparameters that require adjustment. These include the learning rate, number of epochs, number of layers, number of nodes per layer, architecture, and activation function. Each of these hyperparameters plays a vital role in determining the network's performance and complexity.\"\n","    },\n","    {\n","        \"instruction\": \"Summarize the impact of different hyperparameters on neural network performance\",\n","        \"input_content\": \"Different hyperparameters in neural networks, such as learning rate, epochs, number of layers, number of nodes per layer, architecture, and activation function, can affect the network's performance and learning ability.\",\n","        \"expected_output\": \"The performance and learning ability of a neural network are influenced by various hyperparameters. The learning rate determines the convergence speed, the number of epochs affects overfitting, the number of layers and nodes per layer impact complexity, the architecture determines the overall structure, and the activation function introduces non-linearity. Choosing the right values for these hyperparameters is crucial for achieving optimal neural network performance.\"\n","    }\n","]\n","New records appended to my_data.json\n","geeksforgeeks8.pdf\n","[\n","    {\n","        \"instruction\": \"Summarize the concept of Hyperparameter Tuning\",\n","        \"input_content\": \"Hyperparameter Tuning involves finding the best combination of parameters for a model. The three main strategies for Hyperparameter Tuning are GridSearchCV, RandomizedSearchCV, and Bayesian Optimization.\",\n","        \"expected_output\": \"Hyperparameter Tuning is the process of finding the optimal combination of parameters for a model. It can be treated as a search problem and is crucial for improving model performance. The three main strategies for Hyperparameter Tuning are GridSearchCV, which exhaustively searches through all possible combinations of hyperparameters; RandomizedSearchCV, which selects values at random; and Bayesian Optimization, which uses a probabilistic model to select the most promising hyperparameter combination.\"\n","    },\n","    {\n","        \"instruction\": \"Explain the drawbacks of GridSearchCV\",\n","        \"input_content\": \"GridSearchCV is an exhaustive approach to Hyperparameter Tuning. However, it has certain limitations.\",\n","        \"expected_output\": \"GridSearchCV, while effective in identifying the ideal hyperparameter combination, has the drawback of being computationally expensive. It evaluates all intermediate combinations of hyperparameters, which can be time-consuming and require a lot of processing power. Additionally, GridSearchCV may not be feasible if there are a large number of potential combinations or if certain combinations are not available.\"\n","    },\n","    {\n","        \"instruction\": \"Describe the advantages of RandomizedSearchCV\",\n","        \"input_content\": \"RandomizedSearchCV is an alternative approach to Hyperparameter Tuning. Highlight its benefits.\",\n","        \"expected_output\": \"RandomizedSearchCV offers several advantages over GridSearchCV. It selects hyperparameter values at random, reducing unnecessary computation. This approach often produces comparable results faster than GridSearchCV. RandomizedSearchCV is particularly useful when the ideal hyperparameter combination is not known in advance or when there are a large number of potential combinations. It provides a more efficient and flexible way to explore the hyperparameter space.\"\n","    },\n","    {\n","        \"instruction\": \"Explain the concept of Bayesian Optimization in Hyperparameter Tuning\",\n","        \"input_content\": \"Bayesian Optimization is another strategy for Hyperparameter Tuning. Elaborate on how it works.\",\n","        \"expected_output\": \"Bayesian Optimization treats the search for optimal hyperparameters as an optimization problem. It considers previous evaluation results and uses a probabilistic function to select the hyperparameter combination that is likely to yield the best results. Bayesian Optimization uses a surrogate model, such as Gaussian processes or tree-structured Parzen estimators, to estimate the probability of a hyperparameter combination's objective function result. This method efficiently discovers a good hyperparameter combination in relatively few iterations. However, implementing Bayesian Optimization can be complex, and it requires an understanding of the underlying probabilistic model.\"\n","    }\n","]\n","New records appended to my_data.json\n","geeksforgeeks9.pdf\n","[\n","    {\n","        \"instruction\": \"Summarize the challenges in deep learning\",\n","        \"input_content\": \"Deep learning has made significant advancements in various fields, but there are still some challenges that need to be addressed. Here are some of the main challenges in deep learning:\",\n","        \"expected_output\": \"The challenges in deep learning include data availability, computational resources, time-consuming training, interpretability issues, and overfitting.\"\n","    },\n","    {\n","        \"instruction\": \"Summarize the advantages of deep learning\",\n","        \"input_content\": \"Deep learning offers several advantages over traditional machine learning methods. Some of the advantages include:\",\n","        \"expected_output\": \"The advantages of deep learning include high accuracy, automated feature engineering, scalability, flexibility, and continual improvement.\"\n","    },\n","    {\n","        \"instruction\": \"Summarize the disadvantages of deep learning\",\n","        \"input_content\": \"While deep learning has many advantages, it also has some drawbacks that need to be considered. Some of the disadvantages include:\",\n","        \"expected_output\": \"The disadvantages of deep learning include high computational requirements, the need for large amounts of labeled data, interpretability challenges, and the risk of overfitting.\"\n","    },\n","    {\n","        \"instruction\": \"Summarize the key considerations when deciding to use deep learning\",\n","        \"input_content\": \"When deciding whether to use deep learning for a specific task, there are certain factors that need to be carefully considered. Some of the key considerations include:\",\n","        \"expected_output\": \"The key considerations when deciding to use deep learning include the advantages of high accuracy and scalability, as well as the disadvantages of high computational requirements, the need for labeled data, and interpretability challenges.\"\n","    }\n","]\n","New records appended to my_data.json\n","geeksforgeeks10.pdf\n","[\n","  {\n","    \"instruction\": \"Summarize the concept of Machine Learning\",\n","    \"input_content\": \"Examples of Machine Learning: Machine Learning (ML) is a subset of Artificial Intelligence (AI) that involves the use of algorithms and statistical models to allow a computer system to 'learn' from data and improve its performance over time, without being explicitly programmed to do so.\",\n","    \"expected_output\": \"Machine Learning (ML) is a subset of Artificial Intelligence (AI) that utilizes algorithms and statistical models to enable computer systems to learn from data and enhance their performance without explicit programming. ML systems can improve their capabilities over time through data analysis and pattern recognition.\"\n","  },\n","  {\n","    \"instruction\": \"Summarize the applications of Machine Learning in image recognition\",\n","    \"input_content\": \"Examples of Machine Learning: Image recognition: Machine learning algorithms are used in image recognition systems to classify images based on their contents. These systems are used in a variety of applications, such as self-driving cars, security systems, and medical imaging.\",\n","    \"expected_output\": \"Machine Learning (ML) algorithms play a crucial role in image recognition systems, enabling the classification of images based on their content. This technology finds applications in diverse areas, including self-driving cars, security systems, and medical imaging.\"\n","  },\n","  {\n","    \"instruction\": \"Summarize the applications of Machine Learning in natural language processing (NLP)\",\n","    \"input_content\": \"Examples of Machine Learning: Natural language processing (NLP): Machine learning algorithms are used in NLP systems to understand and generate human language. These systems are used in chatbots, virtual assistants, and other applications that involve natural language interactions.\",\n","    \"expected_output\": \"Machine Learning (ML) algorithms are extensively employed in Natural Language Processing (NLP) systems to comprehend and generate human language. These systems are utilized in chatbots, virtual assistants, and various other applications that involve interactions through natural language.\"\n","  },\n","  {\n","    \"instruction\": \"Summarize the applications of Machine Learning in recommendation systems\",\n","    \"input_content\": \"Examples of Machine Learning: Recommendation systems: Machine learning algorithms are used in recommendation systems to analyze user data and recommend products or services that are likely to be of interest. These systems are used in e-commerce sites, streaming services, and other applications.\",\n","    \"expected_output\": \"Machine Learning (ML) algorithms play a vital role in recommendation systems, where they analyze user data to suggest products or services that align with their interests. These systems find applications in e-commerce platforms, streaming services, and various other domains.\"\n","  }\n","]\n","New records appended to my_data.json\n","geeksforgeeks11.pdf\n","[\n","    {\n","        \"instruction\": \"Summarize the hyperparameters in Support Vector Machine (SVM)\",\n","        \"input_content\": \"Hyperparameters in Support Vector Machine (SVM) include C, kernel, and gamma.\",\n","        \"expected_output\": \"Support Vector Machine (SVM) has three important hyperparameters: C, which controls the trade-off between margin and training errors; kernel, which defines the similarity between data points; and gamma, which determines the influence of support vectors on the decision boundary.\"\n","    },\n","    {\n","        \"instruction\": \"Summarize the hyperparameters in XGBoost\",\n","        \"input_content\": \"Hyperparameters in XGBoost include learning_rate, n_estimators, max_depth, min_child_weight, and subsample.\",\n","        \"expected_output\": \"XGBoost has five essential hyperparameters: learning_rate, which determines the step size during training; n_estimators, which determines the number of boosting trees; max_depth, which controls the maximum depth of each tree; min_child_weight, which determines the minimum sum of instance weight needed in a child node; and subsample, which determines the percentage of rows used for each tree construction.\"\n","    },\n","    {\n","        \"instruction\": \"Provide examples of model hyperparameters\",\n","        \"input_content\": \"Examples of model hyperparameters include penalty in Logistic Regression Classifier, number of trees and depth of trees in Random Forests, learning rate in neural networks, number of clusters in clustering algorithms, and k in k-nearest neighbors.\",\n","        \"expected_output\": \"Some examples of model hyperparameters are the penalty in Logistic Regression Classifier (L1 or L2 regularization), the number of trees and depth of trees in Random Forests, the learning rate in neural networks, the number of clusters in clustering algorithms, and the value of k in k-nearest neighbors.\"\n","    },\n","    {\n","        \"instruction\": \"Summarize the importance of hyperparameter tuning\",\n","        \"input_content\": \"Hyperparameter tuning is crucial for optimizing the performance of machine learning models.\",\n","        \"expected_output\": \"Hyperparameter tuning plays a vital role in optimizing the performance of machine learning models. By adjusting hyperparameters, such as regularization strength, learning rate, and tree depth, the model can achieve better accuracy, prevent overfitting, and capture complex relationships in the data. Proper hyperparameter tuning is essential for building robust and accurate machine learning models.\"\n","    }\n","]\n","New records appended to my_data.json\n","geeksforgeeks12.pdf\n","[\n","    {\n","        \"instruction\": \"Summarize the concept of Deep Learning\",\n","        \"input_content\": \"Deep Learning is a type of Machine Learning that uses artificial neural networks with multiple layers to learn and make decisions.\",\n","        \"expected_output\": \"Deep Learning is a subset of Machine Learning that employs artificial neural networks with multiple layers to learn and make decisions.\"\n","    },\n","    {\n","        \"instruction\": \"Summarize the applications of Deep Learning in image and video recognition\",\n","        \"input_content\": \"Deep learning algorithms are used in image and video recognition systems to classify and analyze visual data. These systems are used in self-driving cars, security systems, and medical imaging.\",\n","        \"expected_output\": \"Deep Learning is applied in image and video recognition systems to classify and analyze visual data. It finds applications in self-driving cars, security systems, and medical imaging.\"\n","    },\n","    {\n","        \"instruction\": \"Summarize the applications of Deep Learning in natural language processing\",\n","        \"input_content\": \"Deep learning algorithms are used for tasks such as sentiment analysis, language translation, and text generation.\",\n","        \"expected_output\": \"Deep Learning is utilized in natural language processing tasks, including sentiment analysis, language translation, and text generation.\"\n","    },\n","    {\n","        \"instruction\": \"Summarize the applications of Deep Learning in fraud detection\",\n","        \"input_content\": \"Deep learning algorithms are used in financial transactions to detect patterns of behavior indicative of fraud.\",\n","        \"expected_output\": \"Deep Learning is employed in financial transactions to identify patterns of behavior that suggest fraudulent activity.\"\n","    }\n","]\n","New records appended to my_data.json\n"]}]},{"cell_type":"code","source":["def get_completion_MCQ(prompt):\n","  messages=[{'role':'system', 'content':r\"\"\"\n","  As a machine learning education specialist, your expertise is pivotal in deepening the comprehension of complex machine learning concepts for both educators and students.\n","\n","  Your role entails:\n","\n","  Crafting Insightful Questions: Develop thought-provoking questions that explore the intricacies of machine learning topics.\n","  Providing Detailed Explanations: Deliver comprehensive answers to these questions, elucidating the underlying technical principles.\n","  Assisting in Exam Preparation: Support educators in formulating sophisticated exam and quiz questions, including MCQs, accompanied by thorough explanations.\n","  Summarizing Course Material: Distill key information from course materials, articulating complex ideas within the context of advanced machine learning practices.\n","  Generating MCQs: Create MCQs for each machine learning topic, comprising a question, four choices (A-D), and the correct answer, along with a rationale explaining the answer.\n","\n","  Objective:\n","  Your primary goal is to compile an Instruction Dataset in a structured JSON format. This dataset should integrate specific instructions, relevant content on various machine learning topics, expected outputs with expert-level explanations, and MCQs designed to evaluate comprehension.\n","  Dataset Structure:\n","\n","  Instruction: Specifies the task, such as summarizing, explaining, or creating MCQs.\n","  Input Content: Provides brief summary of context or inputs for the task. Can be left blank if not needed.\n","  Expected Output: The detailed answer or outcome produced by the model, potentially an explanation, summary, or an MCQ with its answer and justification.\n","\n","    Each JSON record entries format:\n","    {\n","      \"instruction\": \"Create an MCQ on the importance of cross-validation in machine learning\",\n","      \"input_content\": \"\",\n","      \"expected_output\": {\n","        \"question\": \"What is the primary purpose of cross-validation in machine learning?\",\n","        \"options\": {\n","          \"A\": \"To increase the speed of training models\",\n","          \"B\": \"To prevent overfitting by validating the model with different data subsets\",\n","          \"C\": \"To enhance the model's performance on the training data\",\n","          \"D\": \"To reduce the computational cost of training\"\n","        },\n","        \"correct_answer\": \"B\",\n","        \"explanation\": \"Cross-validation assesses a model's generalization to independent datasets by training and testing on various data segments, effectively preventing overfitting.\"\n","      }\n","    }\n","  \"\"\"}]\n","\n","  messages = messages+ prompt\n","  reponse = openai.ChatCompletion.create(\n","    model=model_engine,\n","    messages=messages,\n","    temperature=0.3)\n","  response = reponse['choices'][0]['message']['content']\n","\n","  return response"],"metadata":{"id":"AAkPk4AC1qW7"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":["###start of MCQ instrucions dataset generation"],"metadata":{"id":"aBW3QmrxDq72"}},{"cell_type":"code","source":["#mass query for MCQ\n","\n","# List of file paths\n","file_paths = [\"geeksforgeeks0.pdf\",\"geeksforgeeks1.pdf\", \"geeksforgeeks2.pdf\", \"geeksforgeeks3.pdf\",\"geeksforgeeks4.pdf\",\"geeksforgeeks5.pdf\",\"geeksforgeeks6.pdf\",\"geeksforgeeks7.pdf\",\"geeksforgeeks8.pdf\",\"geeksforgeeks9.pdf\",\"geeksforgeeks10.pdf\",\"geeksforgeeks11.pdf\",\"geeksforgeeks12.pdf\"]  # Replace with your actual file paths\n","#file_paths = [\"geeksforgeeks4.pdf\"]#, \"geeksforgeeks2.pdf\"]\n","# Initialize an empty list to store all query data\n","all_query_data = []\n","\n","# Iterate through each file path\n","for file_path in file_paths:\n","    # Initialize an empty list to store query data for the current file\n","    query_data = []\n","    print(file_path)\n","    #convert pdf to json\n","    json_data = pdf_to_json(file_path)\n","\n","    # Loop 10 times to generate 10 summarization records for each file\n","    for i in range(1):\n","        i+1\n","\n","        # Get the completion from the API\n","        prompt_template= f\"\"\"\n","        For given {json_data}, create 5 MCQ questions.\n","        \"\"\"\n","        query = get_completion_MCQ([{'role':'user', 'content':prompt_template}] )\n","        print(query)\n","\n","        # Append the query to the query_data list for the current file\n","        new_records = json.loads(query)\n","        append_to_json(\"my_data_MCQ.json\", new_records)"],"metadata":{"id":"EU_Tm3zpFEGg"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":["### creation of apailang/dataset_mcq_table\n","\n"],"metadata":{"id":"1R-V0UuTGvZn"}},{"cell_type":"code","source":["import json\n","import pandas as pd\n","\n","## load from mcq json and change expected_output into a table from nested dict\n","\n","def load_json_and_convert(file_path):\n","    \"\"\"Loads a JSON file and converts \"expected_output\" to a string.\"\"\"\n","\n","    with open(file_path, \"r\") as json_file:\n","        data = json.load(json_file)\n","\n","    for entry in data:\n","        entry[\"question\"] = entry[\"expected_output\"][\"question\"]\n","        entry[\"A\"] = entry[\"expected_output\"][\"options\"][\"A\"]\n","        entry[\"B\"] = entry[\"expected_output\"][\"options\"][\"B\"]\n","        entry[\"C\"] = entry[\"expected_output\"][\"options\"][\"C\"]\n","        entry[\"D\"] = entry[\"expected_output\"][\"options\"][\"D\"]\n","        entry[\"correct_answer\"] = entry[\"expected_output\"][\"correct_answer\"]\n","        entry[\"explanation\"] = entry[\"expected_output\"][\"explanation\"]\n","\n","    return data\n","\n","\n","file_path = \"my_data_MCQ.json\"  # Replace with your actual file path\n","processed_data = load_json_and_convert(file_path)\n","\n","processed_data[0]\n","\n","\n","df = pd.DataFrame(processed_data)\n","\n","\n","# Create a DatasetDict with the \"train\" split\n","dataset_mcq_table = DatasetDict({\n","   \"train\": Dataset.from_pandas(df[:318], split=\"train\"),\n","   \"test\": Dataset.from_pandas(df[318:368], split=\"test\"),\n","   \"val\": Dataset.from_pandas(df[368:418], split=\"val\"),\n","})\n","\n","print(dataset_mcq_table)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"outputId":"2379c597-a327-4ffb-b82e-934a5c7f2759","id":"mZNeV2TDW_Xk"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["DatasetDict({\n","    train: Dataset({\n","        features: ['instruction', 'input_content', 'expected_output', 'question', 'A', 'B', 'C', 'D', 'correct_answer', 'explanation'],\n","        num_rows: 318\n","    })\n","    test: Dataset({\n","        features: ['instruction', 'input_content', 'expected_output', 'question', 'A', 'B', 'C', 'D', 'correct_answer', 'explanation'],\n","        num_rows: 50\n","    })\n","    val: Dataset({\n","        features: ['instruction', 'input_content', 'expected_output', 'question', 'A', 'B', 'C', 'D', 'correct_answer', 'explanation'],\n","        num_rows: 50\n","    })\n","})\n"]}]},{"cell_type":"code","source":["# Push to Hugging Face Hub\n","dataset_mcq_table.push_to_hub(\"apailang/dataset_mcq_table\")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":385,"referenced_widgets":["fe8d245fe09e4852b7f3e37a6505d641","0bbc237ce4ed42caacd2548706421462","d0adaa2d18f34821972a4c7da8ad00a5","4491d84c927648f2a12232281f8f432f","5e90a10d9bbc4f81bfed78be6095c0c9","cc33318e90a7419e902d5e0bb7f1631c","3f39e3abed3a4404a1238c42e5b92a83","4c71d238b8bd4932be832e763b18b7c9","71d2d8a378fb405690004360dfd8369b","8b9cf44aa9504ae8b3797d5838737410","defb1059cc2f44d8812be091633096e5","bd4395a4f8df4770b8ede90cc6946977","589485d7544e446483fc1a3c00808c6a","96335e11b8e94a228af6fa0378b0f880","553d03197e9a49c2b3babd8b07b88d3a","127f503e2064434a80c45ee5c4964c8d","3bcf945f384349cf99fa3f84993c7134","a817e862a2e240a29000852e29bebd4c","c173273f98e9469398b676f0830fe4ba","3aa832fb797842bd9be70bcd39160c90","74640336853b4bb2b2cff91be9407b52","b1bd126a1c814111a032ba1752109f6c","a8b93bb62eca4fe8844ff032c9dd0122","6a935756eee44fbe9aa17f65e5932da5","9323f202e7d0437394e16150e5fbb140","08284f96f55649b2b0bef2721d0bfbd1","97364153a4734cff90126d8ab36ba8a9","902a4c7ef4f445db9d90b29a60ac9fba","6694ed93dbde4ce6a6bdfd8dd2f511f7","33d44efe248a4ba99f263ebb356f2abc","ba817a16d01b402a9ee8e65f1f2ecf1d","2bba8e0b3d03450d9ba2b26d45a02f8f","4f46ba538cec4f87a96fab111688f506","2f52827a49594608a33418a9ea8683b2","ff361df3397d485abde40d86c098b50f","cb0b4f712ef44d0f9ce301a949eacc6a","83db66d1fa1d43f782896143dc8fbfa0","393f21ef86d24e4a9211437ba48c8fac","cfd10f20005a483fa879bf391229c454","e48482ff80454cae80f6197184fb133d","9f857551fd0c4429baee3c8b32dbd8ac","9f9a7778f213478f9229501d28865939","da6b7edafc154ebc80b13dea1d6b195a","8e76ecf38de340cfb341581b14f9eb37","14bba26a25c5422eb1e5ab40eedc1039","5b0f1caa88194e8fa43cf7a5fe9ba506","c5898b1e695e4781a76fc712d2fe50ba","b238516174704559b71d21ee507edf18","a42fb59ce2cd453dbb2adacefb987b37","42b55aa5f28e4d2e8781e9a3c6bf7998","9a1a12c269a1408bbe21f8fbbb771664","d51f1b853c9747a0a64dc55e8a1e4b1b","4b49bea5b3cd42c78119fcc1ee8faa5f","a8a41dfed7df484fafc10b0f184f2342","b0d36dfde6e44c29baedf730a76111b2","697095894b0746c19cac9c84ee1299a5","6958b08b55cf4803841921a3a58a25bb","9d5d957377a5447fb2918b977332bb09","b4b38b9be896405ebbc4cfacc8a13c6b","95845f3081e3446dbda4d1ebae411e1e","239d99c569664efa89d9e2c101d9595e","c8b2a0c6fcc8424490580b2ad0d0c55e","449721872331456f8efc6695d81b8e2b","2673cfa4debe4d5aac87e2020944cfb9","368f4b55d6b745f5b8ae735eb1407a20","e0eca158cdfb459fab7c6cb2949a8174"]},"id":"v4t5SzZGcu0Y","outputId":"a1d54a5b-e960-4401-f38b-c42d2f33b329"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_token.py:88: 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":["Uploading the dataset shards:   0%|          | 0/1 [00:00<?, ?it/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"fe8d245fe09e4852b7f3e37a6505d641"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"bd4395a4f8df4770b8ede90cc6946977"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Uploading the dataset shards:   0%|          | 0/1 [00:00<?, ?it/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"a8b93bb62eca4fe8844ff032c9dd0122"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"2f52827a49594608a33418a9ea8683b2"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Uploading the dataset shards:   0%|          | 0/1 [00:00<?, ?it/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"14bba26a25c5422eb1e5ab40eedc1039"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"697095894b0746c19cac9c84ee1299a5"}},"metadata":{}},{"output_type":"execute_result","data":{"text/plain":["CommitInfo(commit_url='https://huggingface.co/datasets/apailang/dataset_mcq_table/commit/c3ce44994e8c5247d3737bdb109704779aea3f1f', commit_message='Upload dataset', commit_description='', oid='c3ce44994e8c5247d3737bdb109704779aea3f1f', pr_url=None, pr_revision=None, pr_num=None)"],"application/vnd.google.colaboratory.intrinsic+json":{"type":"string"}},"metadata":{},"execution_count":32}]},{"cell_type":"markdown","source":["### creation of BitBasher/mini-dataset-978\n"],"metadata":{"id":"QgtJTyELEDRg"}},{"cell_type":"code","source":["#to check no. of records in Json\n","def count_records_in_json(file_path):\n","    with open(file_path, \"r\") as f:\n","        data = json.load(f)\n","\n","    # Determine the type of data structure\n","    if isinstance(data, list):\n","        return len(data)  # Count elements in a list\n","    elif isinstance(data, dict):\n","        return len(data.keys())  # Count keys in a dictionary\n","    else:\n","        raise ValueError(f\"Unsupported JSON data structure: {type(data)}\")\n","\n","# Example usage:\n","file_path = \"combined_data.json\"\n","record_count = count_records_in_json(file_path)\n","print(f\"Number of records in {file_path}: {record_count}\")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"s2ycOmA1BPy0","outputId":"19a64f9f-2eb8-4b36-99b7-f7f129ebf21a"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Number of records in combined_data.json: 978\n"]}]},{"cell_type":"code","source":["## load from mcq json and change expected_output into a string from dict\n","\n","def format_expected_output(expected_output):\n","    \"\"\"Formats the expected_output dictionary into a single string.\"\"\"\n","\n","    if not isinstance(expected_output, dict) or not all(key in expected_output for key in [\"question\", \"options\", \"correct_answer\", \"explanation\"]):\n","        raise ValueError(\"Invalid expected_output format: missing required keys.\")\n","\n","    string = f\"[question]: {expected_output['question']} \"\n","\n","    for option, value in expected_output['options'].items():\n","        string += f\"[option {option}]: {value}. \"\n","\n","    string += f\"[correct_answer]: {expected_output['correct_answer']}, [explanation]:{expected_output['explanation']}\"\n","    return string\n","\n","def load_json_and_convert(file_path):\n","    \"\"\"Loads a JSON file and converts \"expected_output\" to a string.\"\"\"\n","\n","    with open(file_path, \"r\") as json_file:\n","        data = json.load(json_file)\n","\n","    for entry in data:\n","        entry[\"expected_output\"] = format_expected_output(entry[\"expected_output\"])\n","\n","    return data\n","\n","\n","file_path = \"my_data_MCQ.json\"  # Replace with your actual file path\n","processed_data = load_json_and_convert(file_path)\n","\n","df = pd.DataFrame(processed_data)\n","\n","\n","# Create a DatasetDict with the \"train\" split\n","dataset_mcq = DatasetDict({\n","    \"train\": Dataset.from_pandas(df, split=\"train\")\n","})\n","\n","print(dataset_mcq)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"oS5lw9JQ6YlQ","outputId":"7f3f8b3b-38b2-4a67-c3ca-d3fee10db124"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["DatasetDict({\n","    train: Dataset({\n","        features: ['instruction', 'input_content', 'expected_output'],\n","        num_rows: 418\n","    })\n","})\n"]}]},{"cell_type":"code","source":["with open(\"data_mcq_string.json\", \"w\") as f:\n","    json.dump(dataset_mcq[\"train\"].to_list(), f, indent=4)"],"metadata":{"id":"aKho69AQZ3MC"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["from datasets import load_dataset\n","from collections import OrderedDict\n","\n","dataset_mcq = load_dataset('json', data_files='data_mcq_string.json')\n","\n","dataset_sum = load_dataset('json', data_files='my_data.json')\n","\n","combined_dataset = concatenate_datasets([dataset_sum['train'], dataset_mcq['train']])"],"metadata":{"id":"CfOaQJYOVU32"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["print(combined_dataset)\n","print(combined_dataset[560])"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"_Abk1s9lW1V9","outputId":"9a0b8c97-b959-4269-d989-69fbf05c31f0"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Dataset({\n","    features: ['expected_output', 'instruction', 'input_content'],\n","    num_rows: 978\n","})\n","{'expected_output': '[question]: What is the structure of an artificial neural network? [option A]: It consists of input layers and hidden layers only. [option B]: It consists of input layers, hidden layers, and output layers. [option C]: It consists of input layers, hidden layers, output layers, and artificial neurons. [option D]: It consists of input layers, hidden layers, output layers, artificial neurons, and weighted connections. [correct_answer]: C, [explanation]:An artificial neural network consists of input layers, hidden layers, output layers, and artificial neurons. The input layer receives data from the outside world, the hidden layers process and compute the weighted total, and the output layer provides the final response. Artificial neurons are the units within the network, and the connections between neurons are weighted to optimize the impact of inputs from the preceding layer.', 'instruction': 'Create an MCQ on the structure of artificial neural networks', 'input_content': 'Artificial neural networks are built on the principles of the structure and operation of human neurons. It is also known as neural networks or neural nets. An artificial neural network’s input layer, which is the first layer, receives input from external sources and passes it on to the hidden layer, which is the second layer. Each neuron in the hidden layer gets information from the neurons in the previous layer, computes the weighted total, and then transfers it to the neurons in the next layer. These connections are weighted, which means that the impacts of the inputs from the preceding layer are more or less optimized by giving each input a distinct weight. These weights are then adjusted during the training process to enhance the performance of the model. Artificial neurons, also known as units, are found in artificial neural networks. The whole Artificial Neural Network is composed of these artificial neurons, which are arranged in a series of layers. The complexities of neural networks will depend on the complexities of the underlying patterns in the dataset whether a layer has a dozen units or millions of units. Commonly, Artificial Neural Network has an input layer, an output layer as well as hidden layers. The input layer receives data from the outside world which the neural network needs to analyze or learn about. In a fully connected artificial neural network, there is an input layer and one or more hidden layers connected one after the other. Each neuron receives input from the previous layer neurons or the input layer. The output of one neuron becomes the input to other neurons in the next layer of the network, and this process continues until the final layer produces the output of the network. Then, after passing through one or more hidden layers, this data is transformed into valuable data for the output layer. Finally, the output layer provides an output in the form of an artificial neural network’s response to the data that comes in.'}\n"]}]},{"cell_type":"markdown","source":["#EDA for created dataset\n","\n","1) check for token >2048\n","\n","2) top-k sampling"],"metadata":{"id":"C05ODEnFHZXF"}},{"cell_type":"code","source":["# 1. Load the tokenizer\n","tokenizer = AutoTokenizer.from_pretrained(\"meta-llama/Llama-2-7b-chat-hf\")\n","\n","#dataset= dataset_mcq['train']\n","dataset=combined_dataset\n","# 2. Tokenize each row and count the number of tokens\n","instruction_token_counts = [len(tokenizer.tokenize(example[\"instruction\"])) for example in dataset]\n","output_token_counts = [len(tokenizer.tokenize(example[\"expected_output\"])) for example in dataset]\n","combined_token_counts = [instruction + output for instruction, output in zip(instruction_token_counts, output_token_counts)]\n","\n","# Helper function to plot the distributions\n","def plot_distribution(token_counts, title):\n","    sns.set_style(\"whitegrid\")\n","    plt.figure(figsize=(15, 6))\n","    plt.hist(token_counts, bins=50, color='#3498db', edgecolor='black')\n","    plt.title(title, fontsize=16)\n","    plt.xlabel(\"Number of tokens\", fontsize=14)\n","    plt.ylabel(\"Number of examples\", fontsize=14)\n","    plt.xticks(fontsize=12)\n","    plt.yticks(fontsize=12)\n","    plt.tight_layout()\n","    plt.show()\n","\n","# Plot the distribution of token counts\n","plot_distribution(instruction_token_counts, \"Distribution of token counts for instruction only\")\n","plot_distribution(output_token_counts, \"Distribution of token counts for output only\")\n","plot_distribution(combined_token_counts, \"Distribution of token counts for combined instruction + output\")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":1000},"id":"M_RNFvMDWK-2","outputId":"4c8d30fd-176b-4da9-d80e-d40a1ae0b128"},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 1500x600 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["<Figure size 1500x600 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["<Figure size 1500x600 with 1 Axes>"],"image/png":"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\n"},"metadata":{}}]},{"cell_type":"markdown","source":["##Filter out rows with more than 2048 tokens\n","\n","We will remove samples with more than 2048 tokens (max context size of Llama 2 by default = 4096)."],"metadata":{"id":"o8fXqz3DXukk"}},{"cell_type":"code","source":["# Filter out rows with more than 2048 tokens\n","valid_indices = [i for i, count in enumerate(combined_token_counts) if count <= 2048]\n","print(f\"Number of valid rows: {len(valid_indices)}\")\n","print(f\"Removing {len(dataset) - len(valid_indices)} rows...\")\n","\n","# Extract valid rows based on indices\n","dataset = dataset.select(valid_indices)\n","\n","# Get token counts for valid rows\n","token_counts = [combined_token_counts[i] for i in valid_indices]\n","\n","plot_distribution(token_counts, \"New distribution of token counts for combined instruction + output\")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":564},"id":"owyavGGyXvdK","outputId":"0117ac6d-b1cf-418f-f915-6ce00f193261"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["Number of valid rows: 978\n","Removing 0 rows...\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 1500x600 with 1 Axes>"],"image/png":"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\n"},"metadata":{}}]},{"cell_type":"markdown","source":["##Top-k sampling\n","\n","Only keep the top k samples with the most tokens."],"metadata":{"id":"TOCspcgXNOav"}},{"cell_type":"code","source":["# Define a function to get the top k rows based on the number of tokens\n","def get_top_k_rows(dataset, token_counts, k):\n","    # Sort the indices of the token counts in descending order and select the top k\n","    sorted_indices = sorted(range(len(token_counts)), key=lambda i: token_counts[i], reverse=True)\n","    top_k_indices = sorted_indices[:k]\n","\n","    # Extract the instruction and output for the top k rows\n","    top_k_data = {\n","        \"instruction\": [dataset[i][\"instruction\"] for i in top_k_indices], #dataset['train']\n","        \"output\": [dataset[i][\"expected_output\"] for i in top_k_indices] #dataset['train']\n","    }\n","\n","    # Return a new dataset created from the top k rows\n","    return Dataset.from_dict(top_k_data)\n","\n","# Calculate the number of tokens in each instruction and output in the deduplicated dataset\n","instruction_token_counts = [len(tokenizer.tokenize(example[\"instruction\"])) for example in dataset]\n","output_token_counts = [len(tokenizer.tokenize(example[\"expected_output\"])) for example in dataset]\n","\n","# Combine the token counts for instructions and outputs\n","combined_token_counts = [instruction + output for instruction, output in zip(instruction_token_counts, output_token_counts)]\n","\n","# Specify the number of rows to retrieve\n","k = 1000  # You can adjust this value as needed\n","\n","# Retrieve the top k rows with the most tokens from the deduplicated dataset\n","top_k_dataset = get_top_k_rows(dataset, combined_token_counts, k) #deduped_dataset\n","\n","# Create a DatasetDict object containing the top k dataset with a 'train' split\n","dataset = DatasetDict({\"train\": top_k_dataset})"],"metadata":{"id":"iUIy1SGqeyFo"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["# Calculate the number of tokens in each instruction in the training set\n","instruction_token_counts = [len(tokenizer.tokenize(example[\"instruction\"])) for example in dataset['train']]\n","\n","# Calculate the number of tokens in each output in the training set\n","output_token_counts = [len(tokenizer.tokenize(example[\"output\"])) for example in dataset['train']]\n","\n","# Combine the token counts of instruction and output for each example\n","combined_token_counts = [instruction + output for instruction, output in zip(instruction_token_counts, output_token_counts)]\n","\n","# Plotting the token count distributions\n","# Plot for distribution of token counts in instructions\n","plot_distribution(instruction_token_counts, \"Distribution of token counts for instruction only\")\n","\n","# Plot for distribution of token counts in outputs\n","plot_distribution(output_token_counts, \"Distribution of token counts for output only\")\n","\n","# Plot for distribution of combined token counts in both instructions and outputs\n","plot_distribution(combined_token_counts, \"Distribution of token counts for combined instruction + output\")"],"metadata":{"id":"oUxPB-KOKEmH","colab":{"base_uri":"https://localhost:8080/","height":1000},"outputId":"77c63192-8db1-4338-f015-180a9e5ab9e9"},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 1500x600 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["<Figure size 1500x600 with 1 Axes>"],"image/png":"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\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["<Figure size 1500x600 with 1 Axes>"],"image/png":"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\n"},"metadata":{}}]},{"cell_type":"code","source":["# Convert the 'train' split of the dataset to a Pandas DataFrame for easier analysis and manipulation\n","dataset.to_pandas()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":423},"id":"BoGShCGIrQJt","outputId":"6370d7c8-d481-4229-fdfb-0f825886253d"},"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":["                                       expected_output  \\\n","0    AI, or artificial intelligence, involves the c...   \n","1    Machine Learning is a branch of AI that enable...   \n","2    Deep Learning, a subset of Machine Learning, e...   \n","3    AI, Machine Learning, and Deep Learning are in...   \n","4    Artificial neural networks are structured base...   \n","..                                                 ...   \n","973  [question]: What is the definition of Artifici...   \n","974  [question]: What is the definition of Machine ...   \n","975  [question]: What is the definition of Deep Lea...   \n","976  [question]: What is the relationship between A...   \n","977  [question]: What is the aim of Deep Learning? ...   \n","\n","                                           instruction  \\\n","0         Summarize the concept and applications of AI   \n","1    Summarize the concept and applications of Mach...   \n","2    Summarize the concept and applications of Deep...   \n","3    Summarize the differences between AI, Machine ...   \n","4    Summarize the concept and structure of artific...   \n","..                                                 ...   \n","973  Create an MCQ on the definition of Artificial ...   \n","974  Create an MCQ on the definition of Machine Lea...   \n","975  Create an MCQ on the definition of Deep Learning.   \n","976  Create an MCQ on the relationship between Arti...   \n","977         Create an MCQ on the aim of Deep Learning.   \n","\n","                                         input_content  \n","0    AI refers to the development of computer syste...  \n","1    Machine Learning is a subset of AI that focuse...  \n","2    Deep Learning is a subset of Machine Learning ...  \n","3                                                       \n","4    Artificial neural networks are built on the pr...  \n","..                                                 ...  \n","973  Artificial Intelligence is basically the mecha...  \n","974  Machine Learning is basically the study/proces...  \n","975  Deep Learning is basically a sub-part of the b...  \n","976  AI is the broader family consisting of ML and ...  \n","977  The aim is to basically increase chances of su...  \n","\n","[978 rows x 3 columns]"],"text/html":["\n","  <div id=\"df-0b2e4511-604c-4a93-9106-4ed38f0a405d\" class=\"colab-df-container\">\n","    <div>\n","<style scoped>\n","    .dataframe tbody tr th:only-of-type {\n","        vertical-align: middle;\n","    }\n","\n","    .dataframe tbody tr th {\n","        vertical-align: top;\n","    }\n","\n","    .dataframe thead th {\n","        text-align: right;\n","    }\n","</style>\n","<table border=\"1\" class=\"dataframe\">\n","  <thead>\n","    <tr style=\"text-align: right;\">\n","      <th></th>\n","      <th>expected_output</th>\n","      <th>instruction</th>\n","      <th>input_content</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>AI, or artificial intelligence, involves the c...</td>\n","      <td>Summarize the concept and applications of AI</td>\n","      <td>AI refers to the development of computer syste...</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>Machine Learning is a branch of AI that enable...</td>\n","      <td>Summarize the concept and applications of Mach...</td>\n","      <td>Machine Learning is a subset of AI that focuse...</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>Deep Learning, a subset of Machine Learning, e...</td>\n","      <td>Summarize the concept and applications of Deep...</td>\n","      <td>Deep Learning is a subset of Machine Learning ...</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>AI, Machine Learning, and Deep Learning are in...</td>\n","      <td>Summarize the differences between AI, Machine ...</td>\n","      <td></td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>Artificial neural networks are structured base...</td>\n","      <td>Summarize the concept and structure of artific...</td>\n","      <td>Artificial neural networks are built on the pr...</td>\n","    </tr>\n","    <tr>\n","      <th>...</th>\n","      <td>...</td>\n","      <td>...</td>\n","      <td>...</td>\n","    </tr>\n","    <tr>\n","      <th>973</th>\n","      <td>[question]: What is the definition of Artifici...</td>\n","      <td>Create an MCQ on the definition of Artificial ...</td>\n","      <td>Artificial Intelligence is basically the mecha...</td>\n","    </tr>\n","    <tr>\n","      <th>974</th>\n","      <td>[question]: What is the definition of Machine ...</td>\n","      <td>Create an MCQ on the definition of Machine Lea...</td>\n","      <td>Machine Learning is basically the study/proces...</td>\n","    </tr>\n","    <tr>\n","      <th>975</th>\n","      <td>[question]: What is the definition of Deep Lea...</td>\n","      <td>Create an MCQ on the definition of Deep Learning.</td>\n","      <td>Deep Learning is basically a sub-part of the b...</td>\n","    </tr>\n","    <tr>\n","      <th>976</th>\n","      <td>[question]: What is the relationship between A...</td>\n","      <td>Create an MCQ on the relationship between Arti...</td>\n","      <td>AI is the broader family consisting of ML and ...</td>\n","    </tr>\n","    <tr>\n","      <th>977</th>\n","      <td>[question]: What is the aim of Deep Learning? ...</td>\n","      <td>Create an MCQ on the aim of Deep Learning.</td>\n","      <td>The aim is to basically increase chances of su...</td>\n","    </tr>\n","  </tbody>\n","</table>\n","<p>978 rows × 3 columns</p>\n","</div>\n","    <div class=\"colab-df-buttons\">\n","\n","  <div class=\"colab-df-container\">\n","    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-0b2e4511-604c-4a93-9106-4ed38f0a405d')\"\n","            title=\"Convert this dataframe to an interactive table.\"\n","            style=\"display:none;\">\n","\n","  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n","    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n","  </svg>\n","    </button>\n","\n","  <style>\n","    .colab-df-container {\n","      display:flex;\n","      gap: 12px;\n","    }\n","\n","    .colab-df-convert {\n","      background-color: #E8F0FE;\n","      border: none;\n","      border-radius: 50%;\n","      cursor: pointer;\n","      display: none;\n","      fill: #1967D2;\n","      height: 32px;\n","      padding: 0 0 0 0;\n","      width: 32px;\n","    }\n","\n","    .colab-df-convert:hover {\n","      background-color: #E2EBFA;\n","      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n","      fill: #174EA6;\n","    }\n","\n","    .colab-df-buttons div {\n","      margin-bottom: 4px;\n","    }\n","\n","    [theme=dark] .colab-df-convert {\n","      background-color: #3B4455;\n","      fill: #D2E3FC;\n","    }\n","\n","    [theme=dark] .colab-df-convert:hover {\n","      background-color: #434B5C;\n","      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n","      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n","      fill: #FFFFFF;\n","    }\n","  </style>\n","\n","    <script>\n","      const buttonEl =\n","        document.querySelector('#df-0b2e4511-604c-4a93-9106-4ed38f0a405d button.colab-df-convert');\n","      buttonEl.style.display =\n","        google.colab.kernel.accessAllowed ? 'block' : 'none';\n","\n","      async function convertToInteractive(key) {\n","        const element = document.querySelector('#df-0b2e4511-604c-4a93-9106-4ed38f0a405d');\n","        const dataTable =\n","          await google.colab.kernel.invokeFunction('convertToInteractive',\n","                                                    [key], {});\n","        if (!dataTable) return;\n","\n","        const docLinkHtml = 'Like what you see? Visit the ' +\n","          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n","          + ' to learn more about interactive tables.';\n","        element.innerHTML = '';\n","        dataTable['output_type'] = 'display_data';\n","        await google.colab.output.renderOutput(dataTable, element);\n","        const docLink = document.createElement('div');\n","        docLink.innerHTML = docLinkHtml;\n","        element.appendChild(docLink);\n","      }\n","    </script>\n","  </div>\n","\n","\n","<div id=\"df-6816f1b9-6c09-4f0d-9001-bfa6aa7bebed\">\n","  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-6816f1b9-6c09-4f0d-9001-bfa6aa7bebed')\"\n","            title=\"Suggest charts\"\n","            style=\"display:none;\">\n","\n","<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n","     width=\"24px\">\n","    <g>\n","        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n","    </g>\n","</svg>\n","  </button>\n","\n","<style>\n","  .colab-df-quickchart {\n","      --bg-color: #E8F0FE;\n","      --fill-color: #1967D2;\n","      --hover-bg-color: #E2EBFA;\n","      --hover-fill-color: #174EA6;\n","      --disabled-fill-color: #AAA;\n","      --disabled-bg-color: #DDD;\n","  }\n","\n","  [theme=dark] .colab-df-quickchart {\n","      --bg-color: #3B4455;\n","      --fill-color: #D2E3FC;\n","      --hover-bg-color: #434B5C;\n","      --hover-fill-color: #FFFFFF;\n","      --disabled-bg-color: #3B4455;\n","      --disabled-fill-color: #666;\n","  }\n","\n","  .colab-df-quickchart {\n","    background-color: var(--bg-color);\n","    border: none;\n","    border-radius: 50%;\n","    cursor: pointer;\n","    display: none;\n","    fill: var(--fill-color);\n","    height: 32px;\n","    padding: 0;\n","    width: 32px;\n","  }\n","\n","  .colab-df-quickchart:hover {\n","    background-color: var(--hover-bg-color);\n","    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n","    fill: var(--button-hover-fill-color);\n","  }\n","\n","  .colab-df-quickchart-complete:disabled,\n","  .colab-df-quickchart-complete:disabled:hover {\n","    background-color: var(--disabled-bg-color);\n","    fill: var(--disabled-fill-color);\n","    box-shadow: none;\n","  }\n","\n","  .colab-df-spinner {\n","    border: 2px solid var(--fill-color);\n","    border-color: transparent;\n","    border-bottom-color: var(--fill-color);\n","    animation:\n","      spin 1s steps(1) infinite;\n","  }\n","\n","  @keyframes spin {\n","    0% {\n","      border-color: transparent;\n","      border-bottom-color: var(--fill-color);\n","      border-left-color: var(--fill-color);\n","    }\n","    20% {\n","      border-color: transparent;\n","      border-left-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","    }\n","    30% {\n","      border-color: transparent;\n","      border-left-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","      border-right-color: var(--fill-color);\n","    }\n","    40% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","      border-top-color: var(--fill-color);\n","    }\n","    60% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","    }\n","    80% {\n","      border-color: transparent;\n","      border-right-color: var(--fill-color);\n","      border-bottom-color: var(--fill-color);\n","    }\n","    90% {\n","      border-color: transparent;\n","      border-bottom-color: var(--fill-color);\n","    }\n","  }\n","</style>\n","\n","  <script>\n","    async function quickchart(key) {\n","      const quickchartButtonEl =\n","        document.querySelector('#' + key + ' button');\n","      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n","      quickchartButtonEl.classList.add('colab-df-spinner');\n","      try {\n","        const charts = await google.colab.kernel.invokeFunction(\n","            'suggestCharts', [key], {});\n","      } catch (error) {\n","        console.error('Error during call to suggestCharts:', error);\n","      }\n","      quickchartButtonEl.classList.remove('colab-df-spinner');\n","      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n","    }\n","    (() => {\n","      let quickchartButtonEl =\n","        document.querySelector('#df-6816f1b9-6c09-4f0d-9001-bfa6aa7bebed button');\n","      quickchartButtonEl.style.display =\n","        google.colab.kernel.accessAllowed ? 'block' : 'none';\n","    })();\n","  </script>\n","</div>\n","\n","    </div>\n","  </div>\n"]},"metadata":{},"execution_count":43}]},{"cell_type":"code","source":["# Push to Hugging Face Hub\n","dataset.push_to_hub(\"BitBasher/mini-dataset-978\")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":116,"referenced_widgets":["bec0bc6d2ddf4279afe39be57f2a7078","77e5b95f38b14ff6a0fcddcd2c9f63ff","1efe64f4294c4f8cb86f14dfbeae466e","f35ce532c3024c0ab8ed5e77ffad0b15","d6ebe833fca3454796271cf0f90843ba","fc199b9f3b2246be86528d5ee27ec7aa","4e636e88bcf04737b6a5a5553164e29d","ee60ebaf2654483fab92f264cb67b0bb","0eff8d93269146ea887f0b70198ac7b1","c7d221edccf644e8bc566ed168f9be0b","4ca842a0d1414d6f8d2bc88d51350372","6f39a20e7d394bc3a31a5371a715e2c6","439be3c81e744204ad7ffb35f6c2edc8","2d401141021e45e1b57228f2a301810c","625c8adb770f44f482c42e07c75bc3b8","3bf5ed3bacad49b3914a3c3b2442833f","c62266e4ee56414c95eabcee2a517613","32206221acca4304b3db8a6d1c9cbdf8","5edbb6b742ea4895ba6cbd54d3d7bafc","e35e27bb30424f3fb2128b76d482ef61","e402634acd784e08839808e210c9b986","db4ec493d9344451ac78a9be25fa0305"]},"id":"M7ll_9dhjnMF","outputId":"83e33250-f40e-4266-b88f-7a38b01dd395"},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":["Uploading the dataset shards:   0%|          | 0/1 [00:00<?, ?it/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"bec0bc6d2ddf4279afe39be57f2a7078"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Creating parquet from Arrow format:   0%|          | 0/1 [00:00<?, ?ba/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"6f39a20e7d394bc3a31a5371a715e2c6"}},"metadata":{}},{"output_type":"execute_result","data":{"text/plain":["CommitInfo(commit_url='https://huggingface.co/datasets/apailang/mini-dataset/commit/686d8047b1fe632067fbc9bc4222b611f19c9fe4', commit_message='Upload dataset', commit_description='', oid='686d8047b1fe632067fbc9bc4222b611f19c9fe4', pr_url=None, pr_revision=None, pr_num=None)"],"application/vnd.google.colaboratory.intrinsic+json":{"type":"string"}},"metadata":{},"execution_count":44}]},{"cell_type":"markdown","source":["\n","END\n","\n","---\n","appendix\n"],"metadata":{"id":"vCGLX65GF3kd"}},{"cell_type":"markdown","source":["To check prompt input tokens required for each pdf"],"metadata":{"id":"-tl69y2XD2GH"}},{"cell_type":"code","source":["#to check token used\n","\n","# List of file paths\n","file_paths = [\"geeksforgeeks0.pdf\",\"geeksforgeeks1.pdf\", \"geeksforgeeks2.pdf\", \"geeksforgeeks3.pdf\",\"geeksforgeeks4.pdf\",\"geeksforgeeks5.pdf\",\"geeksforgeeks6.pdf\",\"geeksforgeeks7.pdf\",\"geeksforgeeks8.pdf\",\"geeksforgeeks9.pdf\",\"geeksforgeeks10.pdf\",\"geeksforgeeks11.pdf\",\"geeksforgeeks12.pdf\"]  # Replace with your actual file paths\n","\n","all_query_data = []\n","\n","# Iterate through each file path\n","for file_path in file_paths:\n","    # Initialize an empty list to store query data for the current file\n","    query_data = []\n","    print(file_path)\n","    #convert pdf to json\n","    json_data = pdf_to_json(file_path)\n","\n","    # Loop 10 times to generate 10 summarization records for each file\n","    for i in range(1):\n","        i+1\n","        print(i)\n","        # Generate the prompt for the current iteration\n","\n","\n","        # Get the completion from the API\n","\n","        #query = get_completion([{'role':'user', 'content':f\"please summarize the topic and provide in 3 summarization records in format of 3 pointer, instruction,context,response. sample output instruction is to clearly indicate topic and learning objective, context is sample data paragraph and response is summarized output.\"}],json_data )\n","        prompt_template= f\"\"\"\n","        For given {json_data} provide 2 concise summary of the topics presented in the content.\n","\n","        Examples:\n","        1. Instruction: Explain the concept of hyperparameter tuning.\n","        Context: A machine learning model has parameters that can be learned from data, but there are also hyperparameters that need to be set before training. Hyperparameter tuning is the process of selecting the optimal values for these hyperparameters.\n","        Response: Hyperparameter tuning is the process of selecting the best values for a machine learning model's hyperparameters, which control its learning process and can significantly impact its performance.\n","\n","        2. Instruction: Describe the difference between hyperparameters and model parameters.\n","        Context: Hyperparameters are configuration variables set before training, while model parameters are learned from data. Hyperparameters control the learning process, while model parameters are the weights and biases of the model.\n","        Response: Hyperparameters are set before training and control the learning process, while model parameters are learned from data and represent the weights and biases of the model.\n","        \"\"\"\n","        query = get_completion([{'role':'user', 'content':prompt_template}] )\n","        print(num_tokens_from_string(prompt_template, \"cl100k_base\"))\n","\n","\n","\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"EzYZAfb2IZTv","outputId":"aac90bc8-71b7-40ba-c56b-f4fd46825e24"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["geeksforgeeks0.pdf\n","0\n","1616\n","geeksforgeeks1.pdf\n","0\n","2203\n","geeksforgeeks2.pdf\n","0\n","1715\n","geeksforgeeks3.pdf\n","0\n","1593\n","geeksforgeeks4.pdf\n","0\n","1238\n","geeksforgeeks5.pdf\n","0\n","2219\n","geeksforgeeks6.pdf\n","0\n","1864\n","geeksforgeeks7.pdf\n","0\n","1452\n","geeksforgeeks8.pdf\n","0\n","2397\n","geeksforgeeks9.pdf\n","0\n","1334\n","geeksforgeeks10.pdf\n","0\n","1384\n","geeksforgeeks11.pdf\n","0\n","1481\n","geeksforgeeks12.pdf\n","0\n","1009\n"]}]}]}