Permalink
Cannot retrieve contributors at this time
Name already in use
A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
Generative-LLMs-for-clinical-classification/extraction/2020/Copy of PMC-LLaMA-7B feature extraction.ipynb
Go to fileThis commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
1 lines (1 sloc)
66 KB
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| {"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[{"file_id":"1RmE4vvjpTsEG3nPm1Ks2_cVcFpCLlKeP","timestamp":1689185844211},{"file_id":"1ZoBYSurFQhjO1od4c5smI7iQt4y-jPbX","timestamp":1689185811494}],"gpuType":"V100","mount_file_id":"117TQa6L38jIHdCbVEsj4dRv4xzPba4R1","authorship_tag":"ABX9TyMboKXCKpqPdiXHE2H2aF0S"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"},"widgets":{"application/vnd.jupyter.widget-state+json":{"641cc70fd55d4d0787f6cfbb10512809":{"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_9a292e3660f4487aa09263977362bdb7","IPY_MODEL_7cecb8718b114ae89e9a061a3d68537c","IPY_MODEL_39acbcfed9bc4e40b1ec9fbb6c04ad6f"],"layout":"IPY_MODEL_63fce2284e49419baa078e637f6b5055"}},"9a292e3660f4487aa09263977362bdb7":{"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_51ccdea594ac4ae7968fda3e1fa0a0f6","placeholder":"","style":"IPY_MODEL_7038eb9c35a34acca60e7b3dbc3491cd","value":"Downloading shards: 100%"}},"7cecb8718b114ae89e9a061a3d68537c":{"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_764f4b10d1074b469470520897342e05","max":3,"min":0,"orientation":"horizontal","style":"IPY_MODEL_2c8d8fad2aa3426e8507ec7b09c2adbc","value":3}},"39acbcfed9bc4e40b1ec9fbb6c04ad6f":{"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_0979c7677f6940e28a13f1712e6d1a8e","placeholder":"","style":"IPY_MODEL_59ae525e257543e4bba85cbfec0b0f20","value":" 3/3 [34:44<00:00, 671.37s/it]"}},"63fce2284e49419baa078e637f6b5055":{"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}},"51ccdea594ac4ae7968fda3e1fa0a0f6":{"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}},"7038eb9c35a34acca60e7b3dbc3491cd":{"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":""}},"764f4b10d1074b469470520897342e05":{"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}},"2c8d8fad2aa3426e8507ec7b09c2adbc":{"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":""}},"0979c7677f6940e28a13f1712e6d1a8e":{"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}},"59ae525e257543e4bba85cbfec0b0f20":{"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":""}},"e5be24b0e5614d11b896a0bd3c370397":{"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_7ffef69843d1403bba9475f3a5515a81","IPY_MODEL_81e78a6e617b4881973b56f8502263b0","IPY_MODEL_444bc839a282401d86582f89c2c82d12"],"layout":"IPY_MODEL_7584db5f2c0f40c4b9f45def9f913900"}},"7ffef69843d1403bba9475f3a5515a81":{"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_743576e8ce564c1ea4fef131362a495f","placeholder":"","style":"IPY_MODEL_85edec0a65c54bb6852fb523af2c4819","value":"Downloading (…)l-00001-of-00003.bin: 100%"}},"81e78a6e617b4881973b56f8502263b0":{"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_ab5ec16e064046d8af1e01b4445fc420","max":9877989650,"min":0,"orientation":"horizontal","style":"IPY_MODEL_38f8c20f2ca94ae693b1663d8de6f9a2","value":9877989650}},"444bc839a282401d86582f89c2c82d12":{"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_c1d4d77f863f4a75a5a4772badffb480","placeholder":"","style":"IPY_MODEL_11c320e667e74669a28bd7fbed898ddb","value":" 9.88G/9.88G [14:16<00:00, 12.4MB/s]"}},"7584db5f2c0f40c4b9f45def9f913900":{"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}},"743576e8ce564c1ea4fef131362a495f":{"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}},"85edec0a65c54bb6852fb523af2c4819":{"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":""}},"ab5ec16e064046d8af1e01b4445fc420":{"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}},"38f8c20f2ca94ae693b1663d8de6f9a2":{"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":""}},"c1d4d77f863f4a75a5a4772badffb480":{"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}},"11c320e667e74669a28bd7fbed898ddb":{"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":""}},"16ecaec567234978b02641062644b9dc":{"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_2f7c478fbe0a407185b43e591b1b209c","IPY_MODEL_a4e2793563224e728858e81c5d3009cb","IPY_MODEL_f225c58210da41948dabd0c0c8bd2969"],"layout":"IPY_MODEL_d2f35dddeac24a06ba1f8e806dfe5d47"}},"2f7c478fbe0a407185b43e591b1b209c":{"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_c8d4ab54b1804f5abe3fd39f6d79aad0","placeholder":"","style":"IPY_MODEL_93c346ee9d20429ab9e9cfb281712500","value":"Downloading (…)l-00002-of-00003.bin: 100%"}},"a4e2793563224e728858e81c5d3009cb":{"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_75437d0e1eb1466aa3f0c04c49d30075","max":9894801206,"min":0,"orientation":"horizontal","style":"IPY_MODEL_a2881eadb5eb4e1788e3b74ee3d93d58","value":9894801206}},"f225c58210da41948dabd0c0c8bd2969":{"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_4b666603783a434f81da74fbfe8e6508","placeholder":"","style":"IPY_MODEL_a5db5f18455f4dc18166a38538bd20b2","value":" 9.89G/9.89G [09:47<00:00, 18.0MB/s]"}},"d2f35dddeac24a06ba1f8e806dfe5d47":{"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}},"c8d4ab54b1804f5abe3fd39f6d79aad0":{"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}},"93c346ee9d20429ab9e9cfb281712500":{"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":""}},"75437d0e1eb1466aa3f0c04c49d30075":{"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}},"a2881eadb5eb4e1788e3b74ee3d93d58":{"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":""}},"4b666603783a434f81da74fbfe8e6508":{"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}},"a5db5f18455f4dc18166a38538bd20b2":{"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":""}},"679f1e4c0eda4b28ae0b288003b413a4":{"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_f7b4bf13d0ec485e82d3ea3d695aa69c","IPY_MODEL_b6a6407b10344a4ca65e1fbcf825d003","IPY_MODEL_9b1aafd28adc491eb76de6867b901828"],"layout":"IPY_MODEL_9251b2320bfa40e48403ebc1a79949b3"}},"f7b4bf13d0ec485e82d3ea3d695aa69c":{"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_aca154fa09344342bf5f362760e3c9fd","placeholder":"","style":"IPY_MODEL_1feb36d66cae455ead5935ea108706c4","value":"Downloading (…)l-00003-of-00003.bin: 100%"}},"b6a6407b10344a4ca65e1fbcf825d003":{"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_7412150077524f8690a7922dfbe68d03","max":7180990841,"min":0,"orientation":"horizontal","style":"IPY_MODEL_3b14414ae1e04474a714d37e65767d01","value":7180990841}},"9b1aafd28adc491eb76de6867b901828":{"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_55508bc086ec48e4adb9c3f1c2088eab","placeholder":"","style":"IPY_MODEL_605220751b2c432fa070189e46c1beb8","value":" 7.18G/7.18G [10:36<00:00, 17.6MB/s]"}},"9251b2320bfa40e48403ebc1a79949b3":{"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}},"aca154fa09344342bf5f362760e3c9fd":{"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}},"1feb36d66cae455ead5935ea108706c4":{"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":""}},"7412150077524f8690a7922dfbe68d03":{"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}},"3b14414ae1e04474a714d37e65767d01":{"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":""}},"55508bc086ec48e4adb9c3f1c2088eab":{"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}},"605220751b2c432fa070189e46c1beb8":{"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":""}},"fb7c7c4de5ba443e87c47dc6b6b268ec":{"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_c3bb5e6ef2054d88a02d0f5d54b32a07","IPY_MODEL_20aab99a368d4fc6a3025c9b239cf656","IPY_MODEL_c568849970504b35aa354cbd8ea4c838"],"layout":"IPY_MODEL_0e9f9419fe934220a12fbbb8e1480a6e"}},"c3bb5e6ef2054d88a02d0f5d54b32a07":{"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_f84049d651f0416e9328fde9dfed62b7","placeholder":"","style":"IPY_MODEL_ef4eed837bba4505a21fab4938ae3b6c","value":"Loading checkpoint shards: 100%"}},"20aab99a368d4fc6a3025c9b239cf656":{"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_a1021ad749b84a0988ec6dee3d3f1a4d","max":3,"min":0,"orientation":"horizontal","style":"IPY_MODEL_1ffa5bf7eecb4d19be7ef3d1d73c9521","value":3}},"c568849970504b35aa354cbd8ea4c838":{"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_e1893afd283344c9adab7ff7442827cc","placeholder":"","style":"IPY_MODEL_f6eb25736bf34f39bae522ac8e167181","value":" 3/3 [00:21<00:00, 6.60s/it]"}},"0e9f9419fe934220a12fbbb8e1480a6e":{"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}},"f84049d651f0416e9328fde9dfed62b7":{"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}},"ef4eed837bba4505a21fab4938ae3b6c":{"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":""}},"a1021ad749b84a0988ec6dee3d3f1a4d":{"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}},"1ffa5bf7eecb4d19be7ef3d1d73c9521":{"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":""}},"e1893afd283344c9adab7ff7442827cc":{"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}},"f6eb25736bf34f39bae522ac8e167181":{"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":["# Install Required libraries"],"metadata":{"id":"oNme5YN3mwRS"}},{"cell_type":"code","execution_count":null,"metadata":{"id":"OmxFfI92lslA","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1689694841246,"user_tz":-60,"elapsed":12334,"user":{"displayName":"Unknown","userId":"16317712665857714848"}},"outputId":"f167cec1-932f-4f7d-e180-81b7f99b497e"},"outputs":[{"output_type":"stream","name":"stdout","text":["Collecting sacremoses\n"," Downloading sacremoses-0.0.53.tar.gz (880 kB)\n","\u001b[?25l \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/880.6 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m880.6/880.6 kB\u001b[0m \u001b[31m52.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n","Collecting transformers\n"," Downloading transformers-4.30.2-py3-none-any.whl (7.2 MB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.2/7.2 MB\u001b[0m \u001b[31m109.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hCollecting sentencepiece\n"," Downloading sentencepiece-0.1.99-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m75.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: regex in /usr/local/lib/python3.10/dist-packages (from sacremoses) (2022.10.31)\n","Requirement already satisfied: six in /usr/local/lib/python3.10/dist-packages (from sacremoses) (1.16.0)\n","Requirement already satisfied: click in /usr/local/lib/python3.10/dist-packages (from sacremoses) (8.1.4)\n","Requirement already satisfied: joblib in /usr/local/lib/python3.10/dist-packages (from sacremoses) (1.3.1)\n","Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from sacremoses) (4.65.0)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers) (3.12.2)\n","Collecting huggingface-hub<1.0,>=0.14.1 (from transformers)\n"," Downloading huggingface_hub-0.16.4-py3-none-any.whl (268 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m268.8/268.8 kB\u001b[0m \u001b[31m31.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (1.22.4)\n","Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers) (23.1)\n","Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (6.0)\n","Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers) (2.27.1)\n","Collecting tokenizers!=0.11.3,<0.14,>=0.11.1 (from transformers)\n"," Downloading tokenizers-0.13.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.8 MB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.8/7.8 MB\u001b[0m \u001b[31m108.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hCollecting safetensors>=0.3.1 (from transformers)\n"," Downloading safetensors-0.3.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m86.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.14.1->transformers) (2023.6.0)\n","Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.14.1->transformers) (4.7.1)\n","Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (1.26.16)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2023.5.7)\n","Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2.0.12)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.4)\n","Building wheels for collected packages: sacremoses\n"," Building wheel for sacremoses (setup.py) ... \u001b[?25l\u001b[?25hdone\n"," Created wheel for sacremoses: filename=sacremoses-0.0.53-py3-none-any.whl size=895241 sha256=b72f5429db597a37d076f5b088a7243d139f8c281fdb87b2259708ed30e281c9\n"," Stored in directory: /root/.cache/pip/wheels/00/24/97/a2ea5324f36bc626e1ea0267f33db6aa80d157ee977e9e42fb\n","Successfully built sacremoses\n","Installing collected packages: tokenizers, sentencepiece, safetensors, sacremoses, huggingface-hub, transformers\n","Successfully installed huggingface-hub-0.16.4 sacremoses-0.0.53 safetensors-0.3.1 sentencepiece-0.1.99 tokenizers-0.13.3 transformers-4.30.2\n"]}],"source":["!pip install sacremoses transformers sentencepiece"]},{"cell_type":"markdown","source":["# Import required libraries"],"metadata":{"id":"nxKi5cK6nU5Z"}},{"cell_type":"code","source":["from transformers import LlamaTokenizer, LlamaModel, pipeline\n","import torch\n","import pandas as pd\n","import numpy as np\n","from sklearn.model_selection import train_test_split"],"metadata":{"id":"9Q4U4TWWnUNa"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":["# Import Data"],"metadata":{"id":"nK9JropUm3yK"}},{"cell_type":"code","source":["df = pd.read_json('/content/drive/MyDrive/Colab Notebooks/dissertation/data/2020_noFT.json')\n","#df = df.drop(\"Predict\", axis=1)\n","#df2 = pd.read_csv('/content/drive/MyDrive/Colab Notebooks/dissertation/data/GOUT-CC-2020-CORPUS-REDACTED.csv')\n","#df2 = df2.drop(\"Predict\", axis=1)\n","\n","#df = pd.concat([df, df2], ignore_index=True)"],"metadata":{"id":"pX9KCq5pSseO"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["df.head()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":337},"id":"Jnm_xTD2S8Gt","executionInfo":{"status":"ok","timestamp":1689617080787,"user_tz":-60,"elapsed":16,"user":{"displayName":"Unknown","userId":"16317712665857714848"}},"outputId":"64821726-d1e2-452e-f3d4-090f284c1481"},"execution_count":null,"outputs":[{"output_type":"execute_result","data":{"text/plain":[" Chief Complaint Predict Consensus \\\n","0 \"been feeling bad\" last 2 weeks & switched BP ... N - \n","1 \"can't walk\", reports onset at <<TIME>>. orien... Y N \n","2 \"dehydration\" Chest hurts, hips hurt, cramps P... Y Y \n","3 \"gout flare up\" L arm swelling x 1 week. denie... Y Y \n","4 \"heart racing,\"dyspnea, and orthopnea that has... N - \n","\n"," emb_biogpt_no_FineT \\\n","0 [[0.4998164773, -1.1454148293, -1.752535819999... \n","1 [[-0.9474165440000001, -0.1887536049, -0.06674... \n","2 [[-0.7398123741, 0.8122399449000001, -0.097419... \n","3 [[-0.3572742343, 0.6445433497, 1.5928075314, -... \n","4 [[0.0717470348, 1.4709169865, -1.7467554808, -... \n","\n"," emb_Stanford_no_FineT \n","0 [[-2.0845830441, 2.0618994236, -0.5788192153, ... \n","1 [[0.5856236815, 1.2349587679, -0.2313203514, -... \n","2 [[-1.4779242277, 2.5207219124, -2.1727879047, ... \n","3 [[-0.8846961856000001, -1.709597826, -1.948533... \n","4 [[0.5032715797, 0.2582928836, 2.9334533215, -1... "],"text/html":["\n","\n"," <div id=\"df-15055f27-0a10-4fbb-9bd2-2246523c6ab2\">\n"," <div 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>Chief Complaint</th>\n"," <th>Predict</th>\n"," <th>Consensus</th>\n"," <th>emb_biogpt_no_FineT</th>\n"," <th>emb_Stanford_no_FineT</th>\n"," </tr>\n"," </thead>\n"," <tbody>\n"," <tr>\n"," <th>0</th>\n"," <td>\"been feeling bad\" last 2 weeks & switched BP ...</td>\n"," <td>N</td>\n"," <td>-</td>\n"," <td>[[0.4998164773, -1.1454148293, -1.752535819999...</td>\n"," <td>[[-2.0845830441, 2.0618994236, -0.5788192153, ...</td>\n"," </tr>\n"," <tr>\n"," <th>1</th>\n"," <td>\"can't walk\", reports onset at <<TIME>>. orien...</td>\n"," <td>Y</td>\n"," <td>N</td>\n"," <td>[[-0.9474165440000001, -0.1887536049, -0.06674...</td>\n"," <td>[[0.5856236815, 1.2349587679, -0.2313203514, -...</td>\n"," </tr>\n"," <tr>\n"," <th>2</th>\n"," <td>\"dehydration\" Chest hurts, hips hurt, cramps P...</td>\n"," <td>Y</td>\n"," <td>Y</td>\n"," <td>[[-0.7398123741, 0.8122399449000001, -0.097419...</td>\n"," <td>[[-1.4779242277, 2.5207219124, -2.1727879047, ...</td>\n"," </tr>\n"," <tr>\n"," <th>3</th>\n"," <td>\"gout flare up\" L arm swelling x 1 week. denie...</td>\n"," <td>Y</td>\n"," <td>Y</td>\n"," <td>[[-0.3572742343, 0.6445433497, 1.5928075314, -...</td>\n"," <td>[[-0.8846961856000001, -1.709597826, -1.948533...</td>\n"," </tr>\n"," <tr>\n"," <th>4</th>\n"," <td>\"heart racing,\"dyspnea, and orthopnea that has...</td>\n"," <td>N</td>\n"," <td>-</td>\n"," <td>[[0.0717470348, 1.4709169865, -1.7467554808, -...</td>\n"," <td>[[0.5032715797, 0.2582928836, 2.9334533215, -1...</td>\n"," </tr>\n"," </tbody>\n","</table>\n","</div>\n"," <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-15055f27-0a10-4fbb-9bd2-2246523c6ab2')\"\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 0 24 24\"\n"," width=\"24px\">\n"," <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n"," <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n"," </svg>\n"," </button>\n","\n","\n","\n"," <div id=\"df-dd973ed8-a929-43ad-b9da-cad147f21909\">\n"," <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-dd973ed8-a929-43ad-b9da-cad147f21909')\"\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"," </div>\n","\n","<style>\n"," .colab-df-quickchart {\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-quickchart: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"," [theme=dark] .colab-df-quickchart {\n"," background-color: #3B4455;\n"," fill: #D2E3FC;\n"," }\n","\n"," [theme=dark] .colab-df-quickchart: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"," async function quickchart(key) {\n"," const containerElement = document.querySelector('#' + key);\n"," const charts = await google.colab.kernel.invokeFunction(\n"," 'suggestCharts', [key], {});\n"," }\n"," </script>\n","\n"," <script>\n","\n","function displayQuickchartButton(domScope) {\n"," let quickchartButtonEl =\n"," domScope.querySelector('#df-dd973ed8-a929-43ad-b9da-cad147f21909 button.colab-df-quickchart');\n"," quickchartButtonEl.style.display =\n"," google.colab.kernel.accessAllowed ? 'block' : 'none';\n","}\n","\n"," displayQuickchartButton(document);\n"," </script>\n"," <style>\n"," .colab-df-container {\n"," display:flex;\n"," flex-wrap:wrap;\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"," [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-15055f27-0a10-4fbb-9bd2-2246523c6ab2 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-15055f27-0a10-4fbb-9bd2-2246523c6ab2');\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"," </div>\n"]},"metadata":{},"execution_count":4}]},{"cell_type":"code","source":["# Check for consensus and mark rows for removal\n","rows_to_drop = []\n","for index, row in df.iterrows():\n"," if row['Consensus'] == '-': #Drop unknown and unmarked\n"," rows_to_drop.append(index)\n","\n","# Drop the marked rows\n","df.drop(rows_to_drop, inplace=True)\n","\n","# Print the updated DataFrame\n","print(df)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"lBfzey48Uufu","executionInfo":{"status":"ok","timestamp":1689183052264,"user_tz":-60,"elapsed":1094,"user":{"displayName":"Unknown","userId":"16317712665857714848"}},"outputId":"50952cb8-a378-45ab-e117-c26332fb5a54"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":[" Chief Complaint Consensus\n","1 \"can't walk\", reports onset at <<TIME>>. orien... N\n","2 \"dehydration\" Chest hurts, hips hurt, cramps P... Y\n","3 \"gout flare up\" L arm swelling x 1 week. denie... Y\n","5 \"I started breathing hard\" hx- htn, gout, anx... N\n","6 \"I think I have a gout flare up\" L wrist pain ... Y\n","... ... ...\n","8424 sob and right chest pain x 1 weeks - hx of mu... N\n","8425 starts in lower back and goes right legs x1 m... N\n","8427 sciatica pain R lower back radiating to R groi... N\n","8432 stepped on a nail at home with right foot, pai... N\n","8436 Rash/sores across body, infection ro left thum... N\n","\n","[445 rows x 2 columns]\n"]}]},{"cell_type":"markdown","source":["# Small data analysis"],"metadata":{"id":"PEoE_tyrm7qS"}},{"cell_type":"markdown","source":["# Load Model and tokenizer (BioGPT)"],"metadata":{"id":"7h7jfsy9njIx"}},{"cell_type":"code","source":["device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n","\n","#GPT-2 is a model with absolute position embeddings so it's usually advised to pad the inputs on the right rather than the left. Remember this\n","tokenizer = LlamaTokenizer.from_pretrained(\"chaoyi-wu/PMC_LLAMA_7B\")\n","tokenizer.padding_side = \"left\"\n","\n","model = LlamaModel.from_pretrained(\"chaoyi-wu/PMC_LLAMA_7B\")\n","\n","model = model.to(device)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":249,"referenced_widgets":["641cc70fd55d4d0787f6cfbb10512809","9a292e3660f4487aa09263977362bdb7","7cecb8718b114ae89e9a061a3d68537c","39acbcfed9bc4e40b1ec9fbb6c04ad6f","63fce2284e49419baa078e637f6b5055","51ccdea594ac4ae7968fda3e1fa0a0f6","7038eb9c35a34acca60e7b3dbc3491cd","764f4b10d1074b469470520897342e05","2c8d8fad2aa3426e8507ec7b09c2adbc","0979c7677f6940e28a13f1712e6d1a8e","59ae525e257543e4bba85cbfec0b0f20","e5be24b0e5614d11b896a0bd3c370397","7ffef69843d1403bba9475f3a5515a81","81e78a6e617b4881973b56f8502263b0","444bc839a282401d86582f89c2c82d12","7584db5f2c0f40c4b9f45def9f913900","743576e8ce564c1ea4fef131362a495f","85edec0a65c54bb6852fb523af2c4819","ab5ec16e064046d8af1e01b4445fc420","38f8c20f2ca94ae693b1663d8de6f9a2","c1d4d77f863f4a75a5a4772badffb480","11c320e667e74669a28bd7fbed898ddb","16ecaec567234978b02641062644b9dc","2f7c478fbe0a407185b43e591b1b209c","a4e2793563224e728858e81c5d3009cb","f225c58210da41948dabd0c0c8bd2969","d2f35dddeac24a06ba1f8e806dfe5d47","c8d4ab54b1804f5abe3fd39f6d79aad0","93c346ee9d20429ab9e9cfb281712500","75437d0e1eb1466aa3f0c04c49d30075","a2881eadb5eb4e1788e3b74ee3d93d58","4b666603783a434f81da74fbfe8e6508","a5db5f18455f4dc18166a38538bd20b2","679f1e4c0eda4b28ae0b288003b413a4","f7b4bf13d0ec485e82d3ea3d695aa69c","b6a6407b10344a4ca65e1fbcf825d003","9b1aafd28adc491eb76de6867b901828","9251b2320bfa40e48403ebc1a79949b3","aca154fa09344342bf5f362760e3c9fd","1feb36d66cae455ead5935ea108706c4","7412150077524f8690a7922dfbe68d03","3b14414ae1e04474a714d37e65767d01","55508bc086ec48e4adb9c3f1c2088eab","605220751b2c432fa070189e46c1beb8","fb7c7c4de5ba443e87c47dc6b6b268ec","c3bb5e6ef2054d88a02d0f5d54b32a07","20aab99a368d4fc6a3025c9b239cf656","c568849970504b35aa354cbd8ea4c838","0e9f9419fe934220a12fbbb8e1480a6e","f84049d651f0416e9328fde9dfed62b7","ef4eed837bba4505a21fab4938ae3b6c","a1021ad749b84a0988ec6dee3d3f1a4d","1ffa5bf7eecb4d19be7ef3d1d73c9521","e1893afd283344c9adab7ff7442827cc","f6eb25736bf34f39bae522ac8e167181"]},"id":"S37ZLL02nMOi","executionInfo":{"status":"ok","timestamp":1689697155053,"user_tz":-60,"elapsed":2168076,"user":{"displayName":"Unknown","userId":"16317712665857714848"}},"outputId":"34e2c4b6-62ce-4ec0-bd08-529dae562af3"},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":["Downloading shards: 0%| | 0/3 [00:00<?, ?it/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"641cc70fd55d4d0787f6cfbb10512809"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Downloading (…)l-00001-of-00003.bin: 0%| | 0.00/9.88G [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"e5be24b0e5614d11b896a0bd3c370397"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Downloading (…)l-00002-of-00003.bin: 0%| | 0.00/9.89G [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"16ecaec567234978b02641062644b9dc"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Downloading (…)l-00003-of-00003.bin: 0%| | 0.00/7.18G [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"679f1e4c0eda4b28ae0b288003b413a4"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"fb7c7c4de5ba443e87c47dc6b6b268ec"}},"metadata":{}},{"output_type":"stream","name":"stderr","text":["Some weights of the model checkpoint at chaoyi-wu/PMC_LLAMA_7B were not used when initializing LlamaModel: ['lm_head.weight']\n","- This IS expected if you are initializing LlamaModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n","- This IS NOT expected if you are initializing LlamaModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n"]}]},{"cell_type":"markdown","source":["## Define the pipeline"],"metadata":{"id":"ppuc0YsrMwiA"}},{"cell_type":"code","source":["# Create the pipeline\n","p = pipeline(\n"," task=\"feature-extraction\",\n"," tokenizer=tokenizer,\n"," model=model,\n"," framework=\"pt\",\n"," device=0, # use CUDA with 0\n",")"],"metadata":{"id":"f9JuA7OTMuw-"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":["### Get the embeddings of the last token of the last hidden state"],"metadata":{"id":"dNTtyRnArThB"}},{"cell_type":"code","source":["# Custom function to extract the embedding of the last token\n","def extract_last_token(last_hidden_states):\n"," last_hidden_states = np.array(last_hidden_states)\n"," return last_hidden_states[:,-1,:]\n","\n","# Process the data using the pipeline\n","results = p([row[\"Chief Complaint\"] for _, row in df.iterrows()])\n","\n","# Extract the last token of the last hidden state\n","embeddings = [extract_last_token(last_hidden_states) for last_hidden_states in results]"],"metadata":{"id":"8TnbZZQ3qqjo"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["# Assign the reshaped embeddings to the \"embeddings\" column in the DataFrame\n","df[\"emb_LLaMA_no_FineT\"] = embeddings\n","\n","# Print the resulting DataFrame\n","print(df)"],"metadata":{"id":"ZzokAh_VU5c4","executionInfo":{"status":"ok","timestamp":1689697190435,"user_tz":-60,"elapsed":16,"user":{"displayName":"Unknown","userId":"16317712665857714848"}},"colab":{"base_uri":"https://localhost:8080/"},"outputId":"fa332ea2-059f-4963-d991-d1e686e8cebb"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":[" Chief Complaint Predict Consensus \\\n","0 \"been feeling bad\" last 2 weeks & switched BP ... N - \n","1 \"can't walk\", reports onset at <<TIME>>. orien... Y N \n","2 \"dehydration\" Chest hurts, hips hurt, cramps P... Y Y \n","3 \"gout flare up\" L arm swelling x 1 week. denie... Y Y \n","4 \"heart racing,\"dyspnea, and orthopnea that has... N - \n",".. ... ... ... \n","295 upper abd/R side chest pain x1 month, new onse... N N \n","296 upper lip swelling x one day, pmh HTN, COPD, b... N N \n","297 walked outside of a gas station and began bein... N - \n","298 was getting prepped for colonoscopy and was se... N N \n","299 Was seen at <<HOSPITAL>> after an MVC. Pt stat... N N \n","\n"," emb_biogpt_no_FineT \\\n","0 [[0.4998164773, -1.1454148293, -1.752535819999... \n","1 [[-0.9474165440000001, -0.1887536049, -0.06674... \n","2 [[-0.7398123741, 0.8122399449000001, -0.097419... \n","3 [[-0.3572742343, 0.6445433497, 1.5928075314, -... \n","4 [[0.0717470348, 1.4709169865, -1.7467554808, -... \n",".. ... \n","295 [[-0.1761449426, 1.5961328745, 0.3407876492, -... \n","296 [[0.6994464993, 1.261431694, -1.8226729631, -1... \n","297 [[1.3378559351, 1.175758481, -1.0489212275, -0... \n","298 [[0.32566601040000004, -0.4120418131, -1.20206... \n","299 [[1.2505469322, 0.0630776435, -1.1872206926, -... \n","\n"," emb_Stanford_no_FineT \\\n","0 [[-2.0845830441, 2.0618994236, -0.5788192153, ... \n","1 [[0.5856236815, 1.2349587679, -0.2313203514, -... \n","2 [[-1.4779242277, 2.5207219124, -2.1727879047, ... \n","3 [[-0.8846961856000001, -1.709597826, -1.948533... \n","4 [[0.5032715797, 0.2582928836, 2.9334533215, -1... \n",".. ... \n","295 [[-1.7635282278000002, 2.4325175285, 1.2939627... \n","296 [[-1.6149325371, 3.6044323444, -1.4300086498, ... \n","297 [[-1.9335254431000002, 4.1861252785, -2.309693... \n","298 [[0.3229598403, 2.0347685814, 0.94253301620000... \n","299 [[-1.4236990213, 3.0796804428, -2.6713602543, ... \n","\n"," emb_LLaMA_no_FineT \n","0 [[-0.5885581970214844, -0.2658204138278961, -0... \n","1 [[-2.8021719455718994, -1.288360357284546, 0.0... \n","2 [[-2.5240955352783203, -1.1037675142288208, -0... \n","3 [[-1.711168885231018, -1.810827612876892, 0.99... \n","4 [[-1.2857794761657715, -0.40648502111434937, -... \n",".. ... \n","295 [[-0.49144142866134644, -0.6700435280799866, 0... \n","296 [[-1.3824286460876465, -0.5182033777236938, -0... \n","297 [[-0.6395374536514282, -1.0870344638824463, -0... \n","298 [[-1.6664118766784668, 0.39107346534729004, 0.... \n","299 [[-0.42206114530563354, -0.26754236221313477, ... \n","\n","[300 rows x 6 columns]\n"]}]},{"cell_type":"markdown","source":["## Save to csv ot txt"],"metadata":{"id":"OeTeIttSNTS9"}},{"cell_type":"code","source":["df.to_json('/content/drive/MyDrive/Colab Notebooks/dissertation/data/2020_noFT.json', orient='records')"],"metadata":{"id":"8OxiKJdDNXI1"},"execution_count":null,"outputs":[]}]} |