diff --git "a/Vision_Releases_transformers_4_56.ipynb" "b/Vision_Releases_transformers_4_56.ipynb" new file mode 100644--- /dev/null +++ "b/Vision_Releases_transformers_4_56.ipynb" @@ -0,0 +1,2907 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "provenance": [], + "gpuType": "T4" + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + }, + "language_info": { + "name": "python" + }, + "accelerator": "GPU", + "widgets": { + "application/vnd.jupyter.widget-state+json": { + "bdd292d1769449dd80b00c540885738b": { + "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_c17c36edba134b999fc2449c2cf3d469", + "IPY_MODEL_bf14f6cc11934619aea6e80f71d3237a", + "IPY_MODEL_8f9bd5f6821c4c4ba88bc32f648fd79b" + ], + "layout": "IPY_MODEL_a9b80ef3b2664eca94f42c2db2cf478c" + } + }, + "c17c36edba134b999fc2449c2cf3d469": { + "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_ebafeb6e5d26417290d79e23b1d7960a", + "placeholder": "​", + "style": "IPY_MODEL_63796f030a32458385a6a30f59a28c97", + "value": "config.json: " + } + }, + "bf14f6cc11934619aea6e80f71d3237a": { + "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_43b2b6d4320e40c498c924f11de65058", + "max": 1, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_93b2328283cf4d08ad8c7407ed7e05af", + "value": 1 + } + }, + "8f9bd5f6821c4c4ba88bc32f648fd79b": { + "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_88ca8fc4f45140f7bca5e66f1edf351d", + "placeholder": "​", + "style": "IPY_MODEL_7c60afe93d114c8388c3f6d69b2f0145", + "value": " 5.70k/? [00:00<00:00, 505kB/s]" + } + }, + "a9b80ef3b2664eca94f42c2db2cf478c": { + "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 + } + }, + "ebafeb6e5d26417290d79e23b1d7960a": { + "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 + } + }, + "63796f030a32458385a6a30f59a28c97": { + "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": "" + } + }, + "43b2b6d4320e40c498c924f11de65058": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "state": { + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": "20px" + } + }, + "93b2328283cf4d08ad8c7407ed7e05af": { + "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": "" + } + }, + "88ca8fc4f45140f7bca5e66f1edf351d": { + "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 + } + }, + "7c60afe93d114c8388c3f6d69b2f0145": { + "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": "" + } + }, + "2e15e10fece246d7a9e1c0685207487e": { + "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_81f5c3b043304f50857d3df7e75de7a8", + "IPY_MODEL_5b9c0e9cca804e6c8ca44682812621a6", + "IPY_MODEL_cdbc7efa2d3842a892db862a4b1bc2b9" + ], + "layout": "IPY_MODEL_3674b7b8076b4b2988fc9e14fd75ef2e" + } + }, + "81f5c3b043304f50857d3df7e75de7a8": { + "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_0273e9d39a2e496cb8e69743f53b9586", + "placeholder": "​", + "style": "IPY_MODEL_9daacec65c204a338a6f5ce7d53b479f", + "value": "model.safetensors: 100%" + } + }, + "5b9c0e9cca804e6c8ca44682812621a6": { + "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_3a2f80b1640a4ff893bb88d20954a6bc", + "max": 155841672, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_41c2832a1fce49688260b05cfdd18c24", + "value": 155841672 + } + }, + "cdbc7efa2d3842a892db862a4b1bc2b9": { + "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_9d34c25eb34c467eac6d8fd80750a536", + "placeholder": "​", + "style": "IPY_MODEL_11bb77f6817b46d68dd6d472fc4e94fe", + "value": " 156M/156M [00:08<00:00, 16.4MB/s]" + } + }, + "3674b7b8076b4b2988fc9e14fd75ef2e": { + "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 + } + }, + "0273e9d39a2e496cb8e69743f53b9586": { + "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 + } + }, + "9daacec65c204a338a6f5ce7d53b479f": { + "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": "" + } + }, + "3a2f80b1640a4ff893bb88d20954a6bc": { + "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 + } + }, + "41c2832a1fce49688260b05cfdd18c24": { + "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": "" + } + }, + "9d34c25eb34c467eac6d8fd80750a536": { + "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 + } + }, + "11bb77f6817b46d68dd6d472fc4e94fe": { + "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": "" + } + }, + "5f452103369c4a5da5254ce45da10b27": { + "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_2890e106c2954fa3b35bd1f1c3964d9f", + "IPY_MODEL_996626dbcbaa4c10a4a56f09ff1ed107", + "IPY_MODEL_b417c2d8048649588b1e223ceb1f1bf1" + ], + "layout": "IPY_MODEL_19d7db5882b54be9bd371dc123248c3e" + } + }, + "2890e106c2954fa3b35bd1f1c3964d9f": { + "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_ad318f6157a046f29ee41fe8fee3095f", + "placeholder": "​", + "style": "IPY_MODEL_d62bfbcce48e4067b9c9d8792722eaca", + "value": "Fetching 2 files: 100%" + } + }, + "996626dbcbaa4c10a4a56f09ff1ed107": { + "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_690b55661f7f46259e4b7af13adee811", + "max": 2, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_9e43e8c6438f449f9d7f2fd313ddbda2", + "value": 2 + } + }, + "b417c2d8048649588b1e223ceb1f1bf1": { + "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_7e83a3d6ebe44556a403a79c4dc2f3df", + "placeholder": "​", + "style": "IPY_MODEL_2bc336c59d4d4455a3bccfb0b7aa53ca", + "value": " 2/2 [00:00<00:00,  2.71it/s]" + } + }, + "19d7db5882b54be9bd371dc123248c3e": { + "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 + } + }, + "ad318f6157a046f29ee41fe8fee3095f": { + "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 + } + }, + "d62bfbcce48e4067b9c9d8792722eaca": { + "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": "" + } + }, + "690b55661f7f46259e4b7af13adee811": { + "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 + } + }, + "9e43e8c6438f449f9d7f2fd313ddbda2": { + "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": "" + } + }, + "7e83a3d6ebe44556a403a79c4dc2f3df": { + "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 + } + }, + "2bc336c59d4d4455a3bccfb0b7aa53ca": { + "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": "" + } + }, + "517804613ac140eaaea5f58f2667332a": { + "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_d0273c4db9f54143a765c683eca5442a", + "IPY_MODEL_be2ac1c412534e8c8781232803861bfa", + "IPY_MODEL_fb55ada03e0a4e89b46f931ca2c54551" + ], + "layout": "IPY_MODEL_ecc7f1d03a6c4bdeadf1547528123dac" + } + }, + "d0273c4db9f54143a765c683eca5442a": { + "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_9f0ac8d10dcf4af3a3cfd0b3184505d1", + "placeholder": "​", + "style": "IPY_MODEL_51934c86e44743d587c990c259d3cfa1", + "value": "preprocessor_config.json: 100%" + } + }, + "be2ac1c412534e8c8781232803861bfa": { + "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_08314c4da2774b7ebac8b3f3a1e93f72", + "max": 683, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_ba6fa0c793514fb48d772966bdadb183", + "value": 683 + } + }, + "fb55ada03e0a4e89b46f931ca2c54551": { + "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_666f9b45b7ee405bb703b621c1ba5f80", + "placeholder": "​", + "style": "IPY_MODEL_9379b87fc3e948809f1f11e4bc816b1d", + "value": " 683/683 [00:00<00:00, 80.6kB/s]" + } + }, + "ecc7f1d03a6c4bdeadf1547528123dac": { + "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 + } + }, + "9f0ac8d10dcf4af3a3cfd0b3184505d1": { + "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 + } + }, + "51934c86e44743d587c990c259d3cfa1": { + "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": "" + } + }, + "08314c4da2774b7ebac8b3f3a1e93f72": { + "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 + } + }, + "ba6fa0c793514fb48d772966bdadb183": { + "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": "" + } + }, + "666f9b45b7ee405bb703b621c1ba5f80": { + "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 + } + }, + "9379b87fc3e948809f1f11e4bc816b1d": { + "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": "" + } + }, + "81f9852cfa7f43178def864d20003f59": { + "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_fadf7de524fe494db2f1691a42fd05c9", + "IPY_MODEL_343c9a6e82444bacb0baa2ac96c8b00f", + "IPY_MODEL_634c5fa2670c4a80902931ef0801c962" + ], + "layout": "IPY_MODEL_944dd815db3944f485ddba171268db23" + } + }, + "fadf7de524fe494db2f1691a42fd05c9": { + "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_606690bc2544411daec9b00316c08381", + "placeholder": "​", + "style": "IPY_MODEL_40091ea3563442aa934c1976232af538", + "value": "processor_config.json: 100%" + } + }, + "343c9a6e82444bacb0baa2ac96c8b00f": { + "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_353d43de98434a9eb2cf0fb39b6d5bb8", + "max": 95, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_51f2f230271f4894b254f1f5cee2773d", + "value": 95 + } + }, + "634c5fa2670c4a80902931ef0801c962": { + "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_3c78030ee62043589cf1f83644a6eba8", + "placeholder": "​", + "style": "IPY_MODEL_4f21f33a8d3746459ebd51f9f671dd94", + "value": " 95.0/95.0 [00:00<00:00, 6.41kB/s]" + } + }, + "944dd815db3944f485ddba171268db23": { + "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 + } + }, + "606690bc2544411daec9b00316c08381": { + "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 + } + }, + "40091ea3563442aa934c1976232af538": { + "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": "" + } + }, + "353d43de98434a9eb2cf0fb39b6d5bb8": { + "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 + } + }, + "51f2f230271f4894b254f1f5cee2773d": { + "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": "" + } + }, + "3c78030ee62043589cf1f83644a6eba8": { + "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 + } + }, + "4f21f33a8d3746459ebd51f9f671dd94": { + "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": [ + "# Transformers 4.56 vision models 🔥\n", + "\n", + "New transformers release comes with amazing vision/multimodal models: Florence-2 by MSFT, SAM-2 by Meta, KOSMOS-2.5 by MSFT, MetaCLIP2 by Meta, all runnable in Colab free tier. This notebook enables you to try them all!\n", + "\n", + "Note: On GH we cannot download notebooks with image outputs so make sure to check it out on [Hugging Face](https://huggingface.co/merve/smol-vision)." + ], + "metadata": { + "id": "zwCKwR_TkwLy" + } + }, + { + "cell_type": "markdown", + "source": [ + "## Florence-2\n", + "\n", + "We'll first take a look at Florence-2. The model in transformers format will be uploaded to microsoft org soon, but in the meantime, we can use the models `ducviet00/Florence-2-large-hf` and `ducviet00/Florence-2-base-hf`. It comes in sizes 200M and 800M parameters, very small." + ], + "metadata": { + "id": "n5tkUIDAf6lW" + } + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "tNCPlyx4fksQ" + }, + "outputs": [], + "source": [ + "from transformers import AutoProcessor, AutoModelForImageTextToText\n", + "import torch\n", + "\n", + "processor = AutoProcessor.from_pretrained(\"ducviet00/Florence-2-large-hf\")\n", + "model = AutoModelForImageTextToText.from_pretrained(\"ducviet00/Florence-2-large-hf\").to(\"cuda\", torch.bfloat16)" + ] + }, + { + "cell_type": "markdown", + "source": [ + "Florence-2 is a prompt based model, you can use following task prompts to use it:\n", + "```\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "\n", + "```" + ], + "metadata": { + "id": "ipCK8Qmvgz05" + } + }, + { + "cell_type": "code", + "source": [ + "import torch\n", + "import requests\n", + "from PIL import Image\n", + "\n", + "url = \"https://huggingface.co/datasets/merve/vlm_test_images/resolve/main/menu.JPG\"\n", + "image = Image.open(requests.get(url, stream=True).raw)\n", + "prompt=\"\"" + ], + "metadata": { + "id": "JudF0LvsgInQ" + }, + "execution_count": 12, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "inputs = processor(text=prompt, images=image, return_tensors=\"pt\").to(\"cuda\", torch.bfloat16)\n", + "\n", + "generated_ids = model.generate(**inputs, max_new_tokens=1024, num_beams=3)\n", + "\n", + "generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]" + ], + "metadata": { + "id": "s3oe_JZ0hiY5" + }, + "execution_count": 13, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "image_size = image.size\n", + "parsed_answer = processor.post_process_generation(generated_text, task=prompt, image_size=image_size)\n", + "print(parsed_answer)" + ], + "metadata": { + "id": "vR6HQdDbhqf4", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "750f0535-6804-403e-98d7-da390d4a1be3" + }, + "execution_count": 14, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "{'': \"FRIDAY, DEC 20th\\nNEW OFFICE PARTY\\n- COCKTAIL MENU -\\nOFFICE MARTINI\\nvodka fraise des bois - liss de framboise - liqueur de fleur de surreau - fleur\\nwild strawberry volks - raspberry juice - raspberry litor - a déflower lior - flower\\nDIFFUSER'S SUNRISE\\ntequila, manchurian impédio, lus d'orange sansquine - contreu - cherry bitter\\ntequila, tangerine lime - blood orange juice - contreau - cherry bitter\\nTRANSFORMERS TWIST\\ngin Intégrale - chèvre-lemon - jauné - citron - pouvre blanc\\npepper\\nPERUVIAN PEFT\\nPapaya - lemonade - orange blanc - green tea & lemon - lemon - white\\npeppers - pomegranate - orange marmalade - ananas\\nplace - creme de crème - cérémonie - mandarin - mandarins\\nroasted mango-infused gin - lemongrass - grenadilla - orange cocktail - pineapple\"}\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "You can also do object detection with it." + ], + "metadata": { + "id": "6jR5JacAilIM" + } + }, + { + "cell_type": "code", + "source": [ + "url = \"https://huggingface.co/datasets/merve/vlm_test_images/resolve/main/candy.JPG\"\n", + "image = Image.open(requests.get(url, stream=True).raw)\n", + "prompt = \"\"\n", + "\n", + "inputs = processor(text=prompt, images=image, return_tensors=\"pt\").to(\"cuda\", torch.bfloat16)\n", + "\n", + "generated_ids = model.generate(**inputs, max_new_tokens=1024, num_beams=3)\n", + "\n", + "generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]" + ], + "metadata": { + "id": "FndxHptOinaC" + }, + "execution_count": 15, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "image_size = image.size\n", + "parsed_answer = processor.post_process_generation(generated_text, task=prompt, image_size=image_size)\n", + "print(parsed_answer)" + ], + "metadata": { + "id": "I9dC1pxGjDJZ", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "de6c2001-caef-4184-8430-448815eabbb3" + }, + "execution_count": 16, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "{'': {'bboxes': [[2272, 2085, 2659, 2453], [1925, 1335, 2296, 1707], [1651, 1431, 1961, 1788], [2457, 1915, 2840, 2193], [2009, 1955, 2388, 2187], [1155, 533, 3784, 3022]], 'labels': ['candy', 'candy', 'candy', 'candy', 'candy', 'human hand']}}\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "from PIL import ImageDraw\n", + "\n", + "draw = ImageDraw.Draw(image)\n", + "bboxes = parsed_answer['']['bboxes']\n", + "labels = parsed_answer['']['labels']\n", + "\n", + "for bbox, label in zip(bboxes, labels):\n", + " x1, y1, x2, y2 = bbox\n", + " draw.rectangle([x1, y1, x2, y2], outline=\"red\", width=3)\n", + " draw.text((x1, y1), label, fill=\"red\")\n", + "\n", + "display(image)" + ], + "metadata": { + "id": "2mHFUOZVjZBo" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "source": [ + "## DINOv3\n", + "\n", + "DINOv3 is an advanced image backbone/embedding model which you can use for variety of tasks as is. Here's a bunch of apps and tutorials in case you're interested in what you can do, and how to fine-tune it for image classification.\n", + "- [DINOv3 Fine-tuning](https://huggingface.co/merve/smol-vision/blob/main/DINOv3_FT.ipynb)\n", + "- [DINOv3 for Keypoint Matching through patch similarities](https://huggingface.co/spaces/merve/DINOv3-keypoint-matching)\n", + "- [DINOv3 object perception](https://huggingface.co/spaces/merve/dinov3-viz)\n", + "\n", + "Note that to run this model, you need to have access to it. Head to repository to ask for access by filling the form if you don't have the access. [Here's all the DINOv3 models](https://huggingface.co/collections/facebook/dinov3-68924841bd6b561778e31009).\n", + "\n" + ], + "metadata": { + "id": "NbSg8KeCnaJr" + } + }, + { + "cell_type": "code", + "source": [ + "import torch\n", + "from transformers import AutoImageProcessor, AutoModel\n", + "from transformers.image_utils import load_image\n", + "\n", + "url = \"https://huggingface.co/datasets/merve/vlm_test_images/resolve/main/thailand.jpg\"\n", + "image = load_image(url)\n", + "\n", + "pretrained_model_name = \"facebook/dinov3-convnext-base-pretrain-lvd1689m\"\n", + "processor = AutoImageProcessor.from_pretrained(pretrained_model_name)\n", + "model = AutoModel.from_pretrained(\n", + " pretrained_model_name,\n", + " device_map=\"auto\",\n", + ")\n", + "\n", + "inputs = processor(images=image, return_tensors=\"pt\").to(model.device)\n", + "with torch.inference_mode():\n", + " outputs = model(**inputs)\n", + "\n", + "pooled_output = outputs.pooler_output\n" + ], + "metadata": { + "id": "nfNxM7qrnZ4e" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "source": [ + "## Kosmos 2.5\n", + "\n", + "Kosmos 2.5 by Microsoft is a great document model that can not only convert documents to markdown, it also can locate meaningful structures on documents.\n", + "It has a \"normal\" checkpoint and a \"chat\" checkpoint which can be used for VQA tasks. Let's see how to use it." + ], + "metadata": { + "id": "0wUqsaHAi2W5" + } + }, + { + "cell_type": "code", + "source": [ + "from transformers import AutoProcessor, Kosmos2_5ForConditionalGeneration\n", + "import torch\n", + "\n", + "model = Kosmos2_5ForConditionalGeneration.from_pretrained(\"microsoft/kosmos-2.5\").to(\"cuda\", torch.bfloat16)\n", + "processor = AutoProcessor.from_pretrained(\"microsoft/kosmos-2.5\")\n" + ], + "metadata": { + "id": "Gjef-fw9fnuL" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "from PIL import Image, ImageDraw\n", + "import requests\n", + "\n", + "url = \"https://huggingface.co/datasets/merve/vlm_test_images/resolve/main/fiche.jpg\"\n", + "image = Image.open(requests.get(url, stream=True).raw)" + ], + "metadata": { + "id": "tPSqn-POl4up" + }, + "execution_count": 3, + "outputs": [] + }, + { + "cell_type": "markdown", + "source": [ + "It works a bit like Florence-2 where you can provide a task prompt. It takes two: `` (for markdown) and `` (for OCR)." + ], + "metadata": { + "id": "m2rgJrMPl-fE" + } + }, + { + "cell_type": "code", + "source": [ + "import re\n", + "\n", + "prompt = \"\"\n", + "inputs = processor(text=prompt, images=image, return_tensors=\"pt\")\n", + "\n", + "height, width = inputs.pop(\"height\"), inputs.pop(\"width\")\n", + "raw_width, raw_height = image.size\n", + "scale_height = raw_height / height\n", + "scale_width = raw_width / width\n", + "\n", + "inputs = {k: v.to(\"cuda\") if v is not None else None for k, v in inputs.items()}\n", + "inputs[\"flattened_patches\"] = inputs[\"flattened_patches\"].to(torch.bfloat16)\n", + "generated_ids = model.generate(\n", + " **inputs,\n", + " max_new_tokens=1024,\n", + ")\n", + "\n", + "generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)\n", + "print(generated_text[0])" + ], + "metadata": { + "id": "YHBt0izHkPY5", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "0bdc32d0-3897-46ef-f897-b2208e1cc28d" + }, + "execution_count": 4, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "# CATERIA DEI FERMENTINI\n", + "\n", + "UNO SRLS\n", + "VIA CIMABUE 1 R\n", + "50125 FIRENZE\n", + "P.iva 04109381204\n", + "Tel. 055 2466781\n", + "\n", + "## DOCUMENTO COMMERCIALE\n", + "\n", + "di vendita o prestazione\n", + "\n", + "- **QTA.** **DESCRIZIONE**\n", + "- 1 x Coperti\n", + "- 1 x Coca Fanta Sprite\n", + "- 1 x Rigatoni 3 pomodori\n", + "\n", + "- **IVA**\n", + "- 10,00%\n", + "- 10,00%\n", + "- 10,00%\n", + "\n", + "- **TOTAL** **EURO**\n", + "- 17,00\n", + "\n", + "di cui **IVA**\n", + "- 1.55\n", + "\n", + "Pagamento elettronico\n", + "Importo pagato\n", + "\n", + "26-05-2023 21:52\n", + "DOC.N. 0175-0011\n", + "RT 941BQ003454\n", + "\n", + "---\n", + "\n", + "**DETTAGLIO FORME DI PAGAMENTO**\n", + "Carta di Credito\n", + "\n", + "17,00\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "Let's try chat version. Note how it takes a chat template as input." + ], + "metadata": { + "id": "6jzqu6MvmfUO" + } + }, + { + "cell_type": "code", + "source": [ + "model = Kosmos2_5ForConditionalGeneration.from_pretrained(\"microsoft/kosmos-2.5-chat\").to(\"cuda\", torch.bfloat16)\n", + "processor = AutoProcessor.from_pretrained(\"microsoft/kosmos-2.5-chat\")" + ], + "metadata": { + "id": "e39vlgY2mtHr" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "question = \"What is the sub total of the receipt?\"\n", + "template = \"A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {} ASSISTANT:\"\n", + "prompt = template.format(question)\n", + "inputs = processor(text=prompt, images=image, return_tensors=\"pt\")\n", + "\n", + "# rest is the same\n", + "height, width = inputs.pop(\"height\"), inputs.pop(\"width\")\n", + "raw_width, raw_height = image.size\n", + "scale_height = raw_height / height\n", + "scale_width = raw_width / width\n", + "\n", + "inputs = {k: v.to(\"cuda\") if v is not None else None for k, v in inputs.items()}\n", + "inputs[\"flattened_patches\"] = inputs[\"flattened_patches\"].to(torch.bfloat16)\n", + "generated_ids = model.generate(\n", + " **inputs,\n", + " max_new_tokens=1024,\n", + ")\n", + "\n", + "generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)\n", + "print(generated_text[0])" + ], + "metadata": { + "id": "StNUuNufmetH", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "58d36158-c08c-4faf-897c-f9a83ce02760" + }, + "execution_count": 6, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: What is the sub total of the receipt? ASSISTANT: 17,00\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "## MetaCLIP2\n", + "\n", + "MetaCLIP2 is a multimodal zero-shot image classifier by Meta, which you can use for a variety of tasks that require image-text understanding. [Here's all the MetaCLIP2 models](https://huggingface.co/collections/facebook/meta-clip-1-2-687e97787e9155bc480ef446), we will use the multilingual one." + ], + "metadata": { + "id": "uGD_FQbcpGYb" + } + }, + { + "cell_type": "code", + "source": [ + "from transformers import AutoProcessor, AutoModelForZeroShotImageClassification\n", + "import torch\n", + "\n", + "model = AutoModelForZeroShotImageClassification.from_pretrained(\"facebook/metaclip-2-worldwide-huge-378\", dtype=torch.bfloat16, attn_implementation=\"sdpa\").to(\"cuda\", torch.bfloat16)\n", + "processor = AutoProcessor.from_pretrained(\"facebook/metaclip-2-worldwide-huge-378\")" + ], + "metadata": { + "id": "P0ESRMJOpUNW" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "import requests\n", + "import torch\n", + "from PIL import Image\n", + "\n", + "url = \"https://huggingface.co/datasets/merve/vlm_test_images/resolve/main/venice.jpg\"\n", + "image = Image.open(requests.get(url, stream=True).raw)\n", + "labels = [\"venice\", \"venezia\", \"berlin\"]" + ], + "metadata": { + "id": "VbHH5RQ2qzlo" + }, + "execution_count": 8, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "inputs = processor(text=labels, images=image, return_tensors=\"pt\", padding=True, ).to(\"cuda\")\n", + "\n", + "outputs = model(**inputs)" + ], + "metadata": { + "id": "XjCTXKWCmWdI" + }, + "execution_count": 9, + "outputs": [] + }, + { + "cell_type": "markdown", + "source": [ + "We take the probabilities assigned to labels \"venice\", \"venezia\", \"berlin\" respectively." + ], + "metadata": { + "id": "zZrVdIKltzFw" + } + }, + { + "cell_type": "code", + "source": [ + "logits_per_image = outputs.logits_per_image\n", + "probs = logits_per_image.softmax(dim=1)\n", + "\n", + "formatted_probs = [f\"{p.item()*100:.2f}%\" for p in probs[0]]\n", + "print(formatted_probs)" + ], + "metadata": { + "id": "L4X8lu7MroNt", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "bab3453d-5846-4518-be23-92cdc0d9e5a1" + }, + "execution_count": 10, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "['59.38%', '40.82%', '0.00%']\n" + ] + } + ] + }, + { + "cell_type": "markdown", + "source": [ + "## SAM2\n", + "\n", + "SAM2 is continuation for SAM (Segment Anything Model) by Meta, with addition of video inference and keeping additional memory across video frames to propagate a mask to next frames." + ], + "metadata": { + "id": "G5Jpbb4HuSLW" + } + }, + { + "cell_type": "code", + "source": [ + "from transformers import Sam2Processor, Sam2Model\n", + "import torch\n", + "\n", + "model = Sam2Model.from_pretrained(\"facebook/sam2-hiera-tiny\").to(\"cuda\")\n", + "processor = Sam2Processor.from_pretrained(\"facebook/sam2-hiera-tiny\")" + ], + "metadata": { + "id": "dDwUVBFkutJs", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 214, + "referenced_widgets": [ + "bdd292d1769449dd80b00c540885738b", + "c17c36edba134b999fc2449c2cf3d469", + "bf14f6cc11934619aea6e80f71d3237a", + "8f9bd5f6821c4c4ba88bc32f648fd79b", + "a9b80ef3b2664eca94f42c2db2cf478c", + "ebafeb6e5d26417290d79e23b1d7960a", + "63796f030a32458385a6a30f59a28c97", + "43b2b6d4320e40c498c924f11de65058", + "93b2328283cf4d08ad8c7407ed7e05af", + "88ca8fc4f45140f7bca5e66f1edf351d", + "7c60afe93d114c8388c3f6d69b2f0145", + "2e15e10fece246d7a9e1c0685207487e", + "81f5c3b043304f50857d3df7e75de7a8", + "5b9c0e9cca804e6c8ca44682812621a6", + "cdbc7efa2d3842a892db862a4b1bc2b9", + "3674b7b8076b4b2988fc9e14fd75ef2e", + "0273e9d39a2e496cb8e69743f53b9586", + "9daacec65c204a338a6f5ce7d53b479f", + "3a2f80b1640a4ff893bb88d20954a6bc", + "41c2832a1fce49688260b05cfdd18c24", + "9d34c25eb34c467eac6d8fd80750a536", + "11bb77f6817b46d68dd6d472fc4e94fe", + "5f452103369c4a5da5254ce45da10b27", + "2890e106c2954fa3b35bd1f1c3964d9f", + "996626dbcbaa4c10a4a56f09ff1ed107", + "b417c2d8048649588b1e223ceb1f1bf1", + "19d7db5882b54be9bd371dc123248c3e", + "ad318f6157a046f29ee41fe8fee3095f", + "d62bfbcce48e4067b9c9d8792722eaca", + "690b55661f7f46259e4b7af13adee811", + "9e43e8c6438f449f9d7f2fd313ddbda2", + "7e83a3d6ebe44556a403a79c4dc2f3df", + "2bc336c59d4d4455a3bccfb0b7aa53ca", + "517804613ac140eaaea5f58f2667332a", + "d0273c4db9f54143a765c683eca5442a", + "be2ac1c412534e8c8781232803861bfa", + "fb55ada03e0a4e89b46f931ca2c54551", + "ecc7f1d03a6c4bdeadf1547528123dac", + "9f0ac8d10dcf4af3a3cfd0b3184505d1", + "51934c86e44743d587c990c259d3cfa1", + "08314c4da2774b7ebac8b3f3a1e93f72", + "ba6fa0c793514fb48d772966bdadb183", + "666f9b45b7ee405bb703b621c1ba5f80", + "9379b87fc3e948809f1f11e4bc816b1d", + "81f9852cfa7f43178def864d20003f59", + "fadf7de524fe494db2f1691a42fd05c9", + "343c9a6e82444bacb0baa2ac96c8b00f", + "634c5fa2670c4a80902931ef0801c962", + "944dd815db3944f485ddba171268db23", + "606690bc2544411daec9b00316c08381", + "40091ea3563442aa934c1976232af538", + "353d43de98434a9eb2cf0fb39b6d5bb8", + "51f2f230271f4894b254f1f5cee2773d", + "3c78030ee62043589cf1f83644a6eba8", + "4f21f33a8d3746459ebd51f9f671dd94" + ] + }, + "outputId": "3f012250-0a09-492e-d675-3950ff447e5f" + }, + "execution_count": 1, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "config.json: 0.00B [00:00, ?B/s]" + ], + "application/vnd.jupyter.widget-view+json": { + "version_major": 2, + "version_minor": 0, + "model_id": "bdd292d1769449dd80b00c540885738b" + } + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + "You are using a model of type sam2_video to instantiate a model of type sam2. This is not supported for all configurations of models and can yield errors.\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "model.safetensors: 0%| | 0.00/156M [00:00