From 8787a9b9d22a4078c6172d03320df7a14a998f34 Mon Sep 17 00:00:00 2001 From: Maxime Labonne <81252890+mlabonne@users.noreply.github.com> Date: Fri, 29 Dec 2023 14:59:39 +0100 Subject: [PATCH] Created using Colaboratory --- Mergekit.ipynb | 1794 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 1794 insertions(+) create mode 100644 Mergekit.ipynb diff --git a/Mergekit.ipynb b/Mergekit.ipynb new file mode 100644 index 0000000..1abb204 --- /dev/null +++ b/Mergekit.ipynb @@ -0,0 +1,1794 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "provenance": [], + "machine_shape": "hm", + "authorship_tag": "ABX9TyMuGevIbBdnvORov5ZLmtGx", + "include_colab_link": true + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + }, + "language_info": { + "name": "python" + }, + "widgets": { + "application/vnd.jupyter.widget-state+json": { + "de24d272f2b842c5b01eedb3f536b810": { + "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_0c5dab2657b2473385a424d90f3d4664", + "IPY_MODEL_57efe36e546c473d8be34102f6ba9a58", + "IPY_MODEL_871bad1d905d4877a9eaa242cfd54c4e" + ], + "layout": "IPY_MODEL_8951f6b2edf64464869391197c900f84" + } + }, + "0c5dab2657b2473385a424d90f3d4664": { + "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_69a61ad28d5141dcbaea44060bc5ebf7", + "placeholder": "​", + "style": "IPY_MODEL_76c2fbf005ae4a5790edfeb499b387b7", + "value": "tokenizer.model: 100%" + } + }, + "57efe36e546c473d8be34102f6ba9a58": { + "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_116964f328dc45d991d895d684ac1216", + "max": 493443, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_1ecec5ba4424498082a5f64cf3d7faf8", + "value": 493443 + } + }, + "871bad1d905d4877a9eaa242cfd54c4e": { + "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_fc4edcef273b4e75894f4b512122de94", + "placeholder": "​", + "style": "IPY_MODEL_ca2323b142f54998985d30481d5cfabe", + "value": " 493k/493k [00:00<00:00, 42.2kB/s]" + } + }, + "8951f6b2edf64464869391197c900f84": { + "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 + } + }, + "69a61ad28d5141dcbaea44060bc5ebf7": { + "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 + } + }, + "76c2fbf005ae4a5790edfeb499b387b7": { + "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": "" + } + }, + "116964f328dc45d991d895d684ac1216": { + "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 + } + }, + "1ecec5ba4424498082a5f64cf3d7faf8": { + "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": "" + } + }, + "fc4edcef273b4e75894f4b512122de94": { + "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 + } + }, + "ca2323b142f54998985d30481d5cfabe": { + "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": "" + } + }, + "63626ac2d0f546188c07512a04c71417": { + "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_decd91747fd04ce39f3e2b733bc7f477", + "IPY_MODEL_7140e4c154424fcab846a71889e99ed2", + "IPY_MODEL_2264d8b75251425e94e635558af4e223" + ], + "layout": "IPY_MODEL_c37478198217457cb30c6649203cf4dc" + } + }, + "decd91747fd04ce39f3e2b733bc7f477": { + "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_4918769e4e984dfda924776e2373154c", + "placeholder": "​", + "style": "IPY_MODEL_9b48494c94cf49b5835489d97f7a24c5", + "value": "model-00001-of-00002.safetensors: 100%" + } + }, + "7140e4c154424fcab846a71889e99ed2": { + "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_6ed844da52fe466eb1c10c814489448c", + "max": 9942990000, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_9c60efa02e80423e828628190dd13bc3", + "value": 9942990000 + } + }, + "2264d8b75251425e94e635558af4e223": { + "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_0170e8cc57d94041956f7afbf2eef449", + "placeholder": "​", + "style": "IPY_MODEL_220c2ba5f2524271b24fe049431a474c", + "value": " 9.94G/9.94G [04:04<00:00, 36.9MB/s]" + } + }, + "c37478198217457cb30c6649203cf4dc": { + "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 + } + }, + "4918769e4e984dfda924776e2373154c": { + "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 + } + }, + "9b48494c94cf49b5835489d97f7a24c5": { + "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": "" + } + }, + "6ed844da52fe466eb1c10c814489448c": { + "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 + } + }, + "9c60efa02e80423e828628190dd13bc3": { + "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": "" + } + }, + "0170e8cc57d94041956f7afbf2eef449": { + "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 + } + }, + "220c2ba5f2524271b24fe049431a474c": { + "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": "" + } + }, + "a6f99dd0662846f9a381d2d507a7b447": { + "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_900b9fcb70a84781bd5b4213df54626d", + "IPY_MODEL_0ea83f270e164795b64f23b143efb300", + "IPY_MODEL_318dcdeac8fb40f88fa60114f1c6a7c1" + ], + "layout": "IPY_MODEL_af89cf715e0e4c5e9f59943a255394c1" + } + }, + "900b9fcb70a84781bd5b4213df54626d": { + "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_40e23e35299d45d499432b8f1a9bc924", + "placeholder": "​", + "style": "IPY_MODEL_126b374e286747768ef7218454534640", + "value": "Upload 3 LFS files: 100%" + } + }, + "0ea83f270e164795b64f23b143efb300": { + "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_bdd26e54eed5477f99b135552e5f3450", + "max": 3, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_163a6fd878134e1eb5f193d1ebfff1c1", + "value": 3 + } + }, + "318dcdeac8fb40f88fa60114f1c6a7c1": { + "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_953d7c014f76413c9805a2ef8c2c9356", + "placeholder": "​", + "style": "IPY_MODEL_348879bf76d1471f9c79c1ec2dc07c1d", + "value": " 3/3 [04:05<00:00, 245.46s/it]" + } + }, + "af89cf715e0e4c5e9f59943a255394c1": { + "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 + } + }, + "40e23e35299d45d499432b8f1a9bc924": { + "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 + } + }, + "126b374e286747768ef7218454534640": { + "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": "" + } + }, + "bdd26e54eed5477f99b135552e5f3450": { + "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 + } + }, + "163a6fd878134e1eb5f193d1ebfff1c1": { + "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": "" + } + }, + "953d7c014f76413c9805a2ef8c2c9356": { + "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 + } + }, + "348879bf76d1471f9c79c1ec2dc07c1d": { + "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": "" + } + }, + "8d54ae0d028b40e7b018454187db1a1c": { + "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_562353040be54593b23734390f49927c", + "IPY_MODEL_00cbebe6df7d4995913f20e39fc71b15", + "IPY_MODEL_aee3c563fdc54f9cb3ebc2630c84a9e6" + ], + "layout": "IPY_MODEL_b74e307a751844ffab9f7f3df367774b" + } + }, + "562353040be54593b23734390f49927c": { + "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_8e6142e41f714fe9abe6a5bb72c071f9", + "placeholder": "​", + "style": "IPY_MODEL_49cd1c5663404fb5a307c345e7e970c3", + "value": "model-00002-of-00002.safetensors: 100%" + } + }, + "00cbebe6df7d4995913f20e39fc71b15": { + "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_920ef8e509d24ccda930f4c47eff158c", + "max": 8030324832, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_c8828d61b26a47ac97a1541e14c00f62", + "value": 8030324832 + } + }, + "aee3c563fdc54f9cb3ebc2630c84a9e6": { + "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_a3d7e352222647a99be79935b1ebd86a", + "placeholder": "​", + "style": "IPY_MODEL_80666ef5f07641c482a23618a767791d", + "value": " 8.03G/8.03G [03:13<00:00, 54.0MB/s]" + } + }, + "b74e307a751844ffab9f7f3df367774b": { + "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 + } + }, + "8e6142e41f714fe9abe6a5bb72c071f9": { + "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 + } + }, + "49cd1c5663404fb5a307c345e7e970c3": { + "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": "" + } + }, + "920ef8e509d24ccda930f4c47eff158c": { + "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 + } + }, + "c8828d61b26a47ac97a1541e14c00f62": { + "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": "" + } + }, + "a3d7e352222647a99be79935b1ebd86a": { + "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 + } + }, + "80666ef5f07641c482a23618a767791d": { + "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", + "metadata": { + "id": "view-in-github", + "colab_type": "text" + }, + "source": [ + "\"Open" + ] + }, + { + "cell_type": "markdown", + "source": [ + "# Merge Large Language Models with mergekit\n", + "> 🗣️ [Large Language Model Course](https://github.com/mlabonne/llm-course)\n", + "\n", + "❤️ Created by [@maximelabonne](https://twitter.com/maximelabonne).\n", + "\n", + "Model merging only requires a lot of RAM. With a free Google Colab account, you should be able to run it using a T4 GPU (VRAM offloading).\n", + "\n", + "Examples of merge configurations:\n", + "\n", + "### TIES-Merging\n", + "\n", + "```yaml\n", + "models:\n", + " - model: mistralai/Mistral-7B-v0.1\n", + " # no parameters necessary for base model\n", + " - model: OpenPipe/mistral-ft-optimized-1218\n", + " parameters:\n", + " density: 0.5\n", + " weight: 0.5\n", + " - model: mlabonne/NeuralHermes-2.5-Mistral-7B\n", + " parameters:\n", + " density: 0.5\n", + " weight: 0.3\n", + "merge_method: ties\n", + "base_model: mistralai/Mistral-7B-v0.1\n", + "parameters:\n", + " normalize: true\n", + "dtype: float16\n", + "```\n", + "\n", + "You can find the final model on the Hugging Face Hub at [mlabonne/NeuralPipe-7B-ties](https://huggingface.co/mlabonne/NeuralPipe-7B-ties).\n", + "\n", + "### SLERP\n", + "\n", + "```yaml\n", + "slices:\n", + " - sources:\n", + " - model: OpenPipe/mistral-ft-optimized-1218\n", + " layer_range: [0, 32]\n", + " - model: mlabonne/NeuralHermes-2.5-Mistral-7B\n", + " layer_range: [0, 32]\n", + "merge_method: slerp\n", + "base_model: OpenPipe/mistral-ft-optimized-1218\n", + "parameters:\n", + " t:\n", + " - filter: self_attn\n", + " value: [0, 0.5, 0.3, 0.7, 1]\n", + " - filter: mlp\n", + " value: [1, 0.5, 0.7, 0.3, 0]\n", + " - value: 0.5\n", + "dtype: bfloat16\n", + "```\n", + "\n", + "You can find the final model on the Hugging Face Hub at [mlabonne/NeuralPipe-7B-slerp](https://huggingface.co/mlabonne/NeuralPipe-7B-slerp).\n", + "\n", + "### Passthrough\n", + "\n", + "```yaml\n", + "slices:\n", + " - sources:\n", + " - model: OpenPipe/mistral-ft-optimized-1218\n", + " layer_range: [0, 32]\n", + " - sources:\n", + " - model: mlabonne/NeuralHermes-2.5-Mistral-7B\n", + " layer_range: [24, 32]\n", + "merge_method: passthrough\n", + "dtype: bfloat16\n", + "```\n", + "\n", + "You can find the final model on the Hugging Face Hub at [mlabonne/NeuralPipe-9B-merged](https://huggingface.co/mlabonne/NeuralPipe-9B-merged)." + ], + "metadata": { + "id": "o12O0YjJvvLW" + } + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "NPNPie5Eo3EZ", + "outputId": "450c623b-7fc8-44df-c437-ea72b44a5a75" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + " Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n", + " Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n", + " Installing backend dependencies ... \u001b[?25l\u001b[?25hdone\n", + " Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m10.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m258.1/258.1 kB\u001b[0m \u001b[31m14.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m395.4/395.4 kB\u001b[0m \u001b[31m20.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m168.3/168.3 kB\u001b[0m \u001b[31m12.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m26.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.0/2.0 MB\u001b[0m \u001b[31m17.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25h Building wheel for mergekit (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", + "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n", + "lida 0.0.10 requires fastapi, which is not installed.\n", + "lida 0.0.10 requires kaleido, which is not installed.\n", + "lida 0.0.10 requires python-multipart, which is not installed.\n", + "lida 0.0.10 requires uvicorn, which is not installed.\n", + "llmx 0.0.15a0 requires cohere, which is not installed.\n", + "llmx 0.0.15a0 requires openai, which is not installed.\n", + "llmx 0.0.15a0 requires tiktoken, which is not installed.\n", + "tensorflow-probability 0.22.0 requires typing-extensions<4.6.0, but you have typing-extensions 4.9.0 which is incompatible.\u001b[0m\u001b[31m\n", + "\u001b[0m" + ] + } + ], + "source": [ + "!git clone https://github.com/cg123/mergekit.git\n", + "%cd mergekit\n", + "!pip install -qe ." + ] + }, + { + "cell_type": "code", + "source": [ + "MODEL_NAME = \"NeuralPipe-9B-merged\"\n", + "yaml_config = \"\"\"\n", + "slices:\n", + " - sources:\n", + " - model: OpenPipe/mistral-ft-optimized-1218\n", + " layer_range: [0, 32]\n", + " - sources:\n", + " - model: mlabonne/NeuralHermes-2.5-Mistral-7B\n", + " layer_range: [24, 32]\n", + "merge_method: passthrough\n", + "dtype: bfloat16\n", + "\"\"\"" + ], + "metadata": { + "id": "LGd7jlfCpNcg" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "import yaml\n", + "import torch\n", + "\n", + "from mergekit.config import MergeConfiguration\n", + "from mergekit.merge import MergeOptions, run_merge\n", + "\n", + "# Load merge config\n", + "data = yaml.safe_load(yaml_config)\n", + "merge_config = MergeConfiguration.model_validate(data)\n", + "\n", + "# Merge models\n", + "run_merge(\n", + " merge_config,\n", + " \"./merged\",\n", + " options=MergeOptions(\n", + " lora_merge_cache='/tmp',\n", + " cuda=torch.cuda.is_available(),\n", + " low_cpu_memory=True, # VRAM offloading\n", + " copy_tokenizer=True,\n", + " trust_remote_code=False,\n", + " lazy_unpickle=False,\n", + " ),\n", + ")" + ], + "metadata": { + "id": "d5mYzDo1q96y" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "!pip install -qU huggingface_hub\n", + "\n", + "from huggingface_hub import ModelCard, ModelCardData\n", + "from jinja2 import Template\n", + "\n", + "template_text = \"\"\"\n", + "---\n", + "license: apache-2.0\n", + "tags:\n", + "- merge\n", + "- mergekit\n", + "---\n", + "\n", + "# {{ model_name }}\n", + "\n", + "This model is a merge of the following models made with [mergekit](https://github.com/cg123/mergekit):\n", + "\n", + "{%- for model in models %}\n", + " * [{{ model }}](https://huggingface.co/{{ model }})\n", + "{%- endfor %}\n", + "\n", + "## 🧩 Configuration\n", + "\n", + "```yaml\n", + "{{- yaml_config -}}\n", + "```\n", + "\"\"\"\n", + "\n", + "# Create a Jinja template object\n", + "jinja_template = Template(template_text.strip())\n", + "\n", + "# Fill the template\n", + "models = [data[\"slices\"][i][\"sources\"][0][\"model\"] for i in range(len(data[\"slices\"]))]\n", + "# models = [\"OpenPipe/mistral-ft-optimized-1218\", \"mlabonne/NeuralHermes-2.5-Mistral-7B\"]\n", + "content = jinja_template.render(\n", + " model_name=MODEL_NAME,\n", + " models=models,\n", + " yaml_config=yaml_config,\n", + ")\n", + "\n", + "# Save the model card\n", + "card = ModelCard(content)\n", + "card.save('merged/README.md')" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "w-RNKev373lI", + "outputId": "fccbbd1d-295f-4def-a398-f226813294bb" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "\u001b[?25l \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/330.1 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K \u001b[91m━━━━━━━━━━━━━\u001b[0m\u001b[91m╸\u001b[0m\u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m112.6/330.1 kB\u001b[0m \u001b[31m3.4 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m330.1/330.1 kB\u001b[0m \u001b[31m4.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25h" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "from google.colab import userdata\n", + "from huggingface_hub import HfApi\n", + "\n", + "username = \"mlabonne\"\n", + "\n", + "# Defined in the secrets tab in Google Colab\n", + "api = HfApi(token=userdata.get(\"HF_TOKEN\"))\n", + "\n", + "api.create_repo(\n", + " repo_id=f\"{username}/{MODEL_NAME}\",\n", + " repo_type=\"model\"\n", + ")\n", + "api.upload_folder(\n", + " repo_id=f\"{username}/{MODEL_NAME}\",\n", + " folder_path=\"merged\",\n", + ")" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 164, + "referenced_widgets": [ + "de24d272f2b842c5b01eedb3f536b810", + "0c5dab2657b2473385a424d90f3d4664", + "57efe36e546c473d8be34102f6ba9a58", + "871bad1d905d4877a9eaa242cfd54c4e", + "8951f6b2edf64464869391197c900f84", + "69a61ad28d5141dcbaea44060bc5ebf7", + "76c2fbf005ae4a5790edfeb499b387b7", + "116964f328dc45d991d895d684ac1216", + "1ecec5ba4424498082a5f64cf3d7faf8", + "fc4edcef273b4e75894f4b512122de94", + "ca2323b142f54998985d30481d5cfabe", + "63626ac2d0f546188c07512a04c71417", + "decd91747fd04ce39f3e2b733bc7f477", + "7140e4c154424fcab846a71889e99ed2", + "2264d8b75251425e94e635558af4e223", + "c37478198217457cb30c6649203cf4dc", + "4918769e4e984dfda924776e2373154c", + "9b48494c94cf49b5835489d97f7a24c5", + "6ed844da52fe466eb1c10c814489448c", + "9c60efa02e80423e828628190dd13bc3", + "0170e8cc57d94041956f7afbf2eef449", + "220c2ba5f2524271b24fe049431a474c", + "a6f99dd0662846f9a381d2d507a7b447", + "900b9fcb70a84781bd5b4213df54626d", + "0ea83f270e164795b64f23b143efb300", + "318dcdeac8fb40f88fa60114f1c6a7c1", + "af89cf715e0e4c5e9f59943a255394c1", + "40e23e35299d45d499432b8f1a9bc924", + "126b374e286747768ef7218454534640", + "bdd26e54eed5477f99b135552e5f3450", + "163a6fd878134e1eb5f193d1ebfff1c1", + "953d7c014f76413c9805a2ef8c2c9356", + "348879bf76d1471f9c79c1ec2dc07c1d", + "8d54ae0d028b40e7b018454187db1a1c", + "562353040be54593b23734390f49927c", + "00cbebe6df7d4995913f20e39fc71b15", + "aee3c563fdc54f9cb3ebc2630c84a9e6", + "b74e307a751844ffab9f7f3df367774b", + "8e6142e41f714fe9abe6a5bb72c071f9", + "49cd1c5663404fb5a307c345e7e970c3", + "920ef8e509d24ccda930f4c47eff158c", + "c8828d61b26a47ac97a1541e14c00f62", + "a3d7e352222647a99be79935b1ebd86a", + "80666ef5f07641c482a23618a767791d" + ] + }, + "id": "ik0V0dF55gfU", + "outputId": "9f6c605c-6b51-473d-c1fa-b103e9208785" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "tokenizer.model: 0%| | 0.00/493k [00:00