commit 2b7b82b05a2e688bd7b1f87f641be2b0365743e5
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Tue May 19 03:06:37 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: CohereForAI/aya-23-8B
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..37aacea
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,44 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+benchmarks.png filter=lfs diff=lfs merge=lfs -text
+winrates.png filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+
+assets/benchmarks.png filter=lfs diff=lfs merge=lfs -text
\ No newline at end of file
diff --git a/Aya_23_notebook.ipynb b/Aya_23_notebook.ipynb
new file mode 100644
index 0000000..08df4cb
--- /dev/null
+++ b/Aya_23_notebook.ipynb
@@ -0,0 +1,1264 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "gpuType": "A100",
+      "machine_shape": "hm"
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    },
+    "accelerator": "GPU",
+    "widgets": {
+      "application/vnd.jupyter.widget-state+json": {
+        "531def06b1f7430983a2e4ba33f41f7f": {
+          "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_847b6b899bfc4e9b89b6ecb136a21385",
+              "IPY_MODEL_412da2e9912f4eb0ab89d44f0bb09cec",
+              "IPY_MODEL_1d56fddc294241f6a7cb4a300cb09afd"
+            ],
+            "layout": "IPY_MODEL_6f83c639357f4729873f6897119532f0"
+          }
+        },
+        "847b6b899bfc4e9b89b6ecb136a21385": {
+          "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_2551b382eca04537a3a11cd70aaf574c",
+            "placeholder": "​",
+            "style": "IPY_MODEL_93e6cbabc77f4fd69ddc3dee9012cb8e",
+            "value": "Loading checkpoint shards: 100%"
+          }
+        },
+        "412da2e9912f4eb0ab89d44f0bb09cec": {
+          "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_da2997c847b84a32b43c377137f64b5e",
+            "max": 4,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_24f16c1efe8547f1ab36efcccda46b59",
+            "value": 4
+          }
+        },
+        "1d56fddc294241f6a7cb4a300cb09afd": {
+          "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_cc8cb81531344463aa881093fff8c2f0",
+            "placeholder": "​",
+            "style": "IPY_MODEL_f4c45b260e7a4feaaeef4c50c560641a",
+            "value": " 4/4 [00:12&lt;00:00,  2.77s/it]"
+          }
+        },
+        "6f83c639357f4729873f6897119532f0": {
+          "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
+          }
+        },
+        "2551b382eca04537a3a11cd70aaf574c": {
+          "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
+          }
+        },
+        "93e6cbabc77f4fd69ddc3dee9012cb8e": {
+          "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": ""
+          }
+        },
+        "da2997c847b84a32b43c377137f64b5e": {
+          "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
+          }
+        },
+        "24f16c1efe8547f1ab36efcccda46b59": {
+          "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": ""
+          }
+        },
+        "cc8cb81531344463aa881093fff8c2f0": {
+          "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
+          }
+        },
+        "f4c45b260e7a4feaaeef4c50c560641a": {
+          "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": ""
+          }
+        },
+        "0272ba7f31a2441ab1cb5b8f77dbaacb": {
+          "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_d1bb171ddebd4f4bbeb4ed5d4b8b7076",
+              "IPY_MODEL_33b4fc55703746778511265e28160837",
+              "IPY_MODEL_7548c151f8764276ad7951e2ac80d981"
+            ],
+            "layout": "IPY_MODEL_d972c72fef7c45998469550318661e71"
+          }
+        },
+        "d1bb171ddebd4f4bbeb4ed5d4b8b7076": {
+          "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_2811b7c68a7b4c95b91bd5690cf06577",
+            "placeholder": "​",
+            "style": "IPY_MODEL_a33ccfdb735948e98a19d901d8091319",
+            "value": "Loading checkpoint shards: 100%"
+          }
+        },
+        "33b4fc55703746778511265e28160837": {
+          "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_c1103244cec74a299265729e630faffd",
+            "max": 4,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_340941cfc49e4ab983b73fb48c30dfe8",
+            "value": 4
+          }
+        },
+        "7548c151f8764276ad7951e2ac80d981": {
+          "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_8bb42aa84f4b4a9ab6417aed92132063",
+            "placeholder": "​",
+            "style": "IPY_MODEL_b0cf428afc21468caeb664428627aaf6",
+            "value": " 4/4 [00:11&lt;00:00,  2.57s/it]"
+          }
+        },
+        "d972c72fef7c45998469550318661e71": {
+          "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
+          }
+        },
+        "2811b7c68a7b4c95b91bd5690cf06577": {
+          "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
+          }
+        },
+        "a33ccfdb735948e98a19d901d8091319": {
+          "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": ""
+          }
+        },
+        "c1103244cec74a299265729e630faffd": {
+          "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
+          }
+        },
+        "340941cfc49e4ab983b73fb48c30dfe8": {
+          "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": ""
+          }
+        },
+        "8bb42aa84f4b4a9ab6417aed92132063": {
+          "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
+          }
+        },
+        "b0cf428afc21468caeb664428627aaf6": {
+          "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": "code",
+      "source": [
+        "!pip install -U bitsandbytes transformers peft accelerate trl datasets sentencepiece wandb\n",
+        "!pip install flash-attn --no-build-isolation"
+      ],
+      "metadata": {
+        "id": "tg1moVggj5sk",
+        "collapsed": true
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "MODEL_NAME = \"CohereForAI/aya-23-8b\"\n",
+        "\n",
+        "# you may want to change the following parameters depending on your GPU configuration\n",
+        "\n",
+        "# free T4 instance\n",
+        "# QUANTIZE_4BIT = True\n",
+        "# USE_GRAD_CHECKPOINTING = True\n",
+        "# TRAIN_BATCH_SIZE = 2\n",
+        "# TRAIN_MAX_SEQ_LENGTH = 512\n",
+        "# USE_FLASH_ATTENTION = False\n",
+        "# GRAD_ACC_STEPS = 16\n",
+        "\n",
+        "# equivalent A100 setting\n",
+        "QUANTIZE_4BIT = True\n",
+        "USE_GRAD_CHECKPOINTING = True\n",
+        "TRAIN_BATCH_SIZE = 16\n",
+        "TRAIN_MAX_SEQ_LENGTH = 512\n",
+        "USE_FLASH_ATTENTION = True\n",
+        "GRAD_ACC_STEPS = 2"
+      ],
+      "metadata": {
+        "id": "Izn6BYEYw4um"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig,HfArgumentParser,TrainingArguments,pipeline, logging\n",
+        "from peft import LoraConfig, PeftModel, prepare_model_for_kbit_training, get_peft_model\n",
+        "import os,torch\n",
+        "import bitsandbytes as bnb\n",
+        "from datasets import load_dataset\n",
+        "from trl import SFTTrainer\n",
+        "from datasets import Dataset\n",
+        "import pyarrow as pa\n",
+        "import pyarrow.dataset as ds\n",
+        "import pandas as pd\n",
+        "import re\n",
+        "import wandb"
+      ],
+      "metadata": {
+        "id": "wMs9uNDMHL6R"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Load Model\n",
+        "quantization_config = None\n",
+        "if QUANTIZE_4BIT:\n",
+        "  quantization_config = BitsAndBytesConfig(\n",
+        "      load_in_4bit=True,\n",
+        "      bnb_4bit_quant_type=\"nf4\",\n",
+        "      bnb_4bit_use_double_quant=True,\n",
+        "      bnb_4bit_compute_dtype=torch.bfloat16,\n",
+        "  )\n",
+        "\n",
+        "attn_implementation = None\n",
+        "if USE_FLASH_ATTENTION:\n",
+        "  attn_implementation=\"flash_attention_2\"\n",
+        "\n",
+        "model = AutoModelForCausalLM.from_pretrained(\n",
+        "          MODEL_NAME,\n",
+        "          quantization_config=quantization_config,\n",
+        "          attn_implementation=attn_implementation,\n",
+        "          torch_dtype=torch.bfloat16,\n",
+        "          device_map=\"auto\",\n",
+        "        )"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 176,
+          "referenced_widgets": [
+            "531def06b1f7430983a2e4ba33f41f7f",
+            "847b6b899bfc4e9b89b6ecb136a21385",
+            "412da2e9912f4eb0ab89d44f0bb09cec",
+            "1d56fddc294241f6a7cb4a300cb09afd",
+            "6f83c639357f4729873f6897119532f0",
+            "2551b382eca04537a3a11cd70aaf574c",
+            "93e6cbabc77f4fd69ddc3dee9012cb8e",
+            "da2997c847b84a32b43c377137f64b5e",
+            "24f16c1efe8547f1ab36efcccda46b59",
+            "cc8cb81531344463aa881093fff8c2f0",
+            "f4c45b260e7a4feaaeef4c50c560641a"
+          ]
+        },
+        "id": "d9a23_jiC-qG",
+        "outputId": "3cf0666d-f23d-4382-b17b-c29cbe91d2f6"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_token.py:89: UserWarning: \n",
+            "The secret `HF_TOKEN` does not exist in your Colab secrets.\n",
+            "To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.\n",
+            "You will be able to reuse this secret in all of your notebooks.\n",
+            "Please note that authentication is recommended but still optional to access public models or datasets.\n",
+            "  warnings.warn(\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "Loading checkpoint shards:   0%|          | 0/4 [00:00<?, ?it/s]"
+            ],
+            "application/vnd.jupyter.widget-view+json": {
+              "version_major": 2,
+              "version_minor": 0,
+              "model_id": "531def06b1f7430983a2e4ba33f41f7f"
+            }
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Load tokenizer\n",
+        "tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "YuqAA8GhYSdO",
+        "outputId": "14553887-8142-492e-ca23-aeddac002815"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "def get_message_format(prompts):\n",
+        "  messages = []\n",
+        "\n",
+        "  for p in prompts:\n",
+        "    messages.append(\n",
+        "        [{\"role\": \"user\", \"content\": p}]\n",
+        "      )\n",
+        "\n",
+        "  return messages\n",
+        "\n",
+        "def generate_aya_23(\n",
+        "      prompts,\n",
+        "      model,\n",
+        "      temperature=0.3,\n",
+        "      top_p=0.75,\n",
+        "      top_k=0,\n",
+        "      max_new_tokens=1024\n",
+        "    ):\n",
+        "\n",
+        "  messages = get_message_format(prompts)\n",
+        "\n",
+        "  input_ids = tokenizer.apply_chat_template(\n",
+        "        messages,\n",
+        "        tokenize=True,\n",
+        "        add_generation_prompt=True,\n",
+        "        padding=True,\n",
+        "        return_tensors=\"pt\",\n",
+        "      )\n",
+        "  input_ids = input_ids.to(model.device)\n",
+        "  prompt_padded_len = len(input_ids[0])\n",
+        "\n",
+        "  gen_tokens = model.generate(\n",
+        "        input_ids,\n",
+        "        temperature=temperature,\n",
+        "        top_p=top_p,\n",
+        "        top_k=top_k,\n",
+        "        max_new_tokens=max_new_tokens,\n",
+        "        do_sample=True,\n",
+        "      )\n",
+        "\n",
+        "  # get only generated tokens\n",
+        "  gen_tokens = [\n",
+        "      gt[prompt_padded_len:] for gt in gen_tokens\n",
+        "    ]\n",
+        "\n",
+        "  gen_text = tokenizer.batch_decode(gen_tokens, skip_special_tokens=True)\n",
+        "  return gen_text"
+      ],
+      "metadata": {
+        "id": "s75a8Vda-eqx"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Test generations on langauges in Aya 23 set\n",
+        "prompts = [\n",
+        "    \"Write a list of three fruits and tell me about each of them\", # English\n",
+        "    \"Viết danh sách ba loại trái cây và kể cho tôi nghe về từng loại trái cây đó\", # Vietnamese\n",
+        "    \"3 つの果物のリストを書いて、それぞれについて教えてください\", # Japanese\n",
+        "    \"Üç meyveden oluşan bir liste yazın ve bana her birini anlatın\" # Turkish\n",
+        "]\n",
+        "\n",
+        "generations = generate_aya_23(prompts, model)\n",
+        "\n",
+        "for p, g in zip(prompts, generations):\n",
+        "  print(\n",
+        "      \"PROMPT\", p ,\"RESPONSE\", g, \"\\n\", sep=\"\\n\"\n",
+        "    )"
+      ],
+      "metadata": {
+        "id": "4l12EC7q-h3I",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "e32ee1a4-9d91-447f-9bde-c8c71c727d80"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "PROMPT\n",
+            "Write a list of three fruits and tell me about each of them\n",
+            "RESPONSE\n",
+            "Sure! Here is a list of three fruits, along with some information about each of them:\n",
+            "\n",
+            "1. Apple: Apples are a popular fruit that are widely cultivated across the world. They are typically round or oval in shape and come in a variety of colors, including red, green, yellow, and a blend of these colors. Apples are known for their crisp texture and sweet or tart taste. They are a good source of dietary fiber, vitamins, and antioxidants.\n",
+            "\n",
+            "2. Banana: Bananas are long, curved fruits that come in a range of colors, from yellow to brown. They are a good source of potassium, vitamins, and fiber. Bananas have a sweet taste and are often eaten raw, but they can also be used in baking or blended into smoothies.\n",
+            "\n",
+            "3. Orange: Oranges are citrus fruits known for their vibrant orange color and sweet, tangy taste. They are a good source of vitamin C and other nutrients. Oranges can be eaten fresh, juiced, or used in various dishes, such as salads, desserts, and marmalades.\n",
+            "\n",
+            "These fruits are not only delicious but also provide various health benefits and are commonly used in various cuisines worldwide.\n",
+            "\n",
+            "\n",
+            "PROMPT\n",
+            "Viết danh sách ba loại trái cây và kể cho tôi nghe về từng loại trái cây đó\n",
+            "RESPONSE\n",
+            "Dưới đây là ba loại trái cây phổ biến, mỗi loại có hương vị và đặc điểm riêng:\n",
+            "\n",
+            "1. Táo: Táo là một loại trái cây quen thuộc và phổ biến trên toàn thế giới. Chúng có nguồn gốc từ Châu Á nhưng hiện nay được trồng ở nhiều nơi. Táo có hình tròn hoặc oval, với nhiều loại khác nhau về kích thước và màu sắc. Vỏ táo có thể có màu đỏ, xanh hoặc vàng, trong khi phần thịt thường có màu trắng hoặc hồng nhạt. Táo có hương vị ngọt ngào và tươi mát, với một chút giòn khi ăn. Chúng chứa nhiều vitamin và chất xơ, làm cho táo trở thành một món ăn vặt lành mạnh. Táo cũng thường được sử dụng trong các món tráng miệng và nước ép.\n",
+            "\n",
+            "2. Cam: Cam là một loại trái cây nhiệt đới có nguồn gốc từ Châu Phi và hiện nay được trồng rộng rãi trên toàn thế giới. Chúng có hình tròn hoặc oval, với vỏ cam hoặc vàng và thịt màu cam tươi sáng. Cam có hương vị ngọt ngào và chua nhẹ, với một chút giòn khi ăn. Chúng chứa nhiều vitamin C và có thể được ăn tươi hoặc ép lấy nước. Cam cũng thường được sử dụng trong các món salad, nước ép và các món tráng miệng.\n",
+            "\n",
+            "3. Dâu tây: Dâu tây là một loại trái cây mọng nước có nguồn gốc từ Châu Âu và hiện nay được trồng rộng rãi trên toàn thế giới. Chúng có hình tròn hoặc oval, với màu đỏ tươi hoặc hồng nhạt và thịt trắng hoặc hồng nhạt. Dâu tây có hương vị ngọt ngào và tươi mát, với một chút giòn. Chúng thường được sử dụng trong các món tráng miệng, bánh ngọt và salad. Dâu tây cũng chứa nhiều vitamin và chất chống oxy hóa, làm cho chúng trở thành một lựa chọn lành mạnh.\n",
+            "\n",
+            "Mỗi loại trái cây này đều có hương vị và đặc điểm riêng, nhưng tất cả đều là những lựa chọn lành mạnh và ngon miệng cho bữa ăn nhẹ hoặc món tráng miệng.\n",
+            "\n",
+            "\n",
+            "PROMPT\n",
+            "3 つの果物のリストを書いて、それぞれについて教えてください\n",
+            "RESPONSE\n",
+            "もちろんです！ 3 つの果物は次のとおりです。\n",
+            "\n",
+            "1. リンゴ: リンゴは世界中で広く栽培されている人気のある果物です。甘くてジューシーな味と食感で知られ、赤、緑、黄色などさまざまな品種があります。リンゴはビタミンや食物繊維が豊富で、健康的なスナックとしてよく食べられています。\n",
+            "\n",
+            "2. オレンジ: オレンジは柑橘類の一種で、ビタミン C が豊富に含まれています。甘酸っぱい味わいとジューシーな食感が特徴で、世界中で広く消費されています。オレンジは免疫力を高め、健康な皮膚と髪を維持するのに役立つと考えられています。\n",
+            "\n",
+            "3. スターフルーツ: スターフルーツは、その名前が示すように、星形をした独特の形をした果物です。甘くて爽やかな味わいで、ビタミン C と食物繊維が豊富です。スターフルーツは通常、生として食べられますが、ジュースやデザートにも使われます。\n",
+            "\n",
+            "これらの果物はすべて、栄養価が高く、さまざまな健康上の利点を提供します。世界中で広く利用可能で、さまざまな方法で楽しむことができます。\n",
+            "\n",
+            "\n",
+            "PROMPT\n",
+            "Üç meyveden oluşan bir liste yazın ve bana her birini anlatın\n",
+            "RESPONSE\n",
+            "Elma, armut ve çilek.\n",
+            "\n",
+            "Elma: Elma, dünyanın birçok bölgesinde yetişen popüler ve yaygın bir meyvedir. Genellikle kırmızı veya yeşil kabuğu ve sulu, tatlı eti vardır. Elma, vitamin C ve lif bakımından zengindir ve sağlıklı bir atıştırmalık olarak kabul edilir.\n",
+            "\n",
+            "Armut: Armut, yaz aylarında hasat edilen ve genellikle sarı, yeşil veya mor renkte olan bir meyvedir. Armut, elmaya benzer bir tada sahiptir, ancak daha yumuşak ve sulu bir dokuya sahiptir. Armut da vitamin C ve K bakımından zengindir ve sindirimi kolay bir meyve olarak bilinir.\n",
+            "\n",
+            "Çilek: Çilek, bahar ve yaz aylarında hasat edilen ve tatlı ve aromatik bir tada sahip kırmızı meyvelerdir. Çilekler genellikle taze olarak yenir, ancak dondurulmuş veya kurutulmuş olarak da tüketilebilir. Vitamin C ve antioksidanlar bakımından zengindir ve kalp sağlığını destekleyebileceği düşünülmektedir.\n",
+            "\n",
+            "Bu üç meyve, her birinin kendine has özellikleri ve faydaları olan lezzetli ve besleyici seçenekler sunar.\n",
+            "\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Test Bengali (not in Aya 23 set) inference on base model\n",
+        "\n",
+        "prompts = [\n",
+        "  'Translate from English to Bengali: \"Rates are competitive, almost always the best in the market\"'\n",
+        "]\n",
+        "\n",
+        "generations = generate_aya_23(prompts, model)\n",
+        "\n",
+        "for p, g in zip(prompts, generations):\n",
+        "  print(\n",
+        "      \"PROMPT\", p ,\"RESPONSE\", g, \"\\n\", sep=\"\\n\"\n",
+        "    )"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "tkEl3__Mwd8N",
+        "outputId": "d4cf3e07-f148-4a57-cd69-b72acfc15b54"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "PROMPT\n",
+            "Translate from English to Bengali: \"Rates are competitive, almost always the best in the market\"\n",
+            "RESPONSE\n",
+            "\"পরিণতি সংসাধানকরি, বাজারের সম্পর্কে সম্প্রতি সবচেয়ে বেশি\"\n",
+            "\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Load an English to Bengali translation dataset from Aya Collection\n",
+        "dataset = load_dataset(\"CohereForAI/aya_collection\", \"templated_indic_sentiment\")['train']\n",
+        "dataset = dataset.filter(lambda example: example['language']=='ben')\n",
+        "\n",
+        "def formatting_prompts_func(example):\n",
+        "    output_texts = []\n",
+        "    for i in range(len(example['inputs'])):\n",
+        "        text = f\"<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{example['inputs'][i]}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>{example['targets'][i]}\"\n",
+        "        output_texts.append(text)\n",
+        "    return output_texts"
+      ],
+      "metadata": {
+        "id": "CHXm3Io5zCrk"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Training Arguments\n",
+        "training_arguments = TrainingArguments(\n",
+        "    output_dir=\"results\",\n",
+        "    num_train_epochs=20,\n",
+        "    per_device_train_batch_size=TRAIN_BATCH_SIZE,\n",
+        "    gradient_accumulation_steps=GRAD_ACC_STEPS,\n",
+        "    gradient_checkpointing=USE_GRAD_CHECKPOINTING,\n",
+        "    optim=\"paged_adamw_32bit\",\n",
+        "    save_steps=50,\n",
+        "    logging_steps=10,\n",
+        "    learning_rate=1e-3,\n",
+        "    weight_decay=0.001,\n",
+        "    fp16=False,\n",
+        "    bf16=True,\n",
+        "    warmup_ratio=0.05,\n",
+        "    group_by_length=True,\n",
+        "    lr_scheduler_type=\"constant\",\n",
+        "    report_to=\"none\"\n",
+        ")\n",
+        "\n",
+        "peft_config = LoraConfig(\n",
+        "    lora_alpha=32,\n",
+        "    r=32,\n",
+        "    bias=\"none\",\n",
+        "    task_type=\"CAUSAL_LM\",\n",
+        "    target_modules=[\"q_proj\", \"v_proj\", \"k_proj\", \"o_proj\"]\n",
+        ")\n",
+        "\n",
+        "trainer = SFTTrainer(\n",
+        "    model=model,\n",
+        "    train_dataset=dataset,\n",
+        "    peft_config=peft_config,\n",
+        "    max_seq_length=TRAIN_MAX_SEQ_LENGTH,\n",
+        "    tokenizer=tokenizer,\n",
+        "    args=training_arguments,\n",
+        "    formatting_func=formatting_prompts_func\n",
+        ")"
+      ],
+      "metadata": {
+        "id": "A9OdyDDEy7rM",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "49592f25-4aaf-4e21-f612-a6fe5c5865e1"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/usr/local/lib/python3.10/dist-packages/trl/trainer/sft_trainer.py:318: UserWarning: You passed a tokenizer with `padding_side` not equal to `right` to the SFTTrainer. This might lead to some unexpected behaviour due to overflow issues when training a model in half-precision. You might consider adding `tokenizer.padding_side = 'right'` to your code.\n",
+            "  warnings.warn(\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "trainer.train()"
+      ],
+      "metadata": {
+        "id": "9BvK-3eYiwhx"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Save the model to disk\n",
+        "trainer.model.save_pretrained(save_directory='aya-qlora')\n",
+        "model.config.use_cache = True\n",
+        "model.eval()"
+      ],
+      "metadata": {
+        "id": "X3Lqfwo-8CCG"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Test Bengali inference on loaded fine-tuned model\n",
+        "\n",
+        "# Load Model and LoRA Adapter\n",
+        "quantization_config = None\n",
+        "if QUANTIZE_4BIT:\n",
+        "  quantization_config = BitsAndBytesConfig(\n",
+        "      load_in_4bit=True,\n",
+        "      bnb_4bit_quant_type=\"nf4\",\n",
+        "      bnb_4bit_use_double_quant=True,\n",
+        "      bnb_4bit_compute_dtype=torch.bfloat16,\n",
+        "  )\n",
+        "\n",
+        "attn_implementation = None\n",
+        "if USE_FLASH_ATTENTION:\n",
+        "  attn_implementation=\"flash_attention_2\"\n",
+        "\n",
+        "loaded_model = AutoModelForCausalLM.from_pretrained(\n",
+        "          MODEL_NAME,\n",
+        "          quantization_config=quantization_config,\n",
+        "          attn_implementation=attn_implementation,\n",
+        "          torch_dtype=torch.bfloat16,\n",
+        "          device_map=\"auto\",\n",
+        "        )\n",
+        "tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)\n",
+        "loaded_model.load_adapter(\"aya-qlora\")\n",
+        "\n",
+        "\n",
+        "prompts = [\n",
+        "  'Translate from English to Bengali: \"Rates are competitive, almost always the best in the market\"'\n",
+        "]\n",
+        "\n",
+        "generations = generate_aya_23(prompts, loaded_model)\n",
+        "\n",
+        "for p, g in zip(prompts, generations):\n",
+        "  print(\n",
+        "      \"PROMPT\", p ,\"RESPONSE\", g, \"\\n\", sep=\"\\n\"\n",
+        "    )"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 174,
+          "referenced_widgets": [
+            "0272ba7f31a2441ab1cb5b8f77dbaacb",
+            "d1bb171ddebd4f4bbeb4ed5d4b8b7076",
+            "33b4fc55703746778511265e28160837",
+            "7548c151f8764276ad7951e2ac80d981",
+            "d972c72fef7c45998469550318661e71",
+            "2811b7c68a7b4c95b91bd5690cf06577",
+            "a33ccfdb735948e98a19d901d8091319",
+            "c1103244cec74a299265729e630faffd",
+            "340941cfc49e4ab983b73fb48c30dfe8",
+            "8bb42aa84f4b4a9ab6417aed92132063",
+            "b0cf428afc21468caeb664428627aaf6"
+          ]
+        },
+        "id": "w5HGIJtRJN-y",
+        "outputId": "441193fe-89fa-40ad-8585-d1f2dcf124e5"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "Loading checkpoint shards:   0%|          | 0/4 [00:00<?, ?it/s]"
+            ],
+            "application/vnd.jupyter.widget-view+json": {
+              "version_major": 2,
+              "version_minor": 0,
+              "model_id": "0272ba7f31a2441ab1cb5b8f77dbaacb"
+            }
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n"
+          ]
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "PROMPT\n",
+            "Translate from English to Bengali: \"Rates are competitive, almost always the best in the market\"\n",
+            "RESPONSE\n",
+            "\"দরগুলি প্রতিযোগিতামূলক, প্রায় সবসময় বাজারে সেরা\"\n",
+            "\n",
+            "\n"
+          ]
+        }
+      ]
+    }
+  ]
+}
\ No newline at end of file
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..8196a65
--- /dev/null
+++ b/README.md
@@ -0,0 +1,385 @@
+---
+inference: false
+library_name: transformers
+language:
+- en
+- fr
+- de
+- es
+- it
+- pt
+- ja
+- ko
+- zh
+- ar
+- el
+- fa
+- pl
+- id
+- cs
+- he
+- hi
+- nl
+- ro
+- ru
+- tr
+- uk
+- vi
+license: cc-by-nc-4.0
+extra_gated_prompt: "By submitting this form, you agree to the [License Agreement](https://cohere.com/c4ai-cc-by-nc-license)  and acknowledge that the information you provide will be collected, used, and shared in accordance with Cohere’s [Privacy Policy]( https://cohere.com/privacy). You’ll receive email updates about Cohere Labs and Cohere research, events, products and services. You can unsubscribe at any time." 
+extra_gated_fields:
+ Name: text
+ Affiliation: text
+ Country:
+    type: select
+    options: 
+      - Aruba
+      - Afghanistan
+      - Angola
+      - Anguilla
+      - Åland Islands
+      - Albania
+      - Andorra
+      - United Arab Emirates
+      - Argentina
+      - Armenia
+      - American Samoa
+      - Antarctica
+      - French Southern Territories
+      - Antigua and Barbuda
+      - Australia
+      - Austria
+      - Azerbaijan
+      - Burundi
+      - Belgium
+      - Benin
+      - Bonaire Sint Eustatius and Saba
+      - Burkina Faso
+      - Bangladesh
+      - Bulgaria
+      - Bahrain
+      - Bahamas
+      - Bosnia and Herzegovina
+      - Saint Barthélemy
+      - Belarus
+      - Belize
+      - Bermuda
+      - Plurinational State of Bolivia
+      - Brazil
+      - Barbados
+      - Brunei-Darussalam
+      - Bhutan
+      - Bouvet-Island
+      - Botswana
+      - Central African Republic
+      - Canada
+      - Cocos (Keeling) Islands
+      - Switzerland
+      - Chile
+      - China
+      - Côte-dIvoire
+      - Cameroon
+      - Democratic Republic of the Congo
+      - Cook Islands
+      - Colombia
+      - Comoros
+      - Cabo Verde
+      - Costa Rica
+      - Cuba
+      - Curaçao
+      - Christmas Island
+      - Cayman Islands
+      - Cyprus
+      - Czechia
+      - Germany
+      - Djibouti
+      - Dominica
+      - Denmark
+      - Dominican Republic
+      - Algeria
+      - Ecuador
+      - Egypt
+      - Eritrea
+      - Western Sahara
+      - Spain
+      - Estonia
+      - Ethiopia
+      - Finland
+      - Fiji
+      - Falkland Islands (Malvinas)
+      - France
+      - Faroe Islands
+      - Federated States of Micronesia
+      - Gabon
+      - United Kingdom
+      - Georgia
+      - Guernsey
+      - Ghana
+      - Gibraltar
+      - Guinea
+      - Guadeloupe
+      - Gambia
+      - Guinea Bissau
+      - Equatorial Guinea
+      - Greece
+      - Grenada
+      - Greenland
+      - Guatemala
+      - French Guiana
+      - Guam
+      - Guyana
+      - Hong Kong
+      - Heard Island and McDonald Islands
+      - Honduras
+      - Croatia
+      - Haiti
+      - Hungary
+      - Indonesia
+      - Isle of Man
+      - India
+      - British Indian Ocean Territory
+      - Ireland
+      - Islamic Republic of Iran
+      - Iraq
+      - Iceland
+      - Israel
+      - Italy
+      - Jamaica
+      - Jersey
+      - Jordan
+      - Japan
+      - Kazakhstan
+      - Kenya
+      - Kyrgyzstan
+      - Cambodia
+      - Kiribati
+      - Saint-Kitts-and-Nevis
+      - South Korea
+      - Kuwait
+      - Lao-Peoples-Democratic-Republic
+      - Lebanon
+      - Liberia
+      - Libya
+      - Saint-Lucia
+      - Liechtenstein
+      - Sri Lanka
+      - Lesotho
+      - Lithuania
+      - Luxembourg
+      - Latvia
+      - Macao
+      - Saint Martin (French-part)
+      - Morocco
+      - Monaco
+      - Republic of Moldova
+      - Madagascar
+      - Maldives
+      - Mexico
+      - Marshall Islands
+      - North Macedonia
+      - Mali
+      - Malta
+      - Myanmar
+      - Montenegro
+      - Mongolia
+      - Northern Mariana Islands
+      - Mozambique
+      - Mauritania
+      - Montserrat
+      - Martinique
+      - Mauritius
+      - Malawi
+      - Malaysia
+      - Mayotte
+      - Namibia
+      - New Caledonia
+      - Niger
+      - Norfolk Island
+      - Nigeria
+      - Nicaragua
+      - Niue
+      - Netherlands
+      - Norway
+      - Nepal
+      - Nauru
+      - New Zealand
+      - Oman
+      - Pakistan
+      - Panama
+      - Pitcairn
+      - Peru
+      - Philippines
+      - Palau
+      - Papua New Guinea
+      - Poland
+      - Puerto Rico
+      - North Korea
+      - Portugal
+      - Paraguay
+      - State of Palestine
+      - French Polynesia
+      - Qatar
+      - Réunion
+      - Romania
+      - Russia
+      - Rwanda
+      - Saudi Arabia
+      - Sudan
+      - Senegal
+      - Singapore
+      - South Georgia and the South Sandwich Islands
+      - Saint Helena Ascension and Tristan da Cunha
+      - Svalbard and Jan Mayen
+      - Solomon Islands
+      - Sierra Leone
+      - El Salvador
+      - San Marino
+      - Somalia
+      - Saint Pierre and Miquelon
+      - Serbia
+      - South Sudan
+      - Sao Tome and Principe
+      - Suriname
+      - Slovakia
+      - Slovenia
+      - Sweden
+      - Eswatini
+      - Sint Maarten (Dutch-part)
+      - Seychelles
+      - Syrian Arab Republic
+      - Turks and Caicos Islands
+      - Chad
+      - Togo
+      - Thailand
+      - Tajikistan
+      - Tokelau
+      - Turkmenistan
+      - Timor Leste
+      - Tonga
+      - Trinidad and Tobago
+      - Tunisia
+      - Turkey
+      - Tuvalu
+      - Taiwan 
+      - United Republic of Tanzania
+      - Uganda
+      - Ukraine
+      - United States Minor Outlying Islands
+      - Uruguay
+      - United-States
+      - Uzbekistan
+      - Holy See (Vatican City State)
+      - Saint Vincent and the Grenadines
+      - Bolivarian Republic of Venezuela
+      - Virgin Islands British
+      - Virgin Islands U.S.
+      - VietNam
+      - Vanuatu
+      - Wallis and Futuna
+      - Samoa
+      - Yemen
+      - South Africa
+      - Zambia
+      - Zimbabwe
+ 
+ I agree to use this model for non-commercial use ONLY: checkbox
+---
+
+# Model Card for Aya-23-8B
+
+**Note:** This is an older version of Aya. The latest version is Aya Expanse 8B which is available [here](https://huggingface.co/CohereLabs/aya-expanse-8b). We also have multimodal variant, Aya Vision 8B which is available [here](https://huggingface.co/CohereLabs/aya-vision-8b).
+
+**Try Aya Expanse and Aya Vision:**
+
+You can try out latest Aya models before downloading the weights in our hosted Hugging Face Space [here](https://huggingface.co/spaces/CohereLabs/aya_expanse).
+
+## Model Summary
+
+Aya 23 is an open weights research release of an instruction fine-tuned model with highly advanced multilingual capabilities. Aya 23 focuses on pairing a highly performant pre-trained [Command family](https://huggingface.co/CohereLabs/c4ai-command-r-plus) of models with the recently released [Aya Collection](https://huggingface.co/datasets/CohereLabs/aya_collection). The result is a powerful multilingual large language model serving 23 languages.
+
+This model card corresponds to the 8-billion version of the Aya 23 model. We also released a 35-billion version which you can find [here](https://huggingface.co/CohereLabs/aya-23-35B).
+
+We cover 23 languages: Arabic, Chinese (simplified & traditional), Czech, Dutch, English, French, German, Greek, Hebrew, Hindi, Indonesian, Italian, Japanese, Korean, Persian, Polish, Portuguese, Romanian, Russian, Spanish, Turkish, Ukrainian, and Vietnamese
+
+Developed by: [Cohere Labs](https://cohere.for.ai) and [Cohere](https://cohere.com/) 
+
+- Point of Contact: Cohere Labs: [cohere.for.ai](https://cohere.for.ai/)
+- License: [CC-BY-NC](https://cohere.com/c4ai-cc-by-nc-license), requires also adhering to [Cohere Lab's Acceptable Use Policy](https://docs.cohere.com/docs/cohere-labs-acceptable-use-policy)
+- Model: aya-23-8B
+- Model Size: 8 billion parameters
+
+### Usage
+
+Please install transformers from the source repository that includes the necessary changes for this model
+
+```python
+# pip install transformers==4.41.1
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_id = "CohereLabs/aya-23-8B"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+# Format message with the command-r-plus chat template
+messages = [{"role": "user", "content": "Anneme onu ne kadar sevdiğimi anlatan bir mektup yaz"}]
+input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
+## <BOS_TOKEN><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Anneme onu ne kadar sevdiğimi anlatan bir mektup yaz<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
+
+gen_tokens = model.generate(
+    input_ids, 
+    max_new_tokens=100, 
+    do_sample=True, 
+    temperature=0.3,
+    )
+
+gen_text = tokenizer.decode(gen_tokens[0])
+print(gen_text)
+```
+
+### Example Notebook
+
+[This notebook](https://huggingface.co/CohereLabs/aya-23-8B/blob/main/Aya_23_notebook.ipynb) showcases a detailed use of Aya 23 (8B) including inference and fine-tuning with [QLoRA](https://huggingface.co/blog/4bit-transformers-bitsandbytes). 
+
+## Model Details
+
+**Input**: Models input text only.
+
+**Output**: Models generate text only.
+
+**Model Architecture**: Aya-23-8B is an auto-regressive language model that uses an optimized transformer architecture. After pretraining, this model is fine-tuned (IFT) to follow human instructions.
+
+**Languages covered**: The model is particularly optimized for multilinguality and supports the following languages: Arabic, Chinese (simplified & traditional), Czech, Dutch, English, French, German, Greek, Hebrew, Hindi, Indonesian, Italian, Japanese, Korean, Persian, Polish, Portuguese, Romanian, Russian, Spanish, Turkish, Ukrainian, and Vietnamese
+
+**Context length**: 8192
+
+### Evaluation
+
+<img src="./assets/benchmarks.png" alt="multilingual benchmarks" width="650" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
+<img src="./assets/winrates.png" alt="average win rates" width="650" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
+
+Please refer to the [Aya 23 technical report](https://cohere.com/research/papers/aya-command-23-8b-and-35b-technical-report-2024-05-23) for further details about the base model, data, instruction tuning, and evaluation.
+
+### Model Card Contact
+
+For errors or additional questions about details in this model card, contact labs@cohere.com
+
+### Terms of Use
+
+We hope that the release of this model will make community-based research efforts more accessible, by releasing the weights of a highly performant multilingual model to researchers all over the world. This model is governed by a [CC-BY-NC](https://cohere.com/c4ai-cc-by-nc-license) License with an acceptable use addendum, and also requires adhering to [Cohere Lab's Acceptable Use Policy](https://docs.cohere.com/docs/c4ai-acceptable-use-policy).
+
+### Try the model today
+
+You can try Aya 23 in the Cohere [playground](https://dashboard.cohere.com/playground/chat) here. You can also use it in our dedicated Hugging Face Space [here](https://huggingface.co/spaces/CohereLabs/aya-23).
+
+### Citation info
+```bibtex
+@misc{aryabumi2024aya,
+      title={Aya 23: Open Weight Releases to Further Multilingual Progress}, 
+      author={Viraat Aryabumi and John Dang and Dwarak Talupuru and Saurabh Dash and David Cairuz and Hangyu Lin and Bharat Venkitesh and Madeline Smith and Kelly Marchisio and Sebastian Ruder and Acyr Locatelli and Julia Kreutzer and Nick Frosst and Phil Blunsom and Marzieh Fadaee and Ahmet Üstün and Sara Hooker},
+      year={2024},
+      eprint={2405.15032},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+
+```
\ No newline at end of file
diff --git a/assets/benchmarks.png b/assets/benchmarks.png
new file mode 100644
index 0000000..2d2e8b0
--- /dev/null
+++ b/assets/benchmarks.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2adc7895ac0db2e66a6af65ff86f06e836d399667ecb293218d49342a77abd6
+size 19001997
diff --git a/assets/winrates.png b/assets/winrates.png
new file mode 100644
index 0000000..df2daf6
--- /dev/null
+++ b/assets/winrates.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29ed3235477a298b6056e85a09036f6e94601bee96f01a51f6597a70d3041a71
+size 368004
diff --git a/benchmarks.png b/benchmarks.png
new file mode 100644
index 0000000..2d2e8b0
--- /dev/null
+++ b/benchmarks.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2adc7895ac0db2e66a6af65ff86f06e836d399667ecb293218d49342a77abd6
+size 19001997
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..7fa0047
--- /dev/null
+++ b/config.json
@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "CohereForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 5,
+  "eos_token_id": 255001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "layer_norm_eps": 1e-05,
+  "logit_scale": 0.0625,
+  "max_position_embeddings": 8192,
+  "model_type": "cohere",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "rope_theta": 10000,
+  "torch_dtype": "float16",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": true,
+  "use_qk_norm": false,
+  "vocab_size": 256000
+}
diff --git a/configuration.json b/configuration.json
new file mode 100644
index 0000000..bbeeda1
--- /dev/null
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
\ No newline at end of file
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..2a59226
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 5,
+  "eos_token_id": 255001,
+  "pad_token_id": 0,
+  "transformers_version": "4.40.0.dev0"
+}
diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors
new file mode 100644
index 0000000..a737e87
--- /dev/null
+++ b/model-00001-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f01f8160949b5749db1b73b5c2ca51443eb658a8a0a736fa3b2a2f2de7576d4c
+size 4915779640
diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors
new file mode 100644
index 0000000..9336d93
--- /dev/null
+++ b/model-00002-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4518e8e02690bb6806709fffc89ef8efa25d6ece7c776ff6c5693d5f78432b0
+size 4915824616
diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors
new file mode 100644
index 0000000..7497d5f
--- /dev/null
+++ b/model-00003-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79f3dcc14a6c6b0233ae5c2749af1071f5c44e4e7b6780d84969f94b1ad6c1c0
+size 4999719496
diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors
new file mode 100644
index 0000000..2b00e63
--- /dev/null
+++ b/model-00004-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6582f3934d7bb6e0d4864d4c29d76c301f22fd7c7453a576b9d6a564fefa7cd6
+size 1224771920
diff --git a/model.safetensors.index.json b/model.safetensors.index.json
new file mode 100644
index 0000000..3136b2a
--- /dev/null
+++ b/model.safetensors.index.json
@@ -0,0 +1,265 @@
+{
+  "metadata": {
+    "total_size": 16056066048
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..cce8550
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9619890aebac311d644236f49462d7f8618ebef7c7020c52645ccb597434a3c9
+size 16543645
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..a18146e
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,322 @@
+{
+    "add_bos_token": true,
+    "add_eos_token": false,
+    "add_prefix_space": false,
+    "added_tokens_decoder": {
+      "0": {
+        "content": "<PAD>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": true
+      },
+      "1": {
+        "content": "<UNK>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": true
+      },
+      "2": {
+        "content": "<CLS>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": true
+      },
+      "3": {
+        "content": "<SEP>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": true
+      },
+      "4": {
+        "content": "<MASK_TOKEN>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": true
+      },
+      "5": {
+        "content": "<BOS_TOKEN>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": true
+      },
+      "6": {
+        "content": "<EOS_TOKEN>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": true
+      },
+      "7": {
+        "content": "<EOP_TOKEN>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": true
+      },
+      "255000": {
+        "content": "<|START_OF_TURN_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255001": {
+        "content": "<|END_OF_TURN_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": true
+      },
+      "255002": {
+        "content": "<|YES_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255003": {
+        "content": "<|NO_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255004": {
+        "content": "<|GOOD_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255005": {
+        "content": "<|BAD_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255006": {
+        "content": "<|USER_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255007": {
+        "content": "<|CHATBOT_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255008": {
+        "content": "<|SYSTEM_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255009": {
+        "content": "<|USER_0_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255010": {
+        "content": "<|USER_1_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255011": {
+        "content": "<|USER_2_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255012": {
+        "content": "<|USER_3_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255013": {
+        "content": "<|USER_4_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255014": {
+        "content": "<|USER_5_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255015": {
+        "content": "<|USER_6_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255016": {
+        "content": "<|USER_7_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255017": {
+        "content": "<|USER_8_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255018": {
+        "content": "<|USER_9_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255019": {
+        "content": "<|EXTRA_0_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255020": {
+        "content": "<|EXTRA_1_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255021": {
+        "content": "<|EXTRA_2_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255022": {
+        "content": "<|EXTRA_3_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255023": {
+        "content": "<|EXTRA_4_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255024": {
+        "content": "<|EXTRA_5_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255025": {
+        "content": "<|EXTRA_6_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255026": {
+        "content": "<|EXTRA_7_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255027": {
+        "content": "<|EXTRA_8_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      },
+      "255028": {
+        "content": "<|EXTRA_9_TOKEN|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false,
+        "special": false
+      }
+    },
+    "bos_token": "<BOS_TOKEN>",
+    "chat_template": [
+      {
+        "name": "default",
+        "template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif false == true %}{% set loop_messages = messages %}{% set system_message = 'You are Aya, a brilliant, sophisticated, AI-assistant trained to assist human users by providing thorough responses. You are trained by Cohere.' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% if system_message != false %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>'  + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}"
+      }
+    ],
+    "clean_up_tokenization_spaces": false,
+    "eos_token": "<|END_OF_TURN_TOKEN|>",
+    "legacy": true,
+    "merges_file": null,
+    "model_max_length": 1000000000000000019884624838656,
+    "pad_token": "<PAD>",
+    "sp_model_kwargs": {},
+    "spaces_between_special_tokens": false,
+    "tokenizer_class": "CohereTokenizer",
+    "unk_token": null,
+    "use_default_system_prompt": false,
+    "vocab_file": null
+  }
\ No newline at end of file
diff --git a/winrates.png b/winrates.png
new file mode 100644
index 0000000..df2daf6
--- /dev/null
+++ b/winrates.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29ed3235477a298b6056e85a09036f6e94601bee96f01a51f6597a70d3041a71
+size 368004