Upload folder using huggingface_hub
Browse files- .gitattributes +3 -0
- Aya_23_notebook.ipynb +1264 -0
- README.md +121 -0
- benchmarks.png +3 -0
- config.json +38 -0
- generation_config.json +7 -0
- model.safetensors.index.json +329 -0
- output-00001-of-00004.safetensors +3 -0
- output-00002-of-00004.safetensors +3 -0
- output-00003-of-00004.safetensors +3 -0
- output-00004-of-00004.safetensors +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +330 -0
- winrates.png +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
benchmarks.png filter=lfs diff=lfs merge=lfs -text
|
37 |
+
winrates.png filter=lfs diff=lfs merge=lfs -text
|
38 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
Aya_23_notebook.ipynb
ADDED
@@ -0,0 +1,1264 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"nbformat": 4,
|
3 |
+
"nbformat_minor": 0,
|
4 |
+
"metadata": {
|
5 |
+
"colab": {
|
6 |
+
"provenance": [],
|
7 |
+
"gpuType": "A100",
|
8 |
+
"machine_shape": "hm"
|
9 |
+
},
|
10 |
+
"kernelspec": {
|
11 |
+
"name": "python3",
|
12 |
+
"display_name": "Python 3"
|
13 |
+
},
|
14 |
+
"language_info": {
|
15 |
+
"name": "python"
|
16 |
+
},
|
17 |
+
"accelerator": "GPU",
|
18 |
+
"widgets": {
|
19 |
+
"application/vnd.jupyter.widget-state+json": {
|
20 |
+
"531def06b1f7430983a2e4ba33f41f7f": {
|
21 |
+
"model_module": "@jupyter-widgets/controls",
|
22 |
+
"model_name": "HBoxModel",
|
23 |
+
"model_module_version": "1.5.0",
|
24 |
+
"state": {
|
25 |
+
"_dom_classes": [],
|
26 |
+
"_model_module": "@jupyter-widgets/controls",
|
27 |
+
"_model_module_version": "1.5.0",
|
28 |
+
"_model_name": "HBoxModel",
|
29 |
+
"_view_count": null,
|
30 |
+
"_view_module": "@jupyter-widgets/controls",
|
31 |
+
"_view_module_version": "1.5.0",
|
32 |
+
"_view_name": "HBoxView",
|
33 |
+
"box_style": "",
|
34 |
+
"children": [
|
35 |
+
"IPY_MODEL_847b6b899bfc4e9b89b6ecb136a21385",
|
36 |
+
"IPY_MODEL_412da2e9912f4eb0ab89d44f0bb09cec",
|
37 |
+
"IPY_MODEL_1d56fddc294241f6a7cb4a300cb09afd"
|
38 |
+
],
|
39 |
+
"layout": "IPY_MODEL_6f83c639357f4729873f6897119532f0"
|
40 |
+
}
|
41 |
+
},
|
42 |
+
"847b6b899bfc4e9b89b6ecb136a21385": {
|
43 |
+
"model_module": "@jupyter-widgets/controls",
|
44 |
+
"model_name": "HTMLModel",
|
45 |
+
"model_module_version": "1.5.0",
|
46 |
+
"state": {
|
47 |
+
"_dom_classes": [],
|
48 |
+
"_model_module": "@jupyter-widgets/controls",
|
49 |
+
"_model_module_version": "1.5.0",
|
50 |
+
"_model_name": "HTMLModel",
|
51 |
+
"_view_count": null,
|
52 |
+
"_view_module": "@jupyter-widgets/controls",
|
53 |
+
"_view_module_version": "1.5.0",
|
54 |
+
"_view_name": "HTMLView",
|
55 |
+
"description": "",
|
56 |
+
"description_tooltip": null,
|
57 |
+
"layout": "IPY_MODEL_2551b382eca04537a3a11cd70aaf574c",
|
58 |
+
"placeholder": "",
|
59 |
+
"style": "IPY_MODEL_93e6cbabc77f4fd69ddc3dee9012cb8e",
|
60 |
+
"value": "Loading checkpoint shards: 100%"
|
61 |
+
}
|
62 |
+
},
|
63 |
+
"412da2e9912f4eb0ab89d44f0bb09cec": {
|
64 |
+
"model_module": "@jupyter-widgets/controls",
|
65 |
+
"model_name": "FloatProgressModel",
|
66 |
+
"model_module_version": "1.5.0",
|
67 |
+
"state": {
|
68 |
+
"_dom_classes": [],
|
69 |
+
"_model_module": "@jupyter-widgets/controls",
|
70 |
+
"_model_module_version": "1.5.0",
|
71 |
+
"_model_name": "FloatProgressModel",
|
72 |
+
"_view_count": null,
|
73 |
+
"_view_module": "@jupyter-widgets/controls",
|
74 |
+
"_view_module_version": "1.5.0",
|
75 |
+
"_view_name": "ProgressView",
|
76 |
+
"bar_style": "success",
|
77 |
+
"description": "",
|
78 |
+
"description_tooltip": null,
|
79 |
+
"layout": "IPY_MODEL_da2997c847b84a32b43c377137f64b5e",
|
80 |
+
"max": 4,
|
81 |
+
"min": 0,
|
82 |
+
"orientation": "horizontal",
|
83 |
+
"style": "IPY_MODEL_24f16c1efe8547f1ab36efcccda46b59",
|
84 |
+
"value": 4
|
85 |
+
}
|
86 |
+
},
|
87 |
+
"1d56fddc294241f6a7cb4a300cb09afd": {
|
88 |
+
"model_module": "@jupyter-widgets/controls",
|
89 |
+
"model_name": "HTMLModel",
|
90 |
+
"model_module_version": "1.5.0",
|
91 |
+
"state": {
|
92 |
+
"_dom_classes": [],
|
93 |
+
"_model_module": "@jupyter-widgets/controls",
|
94 |
+
"_model_module_version": "1.5.0",
|
95 |
+
"_model_name": "HTMLModel",
|
96 |
+
"_view_count": null,
|
97 |
+
"_view_module": "@jupyter-widgets/controls",
|
98 |
+
"_view_module_version": "1.5.0",
|
99 |
+
"_view_name": "HTMLView",
|
100 |
+
"description": "",
|
101 |
+
"description_tooltip": null,
|
102 |
+
"layout": "IPY_MODEL_cc8cb81531344463aa881093fff8c2f0",
|
103 |
+
"placeholder": "",
|
104 |
+
"style": "IPY_MODEL_f4c45b260e7a4feaaeef4c50c560641a",
|
105 |
+
"value": " 4/4 [00:12<00:00, 2.77s/it]"
|
106 |
+
}
|
107 |
+
},
|
108 |
+
"6f83c639357f4729873f6897119532f0": {
|
109 |
+
"model_module": "@jupyter-widgets/base",
|
110 |
+
"model_name": "LayoutModel",
|
111 |
+
"model_module_version": "1.2.0",
|
112 |
+
"state": {
|
113 |
+
"_model_module": "@jupyter-widgets/base",
|
114 |
+
"_model_module_version": "1.2.0",
|
115 |
+
"_model_name": "LayoutModel",
|
116 |
+
"_view_count": null,
|
117 |
+
"_view_module": "@jupyter-widgets/base",
|
118 |
+
"_view_module_version": "1.2.0",
|
119 |
+
"_view_name": "LayoutView",
|
120 |
+
"align_content": null,
|
121 |
+
"align_items": null,
|
122 |
+
"align_self": null,
|
123 |
+
"border": null,
|
124 |
+
"bottom": null,
|
125 |
+
"display": null,
|
126 |
+
"flex": null,
|
127 |
+
"flex_flow": null,
|
128 |
+
"grid_area": null,
|
129 |
+
"grid_auto_columns": null,
|
130 |
+
"grid_auto_flow": null,
|
131 |
+
"grid_auto_rows": null,
|
132 |
+
"grid_column": null,
|
133 |
+
"grid_gap": null,
|
134 |
+
"grid_row": null,
|
135 |
+
"grid_template_areas": null,
|
136 |
+
"grid_template_columns": null,
|
137 |
+
"grid_template_rows": null,
|
138 |
+
"height": null,
|
139 |
+
"justify_content": null,
|
140 |
+
"justify_items": null,
|
141 |
+
"left": null,
|
142 |
+
"margin": null,
|
143 |
+
"max_height": null,
|
144 |
+
"max_width": null,
|
145 |
+
"min_height": null,
|
146 |
+
"min_width": null,
|
147 |
+
"object_fit": null,
|
148 |
+
"object_position": null,
|
149 |
+
"order": null,
|
150 |
+
"overflow": null,
|
151 |
+
"overflow_x": null,
|
152 |
+
"overflow_y": null,
|
153 |
+
"padding": null,
|
154 |
+
"right": null,
|
155 |
+
"top": null,
|
156 |
+
"visibility": null,
|
157 |
+
"width": null
|
158 |
+
}
|
159 |
+
},
|
160 |
+
"2551b382eca04537a3a11cd70aaf574c": {
|
161 |
+
"model_module": "@jupyter-widgets/base",
|
162 |
+
"model_name": "LayoutModel",
|
163 |
+
"model_module_version": "1.2.0",
|
164 |
+
"state": {
|
165 |
+
"_model_module": "@jupyter-widgets/base",
|
166 |
+
"_model_module_version": "1.2.0",
|
167 |
+
"_model_name": "LayoutModel",
|
168 |
+
"_view_count": null,
|
169 |
+
"_view_module": "@jupyter-widgets/base",
|
170 |
+
"_view_module_version": "1.2.0",
|
171 |
+
"_view_name": "LayoutView",
|
172 |
+
"align_content": null,
|
173 |
+
"align_items": null,
|
174 |
+
"align_self": null,
|
175 |
+
"border": null,
|
176 |
+
"bottom": null,
|
177 |
+
"display": null,
|
178 |
+
"flex": null,
|
179 |
+
"flex_flow": null,
|
180 |
+
"grid_area": null,
|
181 |
+
"grid_auto_columns": null,
|
182 |
+
"grid_auto_flow": null,
|
183 |
+
"grid_auto_rows": null,
|
184 |
+
"grid_column": null,
|
185 |
+
"grid_gap": null,
|
186 |
+
"grid_row": null,
|
187 |
+
"grid_template_areas": null,
|
188 |
+
"grid_template_columns": null,
|
189 |
+
"grid_template_rows": null,
|
190 |
+
"height": null,
|
191 |
+
"justify_content": null,
|
192 |
+
"justify_items": null,
|
193 |
+
"left": null,
|
194 |
+
"margin": null,
|
195 |
+
"max_height": null,
|
196 |
+
"max_width": null,
|
197 |
+
"min_height": null,
|
198 |
+
"min_width": null,
|
199 |
+
"object_fit": null,
|
200 |
+
"object_position": null,
|
201 |
+
"order": null,
|
202 |
+
"overflow": null,
|
203 |
+
"overflow_x": null,
|
204 |
+
"overflow_y": null,
|
205 |
+
"padding": null,
|
206 |
+
"right": null,
|
207 |
+
"top": null,
|
208 |
+
"visibility": null,
|
209 |
+
"width": null
|
210 |
+
}
|
211 |
+
},
|
212 |
+
"93e6cbabc77f4fd69ddc3dee9012cb8e": {
|
213 |
+
"model_module": "@jupyter-widgets/controls",
|
214 |
+
"model_name": "DescriptionStyleModel",
|
215 |
+
"model_module_version": "1.5.0",
|
216 |
+
"state": {
|
217 |
+
"_model_module": "@jupyter-widgets/controls",
|
218 |
+
"_model_module_version": "1.5.0",
|
219 |
+
"_model_name": "DescriptionStyleModel",
|
220 |
+
"_view_count": null,
|
221 |
+
"_view_module": "@jupyter-widgets/base",
|
222 |
+
"_view_module_version": "1.2.0",
|
223 |
+
"_view_name": "StyleView",
|
224 |
+
"description_width": ""
|
225 |
+
}
|
226 |
+
},
|
227 |
+
"da2997c847b84a32b43c377137f64b5e": {
|
228 |
+
"model_module": "@jupyter-widgets/base",
|
229 |
+
"model_name": "LayoutModel",
|
230 |
+
"model_module_version": "1.2.0",
|
231 |
+
"state": {
|
232 |
+
"_model_module": "@jupyter-widgets/base",
|
233 |
+
"_model_module_version": "1.2.0",
|
234 |
+
"_model_name": "LayoutModel",
|
235 |
+
"_view_count": null,
|
236 |
+
"_view_module": "@jupyter-widgets/base",
|
237 |
+
"_view_module_version": "1.2.0",
|
238 |
+
"_view_name": "LayoutView",
|
239 |
+
"align_content": null,
|
240 |
+
"align_items": null,
|
241 |
+
"align_self": null,
|
242 |
+
"border": null,
|
243 |
+
"bottom": null,
|
244 |
+
"display": null,
|
245 |
+
"flex": null,
|
246 |
+
"flex_flow": null,
|
247 |
+
"grid_area": null,
|
248 |
+
"grid_auto_columns": null,
|
249 |
+
"grid_auto_flow": null,
|
250 |
+
"grid_auto_rows": null,
|
251 |
+
"grid_column": null,
|
252 |
+
"grid_gap": null,
|
253 |
+
"grid_row": null,
|
254 |
+
"grid_template_areas": null,
|
255 |
+
"grid_template_columns": null,
|
256 |
+
"grid_template_rows": null,
|
257 |
+
"height": null,
|
258 |
+
"justify_content": null,
|
259 |
+
"justify_items": null,
|
260 |
+
"left": null,
|
261 |
+
"margin": null,
|
262 |
+
"max_height": null,
|
263 |
+
"max_width": null,
|
264 |
+
"min_height": null,
|
265 |
+
"min_width": null,
|
266 |
+
"object_fit": null,
|
267 |
+
"object_position": null,
|
268 |
+
"order": null,
|
269 |
+
"overflow": null,
|
270 |
+
"overflow_x": null,
|
271 |
+
"overflow_y": null,
|
272 |
+
"padding": null,
|
273 |
+
"right": null,
|
274 |
+
"top": null,
|
275 |
+
"visibility": null,
|
276 |
+
"width": null
|
277 |
+
}
|
278 |
+
},
|
279 |
+
"24f16c1efe8547f1ab36efcccda46b59": {
|
280 |
+
"model_module": "@jupyter-widgets/controls",
|
281 |
+
"model_name": "ProgressStyleModel",
|
282 |
+
"model_module_version": "1.5.0",
|
283 |
+
"state": {
|
284 |
+
"_model_module": "@jupyter-widgets/controls",
|
285 |
+
"_model_module_version": "1.5.0",
|
286 |
+
"_model_name": "ProgressStyleModel",
|
287 |
+
"_view_count": null,
|
288 |
+
"_view_module": "@jupyter-widgets/base",
|
289 |
+
"_view_module_version": "1.2.0",
|
290 |
+
"_view_name": "StyleView",
|
291 |
+
"bar_color": null,
|
292 |
+
"description_width": ""
|
293 |
+
}
|
294 |
+
},
|
295 |
+
"cc8cb81531344463aa881093fff8c2f0": {
|
296 |
+
"model_module": "@jupyter-widgets/base",
|
297 |
+
"model_name": "LayoutModel",
|
298 |
+
"model_module_version": "1.2.0",
|
299 |
+
"state": {
|
300 |
+
"_model_module": "@jupyter-widgets/base",
|
301 |
+
"_model_module_version": "1.2.0",
|
302 |
+
"_model_name": "LayoutModel",
|
303 |
+
"_view_count": null,
|
304 |
+
"_view_module": "@jupyter-widgets/base",
|
305 |
+
"_view_module_version": "1.2.0",
|
306 |
+
"_view_name": "LayoutView",
|
307 |
+
"align_content": null,
|
308 |
+
"align_items": null,
|
309 |
+
"align_self": null,
|
310 |
+
"border": null,
|
311 |
+
"bottom": null,
|
312 |
+
"display": null,
|
313 |
+
"flex": null,
|
314 |
+
"flex_flow": null,
|
315 |
+
"grid_area": null,
|
316 |
+
"grid_auto_columns": null,
|
317 |
+
"grid_auto_flow": null,
|
318 |
+
"grid_auto_rows": null,
|
319 |
+
"grid_column": null,
|
320 |
+
"grid_gap": null,
|
321 |
+
"grid_row": null,
|
322 |
+
"grid_template_areas": null,
|
323 |
+
"grid_template_columns": null,
|
324 |
+
"grid_template_rows": null,
|
325 |
+
"height": null,
|
326 |
+
"justify_content": null,
|
327 |
+
"justify_items": null,
|
328 |
+
"left": null,
|
329 |
+
"margin": null,
|
330 |
+
"max_height": null,
|
331 |
+
"max_width": null,
|
332 |
+
"min_height": null,
|
333 |
+
"min_width": null,
|
334 |
+
"object_fit": null,
|
335 |
+
"object_position": null,
|
336 |
+
"order": null,
|
337 |
+
"overflow": null,
|
338 |
+
"overflow_x": null,
|
339 |
+
"overflow_y": null,
|
340 |
+
"padding": null,
|
341 |
+
"right": null,
|
342 |
+
"top": null,
|
343 |
+
"visibility": null,
|
344 |
+
"width": null
|
345 |
+
}
|
346 |
+
},
|
347 |
+
"f4c45b260e7a4feaaeef4c50c560641a": {
|
348 |
+
"model_module": "@jupyter-widgets/controls",
|
349 |
+
"model_name": "DescriptionStyleModel",
|
350 |
+
"model_module_version": "1.5.0",
|
351 |
+
"state": {
|
352 |
+
"_model_module": "@jupyter-widgets/controls",
|
353 |
+
"_model_module_version": "1.5.0",
|
354 |
+
"_model_name": "DescriptionStyleModel",
|
355 |
+
"_view_count": null,
|
356 |
+
"_view_module": "@jupyter-widgets/base",
|
357 |
+
"_view_module_version": "1.2.0",
|
358 |
+
"_view_name": "StyleView",
|
359 |
+
"description_width": ""
|
360 |
+
}
|
361 |
+
},
|
362 |
+
"0272ba7f31a2441ab1cb5b8f77dbaacb": {
|
363 |
+
"model_module": "@jupyter-widgets/controls",
|
364 |
+
"model_name": "HBoxModel",
|
365 |
+
"model_module_version": "1.5.0",
|
366 |
+
"state": {
|
367 |
+
"_dom_classes": [],
|
368 |
+
"_model_module": "@jupyter-widgets/controls",
|
369 |
+
"_model_module_version": "1.5.0",
|
370 |
+
"_model_name": "HBoxModel",
|
371 |
+
"_view_count": null,
|
372 |
+
"_view_module": "@jupyter-widgets/controls",
|
373 |
+
"_view_module_version": "1.5.0",
|
374 |
+
"_view_name": "HBoxView",
|
375 |
+
"box_style": "",
|
376 |
+
"children": [
|
377 |
+
"IPY_MODEL_d1bb171ddebd4f4bbeb4ed5d4b8b7076",
|
378 |
+
"IPY_MODEL_33b4fc55703746778511265e28160837",
|
379 |
+
"IPY_MODEL_7548c151f8764276ad7951e2ac80d981"
|
380 |
+
],
|
381 |
+
"layout": "IPY_MODEL_d972c72fef7c45998469550318661e71"
|
382 |
+
}
|
383 |
+
},
|
384 |
+
"d1bb171ddebd4f4bbeb4ed5d4b8b7076": {
|
385 |
+
"model_module": "@jupyter-widgets/controls",
|
386 |
+
"model_name": "HTMLModel",
|
387 |
+
"model_module_version": "1.5.0",
|
388 |
+
"state": {
|
389 |
+
"_dom_classes": [],
|
390 |
+
"_model_module": "@jupyter-widgets/controls",
|
391 |
+
"_model_module_version": "1.5.0",
|
392 |
+
"_model_name": "HTMLModel",
|
393 |
+
"_view_count": null,
|
394 |
+
"_view_module": "@jupyter-widgets/controls",
|
395 |
+
"_view_module_version": "1.5.0",
|
396 |
+
"_view_name": "HTMLView",
|
397 |
+
"description": "",
|
398 |
+
"description_tooltip": null,
|
399 |
+
"layout": "IPY_MODEL_2811b7c68a7b4c95b91bd5690cf06577",
|
400 |
+
"placeholder": "",
|
401 |
+
"style": "IPY_MODEL_a33ccfdb735948e98a19d901d8091319",
|
402 |
+
"value": "Loading checkpoint shards: 100%"
|
403 |
+
}
|
404 |
+
},
|
405 |
+
"33b4fc55703746778511265e28160837": {
|
406 |
+
"model_module": "@jupyter-widgets/controls",
|
407 |
+
"model_name": "FloatProgressModel",
|
408 |
+
"model_module_version": "1.5.0",
|
409 |
+
"state": {
|
410 |
+
"_dom_classes": [],
|
411 |
+
"_model_module": "@jupyter-widgets/controls",
|
412 |
+
"_model_module_version": "1.5.0",
|
413 |
+
"_model_name": "FloatProgressModel",
|
414 |
+
"_view_count": null,
|
415 |
+
"_view_module": "@jupyter-widgets/controls",
|
416 |
+
"_view_module_version": "1.5.0",
|
417 |
+
"_view_name": "ProgressView",
|
418 |
+
"bar_style": "success",
|
419 |
+
"description": "",
|
420 |
+
"description_tooltip": null,
|
421 |
+
"layout": "IPY_MODEL_c1103244cec74a299265729e630faffd",
|
422 |
+
"max": 4,
|
423 |
+
"min": 0,
|
424 |
+
"orientation": "horizontal",
|
425 |
+
"style": "IPY_MODEL_340941cfc49e4ab983b73fb48c30dfe8",
|
426 |
+
"value": 4
|
427 |
+
}
|
428 |
+
},
|
429 |
+
"7548c151f8764276ad7951e2ac80d981": {
|
430 |
+
"model_module": "@jupyter-widgets/controls",
|
431 |
+
"model_name": "HTMLModel",
|
432 |
+
"model_module_version": "1.5.0",
|
433 |
+
"state": {
|
434 |
+
"_dom_classes": [],
|
435 |
+
"_model_module": "@jupyter-widgets/controls",
|
436 |
+
"_model_module_version": "1.5.0",
|
437 |
+
"_model_name": "HTMLModel",
|
438 |
+
"_view_count": null,
|
439 |
+
"_view_module": "@jupyter-widgets/controls",
|
440 |
+
"_view_module_version": "1.5.0",
|
441 |
+
"_view_name": "HTMLView",
|
442 |
+
"description": "",
|
443 |
+
"description_tooltip": null,
|
444 |
+
"layout": "IPY_MODEL_8bb42aa84f4b4a9ab6417aed92132063",
|
445 |
+
"placeholder": "",
|
446 |
+
"style": "IPY_MODEL_b0cf428afc21468caeb664428627aaf6",
|
447 |
+
"value": " 4/4 [00:11<00:00, 2.57s/it]"
|
448 |
+
}
|
449 |
+
},
|
450 |
+
"d972c72fef7c45998469550318661e71": {
|
451 |
+
"model_module": "@jupyter-widgets/base",
|
452 |
+
"model_name": "LayoutModel",
|
453 |
+
"model_module_version": "1.2.0",
|
454 |
+
"state": {
|
455 |
+
"_model_module": "@jupyter-widgets/base",
|
456 |
+
"_model_module_version": "1.2.0",
|
457 |
+
"_model_name": "LayoutModel",
|
458 |
+
"_view_count": null,
|
459 |
+
"_view_module": "@jupyter-widgets/base",
|
460 |
+
"_view_module_version": "1.2.0",
|
461 |
+
"_view_name": "LayoutView",
|
462 |
+
"align_content": null,
|
463 |
+
"align_items": null,
|
464 |
+
"align_self": null,
|
465 |
+
"border": null,
|
466 |
+
"bottom": null,
|
467 |
+
"display": null,
|
468 |
+
"flex": null,
|
469 |
+
"flex_flow": null,
|
470 |
+
"grid_area": null,
|
471 |
+
"grid_auto_columns": null,
|
472 |
+
"grid_auto_flow": null,
|
473 |
+
"grid_auto_rows": null,
|
474 |
+
"grid_column": null,
|
475 |
+
"grid_gap": null,
|
476 |
+
"grid_row": null,
|
477 |
+
"grid_template_areas": null,
|
478 |
+
"grid_template_columns": null,
|
479 |
+
"grid_template_rows": null,
|
480 |
+
"height": null,
|
481 |
+
"justify_content": null,
|
482 |
+
"justify_items": null,
|
483 |
+
"left": null,
|
484 |
+
"margin": null,
|
485 |
+
"max_height": null,
|
486 |
+
"max_width": null,
|
487 |
+
"min_height": null,
|
488 |
+
"min_width": null,
|
489 |
+
"object_fit": null,
|
490 |
+
"object_position": null,
|
491 |
+
"order": null,
|
492 |
+
"overflow": null,
|
493 |
+
"overflow_x": null,
|
494 |
+
"overflow_y": null,
|
495 |
+
"padding": null,
|
496 |
+
"right": null,
|
497 |
+
"top": null,
|
498 |
+
"visibility": null,
|
499 |
+
"width": null
|
500 |
+
}
|
501 |
+
},
|
502 |
+
"2811b7c68a7b4c95b91bd5690cf06577": {
|
503 |
+
"model_module": "@jupyter-widgets/base",
|
504 |
+
"model_name": "LayoutModel",
|
505 |
+
"model_module_version": "1.2.0",
|
506 |
+
"state": {
|
507 |
+
"_model_module": "@jupyter-widgets/base",
|
508 |
+
"_model_module_version": "1.2.0",
|
509 |
+
"_model_name": "LayoutModel",
|
510 |
+
"_view_count": null,
|
511 |
+
"_view_module": "@jupyter-widgets/base",
|
512 |
+
"_view_module_version": "1.2.0",
|
513 |
+
"_view_name": "LayoutView",
|
514 |
+
"align_content": null,
|
515 |
+
"align_items": null,
|
516 |
+
"align_self": null,
|
517 |
+
"border": null,
|
518 |
+
"bottom": null,
|
519 |
+
"display": null,
|
520 |
+
"flex": null,
|
521 |
+
"flex_flow": null,
|
522 |
+
"grid_area": null,
|
523 |
+
"grid_auto_columns": null,
|
524 |
+
"grid_auto_flow": null,
|
525 |
+
"grid_auto_rows": null,
|
526 |
+
"grid_column": null,
|
527 |
+
"grid_gap": null,
|
528 |
+
"grid_row": null,
|
529 |
+
"grid_template_areas": null,
|
530 |
+
"grid_template_columns": null,
|
531 |
+
"grid_template_rows": null,
|
532 |
+
"height": null,
|
533 |
+
"justify_content": null,
|
534 |
+
"justify_items": null,
|
535 |
+
"left": null,
|
536 |
+
"margin": null,
|
537 |
+
"max_height": null,
|
538 |
+
"max_width": null,
|
539 |
+
"min_height": null,
|
540 |
+
"min_width": null,
|
541 |
+
"object_fit": null,
|
542 |
+
"object_position": null,
|
543 |
+
"order": null,
|
544 |
+
"overflow": null,
|
545 |
+
"overflow_x": null,
|
546 |
+
"overflow_y": null,
|
547 |
+
"padding": null,
|
548 |
+
"right": null,
|
549 |
+
"top": null,
|
550 |
+
"visibility": null,
|
551 |
+
"width": null
|
552 |
+
}
|
553 |
+
},
|
554 |
+
"a33ccfdb735948e98a19d901d8091319": {
|
555 |
+
"model_module": "@jupyter-widgets/controls",
|
556 |
+
"model_name": "DescriptionStyleModel",
|
557 |
+
"model_module_version": "1.5.0",
|
558 |
+
"state": {
|
559 |
+
"_model_module": "@jupyter-widgets/controls",
|
560 |
+
"_model_module_version": "1.5.0",
|
561 |
+
"_model_name": "DescriptionStyleModel",
|
562 |
+
"_view_count": null,
|
563 |
+
"_view_module": "@jupyter-widgets/base",
|
564 |
+
"_view_module_version": "1.2.0",
|
565 |
+
"_view_name": "StyleView",
|
566 |
+
"description_width": ""
|
567 |
+
}
|
568 |
+
},
|
569 |
+
"c1103244cec74a299265729e630faffd": {
|
570 |
+
"model_module": "@jupyter-widgets/base",
|
571 |
+
"model_name": "LayoutModel",
|
572 |
+
"model_module_version": "1.2.0",
|
573 |
+
"state": {
|
574 |
+
"_model_module": "@jupyter-widgets/base",
|
575 |
+
"_model_module_version": "1.2.0",
|
576 |
+
"_model_name": "LayoutModel",
|
577 |
+
"_view_count": null,
|
578 |
+
"_view_module": "@jupyter-widgets/base",
|
579 |
+
"_view_module_version": "1.2.0",
|
580 |
+
"_view_name": "LayoutView",
|
581 |
+
"align_content": null,
|
582 |
+
"align_items": null,
|
583 |
+
"align_self": null,
|
584 |
+
"border": null,
|
585 |
+
"bottom": null,
|
586 |
+
"display": null,
|
587 |
+
"flex": null,
|
588 |
+
"flex_flow": null,
|
589 |
+
"grid_area": null,
|
590 |
+
"grid_auto_columns": null,
|
591 |
+
"grid_auto_flow": null,
|
592 |
+
"grid_auto_rows": null,
|
593 |
+
"grid_column": null,
|
594 |
+
"grid_gap": null,
|
595 |
+
"grid_row": null,
|
596 |
+
"grid_template_areas": null,
|
597 |
+
"grid_template_columns": null,
|
598 |
+
"grid_template_rows": null,
|
599 |
+
"height": null,
|
600 |
+
"justify_content": null,
|
601 |
+
"justify_items": null,
|
602 |
+
"left": null,
|
603 |
+
"margin": null,
|
604 |
+
"max_height": null,
|
605 |
+
"max_width": null,
|
606 |
+
"min_height": null,
|
607 |
+
"min_width": null,
|
608 |
+
"object_fit": null,
|
609 |
+
"object_position": null,
|
610 |
+
"order": null,
|
611 |
+
"overflow": null,
|
612 |
+
"overflow_x": null,
|
613 |
+
"overflow_y": null,
|
614 |
+
"padding": null,
|
615 |
+
"right": null,
|
616 |
+
"top": null,
|
617 |
+
"visibility": null,
|
618 |
+
"width": null
|
619 |
+
}
|
620 |
+
},
|
621 |
+
"340941cfc49e4ab983b73fb48c30dfe8": {
|
622 |
+
"model_module": "@jupyter-widgets/controls",
|
623 |
+
"model_name": "ProgressStyleModel",
|
624 |
+
"model_module_version": "1.5.0",
|
625 |
+
"state": {
|
626 |
+
"_model_module": "@jupyter-widgets/controls",
|
627 |
+
"_model_module_version": "1.5.0",
|
628 |
+
"_model_name": "ProgressStyleModel",
|
629 |
+
"_view_count": null,
|
630 |
+
"_view_module": "@jupyter-widgets/base",
|
631 |
+
"_view_module_version": "1.2.0",
|
632 |
+
"_view_name": "StyleView",
|
633 |
+
"bar_color": null,
|
634 |
+
"description_width": ""
|
635 |
+
}
|
636 |
+
},
|
637 |
+
"8bb42aa84f4b4a9ab6417aed92132063": {
|
638 |
+
"model_module": "@jupyter-widgets/base",
|
639 |
+
"model_name": "LayoutModel",
|
640 |
+
"model_module_version": "1.2.0",
|
641 |
+
"state": {
|
642 |
+
"_model_module": "@jupyter-widgets/base",
|
643 |
+
"_model_module_version": "1.2.0",
|
644 |
+
"_model_name": "LayoutModel",
|
645 |
+
"_view_count": null,
|
646 |
+
"_view_module": "@jupyter-widgets/base",
|
647 |
+
"_view_module_version": "1.2.0",
|
648 |
+
"_view_name": "LayoutView",
|
649 |
+
"align_content": null,
|
650 |
+
"align_items": null,
|
651 |
+
"align_self": null,
|
652 |
+
"border": null,
|
653 |
+
"bottom": null,
|
654 |
+
"display": null,
|
655 |
+
"flex": null,
|
656 |
+
"flex_flow": null,
|
657 |
+
"grid_area": null,
|
658 |
+
"grid_auto_columns": null,
|
659 |
+
"grid_auto_flow": null,
|
660 |
+
"grid_auto_rows": null,
|
661 |
+
"grid_column": null,
|
662 |
+
"grid_gap": null,
|
663 |
+
"grid_row": null,
|
664 |
+
"grid_template_areas": null,
|
665 |
+
"grid_template_columns": null,
|
666 |
+
"grid_template_rows": null,
|
667 |
+
"height": null,
|
668 |
+
"justify_content": null,
|
669 |
+
"justify_items": null,
|
670 |
+
"left": null,
|
671 |
+
"margin": null,
|
672 |
+
"max_height": null,
|
673 |
+
"max_width": null,
|
674 |
+
"min_height": null,
|
675 |
+
"min_width": null,
|
676 |
+
"object_fit": null,
|
677 |
+
"object_position": null,
|
678 |
+
"order": null,
|
679 |
+
"overflow": null,
|
680 |
+
"overflow_x": null,
|
681 |
+
"overflow_y": null,
|
682 |
+
"padding": null,
|
683 |
+
"right": null,
|
684 |
+
"top": null,
|
685 |
+
"visibility": null,
|
686 |
+
"width": null
|
687 |
+
}
|
688 |
+
},
|
689 |
+
"b0cf428afc21468caeb664428627aaf6": {
|
690 |
+
"model_module": "@jupyter-widgets/controls",
|
691 |
+
"model_name": "DescriptionStyleModel",
|
692 |
+
"model_module_version": "1.5.0",
|
693 |
+
"state": {
|
694 |
+
"_model_module": "@jupyter-widgets/controls",
|
695 |
+
"_model_module_version": "1.5.0",
|
696 |
+
"_model_name": "DescriptionStyleModel",
|
697 |
+
"_view_count": null,
|
698 |
+
"_view_module": "@jupyter-widgets/base",
|
699 |
+
"_view_module_version": "1.2.0",
|
700 |
+
"_view_name": "StyleView",
|
701 |
+
"description_width": ""
|
702 |
+
}
|
703 |
+
}
|
704 |
+
}
|
705 |
+
}
|
706 |
+
},
|
707 |
+
"cells": [
|
708 |
+
{
|
709 |
+
"cell_type": "code",
|
710 |
+
"source": [
|
711 |
+
"!pip install -U bitsandbytes transformers peft accelerate trl datasets sentencepiece wandb\n",
|
712 |
+
"!pip install flash-attn --no-build-isolation"
|
713 |
+
],
|
714 |
+
"metadata": {
|
715 |
+
"id": "tg1moVggj5sk",
|
716 |
+
"collapsed": true
|
717 |
+
},
|
718 |
+
"execution_count": null,
|
719 |
+
"outputs": []
|
720 |
+
},
|
721 |
+
{
|
722 |
+
"cell_type": "code",
|
723 |
+
"source": [
|
724 |
+
"MODEL_NAME = \"CohereForAI/aya-23-8b\"\n",
|
725 |
+
"\n",
|
726 |
+
"# you may want to change the following parameters depending on your GPU configuration\n",
|
727 |
+
"\n",
|
728 |
+
"# free T4 instance\n",
|
729 |
+
"# QUANTIZE_4BIT = True\n",
|
730 |
+
"# USE_GRAD_CHECKPOINTING = True\n",
|
731 |
+
"# TRAIN_BATCH_SIZE = 2\n",
|
732 |
+
"# TRAIN_MAX_SEQ_LENGTH = 512\n",
|
733 |
+
"# USE_FLASH_ATTENTION = False\n",
|
734 |
+
"# GRAD_ACC_STEPS = 16\n",
|
735 |
+
"\n",
|
736 |
+
"# equivalent A100 setting\n",
|
737 |
+
"QUANTIZE_4BIT = True\n",
|
738 |
+
"USE_GRAD_CHECKPOINTING = True\n",
|
739 |
+
"TRAIN_BATCH_SIZE = 16\n",
|
740 |
+
"TRAIN_MAX_SEQ_LENGTH = 512\n",
|
741 |
+
"USE_FLASH_ATTENTION = True\n",
|
742 |
+
"GRAD_ACC_STEPS = 2"
|
743 |
+
],
|
744 |
+
"metadata": {
|
745 |
+
"id": "Izn6BYEYw4um"
|
746 |
+
},
|
747 |
+
"execution_count": null,
|
748 |
+
"outputs": []
|
749 |
+
},
|
750 |
+
{
|
751 |
+
"cell_type": "code",
|
752 |
+
"source": [
|
753 |
+
"from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig,HfArgumentParser,TrainingArguments,pipeline, logging\n",
|
754 |
+
"from peft import LoraConfig, PeftModel, prepare_model_for_kbit_training, get_peft_model\n",
|
755 |
+
"import os,torch\n",
|
756 |
+
"import bitsandbytes as bnb\n",
|
757 |
+
"from datasets import load_dataset\n",
|
758 |
+
"from trl import SFTTrainer\n",
|
759 |
+
"from datasets import Dataset\n",
|
760 |
+
"import pyarrow as pa\n",
|
761 |
+
"import pyarrow.dataset as ds\n",
|
762 |
+
"import pandas as pd\n",
|
763 |
+
"import re\n",
|
764 |
+
"import wandb"
|
765 |
+
],
|
766 |
+
"metadata": {
|
767 |
+
"id": "wMs9uNDMHL6R"
|
768 |
+
},
|
769 |
+
"execution_count": null,
|
770 |
+
"outputs": []
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"cell_type": "code",
|
774 |
+
"source": [
|
775 |
+
"# Load Model\n",
|
776 |
+
"quantization_config = None\n",
|
777 |
+
"if QUANTIZE_4BIT:\n",
|
778 |
+
" quantization_config = BitsAndBytesConfig(\n",
|
779 |
+
" load_in_4bit=True,\n",
|
780 |
+
" bnb_4bit_quant_type=\"nf4\",\n",
|
781 |
+
" bnb_4bit_use_double_quant=True,\n",
|
782 |
+
" bnb_4bit_compute_dtype=torch.bfloat16,\n",
|
783 |
+
" )\n",
|
784 |
+
"\n",
|
785 |
+
"attn_implementation = None\n",
|
786 |
+
"if USE_FLASH_ATTENTION:\n",
|
787 |
+
" attn_implementation=\"flash_attention_2\"\n",
|
788 |
+
"\n",
|
789 |
+
"model = AutoModelForCausalLM.from_pretrained(\n",
|
790 |
+
" MODEL_NAME,\n",
|
791 |
+
" quantization_config=quantization_config,\n",
|
792 |
+
" attn_implementation=attn_implementation,\n",
|
793 |
+
" torch_dtype=torch.bfloat16,\n",
|
794 |
+
" device_map=\"auto\",\n",
|
795 |
+
" )"
|
796 |
+
],
|
797 |
+
"metadata": {
|
798 |
+
"colab": {
|
799 |
+
"base_uri": "https://localhost:8080/",
|
800 |
+
"height": 176,
|
801 |
+
"referenced_widgets": [
|
802 |
+
"531def06b1f7430983a2e4ba33f41f7f",
|
803 |
+
"847b6b899bfc4e9b89b6ecb136a21385",
|
804 |
+
"412da2e9912f4eb0ab89d44f0bb09cec",
|
805 |
+
"1d56fddc294241f6a7cb4a300cb09afd",
|
806 |
+
"6f83c639357f4729873f6897119532f0",
|
807 |
+
"2551b382eca04537a3a11cd70aaf574c",
|
808 |
+
"93e6cbabc77f4fd69ddc3dee9012cb8e",
|
809 |
+
"da2997c847b84a32b43c377137f64b5e",
|
810 |
+
"24f16c1efe8547f1ab36efcccda46b59",
|
811 |
+
"cc8cb81531344463aa881093fff8c2f0",
|
812 |
+
"f4c45b260e7a4feaaeef4c50c560641a"
|
813 |
+
]
|
814 |
+
},
|
815 |
+
"id": "d9a23_jiC-qG",
|
816 |
+
"outputId": "3cf0666d-f23d-4382-b17b-c29cbe91d2f6"
|
817 |
+
},
|
818 |
+
"execution_count": null,
|
819 |
+
"outputs": [
|
820 |
+
{
|
821 |
+
"output_type": "stream",
|
822 |
+
"name": "stderr",
|
823 |
+
"text": [
|
824 |
+
"/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_token.py:89: UserWarning: \n",
|
825 |
+
"The secret `HF_TOKEN` does not exist in your Colab secrets.\n",
|
826 |
+
"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",
|
827 |
+
"You will be able to reuse this secret in all of your notebooks.\n",
|
828 |
+
"Please note that authentication is recommended but still optional to access public models or datasets.\n",
|
829 |
+
" warnings.warn(\n"
|
830 |
+
]
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"output_type": "display_data",
|
834 |
+
"data": {
|
835 |
+
"text/plain": [
|
836 |
+
"Loading checkpoint shards: 0%| | 0/4 [00:00<?, ?it/s]"
|
837 |
+
],
|
838 |
+
"application/vnd.jupyter.widget-view+json": {
|
839 |
+
"version_major": 2,
|
840 |
+
"version_minor": 0,
|
841 |
+
"model_id": "531def06b1f7430983a2e4ba33f41f7f"
|
842 |
+
}
|
843 |
+
},
|
844 |
+
"metadata": {}
|
845 |
+
}
|
846 |
+
]
|
847 |
+
},
|
848 |
+
{
|
849 |
+
"cell_type": "code",
|
850 |
+
"source": [
|
851 |
+
"# Load tokenizer\n",
|
852 |
+
"tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)"
|
853 |
+
],
|
854 |
+
"metadata": {
|
855 |
+
"colab": {
|
856 |
+
"base_uri": "https://localhost:8080/"
|
857 |
+
},
|
858 |
+
"id": "YuqAA8GhYSdO",
|
859 |
+
"outputId": "14553887-8142-492e-ca23-aeddac002815"
|
860 |
+
},
|
861 |
+
"execution_count": null,
|
862 |
+
"outputs": [
|
863 |
+
{
|
864 |
+
"output_type": "stream",
|
865 |
+
"name": "stderr",
|
866 |
+
"text": [
|
867 |
+
"Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n"
|
868 |
+
]
|
869 |
+
}
|
870 |
+
]
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"cell_type": "code",
|
874 |
+
"source": [
|
875 |
+
"def get_message_format(prompts):\n",
|
876 |
+
" messages = []\n",
|
877 |
+
"\n",
|
878 |
+
" for p in prompts:\n",
|
879 |
+
" messages.append(\n",
|
880 |
+
" [{\"role\": \"user\", \"content\": p}]\n",
|
881 |
+
" )\n",
|
882 |
+
"\n",
|
883 |
+
" return messages\n",
|
884 |
+
"\n",
|
885 |
+
"def generate_aya_23(\n",
|
886 |
+
" prompts,\n",
|
887 |
+
" model,\n",
|
888 |
+
" temperature=0.3,\n",
|
889 |
+
" top_p=0.75,\n",
|
890 |
+
" top_k=0,\n",
|
891 |
+
" max_new_tokens=1024\n",
|
892 |
+
" ):\n",
|
893 |
+
"\n",
|
894 |
+
" messages = get_message_format(prompts)\n",
|
895 |
+
"\n",
|
896 |
+
" input_ids = tokenizer.apply_chat_template(\n",
|
897 |
+
" messages,\n",
|
898 |
+
" tokenize=True,\n",
|
899 |
+
" add_generation_prompt=True,\n",
|
900 |
+
" padding=True,\n",
|
901 |
+
" return_tensors=\"pt\",\n",
|
902 |
+
" )\n",
|
903 |
+
" input_ids = input_ids.to(model.device)\n",
|
904 |
+
" prompt_padded_len = len(input_ids[0])\n",
|
905 |
+
"\n",
|
906 |
+
" gen_tokens = model.generate(\n",
|
907 |
+
" input_ids,\n",
|
908 |
+
" temperature=temperature,\n",
|
909 |
+
" top_p=top_p,\n",
|
910 |
+
" top_k=top_k,\n",
|
911 |
+
" max_new_tokens=max_new_tokens,\n",
|
912 |
+
" do_sample=True,\n",
|
913 |
+
" )\n",
|
914 |
+
"\n",
|
915 |
+
" # get only generated tokens\n",
|
916 |
+
" gen_tokens = [\n",
|
917 |
+
" gt[prompt_padded_len:] for gt in gen_tokens\n",
|
918 |
+
" ]\n",
|
919 |
+
"\n",
|
920 |
+
" gen_text = tokenizer.batch_decode(gen_tokens, skip_special_tokens=True)\n",
|
921 |
+
" return gen_text"
|
922 |
+
],
|
923 |
+
"metadata": {
|
924 |
+
"id": "s75a8Vda-eqx"
|
925 |
+
},
|
926 |
+
"execution_count": null,
|
927 |
+
"outputs": []
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"cell_type": "code",
|
931 |
+
"source": [
|
932 |
+
"# Test generations on langauges in Aya 23 set\n",
|
933 |
+
"prompts = [\n",
|
934 |
+
" \"Write a list of three fruits and tell me about each of them\", # English\n",
|
935 |
+
" \"Viết danh sách ba loại trái cây và kể cho tôi nghe về từng loại trái cây đó\", # Vietnamese\n",
|
936 |
+
" \"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",
|
937 |
+
" \"Üç meyveden oluşan bir liste yazın ve bana her birini anlatın\" # Turkish\n",
|
938 |
+
"]\n",
|
939 |
+
"\n",
|
940 |
+
"generations = generate_aya_23(prompts, model)\n",
|
941 |
+
"\n",
|
942 |
+
"for p, g in zip(prompts, generations):\n",
|
943 |
+
" print(\n",
|
944 |
+
" \"PROMPT\", p ,\"RESPONSE\", g, \"\\n\", sep=\"\\n\"\n",
|
945 |
+
" )"
|
946 |
+
],
|
947 |
+
"metadata": {
|
948 |
+
"id": "4l12EC7q-h3I",
|
949 |
+
"colab": {
|
950 |
+
"base_uri": "https://localhost:8080/"
|
951 |
+
},
|
952 |
+
"outputId": "e32ee1a4-9d91-447f-9bde-c8c71c727d80"
|
953 |
+
},
|
954 |
+
"execution_count": null,
|
955 |
+
"outputs": [
|
956 |
+
{
|
957 |
+
"output_type": "stream",
|
958 |
+
"name": "stdout",
|
959 |
+
"text": [
|
960 |
+
"PROMPT\n",
|
961 |
+
"Write a list of three fruits and tell me about each of them\n",
|
962 |
+
"RESPONSE\n",
|
963 |
+
"Sure! Here is a list of three fruits, along with some information about each of them:\n",
|
964 |
+
"\n",
|
965 |
+
"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",
|
966 |
+
"\n",
|
967 |
+
"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",
|
968 |
+
"\n",
|
969 |
+
"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",
|
970 |
+
"\n",
|
971 |
+
"These fruits are not only delicious but also provide various health benefits and are commonly used in various cuisines worldwide.\n",
|
972 |
+
"\n",
|
973 |
+
"\n",
|
974 |
+
"PROMPT\n",
|
975 |
+
"Viết danh sách ba loại trái cây và kể cho tôi nghe về từng loại trái cây đó\n",
|
976 |
+
"RESPONSE\n",
|
977 |
+
"Dưới đây là ba loại trái cây phổ biến, mỗi loại có hương vị và đặc điểm riêng:\n",
|
978 |
+
"\n",
|
979 |
+
"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",
|
980 |
+
"\n",
|
981 |
+
"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",
|
982 |
+
"\n",
|
983 |
+
"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",
|
984 |
+
"\n",
|
985 |
+
"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",
|
986 |
+
"\n",
|
987 |
+
"\n",
|
988 |
+
"PROMPT\n",
|
989 |
+
"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",
|
990 |
+
"RESPONSE\n",
|
991 |
+
"もちろんです! 3 つの果物は次のとおりです。\n",
|
992 |
+
"\n",
|
993 |
+
"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",
|
994 |
+
"\n",
|
995 |
+
"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",
|
996 |
+
"\n",
|
997 |
+
"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",
|
998 |
+
"\n",
|
999 |
+
"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",
|
1000 |
+
"\n",
|
1001 |
+
"\n",
|
1002 |
+
"PROMPT\n",
|
1003 |
+
"Üç meyveden oluşan bir liste yazın ve bana her birini anlatın\n",
|
1004 |
+
"RESPONSE\n",
|
1005 |
+
"Elma, armut ve çilek.\n",
|
1006 |
+
"\n",
|
1007 |
+
"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",
|
1008 |
+
"\n",
|
1009 |
+
"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",
|
1010 |
+
"\n",
|
1011 |
+
"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",
|
1012 |
+
"\n",
|
1013 |
+
"Bu üç meyve, her birinin kendine has özellikleri ve faydaları olan lezzetli ve besleyici seçenekler sunar.\n",
|
1014 |
+
"\n",
|
1015 |
+
"\n"
|
1016 |
+
]
|
1017 |
+
}
|
1018 |
+
]
|
1019 |
+
},
|
1020 |
+
{
|
1021 |
+
"cell_type": "code",
|
1022 |
+
"source": [
|
1023 |
+
"# Test Bengali (not in Aya 23 set) inference on base model\n",
|
1024 |
+
"\n",
|
1025 |
+
"prompts = [\n",
|
1026 |
+
" 'Translate from English to Bengali: \"Rates are competitive, almost always the best in the market\"'\n",
|
1027 |
+
"]\n",
|
1028 |
+
"\n",
|
1029 |
+
"generations = generate_aya_23(prompts, model)\n",
|
1030 |
+
"\n",
|
1031 |
+
"for p, g in zip(prompts, generations):\n",
|
1032 |
+
" print(\n",
|
1033 |
+
" \"PROMPT\", p ,\"RESPONSE\", g, \"\\n\", sep=\"\\n\"\n",
|
1034 |
+
" )"
|
1035 |
+
],
|
1036 |
+
"metadata": {
|
1037 |
+
"colab": {
|
1038 |
+
"base_uri": "https://localhost:8080/"
|
1039 |
+
},
|
1040 |
+
"id": "tkEl3__Mwd8N",
|
1041 |
+
"outputId": "d4cf3e07-f148-4a57-cd69-b72acfc15b54"
|
1042 |
+
},
|
1043 |
+
"execution_count": null,
|
1044 |
+
"outputs": [
|
1045 |
+
{
|
1046 |
+
"output_type": "stream",
|
1047 |
+
"name": "stdout",
|
1048 |
+
"text": [
|
1049 |
+
"PROMPT\n",
|
1050 |
+
"Translate from English to Bengali: \"Rates are competitive, almost always the best in the market\"\n",
|
1051 |
+
"RESPONSE\n",
|
1052 |
+
"\"পরিণতি সংসাধানকরি, বাজারের সম্পর্কে সম্প্রতি সবচেয়ে বেশি\"\n",
|
1053 |
+
"\n",
|
1054 |
+
"\n"
|
1055 |
+
]
|
1056 |
+
}
|
1057 |
+
]
|
1058 |
+
},
|
1059 |
+
{
|
1060 |
+
"cell_type": "code",
|
1061 |
+
"source": [
|
1062 |
+
"# Load an English to Bengali translation dataset from Aya Collection\n",
|
1063 |
+
"dataset = load_dataset(\"CohereForAI/aya_collection\", \"templated_indic_sentiment\")['train']\n",
|
1064 |
+
"dataset = dataset.filter(lambda example: example['language']=='ben')\n",
|
1065 |
+
"\n",
|
1066 |
+
"def formatting_prompts_func(example):\n",
|
1067 |
+
" output_texts = []\n",
|
1068 |
+
" for i in range(len(example['inputs'])):\n",
|
1069 |
+
" 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",
|
1070 |
+
" output_texts.append(text)\n",
|
1071 |
+
" return output_texts"
|
1072 |
+
],
|
1073 |
+
"metadata": {
|
1074 |
+
"id": "CHXm3Io5zCrk"
|
1075 |
+
},
|
1076 |
+
"execution_count": null,
|
1077 |
+
"outputs": []
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"cell_type": "code",
|
1081 |
+
"source": [
|
1082 |
+
"# Training Arguments\n",
|
1083 |
+
"training_arguments = TrainingArguments(\n",
|
1084 |
+
" output_dir=\"results\",\n",
|
1085 |
+
" num_train_epochs=20,\n",
|
1086 |
+
" per_device_train_batch_size=TRAIN_BATCH_SIZE,\n",
|
1087 |
+
" gradient_accumulation_steps=GRAD_ACC_STEPS,\n",
|
1088 |
+
" gradient_checkpointing=USE_GRAD_CHECKPOINTING,\n",
|
1089 |
+
" optim=\"paged_adamw_32bit\",\n",
|
1090 |
+
" save_steps=50,\n",
|
1091 |
+
" logging_steps=10,\n",
|
1092 |
+
" learning_rate=1e-3,\n",
|
1093 |
+
" weight_decay=0.001,\n",
|
1094 |
+
" fp16=False,\n",
|
1095 |
+
" bf16=True,\n",
|
1096 |
+
" warmup_ratio=0.05,\n",
|
1097 |
+
" group_by_length=True,\n",
|
1098 |
+
" lr_scheduler_type=\"constant\",\n",
|
1099 |
+
" report_to=\"none\"\n",
|
1100 |
+
")\n",
|
1101 |
+
"\n",
|
1102 |
+
"peft_config = LoraConfig(\n",
|
1103 |
+
" lora_alpha=32,\n",
|
1104 |
+
" r=32,\n",
|
1105 |
+
" bias=\"none\",\n",
|
1106 |
+
" task_type=\"CAUSAL_LM\",\n",
|
1107 |
+
" target_modules=[\"q_proj\", \"v_proj\", \"k_proj\", \"o_proj\"]\n",
|
1108 |
+
")\n",
|
1109 |
+
"\n",
|
1110 |
+
"trainer = SFTTrainer(\n",
|
1111 |
+
" model=model,\n",
|
1112 |
+
" train_dataset=dataset,\n",
|
1113 |
+
" peft_config=peft_config,\n",
|
1114 |
+
" max_seq_length=TRAIN_MAX_SEQ_LENGTH,\n",
|
1115 |
+
" tokenizer=tokenizer,\n",
|
1116 |
+
" args=training_arguments,\n",
|
1117 |
+
" formatting_func=formatting_prompts_func\n",
|
1118 |
+
")"
|
1119 |
+
],
|
1120 |
+
"metadata": {
|
1121 |
+
"id": "A9OdyDDEy7rM",
|
1122 |
+
"colab": {
|
1123 |
+
"base_uri": "https://localhost:8080/"
|
1124 |
+
},
|
1125 |
+
"outputId": "49592f25-4aaf-4e21-f612-a6fe5c5865e1"
|
1126 |
+
},
|
1127 |
+
"execution_count": null,
|
1128 |
+
"outputs": [
|
1129 |
+
{
|
1130 |
+
"output_type": "stream",
|
1131 |
+
"name": "stderr",
|
1132 |
+
"text": [
|
1133 |
+
"/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",
|
1134 |
+
" warnings.warn(\n"
|
1135 |
+
]
|
1136 |
+
}
|
1137 |
+
]
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"cell_type": "code",
|
1141 |
+
"source": [
|
1142 |
+
"trainer.train()"
|
1143 |
+
],
|
1144 |
+
"metadata": {
|
1145 |
+
"id": "9BvK-3eYiwhx"
|
1146 |
+
},
|
1147 |
+
"execution_count": null,
|
1148 |
+
"outputs": []
|
1149 |
+
},
|
1150 |
+
{
|
1151 |
+
"cell_type": "code",
|
1152 |
+
"source": [
|
1153 |
+
"# Save the model to disk\n",
|
1154 |
+
"trainer.model.save_pretrained(save_directory='aya-qlora')\n",
|
1155 |
+
"model.config.use_cache = True\n",
|
1156 |
+
"model.eval()"
|
1157 |
+
],
|
1158 |
+
"metadata": {
|
1159 |
+
"id": "X3Lqfwo-8CCG"
|
1160 |
+
},
|
1161 |
+
"execution_count": null,
|
1162 |
+
"outputs": []
|
1163 |
+
},
|
1164 |
+
{
|
1165 |
+
"cell_type": "code",
|
1166 |
+
"source": [
|
1167 |
+
"# Test Bengali inference on loaded fine-tuned model\n",
|
1168 |
+
"\n",
|
1169 |
+
"# Load Model and LoRA Adapter\n",
|
1170 |
+
"quantization_config = None\n",
|
1171 |
+
"if QUANTIZE_4BIT:\n",
|
1172 |
+
" quantization_config = BitsAndBytesConfig(\n",
|
1173 |
+
" load_in_4bit=True,\n",
|
1174 |
+
" bnb_4bit_quant_type=\"nf4\",\n",
|
1175 |
+
" bnb_4bit_use_double_quant=True,\n",
|
1176 |
+
" bnb_4bit_compute_dtype=torch.bfloat16,\n",
|
1177 |
+
" )\n",
|
1178 |
+
"\n",
|
1179 |
+
"attn_implementation = None\n",
|
1180 |
+
"if USE_FLASH_ATTENTION:\n",
|
1181 |
+
" attn_implementation=\"flash_attention_2\"\n",
|
1182 |
+
"\n",
|
1183 |
+
"loaded_model = AutoModelForCausalLM.from_pretrained(\n",
|
1184 |
+
" MODEL_NAME,\n",
|
1185 |
+
" quantization_config=quantization_config,\n",
|
1186 |
+
" attn_implementation=attn_implementation,\n",
|
1187 |
+
" torch_dtype=torch.bfloat16,\n",
|
1188 |
+
" device_map=\"auto\",\n",
|
1189 |
+
" )\n",
|
1190 |
+
"tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)\n",
|
1191 |
+
"loaded_model.load_adapter(\"aya-qlora\")\n",
|
1192 |
+
"\n",
|
1193 |
+
"\n",
|
1194 |
+
"prompts = [\n",
|
1195 |
+
" 'Translate from English to Bengali: \"Rates are competitive, almost always the best in the market\"'\n",
|
1196 |
+
"]\n",
|
1197 |
+
"\n",
|
1198 |
+
"generations = generate_aya_23(prompts, loaded_model)\n",
|
1199 |
+
"\n",
|
1200 |
+
"for p, g in zip(prompts, generations):\n",
|
1201 |
+
" print(\n",
|
1202 |
+
" \"PROMPT\", p ,\"RESPONSE\", g, \"\\n\", sep=\"\\n\"\n",
|
1203 |
+
" )"
|
1204 |
+
],
|
1205 |
+
"metadata": {
|
1206 |
+
"colab": {
|
1207 |
+
"base_uri": "https://localhost:8080/",
|
1208 |
+
"height": 174,
|
1209 |
+
"referenced_widgets": [
|
1210 |
+
"0272ba7f31a2441ab1cb5b8f77dbaacb",
|
1211 |
+
"d1bb171ddebd4f4bbeb4ed5d4b8b7076",
|
1212 |
+
"33b4fc55703746778511265e28160837",
|
1213 |
+
"7548c151f8764276ad7951e2ac80d981",
|
1214 |
+
"d972c72fef7c45998469550318661e71",
|
1215 |
+
"2811b7c68a7b4c95b91bd5690cf06577",
|
1216 |
+
"a33ccfdb735948e98a19d901d8091319",
|
1217 |
+
"c1103244cec74a299265729e630faffd",
|
1218 |
+
"340941cfc49e4ab983b73fb48c30dfe8",
|
1219 |
+
"8bb42aa84f4b4a9ab6417aed92132063",
|
1220 |
+
"b0cf428afc21468caeb664428627aaf6"
|
1221 |
+
]
|
1222 |
+
},
|
1223 |
+
"id": "w5HGIJtRJN-y",
|
1224 |
+
"outputId": "441193fe-89fa-40ad-8585-d1f2dcf124e5"
|
1225 |
+
},
|
1226 |
+
"execution_count": null,
|
1227 |
+
"outputs": [
|
1228 |
+
{
|
1229 |
+
"output_type": "display_data",
|
1230 |
+
"data": {
|
1231 |
+
"text/plain": [
|
1232 |
+
"Loading checkpoint shards: 0%| | 0/4 [00:00<?, ?it/s]"
|
1233 |
+
],
|
1234 |
+
"application/vnd.jupyter.widget-view+json": {
|
1235 |
+
"version_major": 2,
|
1236 |
+
"version_minor": 0,
|
1237 |
+
"model_id": "0272ba7f31a2441ab1cb5b8f77dbaacb"
|
1238 |
+
}
|
1239 |
+
},
|
1240 |
+
"metadata": {}
|
1241 |
+
},
|
1242 |
+
{
|
1243 |
+
"output_type": "stream",
|
1244 |
+
"name": "stderr",
|
1245 |
+
"text": [
|
1246 |
+
"Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n"
|
1247 |
+
]
|
1248 |
+
},
|
1249 |
+
{
|
1250 |
+
"output_type": "stream",
|
1251 |
+
"name": "stdout",
|
1252 |
+
"text": [
|
1253 |
+
"PROMPT\n",
|
1254 |
+
"Translate from English to Bengali: \"Rates are competitive, almost always the best in the market\"\n",
|
1255 |
+
"RESPONSE\n",
|
1256 |
+
"\"দরগুলি প্রতিযোগিতামূলক, প্রায় সবসময় বাজারে সেরা\"\n",
|
1257 |
+
"\n",
|
1258 |
+
"\n"
|
1259 |
+
]
|
1260 |
+
}
|
1261 |
+
]
|
1262 |
+
}
|
1263 |
+
]
|
1264 |
+
}
|
README.md
ADDED
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
- fr
|
6 |
+
- de
|
7 |
+
- es
|
8 |
+
- it
|
9 |
+
- pt
|
10 |
+
- ja
|
11 |
+
- ko
|
12 |
+
- zh
|
13 |
+
- ar
|
14 |
+
- el
|
15 |
+
- fa
|
16 |
+
- pl
|
17 |
+
- id
|
18 |
+
- cs
|
19 |
+
- he
|
20 |
+
- hi
|
21 |
+
- nl
|
22 |
+
- ro
|
23 |
+
- ru
|
24 |
+
- tr
|
25 |
+
- uk
|
26 |
+
- vi
|
27 |
+
license: cc-by-nc-4.0
|
28 |
+
---
|
29 |
+
|
30 |
+
# Model Card for Aya-23-35B
|
31 |
+
|
32 |
+
## Model Summary
|
33 |
+
|
34 |
+
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/CohereForAI/c4ai-command-r-plus) of models with the recently released [Aya Collection](https://huggingface.co/datasets/CohereForAI/aya_collection). The result is a powerful multilingual large language model serving 23 languages.
|
35 |
+
|
36 |
+
This model card corresponds to the 35-billion version of the Aya 23 model. We also released an 8-billion version which you can find [here](https://huggingface.co/CohereForAI/aya-23-8B).
|
37 |
+
|
38 |
+
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
|
39 |
+
|
40 |
+
Developed by: [Cohere For AI](https://cohere.for.ai) and [Cohere](https://cohere.com/)
|
41 |
+
|
42 |
+
- Point of Contact: Cohere For AI: [cohere.for.ai](https://cohere.for.ai/)
|
43 |
+
- License: [CC-BY-NC](https://cohere.com/c4ai-cc-by-nc-license), requires also adhering to [C4AI's Acceptable Use Policy](https://docs.cohere.com/docs/c4ai-acceptable-use-policy)
|
44 |
+
- Model: aya-23-8B
|
45 |
+
- Model Size: 35 billion parameters
|
46 |
+
|
47 |
+
**Try Aya 23**
|
48 |
+
|
49 |
+
You can try out Aya 23 (35B) before downloading the weights in our hosted Hugging Face Space [here](https://huggingface.co/spaces/CohereForAI/aya-23).
|
50 |
+
|
51 |
+
### Usage
|
52 |
+
|
53 |
+
Please install transformers from the source repository that includes the necessary changes for this model
|
54 |
+
|
55 |
+
```python
|
56 |
+
# pip install 'git+https://github.com/huggingface/transformers.git'
|
57 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
58 |
+
|
59 |
+
model_id = "CohereForAI/aya-23-35B"
|
60 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
61 |
+
model = AutoModelForCausalLM.from_pretrained(model_id)
|
62 |
+
|
63 |
+
# Format message with the command-r-plus chat template
|
64 |
+
messages = [{"role": "user", "content": "Anneme onu ne kadar sevdiğimi anlatan bir mektup yaz"}]
|
65 |
+
input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
|
66 |
+
## <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|>
|
67 |
+
|
68 |
+
gen_tokens = model.generate(
|
69 |
+
input_ids,
|
70 |
+
max_new_tokens=100,
|
71 |
+
do_sample=True,
|
72 |
+
temperature=0.3,
|
73 |
+
)
|
74 |
+
|
75 |
+
gen_text = tokenizer.decode(gen_tokens[0])
|
76 |
+
print(gen_text)
|
77 |
+
```
|
78 |
+
|
79 |
+
### Example Notebook
|
80 |
+
|
81 |
+
[This notebook](https://huggingface.co/CohereForAI/aya-23-35B/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).
|
82 |
+
|
83 |
+
## Model Details
|
84 |
+
|
85 |
+
**Input**: Models input text only.
|
86 |
+
|
87 |
+
**Output**: Models generate text only.
|
88 |
+
|
89 |
+
**Model Architecture**: Aya-23-35B is an auto-regressive language model that uses an optimized transformer architecture. After pretraining, this model is fine-tuned (IFT) to follow human instructions.
|
90 |
+
|
91 |
+
**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
|
92 |
+
|
93 |
+
**Context length**: 8192
|
94 |
+
|
95 |
+
### Evaluation
|
96 |
+
|
97 |
+
<img src="benchmarks.png" alt="multilingual benchmarks" width="650" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
98 |
+
<img src="winrates.png" alt="average win rates" width="650" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
|
99 |
+
|
100 |
+
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.
|
101 |
+
|
102 |
+
### Model Card Contact
|
103 |
+
|
104 |
+
For errors or additional questions about details in this model card, contact info@for.ai.
|
105 |
+
|
106 |
+
### Terms of Use
|
107 |
+
|
108 |
+
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 [C4AI's Acceptable Use Policy](https://docs.cohere.com/docs/c4ai-acceptable-use-policy).
|
109 |
+
|
110 |
+
### Try the model today
|
111 |
+
|
112 |
+
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/CohereForAI/aya-23).
|
113 |
+
|
114 |
+
### Citation info
|
115 |
+
```bibtex
|
116 |
+
@misc{aya23technicalreport,
|
117 |
+
title={Aya 23: Open Weight Releases to Further Multilingual Progress},
|
118 |
+
author={Viraat Aryabumi, John Dang, Dwarak Talupuru, Saurabh Dash, David Cairuz, Hangyu Lin, Bharat Venkitesh, Madeline Smith, Kelly Marchisio, Sebastian Ruder, Acyr Locatelli, Julia Kreutzer, Nick Frosst, Phil Blunsom, Marzieh Fadaee, Ahmet Üstün, and Sara Hooker},
|
119 |
+
url={https://cohere.com/research/papers/aya-command-23-8b-and-35b-technical-report-2024-05-23},
|
120 |
+
year={2024}
|
121 |
+
}
|
benchmarks.png
ADDED
![]() |
Git LFS Details
|
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"CohereForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_bias": false,
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 5,
|
8 |
+
"eos_token_id": 255001,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 8192,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 22528,
|
13 |
+
"layer_norm_eps": 1e-05,
|
14 |
+
"logit_scale": 0.0625,
|
15 |
+
"max_position_embeddings": 8192,
|
16 |
+
"model_type": "cohere",
|
17 |
+
"num_attention_heads": 64,
|
18 |
+
"num_hidden_layers": 40,
|
19 |
+
"num_key_value_heads": 64,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"rope_theta": 8000000.0,
|
22 |
+
"torch_dtype": "float16",
|
23 |
+
"transformers_version": "4.41.0.dev0",
|
24 |
+
"use_cache": true,
|
25 |
+
"use_qk_norm": false,
|
26 |
+
"vocab_size": 256000,
|
27 |
+
"quantization_config": {
|
28 |
+
"quant_method": "exl2",
|
29 |
+
"version": "0.0.21",
|
30 |
+
"bits": 6.0,
|
31 |
+
"head_bits": 8,
|
32 |
+
"calibration": {
|
33 |
+
"rows": 100,
|
34 |
+
"length": 2048,
|
35 |
+
"dataset": "(default)"
|
36 |
+
}
|
37 |
+
}
|
38 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 5,
|
4 |
+
"eos_token_id": 255001,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.41.0.dev0"
|
7 |
+
}
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,329 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 69961662464
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"model.embed_tokens.weight": "model-00001-of-00015.safetensors",
|
7 |
+
"model.layers.0.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
8 |
+
"model.layers.0.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
9 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
10 |
+
"model.layers.0.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
11 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
12 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
13 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
14 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
15 |
+
"model.layers.1.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
16 |
+
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
17 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
18 |
+
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
19 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
20 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
21 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
22 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
23 |
+
"model.layers.10.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
24 |
+
"model.layers.10.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
25 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
26 |
+
"model.layers.10.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
27 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
28 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
29 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
30 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
31 |
+
"model.layers.11.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
32 |
+
"model.layers.11.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
33 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
34 |
+
"model.layers.11.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
35 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
36 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
37 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
38 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
39 |
+
"model.layers.12.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
40 |
+
"model.layers.12.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
41 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
42 |
+
"model.layers.12.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
43 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
44 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
45 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
46 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
47 |
+
"model.layers.13.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
48 |
+
"model.layers.13.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
49 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
50 |
+
"model.layers.13.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
51 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
52 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
53 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
54 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
55 |
+
"model.layers.14.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
56 |
+
"model.layers.14.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
57 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
58 |
+
"model.layers.14.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
59 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
60 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
61 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
62 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
63 |
+
"model.layers.15.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
64 |
+
"model.layers.15.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
65 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
66 |
+
"model.layers.15.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
67 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
68 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
69 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
70 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
71 |
+
"model.layers.16.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
72 |
+
"model.layers.16.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
73 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
74 |
+
"model.layers.16.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
75 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
76 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
77 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
78 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
79 |
+
"model.layers.17.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
80 |
+
"model.layers.17.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
81 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
82 |
+
"model.layers.17.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
83 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
84 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
85 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
86 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
87 |
+
"model.layers.18.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
88 |
+
"model.layers.18.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
89 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
90 |
+
"model.layers.18.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
91 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
92 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
93 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
94 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
95 |
+
"model.layers.19.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
96 |
+
"model.layers.19.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
97 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
98 |
+
"model.layers.19.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
99 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
100 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
101 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
102 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
103 |
+
"model.layers.2.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
104 |
+
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
105 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
106 |
+
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
107 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
108 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
109 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
110 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
111 |
+
"model.layers.20.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
112 |
+
"model.layers.20.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
113 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
114 |
+
"model.layers.20.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
115 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
116 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
117 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
118 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
119 |
+
"model.layers.21.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
120 |
+
"model.layers.21.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
121 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
122 |
+
"model.layers.21.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
123 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
124 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
125 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
126 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
127 |
+
"model.layers.22.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
128 |
+
"model.layers.22.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
129 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
130 |
+
"model.layers.22.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
131 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
132 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
133 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
134 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
135 |
+
"model.layers.23.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
136 |
+
"model.layers.23.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
137 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
138 |
+
"model.layers.23.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
139 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
140 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
141 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
142 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
143 |
+
"model.layers.24.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
144 |
+
"model.layers.24.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
145 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
146 |
+
"model.layers.24.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
147 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
148 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
149 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
150 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
151 |
+
"model.layers.25.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
152 |
+
"model.layers.25.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
153 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
154 |
+
"model.layers.25.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
155 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
156 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
157 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
158 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
159 |
+
"model.layers.26.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
160 |
+
"model.layers.26.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
161 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
162 |
+
"model.layers.26.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
163 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
164 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
165 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
166 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
167 |
+
"model.layers.27.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
168 |
+
"model.layers.27.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
169 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
170 |
+
"model.layers.27.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
171 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
172 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
173 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
174 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
175 |
+
"model.layers.28.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
176 |
+
"model.layers.28.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
177 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
178 |
+
"model.layers.28.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
179 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
180 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
181 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
182 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
183 |
+
"model.layers.29.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
184 |
+
"model.layers.29.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
185 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
186 |
+
"model.layers.29.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
187 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
188 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
189 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
190 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
191 |
+
"model.layers.3.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
192 |
+
"model.layers.3.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
193 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
194 |
+
"model.layers.3.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
195 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
196 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
197 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
198 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
199 |
+
"model.layers.30.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
200 |
+
"model.layers.30.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
201 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
202 |
+
"model.layers.30.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
203 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
204 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
205 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
206 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
207 |
+
"model.layers.31.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
208 |
+
"model.layers.31.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
209 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
210 |
+
"model.layers.31.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
211 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
212 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
213 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
214 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
215 |
+
"model.layers.32.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
216 |
+
"model.layers.32.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
217 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
218 |
+
"model.layers.32.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
219 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
220 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
221 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
222 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
223 |
+
"model.layers.33.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
224 |
+
"model.layers.33.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
225 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
226 |
+
"model.layers.33.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
227 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
228 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
229 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
230 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
231 |
+
"model.layers.34.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
232 |
+
"model.layers.34.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
233 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
234 |
+
"model.layers.34.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
235 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
236 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
237 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
238 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
239 |
+
"model.layers.35.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
240 |
+
"model.layers.35.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
241 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
242 |
+
"model.layers.35.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
243 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
244 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
245 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
246 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
247 |
+
"model.layers.36.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
248 |
+
"model.layers.36.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
249 |
+
"model.layers.36.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
250 |
+
"model.layers.36.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
251 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
252 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
253 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
254 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
255 |
+
"model.layers.37.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
256 |
+
"model.layers.37.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
257 |
+
"model.layers.37.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
258 |
+
"model.layers.37.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
259 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
260 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
261 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
262 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
263 |
+
"model.layers.38.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
264 |
+
"model.layers.38.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
265 |
+
"model.layers.38.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
266 |
+
"model.layers.38.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
267 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
268 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
269 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
270 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
271 |
+
"model.layers.39.input_layernorm.weight": "model-00015-of-00015.safetensors",
|
272 |
+
"model.layers.39.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
|
273 |
+
"model.layers.39.mlp.gate_proj.weight": "model-00015-of-00015.safetensors",
|
274 |
+
"model.layers.39.mlp.up_proj.weight": "model-00015-of-00015.safetensors",
|
275 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
276 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
277 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
278 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
279 |
+
"model.layers.4.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
280 |
+
"model.layers.4.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
281 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
282 |
+
"model.layers.4.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
283 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
284 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
285 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
286 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
287 |
+
"model.layers.5.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
288 |
+
"model.layers.5.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
289 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
290 |
+
"model.layers.5.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
291 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
292 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
293 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
294 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
295 |
+
"model.layers.6.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
296 |
+
"model.layers.6.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
297 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
298 |
+
"model.layers.6.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
299 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
300 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
301 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
302 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
303 |
+
"model.layers.7.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
304 |
+
"model.layers.7.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
305 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
306 |
+
"model.layers.7.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
307 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
308 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
309 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
310 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
311 |
+
"model.layers.8.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
312 |
+
"model.layers.8.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
313 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
314 |
+
"model.layers.8.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
315 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
316 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
317 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
318 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
319 |
+
"model.layers.9.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
320 |
+
"model.layers.9.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
321 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
322 |
+
"model.layers.9.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
323 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
324 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
325 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
326 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
327 |
+
"model.norm.weight": "model-00015-of-00015.safetensors"
|
328 |
+
}
|
329 |
+
}
|
output-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20817b808caa6a6bbd4b80fbffb8cbaaca3cdae45a57b94f443404b8c4ce9d8b
|
3 |
+
size 8574112930
|
output-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1236ad407993aa94572ed8798c0593f87cf8db00bb23e32176c6d710a3d5872e
|
3 |
+
size 8550958958
|
output-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b99901b22c50dce446a870f65b457587f895a68243d936aca3ad7dabb0f0b60
|
3 |
+
size 8474326082
|
output-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63bd4d35e6f4aab2be030fe6106b975be1b9345f0d4a95fbadbb2d841bd9e496
|
3 |
+
size 6922028070
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9619890aebac311d644236f49462d7f8618ebef7c7020c52645ccb597434a3c9
|
3 |
+
size 16543645
|
tokenizer_config.json
ADDED
@@ -0,0 +1,330 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": false,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<PAD>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<UNK>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "<CLS>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"3": {
|
31 |
+
"content": "<SEP>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"4": {
|
39 |
+
"content": "<MASK_TOKEN>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"5": {
|
47 |
+
"content": "<BOS_TOKEN>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"6": {
|
55 |
+
"content": "<EOS_TOKEN>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"7": {
|
63 |
+
"content": "<EOP_TOKEN>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"255000": {
|
71 |
+
"content": "<|START_OF_TURN_TOKEN|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": false
|
77 |
+
},
|
78 |
+
"255001": {
|
79 |
+
"content": "<|END_OF_TURN_TOKEN|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"255002": {
|
87 |
+
"content": "<|YES_TOKEN|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": false
|
93 |
+
},
|
94 |
+
"255003": {
|
95 |
+
"content": "<|NO_TOKEN|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": false
|
101 |
+
},
|
102 |
+
"255004": {
|
103 |
+
"content": "<|GOOD_TOKEN|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": false
|
109 |
+
},
|
110 |
+
"255005": {
|
111 |
+
"content": "<|BAD_TOKEN|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": false
|
117 |
+
},
|
118 |
+
"255006": {
|
119 |
+
"content": "<|USER_TOKEN|>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": false
|
125 |
+
},
|
126 |
+
"255007": {
|
127 |
+
"content": "<|CHATBOT_TOKEN|>",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": false,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": false
|
133 |
+
},
|
134 |
+
"255008": {
|
135 |
+
"content": "<|SYSTEM_TOKEN|>",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": false,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": false
|
141 |
+
},
|
142 |
+
"255009": {
|
143 |
+
"content": "<|USER_0_TOKEN|>",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": false
|
149 |
+
},
|
150 |
+
"255010": {
|
151 |
+
"content": "<|USER_1_TOKEN|>",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": false,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": false
|
157 |
+
},
|
158 |
+
"255011": {
|
159 |
+
"content": "<|USER_2_TOKEN|>",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": false,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": false
|
165 |
+
},
|
166 |
+
"255012": {
|
167 |
+
"content": "<|USER_3_TOKEN|>",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": false,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": false
|
173 |
+
},
|
174 |
+
"255013": {
|
175 |
+
"content": "<|USER_4_TOKEN|>",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": false,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": false
|
181 |
+
},
|
182 |
+
"255014": {
|
183 |
+
"content": "<|USER_5_TOKEN|>",
|
184 |
+
"lstrip": false,
|
185 |
+
"normalized": false,
|
186 |
+
"rstrip": false,
|
187 |
+
"single_word": false,
|
188 |
+
"special": false
|
189 |
+
},
|
190 |
+
"255015": {
|
191 |
+
"content": "<|USER_6_TOKEN|>",
|
192 |
+
"lstrip": false,
|
193 |
+
"normalized": false,
|
194 |
+
"rstrip": false,
|
195 |
+
"single_word": false,
|
196 |
+
"special": false
|
197 |
+
},
|
198 |
+
"255016": {
|
199 |
+
"content": "<|USER_7_TOKEN|>",
|
200 |
+
"lstrip": false,
|
201 |
+
"normalized": false,
|
202 |
+
"rstrip": false,
|
203 |
+
"single_word": false,
|
204 |
+
"special": false
|
205 |
+
},
|
206 |
+
"255017": {
|
207 |
+
"content": "<|USER_8_TOKEN|>",
|
208 |
+
"lstrip": false,
|
209 |
+
"normalized": false,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false,
|
212 |
+
"special": false
|
213 |
+
},
|
214 |
+
"255018": {
|
215 |
+
"content": "<|USER_9_TOKEN|>",
|
216 |
+
"lstrip": false,
|
217 |
+
"normalized": false,
|
218 |
+
"rstrip": false,
|
219 |
+
"single_word": false,
|
220 |
+
"special": false
|
221 |
+
},
|
222 |
+
"255019": {
|
223 |
+
"content": "<|EXTRA_0_TOKEN|>",
|
224 |
+
"lstrip": false,
|
225 |
+
"normalized": false,
|
226 |
+
"rstrip": false,
|
227 |
+
"single_word": false,
|
228 |
+
"special": false
|
229 |
+
},
|
230 |
+
"255020": {
|
231 |
+
"content": "<|EXTRA_1_TOKEN|>",
|
232 |
+
"lstrip": false,
|
233 |
+
"normalized": false,
|
234 |
+
"rstrip": false,
|
235 |
+
"single_word": false,
|
236 |
+
"special": false
|
237 |
+
},
|
238 |
+
"255021": {
|
239 |
+
"content": "<|EXTRA_2_TOKEN|>",
|
240 |
+
"lstrip": false,
|
241 |
+
"normalized": false,
|
242 |
+
"rstrip": false,
|
243 |
+
"single_word": false,
|
244 |
+
"special": false
|
245 |
+
},
|
246 |
+
"255022": {
|
247 |
+
"content": "<|EXTRA_3_TOKEN|>",
|
248 |
+
"lstrip": false,
|
249 |
+
"normalized": false,
|
250 |
+
"rstrip": false,
|
251 |
+
"single_word": false,
|
252 |
+
"special": false
|
253 |
+
},
|
254 |
+
"255023": {
|
255 |
+
"content": "<|EXTRA_4_TOKEN|>",
|
256 |
+
"lstrip": false,
|
257 |
+
"normalized": false,
|
258 |
+
"rstrip": false,
|
259 |
+
"single_word": false,
|
260 |
+
"special": false
|
261 |
+
},
|
262 |
+
"255024": {
|
263 |
+
"content": "<|EXTRA_5_TOKEN|>",
|
264 |
+
"lstrip": false,
|
265 |
+
"normalized": false,
|
266 |
+
"rstrip": false,
|
267 |
+
"single_word": false,
|
268 |
+
"special": false
|
269 |
+
},
|
270 |
+
"255025": {
|
271 |
+
"content": "<|EXTRA_6_TOKEN|>",
|
272 |
+
"lstrip": false,
|
273 |
+
"normalized": false,
|
274 |
+
"rstrip": false,
|
275 |
+
"single_word": false,
|
276 |
+
"special": false
|
277 |
+
},
|
278 |
+
"255026": {
|
279 |
+
"content": "<|EXTRA_7_TOKEN|>",
|
280 |
+
"lstrip": false,
|
281 |
+
"normalized": false,
|
282 |
+
"rstrip": false,
|
283 |
+
"single_word": false,
|
284 |
+
"special": false
|
285 |
+
},
|
286 |
+
"255027": {
|
287 |
+
"content": "<|EXTRA_8_TOKEN|>",
|
288 |
+
"lstrip": false,
|
289 |
+
"normalized": false,
|
290 |
+
"rstrip": false,
|
291 |
+
"single_word": false,
|
292 |
+
"special": false
|
293 |
+
},
|
294 |
+
"255028": {
|
295 |
+
"content": "<|EXTRA_9_TOKEN|>",
|
296 |
+
"lstrip": false,
|
297 |
+
"normalized": false,
|
298 |
+
"rstrip": false,
|
299 |
+
"single_word": false,
|
300 |
+
"special": false
|
301 |
+
}
|
302 |
+
},
|
303 |
+
"bos_token": "<BOS_TOKEN>",
|
304 |
+
"chat_template": [
|
305 |
+
{
|
306 |
+
"name": "default",
|
307 |
+
"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 Command-R, 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 %}"
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"name": "tool_use",
|
311 |
+
"template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = '## Task and Context\\nYou help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user\\'s needs as best you can, which will be wide-ranging.\\n\\n## Style Guide\\nUnless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.' %}{% endif %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ '# Safety Preamble' }}{{ '\nThe instructions in this section override those in the task description and style guide sections. Don\\'t answer questions that are harmful or immoral.' }}{{ '\n\n# System Preamble' }}{{ '\n## Basic Rules' }}{{ '\nYou are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user\\'s requests, you cite your sources in your answers, according to those instructions.' }}{{ '\n\n# User Preamble' }}{{ '\n' + system_message }}{{'\n\n## Available Tools\nHere is a list of tools that you have available to you:\n\n'}}{% for tool in tools %}{% if loop.index0 != 0 %}{{ '\n\n'}}{% endif %}{{'```python\ndef ' + tool.name + '('}}{% for param_name, param_fields in tool.parameter_definitions.items() %}{% if loop.index0 != 0 %}{{ ', '}}{% endif %}{{param_name}}: {% if not param_fields.required %}{{'Optional[' + param_fields.type + '] = None'}}{% else %}{{ param_fields.type }}{% endif %}{% endfor %}{{ ') -> List[Dict]:\n \"\"\"'}}{{ tool.description }}{% if tool.parameter_definitions|length != 0 %}{{ '\n\n Args:\n '}}{% for param_name, param_fields in tool.parameter_definitions.items() %}{% if loop.index0 != 0 %}{{ '\n ' }}{% endif %}{{ param_name + ' ('}}{% if not param_fields.required %}{{'Optional[' + param_fields.type + ']'}}{% else %}{{ param_fields.type }}{% endif %}{{ '): ' + param_fields.description }}{% endfor %}{% endif %}{{ '\n \"\"\"\n pass\n```' }}{% endfor %}{{ '<|END_OF_TURN_TOKEN|>'}}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'system' %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_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 %}{{'<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>Write \\'Action:\\' followed by a json-formatted list of actions that you want to perform in order to produce a good response to the user\\'s last input. You can use any of the supplied tools any number of times, but you should aim to execute the minimum number of necessary actions for the input. You should use the `directly-answer` tool if calling the other tools is unnecessary. The list of actions you want to call should be formatted as a list of json objects, for example:\n```json\n[\n {\n \"tool_name\": title of the tool in the specification,\n \"parameters\": a dict of parameters to input into the tool as they are defined in the specs, or {} if it takes no parameters\n }\n]```<|END_OF_TURN_TOKEN|>'}}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}"
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"name": "rag",
|
315 |
+
"template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = '## Task and Context\\nYou help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user\\'s needs as best you can, which will be wide-ranging.\\n\\n## Style Guide\\nUnless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.' %}{% endif %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ '# Safety Preamble' }}{{ '\nThe instructions in this section override those in the task description and style guide sections. Don\\'t answer questions that are harmful or immoral.' }}{{ '\n\n# System Preamble' }}{{ '\n## Basic Rules' }}{{ '\nYou are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user\\'s requests, you cite your sources in your answers, according to those instructions.' }}{{ '\n\n# User Preamble' }}{{ '\n' + system_message }}{{ '<|END_OF_TURN_TOKEN|>'}}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'system' %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_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 %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>'}}{{ '<results>' }}{% for document in documents %}{{ '\nDocument: ' }}{{ loop.index0 }}\n{% for key, value in document.items() %}{{ key }}: {{value}}\n{% endfor %}{% endfor %}{{ '</results>'}}{{ '<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' }}{{ 'Carefully perform the following instructions, in order, starting each with a new line.\n' }}{{ 'Firstly, Decide which of the retrieved documents are relevant to the user\\'s last input by writing \\'Relevant Documents:\\' followed by comma-separated list of document numbers. If none are relevant, you should instead write \\'None\\'.\n' }}{{ 'Secondly, Decide which of the retrieved documents contain facts that should be cited in a good answer to the user\\'s last input by writing \\'Cited Documents:\\' followed a comma-separated list of document numbers. If you dont want to cite any of them, you should instead write \\'None\\'.\n' }}{% if citation_mode=='accurate' %}{{ 'Thirdly, Write \\'Answer:\\' followed by a response to the user\\'s last input in high quality natural english. Use the retrieved documents to help you. Do not insert any citations or grounding markup.\n' }}{% endif %}{{ 'Finally, Write \\'Grounded answer:\\' followed by a response to the user\\'s last input in high quality natural english. Use the symbols <co: doc> and </co: doc> to indicate when a fact comes from a document in the search result, e.g <co: 0>my fact</co: 0> for a fact from document 0.' }}{{ '<|END_OF_TURN_TOKEN|>' }}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}"
|
316 |
+
}
|
317 |
+
],
|
318 |
+
"clean_up_tokenization_spaces": false,
|
319 |
+
"eos_token": "<|END_OF_TURN_TOKEN|>",
|
320 |
+
"legacy": true,
|
321 |
+
"merges_file": null,
|
322 |
+
"model_max_length": 1000000000000000019884624838656,
|
323 |
+
"pad_token": "<PAD>",
|
324 |
+
"sp_model_kwargs": {},
|
325 |
+
"spaces_between_special_tokens": false,
|
326 |
+
"tokenizer_class": "CohereTokenizer",
|
327 |
+
"unk_token": null,
|
328 |
+
"use_default_system_prompt": false,
|
329 |
+
"vocab_file": null
|
330 |
+
}
|
winrates.png
ADDED
![]() |