Hugging Face's logo

executorch-community
/
Llama-3.2-1B-Instruct-ET

llama
Model card Files Community
SocialLocalMobile commited on
Commit
a890af6
·
verified ·
1 Parent(s): 48fa17f

Upload ExportRecipe_1B_Instruct.ipynb

Browse files
Files changed (1) hide show
  1. ExportRecipe_1B_Instruct.ipynb +1541 -0
ExportRecipe_1B_Instruct.ipynb ADDED
@@ -0,0 +1,1541 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "nbformat": 4,
3
+ "nbformat_minor": 0,
4
+ "metadata": {
5
+ "colab": {
6
+ "provenance": []
7
+ },
8
+ "kernelspec": {
9
+ "name": "python3",
10
+ "display_name": "Python 3"
11
+ },
12
+ "language_info": {
13
+ "name": "python"
14
+ },
15
+ "widgets": {
16
+ "application/vnd.jupyter.widget-state+json": {
17
+ "b47150e6eeda43dd83f436f2b213313c": {
18
+ "model_module": "@jupyter-widgets/controls",
19
+ "model_name": "VBoxModel",
20
+ "model_module_version": "1.5.0",
21
+ "state": {
22
+ "_dom_classes": [],
23
+ "_model_module": "@jupyter-widgets/controls",
24
+ "_model_module_version": "1.5.0",
25
+ "_model_name": "VBoxModel",
26
+ "_view_count": null,
27
+ "_view_module": "@jupyter-widgets/controls",
28
+ "_view_module_version": "1.5.0",
29
+ "_view_name": "VBoxView",
30
+ "box_style": "",
31
+ "children": [],
32
+ "layout": "IPY_MODEL_1847d47db62640618969b578650c3bf1"
33
+ }
34
+ },
35
+ "d7788db18daf472a81f3864b08a8350f": {
36
+ "model_module": "@jupyter-widgets/controls",
37
+ "model_name": "HTMLModel",
38
+ "model_module_version": "1.5.0",
39
+ "state": {
40
+ "_dom_classes": [],
41
+ "_model_module": "@jupyter-widgets/controls",
42
+ "_model_module_version": "1.5.0",
43
+ "_model_name": "HTMLModel",
44
+ "_view_count": null,
45
+ "_view_module": "@jupyter-widgets/controls",
46
+ "_view_module_version": "1.5.0",
47
+ "_view_name": "HTMLView",
48
+ "description": "",
49
+ "description_tooltip": null,
50
+ "layout": "IPY_MODEL_4a8eb3c1118b4147bd3340f4332ff913",
51
+ "placeholder": "​",
52
+ "style": "IPY_MODEL_09d4b54a1a274ce9942d6ec9cdbfedb1",
53
+ "value": "<center> <img\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.svg\nalt='Hugging Face'> <br> Copy a token from <a\nhref=\"https://huggingface.co/settings/tokens\" target=\"_blank\">your Hugging Face\ntokens page</a> and paste it below. <br> Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file. </center>"
54
+ }
55
+ },
56
+ "ca772920b59b46818fa1abc92b6f8f41": {
57
+ "model_module": "@jupyter-widgets/controls",
58
+ "model_name": "PasswordModel",
59
+ "model_module_version": "1.5.0",
60
+ "state": {
61
+ "_dom_classes": [],
62
+ "_model_module": "@jupyter-widgets/controls",
63
+ "_model_module_version": "1.5.0",
64
+ "_model_name": "PasswordModel",
65
+ "_view_count": null,
66
+ "_view_module": "@jupyter-widgets/controls",
67
+ "_view_module_version": "1.5.0",
68
+ "_view_name": "PasswordView",
69
+ "continuous_update": true,
70
+ "description": "Token:",
71
+ "description_tooltip": null,
72
+ "disabled": false,
73
+ "layout": "IPY_MODEL_498fb278a25f4b72978c352e05abb5dc",
74
+ "placeholder": "​",
75
+ "style": "IPY_MODEL_897698b9f67a46269c5b00bccd359d2b",
76
+ "value": ""
77
+ }
78
+ },
79
+ "ab6a8d045145424aadc6cb6d35fd7384": {
80
+ "model_module": "@jupyter-widgets/controls",
81
+ "model_name": "CheckboxModel",
82
+ "model_module_version": "1.5.0",
83
+ "state": {
84
+ "_dom_classes": [],
85
+ "_model_module": "@jupyter-widgets/controls",
86
+ "_model_module_version": "1.5.0",
87
+ "_model_name": "CheckboxModel",
88
+ "_view_count": null,
89
+ "_view_module": "@jupyter-widgets/controls",
90
+ "_view_module_version": "1.5.0",
91
+ "_view_name": "CheckboxView",
92
+ "description": "Add token as git credential?",
93
+ "description_tooltip": null,
94
+ "disabled": false,
95
+ "indent": true,
96
+ "layout": "IPY_MODEL_a68abf425d144555b8aa8a88622725a7",
97
+ "style": "IPY_MODEL_a0936f9d05f3402a994f51b5bd4a6687",
98
+ "value": true
99
+ }
100
+ },
101
+ "e0a58c5a83f34cc8a74b2595116df7b3": {
102
+ "model_module": "@jupyter-widgets/controls",
103
+ "model_name": "ButtonModel",
104
+ "model_module_version": "1.5.0",
105
+ "state": {
106
+ "_dom_classes": [],
107
+ "_model_module": "@jupyter-widgets/controls",
108
+ "_model_module_version": "1.5.0",
109
+ "_model_name": "ButtonModel",
110
+ "_view_count": null,
111
+ "_view_module": "@jupyter-widgets/controls",
112
+ "_view_module_version": "1.5.0",
113
+ "_view_name": "ButtonView",
114
+ "button_style": "",
115
+ "description": "Login",
116
+ "disabled": false,
117
+ "icon": "",
118
+ "layout": "IPY_MODEL_ec869b68e4e44c54ba414ff705aa1f0b",
119
+ "style": "IPY_MODEL_6d67d663ac894a3e963bfadc419fff3b",
120
+ "tooltip": ""
121
+ }
122
+ },
123
+ "96adcdbbec594b0594b27c180875845d": {
124
+ "model_module": "@jupyter-widgets/controls",
125
+ "model_name": "HTMLModel",
126
+ "model_module_version": "1.5.0",
127
+ "state": {
128
+ "_dom_classes": [],
129
+ "_model_module": "@jupyter-widgets/controls",
130
+ "_model_module_version": "1.5.0",
131
+ "_model_name": "HTMLModel",
132
+ "_view_count": null,
133
+ "_view_module": "@jupyter-widgets/controls",
134
+ "_view_module_version": "1.5.0",
135
+ "_view_name": "HTMLView",
136
+ "description": "",
137
+ "description_tooltip": null,
138
+ "layout": "IPY_MODEL_c075734b654e4d1fb54e280d8d56134a",
139
+ "placeholder": "​",
140
+ "style": "IPY_MODEL_83035980181d469f85bdd3ac1a20802d",
141
+ "value": "\n<b>Pro Tip:</b> If you don't already have one, you can create a dedicated\n'notebooks' token with 'write' access, that you can then easily reuse for all\nnotebooks. </center>"
142
+ }
143
+ },
144
+ "1847d47db62640618969b578650c3bf1": {
145
+ "model_module": "@jupyter-widgets/base",
146
+ "model_name": "LayoutModel",
147
+ "model_module_version": "1.2.0",
148
+ "state": {
149
+ "_model_module": "@jupyter-widgets/base",
150
+ "_model_module_version": "1.2.0",
151
+ "_model_name": "LayoutModel",
152
+ "_view_count": null,
153
+ "_view_module": "@jupyter-widgets/base",
154
+ "_view_module_version": "1.2.0",
155
+ "_view_name": "LayoutView",
156
+ "align_content": null,
157
+ "align_items": "center",
158
+ "align_self": null,
159
+ "border": null,
160
+ "bottom": null,
161
+ "display": "flex",
162
+ "flex": null,
163
+ "flex_flow": "column",
164
+ "grid_area": null,
165
+ "grid_auto_columns": null,
166
+ "grid_auto_flow": null,
167
+ "grid_auto_rows": null,
168
+ "grid_column": null,
169
+ "grid_gap": null,
170
+ "grid_row": null,
171
+ "grid_template_areas": null,
172
+ "grid_template_columns": null,
173
+ "grid_template_rows": null,
174
+ "height": null,
175
+ "justify_content": null,
176
+ "justify_items": null,
177
+ "left": null,
178
+ "margin": null,
179
+ "max_height": null,
180
+ "max_width": null,
181
+ "min_height": null,
182
+ "min_width": null,
183
+ "object_fit": null,
184
+ "object_position": null,
185
+ "order": null,
186
+ "overflow": null,
187
+ "overflow_x": null,
188
+ "overflow_y": null,
189
+ "padding": null,
190
+ "right": null,
191
+ "top": null,
192
+ "visibility": null,
193
+ "width": "50%"
194
+ }
195
+ },
196
+ "4a8eb3c1118b4147bd3340f4332ff913": {
197
+ "model_module": "@jupyter-widgets/base",
198
+ "model_name": "LayoutModel",
199
+ "model_module_version": "1.2.0",
200
+ "state": {
201
+ "_model_module": "@jupyter-widgets/base",
202
+ "_model_module_version": "1.2.0",
203
+ "_model_name": "LayoutModel",
204
+ "_view_count": null,
205
+ "_view_module": "@jupyter-widgets/base",
206
+ "_view_module_version": "1.2.0",
207
+ "_view_name": "LayoutView",
208
+ "align_content": null,
209
+ "align_items": null,
210
+ "align_self": null,
211
+ "border": null,
212
+ "bottom": null,
213
+ "display": null,
214
+ "flex": null,
215
+ "flex_flow": null,
216
+ "grid_area": null,
217
+ "grid_auto_columns": null,
218
+ "grid_auto_flow": null,
219
+ "grid_auto_rows": null,
220
+ "grid_column": null,
221
+ "grid_gap": null,
222
+ "grid_row": null,
223
+ "grid_template_areas": null,
224
+ "grid_template_columns": null,
225
+ "grid_template_rows": null,
226
+ "height": null,
227
+ "justify_content": null,
228
+ "justify_items": null,
229
+ "left": null,
230
+ "margin": null,
231
+ "max_height": null,
232
+ "max_width": null,
233
+ "min_height": null,
234
+ "min_width": null,
235
+ "object_fit": null,
236
+ "object_position": null,
237
+ "order": null,
238
+ "overflow": null,
239
+ "overflow_x": null,
240
+ "overflow_y": null,
241
+ "padding": null,
242
+ "right": null,
243
+ "top": null,
244
+ "visibility": null,
245
+ "width": null
246
+ }
247
+ },
248
+ "09d4b54a1a274ce9942d6ec9cdbfedb1": {
249
+ "model_module": "@jupyter-widgets/controls",
250
+ "model_name": "DescriptionStyleModel",
251
+ "model_module_version": "1.5.0",
252
+ "state": {
253
+ "_model_module": "@jupyter-widgets/controls",
254
+ "_model_module_version": "1.5.0",
255
+ "_model_name": "DescriptionStyleModel",
256
+ "_view_count": null,
257
+ "_view_module": "@jupyter-widgets/base",
258
+ "_view_module_version": "1.2.0",
259
+ "_view_name": "StyleView",
260
+ "description_width": ""
261
+ }
262
+ },
263
+ "498fb278a25f4b72978c352e05abb5dc": {
264
+ "model_module": "@jupyter-widgets/base",
265
+ "model_name": "LayoutModel",
266
+ "model_module_version": "1.2.0",
267
+ "state": {
268
+ "_model_module": "@jupyter-widgets/base",
269
+ "_model_module_version": "1.2.0",
270
+ "_model_name": "LayoutModel",
271
+ "_view_count": null,
272
+ "_view_module": "@jupyter-widgets/base",
273
+ "_view_module_version": "1.2.0",
274
+ "_view_name": "LayoutView",
275
+ "align_content": null,
276
+ "align_items": null,
277
+ "align_self": null,
278
+ "border": null,
279
+ "bottom": null,
280
+ "display": null,
281
+ "flex": null,
282
+ "flex_flow": null,
283
+ "grid_area": null,
284
+ "grid_auto_columns": null,
285
+ "grid_auto_flow": null,
286
+ "grid_auto_rows": null,
287
+ "grid_column": null,
288
+ "grid_gap": null,
289
+ "grid_row": null,
290
+ "grid_template_areas": null,
291
+ "grid_template_columns": null,
292
+ "grid_template_rows": null,
293
+ "height": null,
294
+ "justify_content": null,
295
+ "justify_items": null,
296
+ "left": null,
297
+ "margin": null,
298
+ "max_height": null,
299
+ "max_width": null,
300
+ "min_height": null,
301
+ "min_width": null,
302
+ "object_fit": null,
303
+ "object_position": null,
304
+ "order": null,
305
+ "overflow": null,
306
+ "overflow_x": null,
307
+ "overflow_y": null,
308
+ "padding": null,
309
+ "right": null,
310
+ "top": null,
311
+ "visibility": null,
312
+ "width": null
313
+ }
314
+ },
315
+ "897698b9f67a46269c5b00bccd359d2b": {
316
+ "model_module": "@jupyter-widgets/controls",
317
+ "model_name": "DescriptionStyleModel",
318
+ "model_module_version": "1.5.0",
319
+ "state": {
320
+ "_model_module": "@jupyter-widgets/controls",
321
+ "_model_module_version": "1.5.0",
322
+ "_model_name": "DescriptionStyleModel",
323
+ "_view_count": null,
324
+ "_view_module": "@jupyter-widgets/base",
325
+ "_view_module_version": "1.2.0",
326
+ "_view_name": "StyleView",
327
+ "description_width": ""
328
+ }
329
+ },
330
+ "a68abf425d144555b8aa8a88622725a7": {
331
+ "model_module": "@jupyter-widgets/base",
332
+ "model_name": "LayoutModel",
333
+ "model_module_version": "1.2.0",
334
+ "state": {
335
+ "_model_module": "@jupyter-widgets/base",
336
+ "_model_module_version": "1.2.0",
337
+ "_model_name": "LayoutModel",
338
+ "_view_count": null,
339
+ "_view_module": "@jupyter-widgets/base",
340
+ "_view_module_version": "1.2.0",
341
+ "_view_name": "LayoutView",
342
+ "align_content": null,
343
+ "align_items": null,
344
+ "align_self": null,
345
+ "border": null,
346
+ "bottom": null,
347
+ "display": null,
348
+ "flex": null,
349
+ "flex_flow": null,
350
+ "grid_area": null,
351
+ "grid_auto_columns": null,
352
+ "grid_auto_flow": null,
353
+ "grid_auto_rows": null,
354
+ "grid_column": null,
355
+ "grid_gap": null,
356
+ "grid_row": null,
357
+ "grid_template_areas": null,
358
+ "grid_template_columns": null,
359
+ "grid_template_rows": null,
360
+ "height": null,
361
+ "justify_content": null,
362
+ "justify_items": null,
363
+ "left": null,
364
+ "margin": null,
365
+ "max_height": null,
366
+ "max_width": null,
367
+ "min_height": null,
368
+ "min_width": null,
369
+ "object_fit": null,
370
+ "object_position": null,
371
+ "order": null,
372
+ "overflow": null,
373
+ "overflow_x": null,
374
+ "overflow_y": null,
375
+ "padding": null,
376
+ "right": null,
377
+ "top": null,
378
+ "visibility": null,
379
+ "width": null
380
+ }
381
+ },
382
+ "a0936f9d05f3402a994f51b5bd4a6687": {
383
+ "model_module": "@jupyter-widgets/controls",
384
+ "model_name": "DescriptionStyleModel",
385
+ "model_module_version": "1.5.0",
386
+ "state": {
387
+ "_model_module": "@jupyter-widgets/controls",
388
+ "_model_module_version": "1.5.0",
389
+ "_model_name": "DescriptionStyleModel",
390
+ "_view_count": null,
391
+ "_view_module": "@jupyter-widgets/base",
392
+ "_view_module_version": "1.2.0",
393
+ "_view_name": "StyleView",
394
+ "description_width": ""
395
+ }
396
+ },
397
+ "ec869b68e4e44c54ba414ff705aa1f0b": {
398
+ "model_module": "@jupyter-widgets/base",
399
+ "model_name": "LayoutModel",
400
+ "model_module_version": "1.2.0",
401
+ "state": {
402
+ "_model_module": "@jupyter-widgets/base",
403
+ "_model_module_version": "1.2.0",
404
+ "_model_name": "LayoutModel",
405
+ "_view_count": null,
406
+ "_view_module": "@jupyter-widgets/base",
407
+ "_view_module_version": "1.2.0",
408
+ "_view_name": "LayoutView",
409
+ "align_content": null,
410
+ "align_items": null,
411
+ "align_self": null,
412
+ "border": null,
413
+ "bottom": null,
414
+ "display": null,
415
+ "flex": null,
416
+ "flex_flow": null,
417
+ "grid_area": null,
418
+ "grid_auto_columns": null,
419
+ "grid_auto_flow": null,
420
+ "grid_auto_rows": null,
421
+ "grid_column": null,
422
+ "grid_gap": null,
423
+ "grid_row": null,
424
+ "grid_template_areas": null,
425
+ "grid_template_columns": null,
426
+ "grid_template_rows": null,
427
+ "height": null,
428
+ "justify_content": null,
429
+ "justify_items": null,
430
+ "left": null,
431
+ "margin": null,
432
+ "max_height": null,
433
+ "max_width": null,
434
+ "min_height": null,
435
+ "min_width": null,
436
+ "object_fit": null,
437
+ "object_position": null,
438
+ "order": null,
439
+ "overflow": null,
440
+ "overflow_x": null,
441
+ "overflow_y": null,
442
+ "padding": null,
443
+ "right": null,
444
+ "top": null,
445
+ "visibility": null,
446
+ "width": null
447
+ }
448
+ },
449
+ "6d67d663ac894a3e963bfadc419fff3b": {
450
+ "model_module": "@jupyter-widgets/controls",
451
+ "model_name": "ButtonStyleModel",
452
+ "model_module_version": "1.5.0",
453
+ "state": {
454
+ "_model_module": "@jupyter-widgets/controls",
455
+ "_model_module_version": "1.5.0",
456
+ "_model_name": "ButtonStyleModel",
457
+ "_view_count": null,
458
+ "_view_module": "@jupyter-widgets/base",
459
+ "_view_module_version": "1.2.0",
460
+ "_view_name": "StyleView",
461
+ "button_color": null,
462
+ "font_weight": ""
463
+ }
464
+ },
465
+ "c075734b654e4d1fb54e280d8d56134a": {
466
+ "model_module": "@jupyter-widgets/base",
467
+ "model_name": "LayoutModel",
468
+ "model_module_version": "1.2.0",
469
+ "state": {
470
+ "_model_module": "@jupyter-widgets/base",
471
+ "_model_module_version": "1.2.0",
472
+ "_model_name": "LayoutModel",
473
+ "_view_count": null,
474
+ "_view_module": "@jupyter-widgets/base",
475
+ "_view_module_version": "1.2.0",
476
+ "_view_name": "LayoutView",
477
+ "align_content": null,
478
+ "align_items": null,
479
+ "align_self": null,
480
+ "border": null,
481
+ "bottom": null,
482
+ "display": null,
483
+ "flex": null,
484
+ "flex_flow": null,
485
+ "grid_area": null,
486
+ "grid_auto_columns": null,
487
+ "grid_auto_flow": null,
488
+ "grid_auto_rows": null,
489
+ "grid_column": null,
490
+ "grid_gap": null,
491
+ "grid_row": null,
492
+ "grid_template_areas": null,
493
+ "grid_template_columns": null,
494
+ "grid_template_rows": null,
495
+ "height": null,
496
+ "justify_content": null,
497
+ "justify_items": null,
498
+ "left": null,
499
+ "margin": null,
500
+ "max_height": null,
501
+ "max_width": null,
502
+ "min_height": null,
503
+ "min_width": null,
504
+ "object_fit": null,
505
+ "object_position": null,
506
+ "order": null,
507
+ "overflow": null,
508
+ "overflow_x": null,
509
+ "overflow_y": null,
510
+ "padding": null,
511
+ "right": null,
512
+ "top": null,
513
+ "visibility": null,
514
+ "width": null
515
+ }
516
+ },
517
+ "83035980181d469f85bdd3ac1a20802d": {
518
+ "model_module": "@jupyter-widgets/controls",
519
+ "model_name": "DescriptionStyleModel",
520
+ "model_module_version": "1.5.0",
521
+ "state": {
522
+ "_model_module": "@jupyter-widgets/controls",
523
+ "_model_module_version": "1.5.0",
524
+ "_model_name": "DescriptionStyleModel",
525
+ "_view_count": null,
526
+ "_view_module": "@jupyter-widgets/base",
527
+ "_view_module_version": "1.2.0",
528
+ "_view_name": "StyleView",
529
+ "description_width": ""
530
+ }
531
+ },
532
+ "09d8892ab8874bd795dc394de9fa111c": {
533
+ "model_module": "@jupyter-widgets/controls",
534
+ "model_name": "LabelModel",
535
+ "model_module_version": "1.5.0",
536
+ "state": {
537
+ "_dom_classes": [],
538
+ "_model_module": "@jupyter-widgets/controls",
539
+ "_model_module_version": "1.5.0",
540
+ "_model_name": "LabelModel",
541
+ "_view_count": null,
542
+ "_view_module": "@jupyter-widgets/controls",
543
+ "_view_module_version": "1.5.0",
544
+ "_view_name": "LabelView",
545
+ "description": "",
546
+ "description_tooltip": null,
547
+ "layout": "IPY_MODEL_5267694b162f423f83bf762d8869b607",
548
+ "placeholder": "​",
549
+ "style": "IPY_MODEL_63e2297265194761b3b7b76fd5d82538",
550
+ "value": "Connecting..."
551
+ }
552
+ },
553
+ "5267694b162f423f83bf762d8869b607": {
554
+ "model_module": "@jupyter-widgets/base",
555
+ "model_name": "LayoutModel",
556
+ "model_module_version": "1.2.0",
557
+ "state": {
558
+ "_model_module": "@jupyter-widgets/base",
559
+ "_model_module_version": "1.2.0",
560
+ "_model_name": "LayoutModel",
561
+ "_view_count": null,
562
+ "_view_module": "@jupyter-widgets/base",
563
+ "_view_module_version": "1.2.0",
564
+ "_view_name": "LayoutView",
565
+ "align_content": null,
566
+ "align_items": null,
567
+ "align_self": null,
568
+ "border": null,
569
+ "bottom": null,
570
+ "display": null,
571
+ "flex": null,
572
+ "flex_flow": null,
573
+ "grid_area": null,
574
+ "grid_auto_columns": null,
575
+ "grid_auto_flow": null,
576
+ "grid_auto_rows": null,
577
+ "grid_column": null,
578
+ "grid_gap": null,
579
+ "grid_row": null,
580
+ "grid_template_areas": null,
581
+ "grid_template_columns": null,
582
+ "grid_template_rows": null,
583
+ "height": null,
584
+ "justify_content": null,
585
+ "justify_items": null,
586
+ "left": null,
587
+ "margin": null,
588
+ "max_height": null,
589
+ "max_width": null,
590
+ "min_height": null,
591
+ "min_width": null,
592
+ "object_fit": null,
593
+ "object_position": null,
594
+ "order": null,
595
+ "overflow": null,
596
+ "overflow_x": null,
597
+ "overflow_y": null,
598
+ "padding": null,
599
+ "right": null,
600
+ "top": null,
601
+ "visibility": null,
602
+ "width": null
603
+ }
604
+ },
605
+ "63e2297265194761b3b7b76fd5d82538": {
606
+ "model_module": "@jupyter-widgets/controls",
607
+ "model_name": "DescriptionStyleModel",
608
+ "model_module_version": "1.5.0",
609
+ "state": {
610
+ "_model_module": "@jupyter-widgets/controls",
611
+ "_model_module_version": "1.5.0",
612
+ "_model_name": "DescriptionStyleModel",
613
+ "_view_count": null,
614
+ "_view_module": "@jupyter-widgets/base",
615
+ "_view_module_version": "1.2.0",
616
+ "_view_name": "StyleView",
617
+ "description_width": ""
618
+ }
619
+ }
620
+ }
621
+ }
622
+ },
623
+ "cells": [
624
+ {
625
+ "cell_type": "markdown",
626
+ "source": [
627
+ "**Step 1: Setting Up ExecuTorch**"
628
+ ],
629
+ "metadata": {
630
+ "id": "ZOq6nHdVElC6"
631
+ }
632
+ },
633
+ {
634
+ "cell_type": "code",
635
+ "execution_count": 1,
636
+ "metadata": {
637
+ "colab": {
638
+ "base_uri": "https://localhost:8080/"
639
+ },
640
+ "collapsed": true,
641
+ "id": "EWz6sJfRDQKT",
642
+ "outputId": "c214e9a7-4553-46f4-a591-6d3d4ed4d749"
643
+ },
644
+ "outputs": [
645
+ {
646
+ "output_type": "stream",
647
+ "name": "stdout",
648
+ "text": [
649
+ "Requirement already satisfied: executorch in /usr/local/lib/python3.11/dist-packages (0.6.0+cpu)\n",
650
+ "Requirement already satisfied: expecttest in /usr/local/lib/python3.11/dist-packages (from executorch) (0.3.0)\n",
651
+ "Requirement already satisfied: flatbuffers in /usr/local/lib/python3.11/dist-packages (from executorch) (25.2.10)\n",
652
+ "Requirement already satisfied: hypothesis in /usr/local/lib/python3.11/dist-packages (from executorch) (6.131.0)\n",
653
+ "Requirement already satisfied: mpmath==1.3.0 in /usr/local/lib/python3.11/dist-packages (from executorch) (1.3.0)\n",
654
+ "Requirement already satisfied: numpy>=2.0.0 in /usr/local/lib/python3.11/dist-packages (from executorch) (2.0.2)\n",
655
+ "Requirement already satisfied: packaging in /usr/local/lib/python3.11/dist-packages (from executorch) (24.2)\n",
656
+ "Requirement already satisfied: pandas>=2.2.2 in /usr/local/lib/python3.11/dist-packages (from executorch) (2.2.2)\n",
657
+ "Requirement already satisfied: parameterized in /usr/local/lib/python3.11/dist-packages (from executorch) (0.9.0)\n",
658
+ "Requirement already satisfied: pytest in /usr/local/lib/python3.11/dist-packages (from executorch) (8.3.5)\n",
659
+ "Requirement already satisfied: pytest-xdist in /usr/local/lib/python3.11/dist-packages (from executorch) (3.6.1)\n",
660
+ "Requirement already satisfied: pytest-rerunfailures in /usr/local/lib/python3.11/dist-packages (from executorch) (15.0)\n",
661
+ "Requirement already satisfied: pyyaml in /usr/local/lib/python3.11/dist-packages (from executorch) (6.0.2)\n",
662
+ "Requirement already satisfied: ruamel.yaml in /usr/local/lib/python3.11/dist-packages (from executorch) (0.18.10)\n",
663
+ "Requirement already satisfied: sympy in /usr/local/lib/python3.11/dist-packages (from executorch) (1.13.3)\n",
664
+ "Requirement already satisfied: tabulate in /usr/local/lib/python3.11/dist-packages (from executorch) (0.9.0)\n",
665
+ "Requirement already satisfied: torchao==0.10.0 in /usr/local/lib/python3.11/dist-packages (from executorch) (0.10.0+cpu)\n",
666
+ "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.11/dist-packages (from executorch) (4.13.1)\n",
667
+ "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.11/dist-packages (from pandas>=2.2.2->executorch) (2.8.2)\n",
668
+ "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas>=2.2.2->executorch) (2025.2)\n",
669
+ "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.11/dist-packages (from pandas>=2.2.2->executorch) (2025.2)\n",
670
+ "Requirement already satisfied: attrs>=22.2.0 in /usr/local/lib/python3.11/dist-packages (from hypothesis->executorch) (25.3.0)\n",
671
+ "Requirement already satisfied: sortedcontainers<3.0.0,>=2.1.0 in /usr/local/lib/python3.11/dist-packages (from hypothesis->executorch) (2.4.0)\n",
672
+ "Requirement already satisfied: iniconfig in /usr/local/lib/python3.11/dist-packages (from pytest->executorch) (2.1.0)\n",
673
+ "Requirement already satisfied: pluggy<2,>=1.5 in /usr/local/lib/python3.11/dist-packages (from pytest->executorch) (1.5.0)\n",
674
+ "Requirement already satisfied: execnet>=2.1 in /usr/local/lib/python3.11/dist-packages (from pytest-xdist->executorch) (2.1.1)\n",
675
+ "Requirement already satisfied: ruamel.yaml.clib>=0.2.7 in /usr/local/lib/python3.11/dist-packages (from ruamel.yaml->executorch) (0.2.12)\n",
676
+ "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/dist-packages (from python-dateutil>=2.8.2->pandas>=2.2.2->executorch) (1.17.0)\n"
677
+ ]
678
+ }
679
+ ],
680
+ "source": [
681
+ "!pip install executorch\n",
682
+ "# Testing release candidate\n",
683
+ "# pip install --extra-index-url https://download.pytorch.org/whl/test/cpu executorch==0.6.0 torch==2.7.0 torchaudio==2.7.0 torchvision==0.22.0"
684
+ ]
685
+ },
686
+ {
687
+ "cell_type": "markdown",
688
+ "source": [],
689
+ "metadata": {
690
+ "id": "0DwPYBnLEChh"
691
+ }
692
+ },
693
+ {
694
+ "cell_type": "code",
695
+ "source": [
696
+ "# Installing dependencies for Llama\n",
697
+ "!pip install transformers accelerate sentencepiece huggingface_hub tiktoken torchtune tokenizers snakeviz lm_eval==0.4.5 blobfile"
698
+ ],
699
+ "metadata": {
700
+ "colab": {
701
+ "base_uri": "https://localhost:8080/"
702
+ },
703
+ "collapsed": true,
704
+ "id": "vhSLDN0sDp9-",
705
+ "outputId": "8891704b-2f9a-4f29-8e04-7aeafd989a77"
706
+ },
707
+ "execution_count": 2,
708
+ "outputs": [
709
+ {
710
+ "output_type": "stream",
711
+ "name": "stdout",
712
+ "text": [
713
+ "Requirement already satisfied: transformers in /usr/local/lib/python3.11/dist-packages (4.50.3)\n",
714
+ "Requirement already satisfied: accelerate in /usr/local/lib/python3.11/dist-packages (1.5.2)\n",
715
+ "Requirement already satisfied: sentencepiece in /usr/local/lib/python3.11/dist-packages (0.2.0)\n",
716
+ "Requirement already satisfied: huggingface_hub in /usr/local/lib/python3.11/dist-packages (0.30.1)\n",
717
+ "Requirement already satisfied: tiktoken in /usr/local/lib/python3.11/dist-packages (0.9.0)\n",
718
+ "Requirement already satisfied: torchtune in /usr/local/lib/python3.11/dist-packages (0.6.1)\n",
719
+ "Requirement already satisfied: tokenizers in /usr/local/lib/python3.11/dist-packages (0.21.1)\n",
720
+ "Requirement already satisfied: snakeviz in /usr/local/lib/python3.11/dist-packages (2.2.2)\n",
721
+ "Requirement already satisfied: lm_eval==0.4.5 in /usr/local/lib/python3.11/dist-packages (0.4.5)\n",
722
+ "Requirement already satisfied: blobfile in /usr/local/lib/python3.11/dist-packages (3.0.0)\n",
723
+ "Requirement already satisfied: evaluate in /usr/local/lib/python3.11/dist-packages (from lm_eval==0.4.5) (0.4.3)\n",
724
+ "Requirement already satisfied: datasets>=2.16.0 in /usr/local/lib/python3.11/dist-packages (from lm_eval==0.4.5) (3.5.0)\n",
725
+ "Requirement already satisfied: jsonlines in /usr/local/lib/python3.11/dist-packages (from lm_eval==0.4.5) (4.0.0)\n",
726
+ "Requirement already satisfied: numexpr in /usr/local/lib/python3.11/dist-packages (from lm_eval==0.4.5) (2.10.2)\n",
727
+ "Requirement already satisfied: peft>=0.2.0 in /usr/local/lib/python3.11/dist-packages (from lm_eval==0.4.5) (0.14.0)\n",
728
+ "Requirement already satisfied: pybind11>=2.6.2 in /usr/local/lib/python3.11/dist-packages (from lm_eval==0.4.5) (2.13.6)\n",
729
+ "Requirement already satisfied: pytablewriter in /usr/local/lib/python3.11/dist-packages (from lm_eval==0.4.5) (1.2.1)\n",
730
+ "Requirement already satisfied: rouge-score>=0.0.4 in /usr/local/lib/python3.11/dist-packages (from lm_eval==0.4.5) (0.1.2)\n",
731
+ "Requirement already satisfied: sacrebleu>=1.5.0 in /usr/local/lib/python3.11/dist-packages (from lm_eval==0.4.5) (2.5.1)\n",
732
+ "Requirement already satisfied: scikit-learn>=0.24.1 in /usr/local/lib/python3.11/dist-packages (from lm_eval==0.4.5) (1.6.1)\n",
733
+ "Requirement already satisfied: sqlitedict in /usr/local/lib/python3.11/dist-packages (from lm_eval==0.4.5) (2.1.0)\n",
734
+ "Requirement already satisfied: torch>=1.8 in /usr/local/lib/python3.11/dist-packages (from lm_eval==0.4.5) (2.7.0+cpu)\n",
735
+ "Requirement already satisfied: tqdm-multiprocess in /usr/local/lib/python3.11/dist-packages (from lm_eval==0.4.5) (0.0.11)\n",
736
+ "Requirement already satisfied: zstandard in /usr/local/lib/python3.11/dist-packages (from lm_eval==0.4.5) (0.23.0)\n",
737
+ "Requirement already satisfied: dill in /usr/local/lib/python3.11/dist-packages (from lm_eval==0.4.5) (0.3.8)\n",
738
+ "Requirement already satisfied: word2number in /usr/local/lib/python3.11/dist-packages (from lm_eval==0.4.5) (1.1)\n",
739
+ "Requirement already satisfied: more-itertools in /usr/local/lib/python3.11/dist-packages (from lm_eval==0.4.5) (10.6.0)\n",
740
+ "Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from transformers) (3.18.0)\n",
741
+ "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.11/dist-packages (from transformers) (2.0.2)\n",
742
+ "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.11/dist-packages (from transformers) (24.2)\n",
743
+ "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.11/dist-packages (from transformers) (6.0.2)\n",
744
+ "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.11/dist-packages (from transformers) (2024.11.6)\n",
745
+ "Requirement already satisfied: requests in /usr/local/lib/python3.11/dist-packages (from transformers) (2.32.3)\n",
746
+ "Requirement already satisfied: safetensors>=0.4.3 in /usr/local/lib/python3.11/dist-packages (from transformers) (0.5.3)\n",
747
+ "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.11/dist-packages (from transformers) (4.67.1)\n",
748
+ "Requirement already satisfied: psutil in /usr/local/lib/python3.11/dist-packages (from accelerate) (5.9.5)\n",
749
+ "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.11/dist-packages (from huggingface_hub) (2024.12.0)\n",
750
+ "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.11/dist-packages (from huggingface_hub) (4.13.1)\n",
751
+ "Requirement already satisfied: torchdata==0.11.0 in /usr/local/lib/python3.11/dist-packages (from torchtune) (0.11.0)\n",
752
+ "Requirement already satisfied: kagglehub in /usr/local/lib/python3.11/dist-packages (from torchtune) (0.3.11)\n",
753
+ "Requirement already satisfied: omegaconf in /usr/local/lib/python3.11/dist-packages (from torchtune) (2.3.0)\n",
754
+ "Requirement already satisfied: Pillow>=9.4.0 in /usr/local/lib/python3.11/dist-packages (from torchtune) (11.1.0)\n",
755
+ "Requirement already satisfied: urllib3>=1.25 in /usr/local/lib/python3.11/dist-packages (from torchdata==0.11.0->torchtune) (2.3.0)\n",
756
+ "Requirement already satisfied: tornado>=2.0 in /usr/local/lib/python3.11/dist-packages (from snakeviz) (6.4.2)\n",
757
+ "Requirement already satisfied: pycryptodomex>=3.8 in /usr/local/lib/python3.11/dist-packages (from blobfile) (3.22.0)\n",
758
+ "Requirement already satisfied: lxml>=4.9 in /usr/local/lib/python3.11/dist-packages (from blobfile) (5.3.1)\n",
759
+ "Requirement already satisfied: pyarrow>=15.0.0 in /usr/local/lib/python3.11/dist-packages (from datasets>=2.16.0->lm_eval==0.4.5) (18.1.0)\n",
760
+ "Requirement already satisfied: pandas in /usr/local/lib/python3.11/dist-packages (from datasets>=2.16.0->lm_eval==0.4.5) (2.2.2)\n",
761
+ "Requirement already satisfied: xxhash in /usr/local/lib/python3.11/dist-packages (from datasets>=2.16.0->lm_eval==0.4.5) (3.5.0)\n",
762
+ "Requirement already satisfied: multiprocess<0.70.17 in /usr/local/lib/python3.11/dist-packages (from datasets>=2.16.0->lm_eval==0.4.5) (0.70.16)\n",
763
+ "Requirement already satisfied: aiohttp in /usr/local/lib/python3.11/dist-packages (from datasets>=2.16.0->lm_eval==0.4.5) (3.11.15)\n",
764
+ "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests->transformers) (3.4.1)\n",
765
+ "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests->transformers) (3.10)\n",
766
+ "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/dist-packages (from requests->transformers) (2025.1.31)\n",
767
+ "Requirement already satisfied: absl-py in /usr/local/lib/python3.11/dist-packages (from rouge-score>=0.0.4->lm_eval==0.4.5) (1.4.0)\n",
768
+ "Requirement already satisfied: nltk in /usr/local/lib/python3.11/dist-packages (from rouge-score>=0.0.4->lm_eval==0.4.5) (3.9.1)\n",
769
+ "Requirement already satisfied: six>=1.14.0 in /usr/local/lib/python3.11/dist-packages (from rouge-score>=0.0.4->lm_eval==0.4.5) (1.17.0)\n",
770
+ "Requirement already satisfied: portalocker in /usr/local/lib/python3.11/dist-packages (from sacrebleu>=1.5.0->lm_eval==0.4.5) (3.1.1)\n",
771
+ "Requirement already satisfied: tabulate>=0.8.9 in /usr/local/lib/python3.11/dist-packages (from sacrebleu>=1.5.0->lm_eval==0.4.5) (0.9.0)\n",
772
+ "Requirement already satisfied: colorama in /usr/local/lib/python3.11/dist-packages (from sacrebleu>=1.5.0->lm_eval==0.4.5) (0.4.6)\n",
773
+ "Requirement already satisfied: scipy>=1.6.0 in /usr/local/lib/python3.11/dist-packages (from scikit-learn>=0.24.1->lm_eval==0.4.5) (1.14.1)\n",
774
+ "Requirement already satisfied: joblib>=1.2.0 in /usr/local/lib/python3.11/dist-packages (from scikit-learn>=0.24.1->lm_eval==0.4.5) (1.4.2)\n",
775
+ "Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.11/dist-packages (from scikit-learn>=0.24.1->lm_eval==0.4.5) (3.6.0)\n",
776
+ "Requirement already satisfied: sympy>=1.13.3 in /usr/local/lib/python3.11/dist-packages (from torch>=1.8->lm_eval==0.4.5) (1.13.3)\n",
777
+ "Requirement already satisfied: networkx in /usr/local/lib/python3.11/dist-packages (from torch>=1.8->lm_eval==0.4.5) (3.4.2)\n",
778
+ "Requirement already satisfied: jinja2 in /usr/local/lib/python3.11/dist-packages (from torch>=1.8->lm_eval==0.4.5) (3.1.6)\n",
779
+ "Requirement already satisfied: hf-transfer>=0.1.4 in /usr/local/lib/python3.11/dist-packages (from huggingface_hub[hf_transfer]->torchtune) (0.1.9)\n",
780
+ "Requirement already satisfied: attrs>=19.2.0 in /usr/local/lib/python3.11/dist-packages (from jsonlines->lm_eval==0.4.5) (25.3.0)\n",
781
+ "Requirement already satisfied: antlr4-python3-runtime==4.9.* in /usr/local/lib/python3.11/dist-packages (from omegaconf->torchtune) (4.9.3)\n",
782
+ "Requirement already satisfied: setuptools>=38.3.0 in /usr/local/lib/python3.11/dist-packages (from pytablewriter->lm_eval==0.4.5) (75.2.0)\n",
783
+ "Requirement already satisfied: DataProperty<2,>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from pytablewriter->lm_eval==0.4.5) (1.1.0)\n",
784
+ "Requirement already satisfied: mbstrdecoder<2,>=1.0.0 in /usr/local/lib/python3.11/dist-packages (from pytablewriter->lm_eval==0.4.5) (1.1.4)\n",
785
+ "Requirement already satisfied: pathvalidate<4,>=2.3.0 in /usr/local/lib/python3.11/dist-packages (from pytablewriter->lm_eval==0.4.5) (3.2.3)\n",
786
+ "Requirement already satisfied: tabledata<2,>=1.3.1 in /usr/local/lib/python3.11/dist-packages (from pytablewriter->lm_eval==0.4.5) (1.3.4)\n",
787
+ "Requirement already satisfied: tcolorpy<1,>=0.0.5 in /usr/local/lib/python3.11/dist-packages (from pytablewriter->lm_eval==0.4.5) (0.1.7)\n",
788
+ "Requirement already satisfied: typepy<2,>=1.3.2 in /usr/local/lib/python3.11/dist-packages (from typepy[datetime]<2,>=1.3.2->pytablewriter->lm_eval==0.4.5) (1.3.4)\n",
789
+ "Requirement already satisfied: aiohappyeyeballs>=2.3.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets>=2.16.0->lm_eval==0.4.5) (2.6.1)\n",
790
+ "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets>=2.16.0->lm_eval==0.4.5) (1.3.2)\n",
791
+ "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets>=2.16.0->lm_eval==0.4.5) (1.5.0)\n",
792
+ "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets>=2.16.0->lm_eval==0.4.5) (6.2.0)\n",
793
+ "Requirement already satisfied: propcache>=0.2.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets>=2.16.0->lm_eval==0.4.5) (0.3.1)\n",
794
+ "Requirement already satisfied: yarl<2.0,>=1.17.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp->datasets>=2.16.0->lm_eval==0.4.5) (1.18.3)\n",
795
+ "Requirement already satisfied: chardet<6,>=3.0.4 in /usr/local/lib/python3.11/dist-packages (from mbstrdecoder<2,>=1.0.0->pytablewriter->lm_eval==0.4.5) (5.2.0)\n",
796
+ "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from sympy>=1.13.3->torch>=1.8->lm_eval==0.4.5) (1.3.0)\n",
797
+ "Requirement already satisfied: python-dateutil<3.0.0,>=2.8.0 in /usr/local/lib/python3.11/dist-packages (from typepy[datetime]<2,>=1.3.2->pytablewriter->lm_eval==0.4.5) (2.8.2)\n",
798
+ "Requirement already satisfied: pytz>=2018.9 in /usr/local/lib/python3.11/dist-packages (from typepy[datetime]<2,>=1.3.2->pytablewriter->lm_eval==0.4.5) (2025.2)\n",
799
+ "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.11/dist-packages (from jinja2->torch>=1.8->lm_eval==0.4.5) (3.0.2)\n",
800
+ "Requirement already satisfied: click in /usr/local/lib/python3.11/dist-packages (from nltk->rouge-score>=0.0.4->lm_eval==0.4.5) (8.1.8)\n",
801
+ "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.11/dist-packages (from pandas->datasets>=2.16.0->lm_eval==0.4.5) (2025.2)\n"
802
+ ]
803
+ }
804
+ ]
805
+ },
806
+ {
807
+ "cell_type": "markdown",
808
+ "source": [
809
+ "**Step 2. Download Llama 3.2 1B/3B models**"
810
+ ],
811
+ "metadata": {
812
+ "id": "px0lGiHFErF_"
813
+ }
814
+ },
815
+ {
816
+ "cell_type": "code",
817
+ "source": [
818
+ "from huggingface_hub import login\n",
819
+ "login()"
820
+ ],
821
+ "metadata": {
822
+ "colab": {
823
+ "base_uri": "https://localhost:8080/",
824
+ "height": 17,
825
+ "referenced_widgets": [
826
+ "b47150e6eeda43dd83f436f2b213313c",
827
+ "d7788db18daf472a81f3864b08a8350f",
828
+ "ca772920b59b46818fa1abc92b6f8f41",
829
+ "ab6a8d045145424aadc6cb6d35fd7384",
830
+ "e0a58c5a83f34cc8a74b2595116df7b3",
831
+ "96adcdbbec594b0594b27c180875845d",
832
+ "1847d47db62640618969b578650c3bf1",
833
+ "4a8eb3c1118b4147bd3340f4332ff913",
834
+ "09d4b54a1a274ce9942d6ec9cdbfedb1",
835
+ "498fb278a25f4b72978c352e05abb5dc",
836
+ "897698b9f67a46269c5b00bccd359d2b",
837
+ "a68abf425d144555b8aa8a88622725a7",
838
+ "a0936f9d05f3402a994f51b5bd4a6687",
839
+ "ec869b68e4e44c54ba414ff705aa1f0b",
840
+ "6d67d663ac894a3e963bfadc419fff3b",
841
+ "c075734b654e4d1fb54e280d8d56134a",
842
+ "83035980181d469f85bdd3ac1a20802d",
843
+ "09d8892ab8874bd795dc394de9fa111c",
844
+ "5267694b162f423f83bf762d8869b607",
845
+ "63e2297265194761b3b7b76fd5d82538"
846
+ ]
847
+ },
848
+ "id": "fKKfjA_KEDnU",
849
+ "outputId": "433c5f40-5c02-4315-c158-cd1b6c8ded4d"
850
+ },
851
+ "execution_count": 3,
852
+ "outputs": [
853
+ {
854
+ "output_type": "display_data",
855
+ "data": {
856
+ "text/plain": [
857
+ "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
858
+ ],
859
+ "application/vnd.jupyter.widget-view+json": {
860
+ "version_major": 2,
861
+ "version_minor": 0,
862
+ "model_id": "b47150e6eeda43dd83f436f2b213313c"
863
+ }
864
+ },
865
+ "metadata": {}
866
+ }
867
+ ]
868
+ },
869
+ {
870
+ "cell_type": "code",
871
+ "source": [
872
+ "!huggingface-cli download meta-llama/Llama-3.2-1B-Instruct --local-dir /content/models/Llama-3.2-1B-Instruct --local-dir-use-symlinks False"
873
+ ],
874
+ "metadata": {
875
+ "colab": {
876
+ "base_uri": "https://localhost:8080/"
877
+ },
878
+ "collapsed": true,
879
+ "id": "JJdsEZaSEEFR",
880
+ "outputId": "6b8a0261-527e-417e-ad51-7aa65d88f270"
881
+ },
882
+ "execution_count": 4,
883
+ "outputs": [
884
+ {
885
+ "output_type": "stream",
886
+ "name": "stdout",
887
+ "text": [
888
+ "/usr/local/lib/python3.11/dist-packages/huggingface_hub/commands/download.py:139: FutureWarning: Ignoring --local-dir-use-symlinks. Downloading to a local directory does not use symlinks anymore.\n",
889
+ " warnings.warn(\n",
890
+ "Fetching 13 files: 0% 0/13 [00:00<?, ?it/s]Downloading 'LICENSE.txt' to '/content/models/Llama-3.2-1B-Instruct/.cache/huggingface/download/cyBuwAu93UXke23CJCWORBYR70A=.085b47c1575cb889b7024030e60b78f54f0b8c9e.incomplete'\n",
891
+ "Downloading 'model.safetensors' to '/content/models/Llama-3.2-1B-Instruct/.cache/huggingface/download/xGOKKLRSlIhH692hSVvI1-gpoa8=.1ff795ff6a07e6a68085d206fb84417da2f083f68391c2843cd2b8ac6df8538f.incomplete'\n",
892
+ "Downloading '.gitattributes' to '/content/models/Llama-3.2-1B-Instruct/.cache/huggingface/download/wPaCkH-WbT7GsmxMKKrNZTV4nSM=.a6344aac8c09253b3b630fb776ae94478aa0275b.incomplete'\n",
893
+ "Downloading 'config.json' to '/content/models/Llama-3.2-1B-Instruct/.cache/huggingface/download/8_PA_wEVGiVa2goH2H4KQOQpvVY=.3e3aaf51a035cb5092d9f6827a0dc074657ba88c.incomplete'\n",
894
+ "Downloading 'original/consolidated.00.pth' to '/content/models/Llama-3.2-1B-Instruct/.cache/huggingface/download/original/_dLw4ih-O1I9AkO57vYC89Z48Os=.fc17d497df5e4175b3a8acb4f5865b26f7fc1b009b25bef814b95fde10e8a1f3.incomplete'\n",
895
+ "Downloading 'USE_POLICY.md' to '/content/models/Llama-3.2-1B-Instruct/.cache/huggingface/download/UcPfAI5B08awK9_TiALuc0iOThI=.ac3c5f21b9779e3da0677d6d3c587778fe3a331e.incomplete'\n",
896
+ "Downloading 'README.md' to '/content/models/Llama-3.2-1B-Instruct/.cache/huggingface/download/Xn7B-BWUGOee2Y6hCZtEhtFu4BE=.b3c62ef6190712fb3e31af1628f0b85706fc4ba8.incomplete'\n",
897
+ "\n",
898
+ "LICENSE.txt: 100% 7.71k/7.71k [00:00<00:00, 30.6MB/s]\n",
899
+ "Download complete. Moving file to /content/models/Llama-3.2-1B-Instruct/LICENSE.txt\n",
900
+ "\n",
901
+ "config.json: 100% 877/877 [00:00<00:00, 4.66MB/s]\n",
902
+ "Download complete. Moving file to /content/models/Llama-3.2-1B-Instruct/config.json\n",
903
+ "\n",
904
+ "USE_POLICY.md: 100% 6.02k/6.02k [00:00<00:00, 31.1MB/s]\n",
905
+ "Download complete. Moving file to /content/models/Llama-3.2-1B-Instruct/USE_POLICY.md\n",
906
+ "\n",
907
+ "README.md: 0% 0.00/41.7k [00:00<?, ?B/s]\u001b[A\n",
908
+ "\n",
909
+ "README.md: 100% 41.7k/41.7k [00:00<00:00, 3.71MB/s]\n",
910
+ "Download complete. Moving file to /content/models/Llama-3.2-1B-Instruct/README.md\n",
911
+ "Downloading 'generation_config.json' to '/content/models/Llama-3.2-1B-Instruct/.cache/huggingface/download/3EVKVggOldJcKSsGjSdoUCN1AyQ=.75ae08310d6d23df373ee2644b497192b3cce6d8.incomplete'\n",
912
+ "Downloading 'original/params.json' to '/content/models/Llama-3.2-1B-Instruct/.cache/huggingface/download/original/jqHB00sRqBVJXCrFOHz5gDS2Bg8=.9cd8dbdf2dc6f4d8abb60bdb5ce64f4bec2fdfd9.incomplete'\n",
913
+ "\n",
914
+ "consolidated.00.pth: 0% 0.00/2.47G [00:00<?, ?B/s]\u001b[ADownloading 'original/tokenizer.model' to '/content/models/Llama-3.2-1B-Instruct/.cache/huggingface/download/original/7iVfz3cUOMr-hyjiqqRDHEwVBAM=.82e9d31979e92ab929cd544440f129d9ecd797b69e327f80f17e1c50d5551b55.incomplete'\n",
915
+ "Downloading 'special_tokens_map.json' to '/content/models/Llama-3.2-1B-Instruct/.cache/huggingface/download/ahkChHUJFxEmOdq5GDFEmerRzCY=.02ee80b6196926a5ad790a004d9efd6ab1ba6542.incomplete'\n",
916
+ "\n",
917
+ "\n",
918
+ "\n",
919
+ "generation_config.json: 100% 189/189 [00:00<00:00, 815kB/s]\n",
920
+ "Download complete. Moving file to /content/models/Llama-3.2-1B-Instruct/generation_config.json\n",
921
+ "Downloading 'tokenizer.json' to '/content/models/Llama-3.2-1B-Instruct/.cache/huggingface/download/HgM_lKo9sdSCfRtVg7MMFS7EKqo=.5cc5f00a5b203e90a27a3bd60d1ec393b07971e8.incomplete'\n",
922
+ "\n",
923
+ "\n",
924
+ "\n",
925
+ "tokenizer.model: 0% 0.00/2.18M [00:00<?, ?B/s]\u001b[A\u001b[A\u001b[A\n",
926
+ "\n",
927
+ "\n",
928
+ "\n",
929
+ "params.json: 100% 220/220 [00:00<00:00, 1.16MB/s]\n",
930
+ "Download complete. Moving file to /content/models/Llama-3.2-1B-Instruct/original/params.json\n",
931
+ "\n",
932
+ "\n",
933
+ "\n",
934
+ "\n",
935
+ "special_tokens_map.json: 100% 296/296 [00:00<00:00, 1.19MB/s]\n",
936
+ "Download complete. Moving file to /content/models/Llama-3.2-1B-Instruct/special_tokens_map.json\n",
937
+ "\n",
938
+ "\n",
939
+ "model.safetensors: 0% 10.5M/2.47G [00:00<00:32, 75.6MB/s]\u001b[A\u001b[A\n",
940
+ "\n",
941
+ "\n",
942
+ "\n",
943
+ "tokenizer.json: 0% 0.00/9.09M [00:00<?, ?B/s]\u001b[A\u001b[A\u001b[A\u001b[ADownloading 'tokenizer_config.json' to '/content/models/Llama-3.2-1B-Instruct/.cache/huggingface/download/vzaExXFZNBay89bvlQv-ZcI6BTg=.4ff488a165e900e5129cda7c20ab32d568d2a475.incomplete'\n",
944
+ "\n",
945
+ "\n",
946
+ "\n",
947
+ "\n",
948
+ "\n",
949
+ ".gitattributes: 100% 1.52k/1.52k [00:00<00:00, 6.15MB/s]\n",
950
+ "Download complete. Moving file to /content/models/Llama-3.2-1B-Instruct/.gitattributes\n",
951
+ "Fetching 13 files: 8% 1/13 [00:00<00:04, 2.71it/s]\n",
952
+ "consolidated.00.pth: 0% 10.5M/2.47G [00:00<00:35, 68.8MB/s]\u001b[A\n",
953
+ "\n",
954
+ "\n",
955
+ "tokenizer.model: 100% 2.18M/2.18M [00:00<00:00, 20.8MB/s]\u001b[A\u001b[A\u001b[A\n",
956
+ "\n",
957
+ "\n",
958
+ "\n",
959
+ "\n",
960
+ "tokenizer.model: 100% 2.18M/2.18M [00:00<00:00, 19.9MB/s]\n",
961
+ "Download complete. Moving file to /content/models/Llama-3.2-1B-Instruct/original/tokenizer.model\n",
962
+ "tokenizer_config.json: 100% 54.5k/54.5k [00:00<00:00, 2.05MB/s]\n",
963
+ "Download complete. Moving file to /content/models/Llama-3.2-1B-Instruct/tokenizer_config.json\n",
964
+ "\n",
965
+ "consolidated.00.pth: 1% 21.0M/2.47G [00:00<00:28, 85.3MB/s]\u001b[A\n",
966
+ "\n",
967
+ "model.safetensors: 1% 31.5M/2.47G [00:00<00:22, 109MB/s] \u001b[A\u001b[A\n",
968
+ "\n",
969
+ "model.safetensors: 2% 52.4M/2.47G [00:00<00:17, 136MB/s]\u001b[A\u001b[A\n",
970
+ "consolidated.00.pth: 2% 41.9M/2.47G [00:00<00:23, 104MB/s] \u001b[A\n",
971
+ "\n",
972
+ "\n",
973
+ "\n",
974
+ "tokenizer.json: 100% 9.09M/9.09M [00:00<00:00, 23.2MB/s]\n",
975
+ "Download complete. Moving file to /content/models/Llama-3.2-1B-Instruct/tokenizer.json\n",
976
+ "\n",
977
+ "\n",
978
+ "model.safetensors: 3% 73.4M/2.47G [00:00<00:16, 141MB/s]\u001b[A\u001b[A\n",
979
+ "consolidated.00.pth: 3% 62.9M/2.47G [00:00<00:20, 118MB/s]\u001b[A\n",
980
+ "\n",
981
+ "model.safetensors: 4% 94.4M/2.47G [00:00<00:17, 138MB/s]\u001b[A\u001b[A\n",
982
+ "consolidated.00.pth: 3% 83.9M/2.47G [00:00<00:19, 121MB/s]\u001b[A\n",
983
+ "\n",
984
+ "model.safetensors: 5% 115M/2.47G [00:00<00:18, 125MB/s] \u001b[A\u001b[A\n",
985
+ "consolidated.00.pth: 4% 105M/2.47G [00:00<00:19, 121MB/s] \u001b[A\n",
986
+ "\n",
987
+ "model.safetensors: 6% 136M/2.47G [00:01<00:18, 129MB/s]\u001b[A\u001b[A\n",
988
+ "consolidated.00.pth: 5% 126M/2.47G [00:01<00:17, 133MB/s]\u001b[A\n",
989
+ "consolidated.00.pth: 6% 147M/2.47G [00:01<00:16, 140MB/s]\u001b[A\n",
990
+ "\n",
991
+ "model.safetensors: 6% 157M/2.47G [00:01<00:18, 128MB/s]\u001b[A\u001b[A\n",
992
+ "consolidated.00.pth: 7% 168M/2.47G [00:01<00:17, 129MB/s]\u001b[A\n",
993
+ "\n",
994
+ "model.safetensors: 7% 178M/2.47G [00:01<00:18, 126MB/s]\u001b[A\u001b[A\n",
995
+ "consolidated.00.pth: 8% 189M/2.47G [00:01<00:17, 131MB/s]\u001b[A\n",
996
+ "\n",
997
+ "model.safetensors: 8% 199M/2.47G [00:01<00:18, 120MB/s]\u001b[A\u001b[A\n",
998
+ "consolidated.00.pth: 8% 210M/2.47G [00:01<00:18, 123MB/s]\u001b[A\n",
999
+ "\n",
1000
+ "model.safetensors: 9% 220M/2.47G [00:01<00:19, 116MB/s]\u001b[A\u001b[A\n",
1001
+ "consolidated.00.pth: 9% 231M/2.47G [00:01<00:19, 115MB/s]\u001b[A\n",
1002
+ "\n",
1003
+ "model.safetensors: 10% 241M/2.47G [00:02<00:20, 110MB/s]\u001b[A\u001b[A\n",
1004
+ "consolidated.00.pth: 10% 252M/2.47G [00:02<00:19, 112MB/s]\u001b[A\n",
1005
+ "\n",
1006
+ "model.safetensors: 11% 262M/2.47G [00:02<00:20, 106MB/s]\u001b[A\u001b[A\n",
1007
+ "consolidated.00.pth: 11% 273M/2.47G [00:02<00:19, 112MB/s]\u001b[A\n",
1008
+ "\n",
1009
+ "model.safetensors: 11% 283M/2.47G [00:02<00:20, 109MB/s]\u001b[A\u001b[A\n",
1010
+ "consolidated.00.pth: 12% 294M/2.47G [00:02<00:19, 114MB/s]\u001b[A\n",
1011
+ "\n",
1012
+ "model.safetensors: 12% 304M/2.47G [00:02<00:20, 105MB/s]\u001b[A\u001b[A\n",
1013
+ "consolidated.00.pth: 13% 315M/2.47G [00:02<00:18, 114MB/s]\u001b[A\n",
1014
+ "\n",
1015
+ "model.safetensors: 13% 325M/2.47G [00:02<00:18, 114MB/s]\u001b[A\u001b[A\n",
1016
+ "consolidated.00.pth: 14% 336M/2.47G [00:02<00:18, 114MB/s]\u001b[A\n",
1017
+ "\n",
1018
+ "model.safetensors: 14% 346M/2.47G [00:02<00:19, 111MB/s]\u001b[A\u001b[A\n",
1019
+ "consolidated.00.pth: 14% 357M/2.47G [00:03<00:17, 118MB/s]\u001b[A\n",
1020
+ "\n",
1021
+ "model.safetensors: 15% 367M/2.47G [00:03<00:17, 118MB/s]\u001b[A\u001b[A\n",
1022
+ "consolidated.00.pth: 15% 377M/2.47G [00:03<00:16, 125MB/s]\u001b[A\n",
1023
+ "\n",
1024
+ "model.safetensors: 16% 388M/2.47G [00:03<00:17, 120MB/s]\u001b[A\u001b[A\n",
1025
+ "consolidated.00.pth: 16% 398M/2.47G [00:03<00:17, 120MB/s]\u001b[A\n",
1026
+ "\n",
1027
+ "model.safetensors: 17% 409M/2.47G [00:03<00:18, 112MB/s]\u001b[A\u001b[A\n",
1028
+ "consolidated.00.pth: 17% 419M/2.47G [00:03<00:17, 117MB/s]\u001b[A\n",
1029
+ "\n",
1030
+ "model.safetensors: 17% 430M/2.47G [00:03<00:20, 97.3MB/s]\u001b[A\u001b[A\n",
1031
+ "consolidated.00.pth: 18% 440M/2.47G [00:03<00:19, 106MB/s]\u001b[A\n",
1032
+ "\n",
1033
+ "model.safetensors: 18% 440M/2.47G [00:03<00:21, 96.5MB/s]\u001b[A\u001b[A\n",
1034
+ "\n",
1035
+ "model.safetensors: 18% 451M/2.47G [00:04<00:21, 95.3MB/s]\u001b[A\u001b[A\n",
1036
+ "consolidated.00.pth: 19% 461M/2.47G [00:03<00:19, 106MB/s]\u001b[A\n",
1037
+ "\n",
1038
+ "model.safetensors: 19% 461M/2.47G [00:04<00:20, 96.6MB/s]\u001b[A\u001b[A\n",
1039
+ "consolidated.00.pth: 20% 482M/2.47G [00:04<00:18, 108MB/s]\u001b[A\n",
1040
+ "\n",
1041
+ "model.safetensors: 20% 482M/2.47G [00:04<00:19, 104MB/s] \u001b[A\u001b[A\n",
1042
+ "consolidated.00.pth: 20% 503M/2.47G [00:04<00:17, 114MB/s]\u001b[A\n",
1043
+ "\n",
1044
+ "model.safetensors: 20% 493M/2.47G [00:04<00:20, 97.5MB/s]\u001b[A\u001b[A\n",
1045
+ "\n",
1046
+ "model.safetensors: 20% 503M/2.47G [00:04<00:21, 91.8MB/s]\u001b[A\u001b[A\n",
1047
+ "consolidated.00.pth: 21% 524M/2.47G [00:04<00:17, 109MB/s]\u001b[A\n",
1048
+ "\n",
1049
+ "model.safetensors: 21% 524M/2.47G [00:04<00:19, 99.6MB/s]\u001b[A\u001b[A\n",
1050
+ "consolidated.00.pth: 22% 545M/2.47G [00:04<00:17, 112MB/s]\u001b[A\n",
1051
+ "\n",
1052
+ "model.safetensors: 22% 535M/2.47G [00:04<00:20, 94.0MB/s]\u001b[A\u001b[A\n",
1053
+ "consolidated.00.pth: 23% 566M/2.47G [00:04<00:18, 104MB/s]\u001b[A\n",
1054
+ "\n",
1055
+ "model.safetensors: 22% 545M/2.47G [00:04<00:20, 92.9MB/s]\u001b[A\u001b[A\n",
1056
+ "\n",
1057
+ "model.safetensors: 23% 566M/2.47G [00:05<00:19, 97.5MB/s]\u001b[A\u001b[A\n",
1058
+ "consolidated.00.pth: 24% 587M/2.47G [00:05<00:18, 102MB/s]\u001b[A\n",
1059
+ "consolidated.00.pth: 25% 608M/2.47G [00:05<00:18, 102MB/s]\u001b[A\n",
1060
+ "\n",
1061
+ "model.safetensors: 24% 587M/2.47G [00:05<00:19, 95.5MB/s]\u001b[A\u001b[A\n",
1062
+ "\n",
1063
+ "model.safetensors: 25% 608M/2.47G [00:05<00:17, 105MB/s] \u001b[A\u001b[A\n",
1064
+ "consolidated.00.pth: 25% 629M/2.47G [00:05<00:17, 104MB/s]\u001b[A\n",
1065
+ "consolidated.00.pth: 26% 650M/2.47G [00:05<00:15, 120MB/s]\u001b[A\n",
1066
+ "\n",
1067
+ "model.safetensors: 25% 629M/2.47G [00:05<00:15, 117MB/s]\u001b[A\u001b[A\n",
1068
+ "consolidated.00.pth: 27% 671M/2.47G [00:05<00:13, 134MB/s]\u001b[A\n",
1069
+ "\n",
1070
+ "model.safetensors: 26% 650M/2.47G [00:05<00:14, 122MB/s]\u001b[A\u001b[A\n",
1071
+ "consolidated.00.pth: 28% 692M/2.47G [00:05<00:13, 134MB/s]\u001b[A\n",
1072
+ "\n",
1073
+ "model.safetensors: 27% 671M/2.47G [00:06<00:15, 119MB/s]\u001b[A\u001b[A\n",
1074
+ "consolidated.00.pth: 29% 713M/2.47G [00:06<00:13, 132MB/s]\u001b[A\n",
1075
+ "\n",
1076
+ "model.safetensors: 28% 692M/2.47G [00:06<00:15, 115MB/s]\u001b[A\u001b[A\n",
1077
+ "consolidated.00.pth: 30% 734M/2.47G [00:06<00:13, 126MB/s]\u001b[A\n",
1078
+ "\n",
1079
+ "model.safetensors: 29% 713M/2.47G [00:06<00:15, 114MB/s]\u001b[A\u001b[A\n",
1080
+ "consolidated.00.pth: 31% 755M/2.47G [00:09<01:23, 20.5MB/s]\u001b[A\n",
1081
+ "\n",
1082
+ "model.safetensors: 30% 734M/2.47G [00:09<01:25, 20.4MB/s]\u001b[A\u001b[A\n",
1083
+ "consolidated.00.pth: 31% 776M/2.47G [00:09<01:01, 27.6MB/s]\u001b[A\n",
1084
+ "\n",
1085
+ "model.safetensors: 31% 755M/2.47G [00:09<01:04, 26.7MB/s]\u001b[A\u001b[A\n",
1086
+ "consolidated.00.pth: 32% 797M/2.47G [00:09<00:47, 35.1MB/s]\u001b[A\n",
1087
+ "\n",
1088
+ "model.safetensors: 31% 776M/2.47G [00:09<00:48, 34.8MB/s]\u001b[A\u001b[A\n",
1089
+ "consolidated.00.pth: 33% 818M/2.47G [00:09<00:37, 44.7MB/s]\u001b[A\n",
1090
+ "\n",
1091
+ "model.safetensors: 32% 797M/2.47G [00:09<00:37, 44.1MB/s]\u001b[A\u001b[A\n",
1092
+ "consolidated.00.pth: 34% 839M/2.47G [00:10<00:29, 55.0MB/s]\u001b[A\n",
1093
+ "\n",
1094
+ "model.safetensors: 33% 807M/2.47G [00:10<00:34, 48.3MB/s]\u001b[A\u001b[A\n",
1095
+ "consolidated.00.pth: 35% 860M/2.47G [00:10<00:24, 66.8MB/s]\u001b[A\n",
1096
+ "\n",
1097
+ "model.safetensors: 34% 828M/2.47G [00:10<00:26, 62.1MB/s]\u001b[A\u001b[A\n",
1098
+ "consolidated.00.pth: 36% 881M/2.47G [00:10<00:19, 80.0MB/s]\u001b[A\n",
1099
+ "\n",
1100
+ "model.safetensors: 34% 849M/2.47G [00:10<00:22, 72.8MB/s]\u001b[A\u001b[A\n",
1101
+ "consolidated.00.pth: 36% 902M/2.47G [00:10<00:16, 94.8MB/s]\u001b[A\n",
1102
+ "\n",
1103
+ "model.safetensors: 35% 870M/2.47G [00:10<00:18, 85.3MB/s]\u001b[A\u001b[A\n",
1104
+ "consolidated.00.pth: 37% 923M/2.47G [00:10<00:14, 106MB/s] \u001b[A\n",
1105
+ "\n",
1106
+ "model.safetensors: 36% 891M/2.47G [00:10<00:16, 95.3MB/s]\u001b[A\u001b[A\n",
1107
+ "consolidated.00.pth: 38% 944M/2.47G [00:10<00:15, 101MB/s]\u001b[A\n",
1108
+ "\n",
1109
+ "model.safetensors: 37% 912M/2.47G [00:10<00:15, 104MB/s] \u001b[A\u001b[A\n",
1110
+ "consolidated.00.pth: 39% 965M/2.47G [00:10<00:13, 109MB/s]\u001b[A\n",
1111
+ "\n",
1112
+ "model.safetensors: 38% 933M/2.47G [00:11<00:14, 109MB/s]\u001b[A\u001b[A\n",
1113
+ "consolidated.00.pth: 40% 986M/2.47G [00:11<00:12, 115MB/s]\u001b[A\n",
1114
+ "\n",
1115
+ "model.safetensors: 39% 954M/2.47G [00:11<00:13, 112MB/s]\u001b[A\u001b[A\n",
1116
+ "consolidated.00.pth: 41% 1.01G/2.47G [00:11<00:11, 123MB/s]\u001b[A\n",
1117
+ "\n",
1118
+ "model.safetensors: 39% 975M/2.47G [00:11<00:13, 109MB/s]\u001b[A\u001b[A\n",
1119
+ "consolidated.00.pth: 42% 1.03G/2.47G [00:11<00:13, 108MB/s]\u001b[A\n",
1120
+ "\n",
1121
+ "model.safetensors: 40% 996M/2.47G [00:11<00:12, 117MB/s]\u001b[A\u001b[A\n",
1122
+ "\n",
1123
+ "model.safetensors: 41% 1.02G/2.47G [00:11<00:11, 125MB/s]\u001b[A\u001b[A\n",
1124
+ "consolidated.00.pth: 42% 1.05G/2.47G [00:11<00:14, 101MB/s]\u001b[A\n",
1125
+ "\n",
1126
+ "model.safetensors: 42% 1.04G/2.47G [00:11<00:11, 124MB/s]\u001b[A\u001b[A\n",
1127
+ "consolidated.00.pth: 43% 1.07G/2.47G [00:11<00:12, 111MB/s]\u001b[A\n",
1128
+ "consolidated.00.pth: 44% 1.09G/2.47G [00:12<00:11, 125MB/s]\u001b[A\n",
1129
+ "\n",
1130
+ "model.safetensors: 43% 1.06G/2.47G [00:12<00:11, 120MB/s]\u001b[A\u001b[A\n",
1131
+ "\n",
1132
+ "model.safetensors: 44% 1.08G/2.47G [00:12<00:12, 116MB/s]\u001b[A\u001b[A\n",
1133
+ "consolidated.00.pth: 45% 1.11G/2.47G [00:12<00:14, 95.5MB/s]\u001b[A\n",
1134
+ "\n",
1135
+ "model.safetensors: 45% 1.10G/2.47G [00:12<00:10, 125MB/s]\u001b[A\u001b[A\n",
1136
+ "consolidated.00.pth: 46% 1.13G/2.47G [00:12<00:13, 100MB/s] \u001b[A\n",
1137
+ "\n",
1138
+ "model.safetensors: 45% 1.12G/2.47G [00:12<00:11, 122MB/s]\u001b[A\u001b[A\n",
1139
+ "consolidated.00.pth: 47% 1.15G/2.47G [00:12<00:11, 115MB/s]\u001b[A\n",
1140
+ "\n",
1141
+ "model.safetensors: 46% 1.14G/2.47G [00:12<00:10, 121MB/s]\u001b[A\u001b[A\n",
1142
+ "consolidated.00.pth: 48% 1.17G/2.47G [00:12<00:10, 128MB/s]\u001b[A\n",
1143
+ "consolidated.00.pth: 48% 1.20G/2.47G [00:12<00:09, 128MB/s]\u001b[A\n",
1144
+ "\n",
1145
+ "model.safetensors: 47% 1.16G/2.47G [00:13<00:11, 114MB/s]\u001b[A\u001b[A\n",
1146
+ "consolidated.00.pth: 49% 1.22G/2.47G [00:13<00:09, 131MB/s]\u001b[A\n",
1147
+ "\n",
1148
+ "model.safetensors: 48% 1.18G/2.47G [00:13<00:11, 117MB/s]\u001b[A\u001b[A\n",
1149
+ "consolidated.00.pth: 50% 1.24G/2.47G [00:13<00:09, 131MB/s]\u001b[A\n",
1150
+ "\n",
1151
+ "model.safetensors: 49% 1.21G/2.47G [00:13<00:10, 119MB/s]\u001b[A\u001b[A\n",
1152
+ "consolidated.00.pth: 51% 1.26G/2.47G [00:13<00:09, 134MB/s]\u001b[A\n",
1153
+ "\n",
1154
+ "model.safetensors: 50% 1.23G/2.47G [00:13<00:10, 120MB/s]\u001b[A\u001b[A\n",
1155
+ "consolidated.00.pth: 52% 1.28G/2.47G [00:13<00:09, 129MB/s]\u001b[A\n",
1156
+ "\n",
1157
+ "model.safetensors: 50% 1.25G/2.47G [00:13<00:10, 116MB/s]\u001b[A\u001b[A\n",
1158
+ "consolidated.00.pth: 53% 1.30G/2.47G [00:13<00:08, 132MB/s]\u001b[A\n",
1159
+ "\n",
1160
+ "model.safetensors: 51% 1.27G/2.47G [00:13<00:10, 115MB/s]\u001b[A\u001b[A\n",
1161
+ "consolidated.00.pth: 53% 1.32G/2.47G [00:13<00:08, 135MB/s]\u001b[A\n",
1162
+ "consolidated.00.pth: 54% 1.34G/2.47G [00:14<00:08, 135MB/s]\u001b[A\n",
1163
+ "\n",
1164
+ "model.safetensors: 52% 1.29G/2.47G [00:14<00:10, 115MB/s]\u001b[A\u001b[A\n",
1165
+ "consolidated.00.pth: 55% 1.36G/2.47G [00:14<00:08, 125MB/s]\u001b[A\n",
1166
+ "\n",
1167
+ "model.safetensors: 53% 1.31G/2.47G [00:14<00:10, 110MB/s]\u001b[A\u001b[A\n",
1168
+ "consolidated.00.pth: 56% 1.38G/2.47G [00:14<00:08, 128MB/s]\u001b[A\n",
1169
+ "\n",
1170
+ "model.safetensors: 54% 1.33G/2.47G [00:14<00:10, 111MB/s]\u001b[A\u001b[A\n",
1171
+ "consolidated.00.pth: 57% 1.41G/2.47G [00:14<00:08, 133MB/s]\u001b[A\n",
1172
+ "\n",
1173
+ "model.safetensors: 55% 1.35G/2.47G [00:14<00:09, 114MB/s]\u001b[A\u001b[A\n",
1174
+ "consolidated.00.pth: 58% 1.43G/2.47G [00:14<00:08, 125MB/s]\u001b[A\n",
1175
+ "\n",
1176
+ "model.safetensors: 56% 1.37G/2.47G [00:14<00:09, 111MB/s]\u001b[A\u001b[A\n",
1177
+ "consolidated.00.pth: 59% 1.45G/2.47G [00:14<00:08, 121MB/s]\u001b[A\n",
1178
+ "\n",
1179
+ "model.safetensors: 56% 1.39G/2.47G [00:15<00:09, 112MB/s]\u001b[A\u001b[A\n",
1180
+ "consolidated.00.pth: 59% 1.47G/2.47G [00:15<00:07, 126MB/s]\u001b[A\n",
1181
+ "\n",
1182
+ "model.safetensors: 57% 1.42G/2.47G [00:15<00:09, 116MB/s]\u001b[A\u001b[A\n",
1183
+ "consolidated.00.pth: 60% 1.49G/2.47G [00:15<00:07, 127MB/s]\u001b[A\n",
1184
+ "\n",
1185
+ "model.safetensors: 58% 1.44G/2.47G [00:15<00:08, 121MB/s]\u001b[A\u001b[A\n",
1186
+ "consolidated.00.pth: 61% 1.51G/2.47G [00:15<00:07, 125MB/s]\u001b[A\n",
1187
+ "\n",
1188
+ "model.safetensors: 59% 1.46G/2.47G [00:15<00:08, 121MB/s]\u001b[A\u001b[A\n",
1189
+ "consolidated.00.pth: 62% 1.53G/2.47G [00:15<00:08, 116MB/s]\u001b[A\n",
1190
+ "\n",
1191
+ "model.safetensors: 60% 1.48G/2.47G [00:15<00:09, 105MB/s]\u001b[A\u001b[A\n",
1192
+ "consolidated.00.pth: 63% 1.55G/2.47G [00:15<00:08, 112MB/s]\u001b[A\n",
1193
+ "\n",
1194
+ "model.safetensors: 61% 1.50G/2.47G [00:15<00:09, 106MB/s]\u001b[A\u001b[A\n",
1195
+ "consolidated.00.pth: 64% 1.57G/2.47G [00:16<00:07, 115MB/s]\u001b[A\n",
1196
+ "\n",
1197
+ "model.safetensors: 62% 1.52G/2.47G [00:16<00:10, 94.6MB/s]\u001b[A\u001b[A\n",
1198
+ "consolidated.00.pth: 64% 1.59G/2.47G [00:16<00:08, 103MB/s]\u001b[A\n",
1199
+ "\n",
1200
+ "model.safetensors: 62% 1.53G/2.47G [00:16<00:09, 95.2MB/s]\u001b[A\u001b[A\n",
1201
+ "consolidated.00.pth: 65% 1.61G/2.47G [00:16<00:07, 110MB/s]\u001b[A\n",
1202
+ "\n",
1203
+ "model.safetensors: 62% 1.54G/2.47G [00:16<00:09, 94.0MB/s]\u001b[A\u001b[A\n",
1204
+ "consolidated.00.pth: 66% 1.64G/2.47G [00:16<00:07, 108MB/s]\u001b[A\n",
1205
+ "\n",
1206
+ "model.safetensors: 63% 1.56G/2.47G [00:16<00:09, 99.4MB/s]\u001b[A\u001b[A\n",
1207
+ "consolidated.00.pth: 67% 1.66G/2.47G [00:16<00:07, 110MB/s]\u001b[A\n",
1208
+ "\n",
1209
+ "model.safetensors: 64% 1.58G/2.47G [00:16<00:08, 105MB/s] \u001b[A\u001b[A\n",
1210
+ "consolidated.00.pth: 68% 1.68G/2.47G [00:17<00:07, 109MB/s]\u001b[A\n",
1211
+ "\n",
1212
+ "model.safetensors: 65% 1.60G/2.47G [00:17<00:08, 101MB/s]\u001b[A\u001b[A\n",
1213
+ "\n",
1214
+ "model.safetensors: 65% 1.61G/2.47G [00:17<00:08, 100MB/s]\u001b[A\u001b[A\n",
1215
+ "consolidated.00.pth: 69% 1.70G/2.47G [00:17<00:07, 103MB/s]\u001b[A\n",
1216
+ "\n",
1217
+ "model.safetensors: 66% 1.63G/2.47G [00:17<00:09, 90.6MB/s]\u001b[A\u001b[A\n",
1218
+ "consolidated.00.pth: 69% 1.71G/2.47G [00:17<00:07, 96.6MB/s]\u001b[A\n",
1219
+ "\n",
1220
+ "model.safetensors: 66% 1.64G/2.47G [00:17<00:09, 89.0MB/s]\u001b[A\u001b[A\n",
1221
+ "consolidated.00.pth: 70% 1.73G/2.47G [00:17<00:07, 104MB/s] \u001b[A\n",
1222
+ "\n",
1223
+ "model.safetensors: 67% 1.66G/2.47G [00:17<00:09, 90.3MB/s]\u001b[A\u001b[A\n",
1224
+ "consolidated.00.pth: 70% 1.74G/2.47G [00:17<00:07, 96.6MB/s]\u001b[A\n",
1225
+ "\n",
1226
+ "model.safetensors: 68% 1.68G/2.47G [00:17<00:08, 95.6MB/s]\u001b[A\u001b[A\n",
1227
+ "consolidated.00.pth: 71% 1.76G/2.47G [00:17<00:07, 99.4MB/s]\u001b[A\n",
1228
+ "consolidated.00.pth: 72% 1.78G/2.47G [00:18<00:06, 108MB/s] \u001b[A\n",
1229
+ "\n",
1230
+ "model.safetensors: 69% 1.70G/2.47G [00:18<00:07, 101MB/s] \u001b[A\u001b[A\n",
1231
+ "\n",
1232
+ "model.safetensors: 70% 1.72G/2.47G [00:18<00:07, 98.2MB/s]\u001b[A\u001b[A\n",
1233
+ "consolidated.00.pth: 73% 1.80G/2.47G [00:18<00:06, 98.8MB/s]\u001b[A\n",
1234
+ "\n",
1235
+ "model.safetensors: 70% 1.73G/2.47G [00:18<00:07, 94.3MB/s]\u001b[A\u001b[A\n",
1236
+ "consolidated.00.pth: 73% 1.81G/2.47G [00:18<00:06, 94.8MB/s]\u001b[A\n",
1237
+ "\n",
1238
+ "model.safetensors: 70% 1.74G/2.47G [00:18<00:08, 90.5MB/s]\u001b[A\u001b[A\n",
1239
+ "consolidated.00.pth: 74% 1.82G/2.47G [00:18<00:07, 92.3MB/s]\u001b[A\n",
1240
+ "\n",
1241
+ "model.safetensors: 71% 1.75G/2.47G [00:18<00:07, 91.9MB/s]\u001b[A\u001b[A\n",
1242
+ "consolidated.00.pth: 74% 1.84G/2.47G [00:18<00:06, 92.8MB/s]\u001b[A\n",
1243
+ "\n",
1244
+ "model.safetensors: 71% 1.76G/2.47G [00:18<00:07, 91.6MB/s]\u001b[A\u001b[A\n",
1245
+ "consolidated.00.pth: 75% 1.85G/2.47G [00:18<00:06, 93.0MB/s]\u001b[A\n",
1246
+ "\n",
1247
+ "model.safetensors: 72% 1.77G/2.47G [00:18<00:07, 94.0MB/s]\u001b[A\u001b[A\n",
1248
+ "consolidated.00.pth: 76% 1.87G/2.47G [00:18<00:05, 102MB/s] \u001b[A\n",
1249
+ "consolidated.00.pth: 76% 1.88G/2.47G [00:19<00:05, 103MB/s]\u001b[A\n",
1250
+ "\n",
1251
+ "model.safetensors: 73% 1.79G/2.47G [00:19<00:06, 101MB/s] \u001b[A\u001b[A\n",
1252
+ "consolidated.00.pth: 76% 1.89G/2.47G [00:19<00:05, 102MB/s]\u001b[A\n",
1253
+ "consolidated.00.pth: 77% 1.91G/2.47G [00:19<00:04, 113MB/s]\u001b[A\n",
1254
+ "\n",
1255
+ "model.safetensors: 73% 1.80G/2.47G [00:19<00:09, 68.1MB/s]\u001b[A\u001b[A\n",
1256
+ "consolidated.00.pth: 78% 1.93G/2.47G [00:19<00:04, 110MB/s]\u001b[A\n",
1257
+ "\n",
1258
+ "model.safetensors: 74% 1.82G/2.47G [00:19<00:07, 83.5MB/s]\u001b[A\u001b[A\n",
1259
+ "\n",
1260
+ "model.safetensors: 74% 1.84G/2.47G [00:19<00:07, 85.5MB/s]\u001b[A\u001b[A\n",
1261
+ "consolidated.00.pth: 79% 1.95G/2.47G [00:19<00:04, 110MB/s]\u001b[A\n",
1262
+ "\n",
1263
+ "model.safetensors: 75% 1.85G/2.47G [00:19<00:07, 87.6MB/s]\u001b[A\u001b[A\n",
1264
+ "consolidated.00.pth: 80% 1.97G/2.47G [00:19<00:04, 107MB/s]\u001b[A\n",
1265
+ "\n",
1266
+ "model.safetensors: 76% 1.87G/2.47G [00:20<00:07, 81.3MB/s]\u001b[A\u001b[A\n",
1267
+ "\n",
1268
+ "model.safetensors: 76% 1.88G/2.47G [00:20<00:06, 85.5MB/s]\u001b[A\u001b[A\n",
1269
+ "consolidated.00.pth: 81% 1.99G/2.47G [00:20<00:04, 96.4MB/s]\u001b[A\n",
1270
+ "\n",
1271
+ "model.safetensors: 77% 1.90G/2.47G [00:20<00:05, 97.9MB/s]\u001b[A\u001b[A\n",
1272
+ "consolidated.00.pth: 81% 2.01G/2.47G [00:20<00:04, 105MB/s] \u001b[A\n",
1273
+ "\n",
1274
+ "model.safetensors: 77% 1.91G/2.47G [00:20<00:05, 95.5MB/s]\u001b[A\u001b[A\n",
1275
+ "consolidated.00.pth: 82% 2.03G/2.47G [00:20<00:04, 93.2MB/s]\u001b[A\n",
1276
+ "consolidated.00.pth: 83% 2.04G/2.47G [00:20<00:04, 88.8MB/s]\u001b[A\n",
1277
+ "\n",
1278
+ "model.safetensors: 78% 1.93G/2.47G [00:20<00:07, 76.0MB/s]\u001b[A\u001b[A\n",
1279
+ "\n",
1280
+ "model.safetensors: 78% 1.94G/2.47G [00:21<00:07, 71.9MB/s]\u001b[A\u001b[A\n",
1281
+ "consolidated.00.pth: 84% 2.07G/2.47G [00:21<00:04, 86.9MB/s]\u001b[A\n",
1282
+ "\n",
1283
+ "model.safetensors: 79% 1.95G/2.47G [00:21<00:07, 71.5MB/s]\u001b[A\u001b[A\n",
1284
+ "consolidated.00.pth: 84% 2.08G/2.47G [00:21<00:04, 84.1MB/s]\u001b[A\n",
1285
+ "consolidated.00.pth: 84% 2.09G/2.47G [00:21<00:04, 85.4MB/s]\u001b[A\n",
1286
+ "\n",
1287
+ "model.safetensors: 79% 1.96G/2.47G [00:21<00:07, 72.0MB/s]\u001b[A\u001b[A\n",
1288
+ "\n",
1289
+ "model.safetensors: 80% 1.97G/2.47G [00:21<00:06, 77.2MB/s]\u001b[A\u001b[A\n",
1290
+ "consolidated.00.pth: 85% 2.10G/2.47G [00:21<00:04, 84.8MB/s]\u001b[A\n",
1291
+ "\n",
1292
+ "model.safetensors: 80% 1.98G/2.47G [00:21<00:06, 78.6MB/s]\u001b[A\u001b[A\n",
1293
+ "consolidated.00.pth: 85% 2.11G/2.47G [00:21<00:04, 83.0MB/s]\u001b[A\n",
1294
+ "\n",
1295
+ "model.safetensors: 81% 1.99G/2.47G [00:21<00:06, 73.0MB/s]\u001b[A\u001b[A\n",
1296
+ "consolidated.00.pth: 86% 2.12G/2.47G [00:21<00:04, 71.8MB/s]\u001b[A\n",
1297
+ "\n",
1298
+ "model.safetensors: 81% 2.00G/2.47G [00:21<00:06, 77.5MB/s]\u001b[A\u001b[A\n",
1299
+ "consolidated.00.pth: 86% 2.13G/2.47G [00:21<00:04, 78.3MB/s]\u001b[A\n",
1300
+ "\n",
1301
+ "model.safetensors: 81% 2.01G/2.47G [00:21<00:05, 82.3MB/s]\u001b[A\u001b[A\n",
1302
+ "consolidated.00.pth: 87% 2.14G/2.47G [00:21<00:04, 75.1MB/s]\u001b[A\n",
1303
+ "\n",
1304
+ "model.safetensors: 82% 2.02G/2.47G [00:22<00:05, 84.3MB/s]\u001b[A\u001b[A\n",
1305
+ "consolidated.00.pth: 87% 2.15G/2.47G [00:22<00:04, 76.9MB/s]\u001b[A\n",
1306
+ "\n",
1307
+ "model.safetensors: 82% 2.03G/2.47G [00:22<00:05, 86.6MB/s]\u001b[A\u001b[A\n",
1308
+ "\n",
1309
+ "model.safetensors: 83% 2.06G/2.47G [00:22<00:04, 101MB/s] \u001b[A\u001b[A\n",
1310
+ "consolidated.00.pth: 88% 2.17G/2.47G [00:22<00:03, 87.7MB/s]\u001b[A\n",
1311
+ "consolidated.00.pth: 88% 2.18G/2.47G [00:23<00:08, 36.2MB/s]\u001b[A\n",
1312
+ "\n",
1313
+ "model.safetensors: 84% 2.07G/2.47G [00:23<00:11, 36.7MB/s]\u001b[A\u001b[A\n",
1314
+ "consolidated.00.pth: 89% 2.20G/2.47G [00:23<00:05, 51.8MB/s]\u001b[A\n",
1315
+ "\n",
1316
+ "model.safetensors: 84% 2.09G/2.47G [00:23<00:07, 52.8MB/s]\u001b[A\u001b[A\n",
1317
+ "\n",
1318
+ "model.safetensors: 85% 2.10G/2.47G [00:23<00:06, 59.4MB/s]\u001b[A\u001b[A\n",
1319
+ "consolidated.00.pth: 90% 2.22G/2.47G [00:23<00:03, 62.3MB/s]\u001b[A\n",
1320
+ "\n",
1321
+ "model.safetensors: 86% 2.12G/2.47G [00:23<00:04, 77.6MB/s]\u001b[A\u001b[A\n",
1322
+ "\n",
1323
+ "model.safetensors: 87% 2.14G/2.47G [00:23<00:03, 96.8MB/s]\u001b[A\u001b[A\n",
1324
+ "consolidated.00.pth: 91% 2.24G/2.47G [00:23<00:03, 68.8MB/s]\u001b[A\n",
1325
+ "consolidated.00.pth: 91% 2.25G/2.47G [00:24<00:04, 52.9MB/s]\u001b[A\n",
1326
+ "\n",
1327
+ "model.safetensors: 87% 2.16G/2.47G [00:24<00:04, 62.8MB/s]\u001b[A\u001b[A\n",
1328
+ "consolidated.00.pth: 92% 2.26G/2.47G [00:24<00:03, 57.8MB/s]\u001b[A\n",
1329
+ "\n",
1330
+ "model.safetensors: 88% 2.17G/2.47G [00:24<00:04, 66.6MB/s]\u001b[A\u001b[A\n",
1331
+ "consolidated.00.pth: 92% 2.29G/2.47G [00:24<00:02, 76.0MB/s]\u001b[A\n",
1332
+ "\n",
1333
+ "model.safetensors: 88% 2.18G/2.47G [00:24<00:04, 72.0MB/s]\u001b[A\u001b[A\n",
1334
+ "consolidated.00.pth: 93% 2.31G/2.47G [00:24<00:01, 96.9MB/s]\u001b[A\n",
1335
+ "\n",
1336
+ "model.safetensors: 89% 2.19G/2.47G [00:24<00:03, 75.5MB/s]\u001b[A\u001b[A\n",
1337
+ "consolidated.00.pth: 94% 2.33G/2.47G [00:24<00:01, 107MB/s] \u001b[A\n",
1338
+ "\n",
1339
+ "model.safetensors: 89% 2.20G/2.47G [00:24<00:03, 78.1MB/s]\u001b[A\u001b[A\n",
1340
+ "\n",
1341
+ "model.safetensors: 90% 2.21G/2.47G [00:24<00:03, 83.3MB/s]\u001b[A\u001b[A\n",
1342
+ "consolidated.00.pth: 95% 2.35G/2.47G [00:24<00:01, 109MB/s]\u001b[A\n",
1343
+ "\n",
1344
+ "model.safetensors: 90% 2.22G/2.47G [00:24<00:02, 88.1MB/s]\u001b[A\u001b[A\n",
1345
+ "consolidated.00.pth: 96% 2.37G/2.47G [00:24<00:00, 116MB/s]\u001b[A\n",
1346
+ "\n",
1347
+ "model.safetensors: 91% 2.24G/2.47G [00:25<00:02, 96.7MB/s]\u001b[A\u001b[A\n",
1348
+ "consolidated.00.pth: 97% 2.39G/2.47G [00:25<00:00, 113MB/s]\u001b[A\n",
1349
+ "\n",
1350
+ "model.safetensors: 92% 2.26G/2.47G [00:25<00:02, 97.7MB/s]\u001b[A\u001b[A\n",
1351
+ "\n",
1352
+ "model.safetensors: 92% 2.29G/2.47G [00:25<00:01, 114MB/s] \u001b[A\u001b[A\n",
1353
+ "\n",
1354
+ "model.safetensors: 93% 2.31G/2.47G [00:25<00:01, 128MB/s]\u001b[A\u001b[A\n",
1355
+ "consolidated.00.pth: 98% 2.41G/2.47G [00:25<00:00, 86.6MB/s]\u001b[A\n",
1356
+ "consolidated.00.pth: 98% 2.43G/2.47G [00:25<00:00, 104MB/s] \u001b[A\n",
1357
+ "\n",
1358
+ "model.safetensors: 94% 2.33G/2.47G [00:25<00:01, 132MB/s]\u001b[A\u001b[A\n",
1359
+ "consolidated.00.pth: 99% 2.45G/2.47G [00:25<00:00, 114MB/s]\u001b[A\n",
1360
+ "\n",
1361
+ "model.safetensors: 95% 2.35G/2.47G [00:25<00:00, 129MB/s]\u001b[A\u001b[A\n",
1362
+ "consolidated.00.pth: 100% 2.47G/2.47G [00:25<00:00, 95.2MB/s]\n",
1363
+ "Download complete. Moving file to /content/models/Llama-3.2-1B-Instruct/original/consolidated.00.pth\n",
1364
+ "\n",
1365
+ "\n",
1366
+ "model.safetensors: 96% 2.37G/2.47G [00:26<00:00, 130MB/s]\u001b[A\u001b[A\n",
1367
+ "\n",
1368
+ "model.safetensors: 97% 2.39G/2.47G [00:26<00:00, 138MB/s]\u001b[A\u001b[A\n",
1369
+ "\n",
1370
+ "model.safetensors: 98% 2.41G/2.47G [00:27<00:01, 45.3MB/s]\u001b[A\u001b[A\n",
1371
+ "\n",
1372
+ "model.safetensors: 98% 2.42G/2.47G [00:30<00:03, 13.7MB/s]\u001b[A\u001b[A\n",
1373
+ "\n",
1374
+ "model.safetensors: 98% 2.43G/2.47G [00:30<00:02, 16.2MB/s]\u001b[A\u001b[A\n",
1375
+ "\n",
1376
+ "model.safetensors: 99% 2.44G/2.47G [00:30<00:01, 19.0MB/s]\u001b[A\u001b[A\n",
1377
+ "\n",
1378
+ "model.safetensors: 99% 2.45G/2.47G [00:31<00:00, 23.0MB/s]\u001b[A\u001b[A\n",
1379
+ "\n",
1380
+ "model.safetensors: 100% 2.46G/2.47G [00:31<00:00, 27.4MB/s]\u001b[A\u001b[A\n",
1381
+ "\n",
1382
+ "model.safetensors: 100% 2.47G/2.47G [00:31<00:00, 78.6MB/s]\n",
1383
+ "Download complete. Moving file to /content/models/Llama-3.2-1B-Instruct/model.safetensors\n",
1384
+ "Fetching 13 files: 100% 13/13 [00:31<00:00, 2.43s/it]\n",
1385
+ "/content/models/Llama-3.2-1B-Instruct\n"
1386
+ ]
1387
+ }
1388
+ ]
1389
+ },
1390
+ {
1391
+ "cell_type": "markdown",
1392
+ "source": [
1393
+ "**Step 3: Export to ExecuTorch**"
1394
+ ],
1395
+ "metadata": {
1396
+ "id": "XLsl5STwEyEh"
1397
+ }
1398
+ },
1399
+ {
1400
+ "cell_type": "code",
1401
+ "source": [
1402
+ "!cd /content/; python -m executorch.examples.models.llama.export_llama \\\n",
1403
+ " --model \"llama3_2\" \\\n",
1404
+ " --checkpoint /content/models/Llama-3.2-1B-Instruct/original/consolidated.00.pth \\\n",
1405
+ " --params /content/models/Llama-3.2-1B-Instruct/original/params.json \\\n",
1406
+ " -kv \\\n",
1407
+ " --use_sdpa_with_kv_cache \\\n",
1408
+ " -X \\\n",
1409
+ " -d bf16 \\\n",
1410
+ " --metadata '{\"get_bos_id\":128000, \"get_eos_ids\":[128009, 128001]}' \\\n",
1411
+ " --output_name=\"Llama-3.2-1B-Instruct.pte\""
1412
+ ],
1413
+ "metadata": {
1414
+ "colab": {
1415
+ "base_uri": "https://localhost:8080/"
1416
+ },
1417
+ "id": "gXLuFtVVEZov",
1418
+ "outputId": "6cabee23-6bc5-4aaa-f396-d7520e623757"
1419
+ },
1420
+ "execution_count": 10,
1421
+ "outputs": [
1422
+ {
1423
+ "output_type": "stream",
1424
+ "name": "stdout",
1425
+ "text": [
1426
+ "[INFO 2025-04-10 15:15:57,966 utils.py:162] NumExpr defaulting to 2 threads.\n",
1427
+ "[INFO 2025-04-10 15:15:59,519 export_llama_lib.py:684] Applying quantizers: []\n",
1428
+ "[INFO 2025-04-10 15:15:59,805 export_llama_lib.py:649] Checkpoint dtype: torch.bfloat16\n",
1429
+ "[INFO 2025-04-10 15:15:59,806 quantized_kv_cache.py:277] Replacing KVCache with CustomKVCache. This modifies the model in place.\n",
1430
+ "[INFO 2025-04-10 15:15:59,847 custom_ops.py:34] Looking for libcustom_ops_aot_lib.so in /usr/local/lib/python3.11/dist-packages/executorch/extension/llm/custom_ops\n",
1431
+ "[INFO 2025-04-10 15:15:59,855 custom_ops.py:39] Loading custom ops library: /usr/local/lib/python3.11/dist-packages/executorch/extension/llm/custom_ops/libcustom_ops_aot_lib.so\n",
1432
+ "[INFO 2025-04-10 15:15:59,875 builder.py:173] Model after source transforms: Transformer(\n",
1433
+ " (tok_embeddings): Embedding(128256, 2048)\n",
1434
+ " (rope): Rope(\n",
1435
+ " (apply_rotary_emb): RotaryEmbedding()\n",
1436
+ " )\n",
1437
+ " (layers): ModuleList(\n",
1438
+ " (0-15): 16 x TransformerBlock(\n",
1439
+ " (attention): AttentionMHA(\n",
1440
+ " (wq): Linear(in_features=2048, out_features=2048, bias=False)\n",
1441
+ " (wk): Linear(in_features=2048, out_features=512, bias=False)\n",
1442
+ " (wv): Linear(in_features=2048, out_features=512, bias=False)\n",
1443
+ " (wo): Linear(in_features=2048, out_features=2048, bias=False)\n",
1444
+ " (rope): Rope(\n",
1445
+ " (apply_rotary_emb): RotaryEmbedding()\n",
1446
+ " )\n",
1447
+ " (kv_cache): CustomKVCache()\n",
1448
+ " (SDPA): SDPACustom()\n",
1449
+ " )\n",
1450
+ " (feed_forward): FeedForward(\n",
1451
+ " (w1): Linear(in_features=2048, out_features=8192, bias=False)\n",
1452
+ " (w2): Linear(in_features=8192, out_features=2048, bias=False)\n",
1453
+ " (w3): Linear(in_features=2048, out_features=8192, bias=False)\n",
1454
+ " )\n",
1455
+ " (attention_norm): RMSNorm()\n",
1456
+ " (ffn_norm): RMSNorm()\n",
1457
+ " )\n",
1458
+ " )\n",
1459
+ " (norm): RMSNorm()\n",
1460
+ " (output): Linear(in_features=2048, out_features=128256, bias=False)\n",
1461
+ ")\n",
1462
+ "[INFO 2025-04-10 15:15:59,978 builder.py:228] Exporting with:\n",
1463
+ "[INFO 2025-04-10 15:15:59,980 builder.py:229] inputs: (tensor([[2, 3, 4]]), {'input_pos': tensor([0])})\n",
1464
+ "[INFO 2025-04-10 15:15:59,980 builder.py:230] kwargs: None\n",
1465
+ "[INFO 2025-04-10 15:15:59,980 builder.py:231] dynamic shapes: ({1: <class 'executorch.extension.llm.export.builder.token_dim'>}, {'input_pos': {0: 1}})\n",
1466
+ "[INFO 2025-04-10 15:16:25,457 builder.py:262] Running canonical pass: RemoveRedundantTransposes\n",
1467
+ "[INFO 2025-04-10 15:16:25,525 export_llama_lib.py:755] Lowering model using following partitioner(s): \n",
1468
+ "[INFO 2025-04-10 15:16:25,525 export_llama_lib.py:757] --> XnnpackDynamicallyQuantizedPartitioner\n",
1469
+ "[INFO 2025-04-10 15:16:25,525 builder.py:348] Using pt2e [] to quantizing the model...\n",
1470
+ "[INFO 2025-04-10 15:16:25,525 builder.py:399] No quantizer provided, passing...\n",
1471
+ "[INFO 2025-04-10 15:16:25,525 builder.py:226] Re-exporting with:\n",
1472
+ "[INFO 2025-04-10 15:16:25,526 builder.py:229] inputs: (tensor([[2, 3, 4]]), {'input_pos': tensor([0])})\n",
1473
+ "[INFO 2025-04-10 15:16:25,526 builder.py:230] kwargs: None\n",
1474
+ "[INFO 2025-04-10 15:16:25,526 builder.py:231] dynamic shapes: ({1: <class 'executorch.extension.llm.export.builder.token_dim'>}, {'input_pos': {0: 1}})\n",
1475
+ "/usr/local/lib/python3.11/dist-packages/executorch/exir/emit/_emitter.py:1592: UserWarning: Mutation on a buffer in the model is detected. ExecuTorch assumes buffers that are mutated in the graph have a meaningless initial state, only the shape and dtype will be serialized, unless a pass which sets meta[\"et_init_buffer\"] to True such as InitializedMutableBufferPass is run.\n",
1476
+ " warnings.warn(\n",
1477
+ "[INFO 2025-04-10 15:18:34,838 builder.py:518] Required memory for activation in bytes: [0, 17735552]\n",
1478
+ "modelname: Llama-3.2-1B-Instruct\n",
1479
+ "output_file: Llama-3.2-1B-Instruct.pte\n",
1480
+ "[INFO 2025-04-10 15:19:17,220 utils.py:141] Saved exported program to Llama-3.2-1B-Instruct.pte\n"
1481
+ ]
1482
+ }
1483
+ ]
1484
+ },
1485
+ {
1486
+ "cell_type": "markdown",
1487
+ "source": [],
1488
+ "metadata": {
1489
+ "id": "d_urCPkvEi98"
1490
+ }
1491
+ },
1492
+ {
1493
+ "cell_type": "code",
1494
+ "source": [
1495
+ "!mv /content/Llama-3.2-1B-Instruct.pte /content/models/Llama-3.2-1B-Instruct/original/"
1496
+ ],
1497
+ "metadata": {
1498
+ "id": "XOAVJceLE68b"
1499
+ },
1500
+ "execution_count": 11,
1501
+ "outputs": []
1502
+ },
1503
+ {
1504
+ "cell_type": "markdown",
1505
+ "source": [
1506
+ "**Step 4: Upload to HF**"
1507
+ ],
1508
+ "metadata": {
1509
+ "id": "-urRwR_iF0QX"
1510
+ }
1511
+ },
1512
+ {
1513
+ "cell_type": "code",
1514
+ "source": [
1515
+ "!huggingface-cli upload executorch-community/Llama-3.2-1B-Instruct-ET /content/models/Llama-3.2-1B-Instruct/original/ --exclude=\"*.pth\""
1516
+ ],
1517
+ "metadata": {
1518
+ "colab": {
1519
+ "base_uri": "https://localhost:8080/"
1520
+ },
1521
+ "id": "9YvGfvgxF8sn",
1522
+ "outputId": "d569be4d-6699-4b0c-b966-79ad7e9baef9"
1523
+ },
1524
+ "execution_count": 12,
1525
+ "outputs": [
1526
+ {
1527
+ "output_type": "stream",
1528
+ "name": "stdout",
1529
+ "text": [
1530
+ "Consider using `hf_transfer` for faster uploads. This solution comes with some limitations. See https://huggingface.co/docs/huggingface_hub/hf_transfer for more details.\n",
1531
+ "Start hashing 3 files.\n",
1532
+ "Finished hashing 3 files.\n",
1533
+ "Llama-3.2-1B-Instruct.pte: 100% 2.47G/2.47G [01:01<00:00, 40.4MB/s]\n",
1534
+ "Removing 2 file(s) from commit that have not changed.\n",
1535
+ "https://huggingface.co/executorch-community/Llama-3.2-1B-Instruct-ET/tree/main/.\n"
1536
+ ]
1537
+ }
1538
+ ]
1539
+ }
1540
+ ]
1541
+ }