AlexKitipov commited on
Commit
eba5b23
·
verified ·
1 Parent(s): 335cdce

Upload phi_2.ipynb

Browse files
Files changed (1) hide show
  1. phi_2.ipynb +1654 -0
phi_2.ipynb ADDED
@@ -0,0 +1,1654 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "nbformat": 4,
3
+ "nbformat_minor": 0,
4
+ "metadata": {
5
+ "colab": {
6
+ "machine_shape": "hm",
7
+ "gpuType": "T4",
8
+ "provenance": []
9
+ },
10
+ "accelerator": "GPU",
11
+ "kaggle": {
12
+ "accelerator": "gpu"
13
+ },
14
+ "language_info": {
15
+ "name": "python"
16
+ },
17
+ "kernelspec": {
18
+ "name": "python3",
19
+ "display_name": "Python 3"
20
+ },
21
+ "widgets": {
22
+ "application/vnd.jupyter.widget-state+json": {
23
+ "b486eefffb274a1d89c401ee56f0ea7b": {
24
+ "model_module": "@jupyter-widgets/controls",
25
+ "model_name": "HBoxModel",
26
+ "model_module_version": "1.5.0",
27
+ "state": {
28
+ "_dom_classes": [],
29
+ "_model_module": "@jupyter-widgets/controls",
30
+ "_model_module_version": "1.5.0",
31
+ "_model_name": "HBoxModel",
32
+ "_view_count": null,
33
+ "_view_module": "@jupyter-widgets/controls",
34
+ "_view_module_version": "1.5.0",
35
+ "_view_name": "HBoxView",
36
+ "box_style": "",
37
+ "children": [
38
+ "IPY_MODEL_2757c39f0c9a4fa599bd2a7b58c3ad4a",
39
+ "IPY_MODEL_696a9b10ead84306a3886b2a5853eb7c",
40
+ "IPY_MODEL_d7684e7d23764317acc7bcc512944758"
41
+ ],
42
+ "layout": "IPY_MODEL_e44dbcae75684967ae5a797d20c2ec16"
43
+ }
44
+ },
45
+ "2757c39f0c9a4fa599bd2a7b58c3ad4a": {
46
+ "model_module": "@jupyter-widgets/controls",
47
+ "model_name": "HTMLModel",
48
+ "model_module_version": "1.5.0",
49
+ "state": {
50
+ "_dom_classes": [],
51
+ "_model_module": "@jupyter-widgets/controls",
52
+ "_model_module_version": "1.5.0",
53
+ "_model_name": "HTMLModel",
54
+ "_view_count": null,
55
+ "_view_module": "@jupyter-widgets/controls",
56
+ "_view_module_version": "1.5.0",
57
+ "_view_name": "HTMLView",
58
+ "description": "",
59
+ "description_tooltip": null,
60
+ "layout": "IPY_MODEL_f318babe826841ab96db9716af5adc5e",
61
+ "placeholder": "​",
62
+ "style": "IPY_MODEL_fa14e7cbb0d14d56b5276d77f97f4315",
63
+ "value": "Loading weights: 100%"
64
+ }
65
+ },
66
+ "696a9b10ead84306a3886b2a5853eb7c": {
67
+ "model_module": "@jupyter-widgets/controls",
68
+ "model_name": "FloatProgressModel",
69
+ "model_module_version": "1.5.0",
70
+ "state": {
71
+ "_dom_classes": [],
72
+ "_model_module": "@jupyter-widgets/controls",
73
+ "_model_module_version": "1.5.0",
74
+ "_model_name": "FloatProgressModel",
75
+ "_view_count": null,
76
+ "_view_module": "@jupyter-widgets/controls",
77
+ "_view_module_version": "1.5.0",
78
+ "_view_name": "ProgressView",
79
+ "bar_style": "success",
80
+ "description": "",
81
+ "description_tooltip": null,
82
+ "layout": "IPY_MODEL_fd3f39e32b514e1f949a98ebc2922be0",
83
+ "max": 453,
84
+ "min": 0,
85
+ "orientation": "horizontal",
86
+ "style": "IPY_MODEL_e94a0224955143e59fb03000dff11208",
87
+ "value": 453
88
+ }
89
+ },
90
+ "d7684e7d23764317acc7bcc512944758": {
91
+ "model_module": "@jupyter-widgets/controls",
92
+ "model_name": "HTMLModel",
93
+ "model_module_version": "1.5.0",
94
+ "state": {
95
+ "_dom_classes": [],
96
+ "_model_module": "@jupyter-widgets/controls",
97
+ "_model_module_version": "1.5.0",
98
+ "_model_name": "HTMLModel",
99
+ "_view_count": null,
100
+ "_view_module": "@jupyter-widgets/controls",
101
+ "_view_module_version": "1.5.0",
102
+ "_view_name": "HTMLView",
103
+ "description": "",
104
+ "description_tooltip": null,
105
+ "layout": "IPY_MODEL_51f5cb0a06e84813a224e51e8a11c128",
106
+ "placeholder": "​",
107
+ "style": "IPY_MODEL_adc120af345247d6b3de0611e6d44490",
108
+ "value": " 453/453 [00:00<00:00, 611.00it/s, Materializing param=model.layers.31.self_attn.v_proj.weight]"
109
+ }
110
+ },
111
+ "e44dbcae75684967ae5a797d20c2ec16": {
112
+ "model_module": "@jupyter-widgets/base",
113
+ "model_name": "LayoutModel",
114
+ "model_module_version": "1.2.0",
115
+ "state": {
116
+ "_model_module": "@jupyter-widgets/base",
117
+ "_model_module_version": "1.2.0",
118
+ "_model_name": "LayoutModel",
119
+ "_view_count": null,
120
+ "_view_module": "@jupyter-widgets/base",
121
+ "_view_module_version": "1.2.0",
122
+ "_view_name": "LayoutView",
123
+ "align_content": null,
124
+ "align_items": null,
125
+ "align_self": null,
126
+ "border": null,
127
+ "bottom": null,
128
+ "display": null,
129
+ "flex": null,
130
+ "flex_flow": null,
131
+ "grid_area": null,
132
+ "grid_auto_columns": null,
133
+ "grid_auto_flow": null,
134
+ "grid_auto_rows": null,
135
+ "grid_column": null,
136
+ "grid_gap": null,
137
+ "grid_row": null,
138
+ "grid_template_areas": null,
139
+ "grid_template_columns": null,
140
+ "grid_template_rows": null,
141
+ "height": null,
142
+ "justify_content": null,
143
+ "justify_items": null,
144
+ "left": null,
145
+ "margin": null,
146
+ "max_height": null,
147
+ "max_width": null,
148
+ "min_height": null,
149
+ "min_width": null,
150
+ "object_fit": null,
151
+ "object_position": null,
152
+ "order": null,
153
+ "overflow": null,
154
+ "overflow_x": null,
155
+ "overflow_y": null,
156
+ "padding": null,
157
+ "right": null,
158
+ "top": null,
159
+ "visibility": null,
160
+ "width": null
161
+ }
162
+ },
163
+ "f318babe826841ab96db9716af5adc5e": {
164
+ "model_module": "@jupyter-widgets/base",
165
+ "model_name": "LayoutModel",
166
+ "model_module_version": "1.2.0",
167
+ "state": {
168
+ "_model_module": "@jupyter-widgets/base",
169
+ "_model_module_version": "1.2.0",
170
+ "_model_name": "LayoutModel",
171
+ "_view_count": null,
172
+ "_view_module": "@jupyter-widgets/base",
173
+ "_view_module_version": "1.2.0",
174
+ "_view_name": "LayoutView",
175
+ "align_content": null,
176
+ "align_items": null,
177
+ "align_self": null,
178
+ "border": null,
179
+ "bottom": null,
180
+ "display": null,
181
+ "flex": null,
182
+ "flex_flow": null,
183
+ "grid_area": null,
184
+ "grid_auto_columns": null,
185
+ "grid_auto_flow": null,
186
+ "grid_auto_rows": null,
187
+ "grid_column": null,
188
+ "grid_gap": null,
189
+ "grid_row": null,
190
+ "grid_template_areas": null,
191
+ "grid_template_columns": null,
192
+ "grid_template_rows": null,
193
+ "height": null,
194
+ "justify_content": null,
195
+ "justify_items": null,
196
+ "left": null,
197
+ "margin": null,
198
+ "max_height": null,
199
+ "max_width": null,
200
+ "min_height": null,
201
+ "min_width": null,
202
+ "object_fit": null,
203
+ "object_position": null,
204
+ "order": null,
205
+ "overflow": null,
206
+ "overflow_x": null,
207
+ "overflow_y": null,
208
+ "padding": null,
209
+ "right": null,
210
+ "top": null,
211
+ "visibility": null,
212
+ "width": null
213
+ }
214
+ },
215
+ "fa14e7cbb0d14d56b5276d77f97f4315": {
216
+ "model_module": "@jupyter-widgets/controls",
217
+ "model_name": "DescriptionStyleModel",
218
+ "model_module_version": "1.5.0",
219
+ "state": {
220
+ "_model_module": "@jupyter-widgets/controls",
221
+ "_model_module_version": "1.5.0",
222
+ "_model_name": "DescriptionStyleModel",
223
+ "_view_count": null,
224
+ "_view_module": "@jupyter-widgets/base",
225
+ "_view_module_version": "1.2.0",
226
+ "_view_name": "StyleView",
227
+ "description_width": ""
228
+ }
229
+ },
230
+ "fd3f39e32b514e1f949a98ebc2922be0": {
231
+ "model_module": "@jupyter-widgets/base",
232
+ "model_name": "LayoutModel",
233
+ "model_module_version": "1.2.0",
234
+ "state": {
235
+ "_model_module": "@jupyter-widgets/base",
236
+ "_model_module_version": "1.2.0",
237
+ "_model_name": "LayoutModel",
238
+ "_view_count": null,
239
+ "_view_module": "@jupyter-widgets/base",
240
+ "_view_module_version": "1.2.0",
241
+ "_view_name": "LayoutView",
242
+ "align_content": null,
243
+ "align_items": null,
244
+ "align_self": null,
245
+ "border": null,
246
+ "bottom": null,
247
+ "display": null,
248
+ "flex": null,
249
+ "flex_flow": null,
250
+ "grid_area": null,
251
+ "grid_auto_columns": null,
252
+ "grid_auto_flow": null,
253
+ "grid_auto_rows": null,
254
+ "grid_column": null,
255
+ "grid_gap": null,
256
+ "grid_row": null,
257
+ "grid_template_areas": null,
258
+ "grid_template_columns": null,
259
+ "grid_template_rows": null,
260
+ "height": null,
261
+ "justify_content": null,
262
+ "justify_items": null,
263
+ "left": null,
264
+ "margin": null,
265
+ "max_height": null,
266
+ "max_width": null,
267
+ "min_height": null,
268
+ "min_width": null,
269
+ "object_fit": null,
270
+ "object_position": null,
271
+ "order": null,
272
+ "overflow": null,
273
+ "overflow_x": null,
274
+ "overflow_y": null,
275
+ "padding": null,
276
+ "right": null,
277
+ "top": null,
278
+ "visibility": null,
279
+ "width": null
280
+ }
281
+ },
282
+ "e94a0224955143e59fb03000dff11208": {
283
+ "model_module": "@jupyter-widgets/controls",
284
+ "model_name": "ProgressStyleModel",
285
+ "model_module_version": "1.5.0",
286
+ "state": {
287
+ "_model_module": "@jupyter-widgets/controls",
288
+ "_model_module_version": "1.5.0",
289
+ "_model_name": "ProgressStyleModel",
290
+ "_view_count": null,
291
+ "_view_module": "@jupyter-widgets/base",
292
+ "_view_module_version": "1.2.0",
293
+ "_view_name": "StyleView",
294
+ "bar_color": null,
295
+ "description_width": ""
296
+ }
297
+ },
298
+ "51f5cb0a06e84813a224e51e8a11c128": {
299
+ "model_module": "@jupyter-widgets/base",
300
+ "model_name": "LayoutModel",
301
+ "model_module_version": "1.2.0",
302
+ "state": {
303
+ "_model_module": "@jupyter-widgets/base",
304
+ "_model_module_version": "1.2.0",
305
+ "_model_name": "LayoutModel",
306
+ "_view_count": null,
307
+ "_view_module": "@jupyter-widgets/base",
308
+ "_view_module_version": "1.2.0",
309
+ "_view_name": "LayoutView",
310
+ "align_content": null,
311
+ "align_items": null,
312
+ "align_self": null,
313
+ "border": null,
314
+ "bottom": null,
315
+ "display": null,
316
+ "flex": null,
317
+ "flex_flow": null,
318
+ "grid_area": null,
319
+ "grid_auto_columns": null,
320
+ "grid_auto_flow": null,
321
+ "grid_auto_rows": null,
322
+ "grid_column": null,
323
+ "grid_gap": null,
324
+ "grid_row": null,
325
+ "grid_template_areas": null,
326
+ "grid_template_columns": null,
327
+ "grid_template_rows": null,
328
+ "height": null,
329
+ "justify_content": null,
330
+ "justify_items": null,
331
+ "left": null,
332
+ "margin": null,
333
+ "max_height": null,
334
+ "max_width": null,
335
+ "min_height": null,
336
+ "min_width": null,
337
+ "object_fit": null,
338
+ "object_position": null,
339
+ "order": null,
340
+ "overflow": null,
341
+ "overflow_x": null,
342
+ "overflow_y": null,
343
+ "padding": null,
344
+ "right": null,
345
+ "top": null,
346
+ "visibility": null,
347
+ "width": null
348
+ }
349
+ },
350
+ "adc120af345247d6b3de0611e6d44490": {
351
+ "model_module": "@jupyter-widgets/controls",
352
+ "model_name": "DescriptionStyleModel",
353
+ "model_module_version": "1.5.0",
354
+ "state": {
355
+ "_model_module": "@jupyter-widgets/controls",
356
+ "_model_module_version": "1.5.0",
357
+ "_model_name": "DescriptionStyleModel",
358
+ "_view_count": null,
359
+ "_view_module": "@jupyter-widgets/base",
360
+ "_view_module_version": "1.2.0",
361
+ "_view_name": "StyleView",
362
+ "description_width": ""
363
+ }
364
+ },
365
+ "1e548b10c6b44b5fb6ea8687d94486f7": {
366
+ "model_module": "@jupyter-widgets/controls",
367
+ "model_name": "HBoxModel",
368
+ "model_module_version": "1.5.0",
369
+ "state": {
370
+ "_dom_classes": [],
371
+ "_model_module": "@jupyter-widgets/controls",
372
+ "_model_module_version": "1.5.0",
373
+ "_model_name": "HBoxModel",
374
+ "_view_count": null,
375
+ "_view_module": "@jupyter-widgets/controls",
376
+ "_view_module_version": "1.5.0",
377
+ "_view_name": "HBoxView",
378
+ "box_style": "",
379
+ "children": [
380
+ "IPY_MODEL_603cb08fbfdf4aa5bb1072da1501116f",
381
+ "IPY_MODEL_b30d2933522342bb8df152670e068a61",
382
+ "IPY_MODEL_c04efaac2bd042618f7d4923ec2be8c0"
383
+ ],
384
+ "layout": "IPY_MODEL_90559a506ecb4f46a345855a05cfc2d4"
385
+ }
386
+ },
387
+ "603cb08fbfdf4aa5bb1072da1501116f": {
388
+ "model_module": "@jupyter-widgets/controls",
389
+ "model_name": "HTMLModel",
390
+ "model_module_version": "1.5.0",
391
+ "state": {
392
+ "_dom_classes": [],
393
+ "_model_module": "@jupyter-widgets/controls",
394
+ "_model_module_version": "1.5.0",
395
+ "_model_name": "HTMLModel",
396
+ "_view_count": null,
397
+ "_view_module": "@jupyter-widgets/controls",
398
+ "_view_module_version": "1.5.0",
399
+ "_view_name": "HTMLView",
400
+ "description": "",
401
+ "description_tooltip": null,
402
+ "layout": "IPY_MODEL_e36f24e96c9a4941a071ad0a10e486af",
403
+ "placeholder": "​",
404
+ "style": "IPY_MODEL_e2962aae45854cc39eb90fdbcef0f460",
405
+ "value": "Loading weights: 100%"
406
+ }
407
+ },
408
+ "b30d2933522342bb8df152670e068a61": {
409
+ "model_module": "@jupyter-widgets/controls",
410
+ "model_name": "FloatProgressModel",
411
+ "model_module_version": "1.5.0",
412
+ "state": {
413
+ "_dom_classes": [],
414
+ "_model_module": "@jupyter-widgets/controls",
415
+ "_model_module_version": "1.5.0",
416
+ "_model_name": "FloatProgressModel",
417
+ "_view_count": null,
418
+ "_view_module": "@jupyter-widgets/controls",
419
+ "_view_module_version": "1.5.0",
420
+ "_view_name": "ProgressView",
421
+ "bar_style": "success",
422
+ "description": "",
423
+ "description_tooltip": null,
424
+ "layout": "IPY_MODEL_b004dc925fb64e43ae97d73788648ef7",
425
+ "max": 453,
426
+ "min": 0,
427
+ "orientation": "horizontal",
428
+ "style": "IPY_MODEL_c76b9cb1d93b48829805003ed178a2fa",
429
+ "value": 453
430
+ }
431
+ },
432
+ "c04efaac2bd042618f7d4923ec2be8c0": {
433
+ "model_module": "@jupyter-widgets/controls",
434
+ "model_name": "HTMLModel",
435
+ "model_module_version": "1.5.0",
436
+ "state": {
437
+ "_dom_classes": [],
438
+ "_model_module": "@jupyter-widgets/controls",
439
+ "_model_module_version": "1.5.0",
440
+ "_model_name": "HTMLModel",
441
+ "_view_count": null,
442
+ "_view_module": "@jupyter-widgets/controls",
443
+ "_view_module_version": "1.5.0",
444
+ "_view_name": "HTMLView",
445
+ "description": "",
446
+ "description_tooltip": null,
447
+ "layout": "IPY_MODEL_19103b3d686c4da994dc68912fe162b6",
448
+ "placeholder": "​",
449
+ "style": "IPY_MODEL_f3a46d6eebe04dd3894cb893ca8bc58a",
450
+ "value": " 453/453 [00:01<00:00, 404.11it/s, Materializing param=model.layers.31.self_attn.v_proj.weight]"
451
+ }
452
+ },
453
+ "90559a506ecb4f46a345855a05cfc2d4": {
454
+ "model_module": "@jupyter-widgets/base",
455
+ "model_name": "LayoutModel",
456
+ "model_module_version": "1.2.0",
457
+ "state": {
458
+ "_model_module": "@jupyter-widgets/base",
459
+ "_model_module_version": "1.2.0",
460
+ "_model_name": "LayoutModel",
461
+ "_view_count": null,
462
+ "_view_module": "@jupyter-widgets/base",
463
+ "_view_module_version": "1.2.0",
464
+ "_view_name": "LayoutView",
465
+ "align_content": null,
466
+ "align_items": null,
467
+ "align_self": null,
468
+ "border": null,
469
+ "bottom": null,
470
+ "display": null,
471
+ "flex": null,
472
+ "flex_flow": null,
473
+ "grid_area": null,
474
+ "grid_auto_columns": null,
475
+ "grid_auto_flow": null,
476
+ "grid_auto_rows": null,
477
+ "grid_column": null,
478
+ "grid_gap": null,
479
+ "grid_row": null,
480
+ "grid_template_areas": null,
481
+ "grid_template_columns": null,
482
+ "grid_template_rows": null,
483
+ "height": null,
484
+ "justify_content": null,
485
+ "justify_items": null,
486
+ "left": null,
487
+ "margin": null,
488
+ "max_height": null,
489
+ "max_width": null,
490
+ "min_height": null,
491
+ "min_width": null,
492
+ "object_fit": null,
493
+ "object_position": null,
494
+ "order": null,
495
+ "overflow": null,
496
+ "overflow_x": null,
497
+ "overflow_y": null,
498
+ "padding": null,
499
+ "right": null,
500
+ "top": null,
501
+ "visibility": null,
502
+ "width": null
503
+ }
504
+ },
505
+ "e36f24e96c9a4941a071ad0a10e486af": {
506
+ "model_module": "@jupyter-widgets/base",
507
+ "model_name": "LayoutModel",
508
+ "model_module_version": "1.2.0",
509
+ "state": {
510
+ "_model_module": "@jupyter-widgets/base",
511
+ "_model_module_version": "1.2.0",
512
+ "_model_name": "LayoutModel",
513
+ "_view_count": null,
514
+ "_view_module": "@jupyter-widgets/base",
515
+ "_view_module_version": "1.2.0",
516
+ "_view_name": "LayoutView",
517
+ "align_content": null,
518
+ "align_items": null,
519
+ "align_self": null,
520
+ "border": null,
521
+ "bottom": null,
522
+ "display": null,
523
+ "flex": null,
524
+ "flex_flow": null,
525
+ "grid_area": null,
526
+ "grid_auto_columns": null,
527
+ "grid_auto_flow": null,
528
+ "grid_auto_rows": null,
529
+ "grid_column": null,
530
+ "grid_gap": null,
531
+ "grid_row": null,
532
+ "grid_template_areas": null,
533
+ "grid_template_columns": null,
534
+ "grid_template_rows": null,
535
+ "height": null,
536
+ "justify_content": null,
537
+ "justify_items": null,
538
+ "left": null,
539
+ "margin": null,
540
+ "max_height": null,
541
+ "max_width": null,
542
+ "min_height": null,
543
+ "min_width": null,
544
+ "object_fit": null,
545
+ "object_position": null,
546
+ "order": null,
547
+ "overflow": null,
548
+ "overflow_x": null,
549
+ "overflow_y": null,
550
+ "padding": null,
551
+ "right": null,
552
+ "top": null,
553
+ "visibility": null,
554
+ "width": null
555
+ }
556
+ },
557
+ "e2962aae45854cc39eb90fdbcef0f460": {
558
+ "model_module": "@jupyter-widgets/controls",
559
+ "model_name": "DescriptionStyleModel",
560
+ "model_module_version": "1.5.0",
561
+ "state": {
562
+ "_model_module": "@jupyter-widgets/controls",
563
+ "_model_module_version": "1.5.0",
564
+ "_model_name": "DescriptionStyleModel",
565
+ "_view_count": null,
566
+ "_view_module": "@jupyter-widgets/base",
567
+ "_view_module_version": "1.2.0",
568
+ "_view_name": "StyleView",
569
+ "description_width": ""
570
+ }
571
+ },
572
+ "b004dc925fb64e43ae97d73788648ef7": {
573
+ "model_module": "@jupyter-widgets/base",
574
+ "model_name": "LayoutModel",
575
+ "model_module_version": "1.2.0",
576
+ "state": {
577
+ "_model_module": "@jupyter-widgets/base",
578
+ "_model_module_version": "1.2.0",
579
+ "_model_name": "LayoutModel",
580
+ "_view_count": null,
581
+ "_view_module": "@jupyter-widgets/base",
582
+ "_view_module_version": "1.2.0",
583
+ "_view_name": "LayoutView",
584
+ "align_content": null,
585
+ "align_items": null,
586
+ "align_self": null,
587
+ "border": null,
588
+ "bottom": null,
589
+ "display": null,
590
+ "flex": null,
591
+ "flex_flow": null,
592
+ "grid_area": null,
593
+ "grid_auto_columns": null,
594
+ "grid_auto_flow": null,
595
+ "grid_auto_rows": null,
596
+ "grid_column": null,
597
+ "grid_gap": null,
598
+ "grid_row": null,
599
+ "grid_template_areas": null,
600
+ "grid_template_columns": null,
601
+ "grid_template_rows": null,
602
+ "height": null,
603
+ "justify_content": null,
604
+ "justify_items": null,
605
+ "left": null,
606
+ "margin": null,
607
+ "max_height": null,
608
+ "max_width": null,
609
+ "min_height": null,
610
+ "min_width": null,
611
+ "object_fit": null,
612
+ "object_position": null,
613
+ "order": null,
614
+ "overflow": null,
615
+ "overflow_x": null,
616
+ "overflow_y": null,
617
+ "padding": null,
618
+ "right": null,
619
+ "top": null,
620
+ "visibility": null,
621
+ "width": null
622
+ }
623
+ },
624
+ "c76b9cb1d93b48829805003ed178a2fa": {
625
+ "model_module": "@jupyter-widgets/controls",
626
+ "model_name": "ProgressStyleModel",
627
+ "model_module_version": "1.5.0",
628
+ "state": {
629
+ "_model_module": "@jupyter-widgets/controls",
630
+ "_model_module_version": "1.5.0",
631
+ "_model_name": "ProgressStyleModel",
632
+ "_view_count": null,
633
+ "_view_module": "@jupyter-widgets/base",
634
+ "_view_module_version": "1.2.0",
635
+ "_view_name": "StyleView",
636
+ "bar_color": null,
637
+ "description_width": ""
638
+ }
639
+ },
640
+ "19103b3d686c4da994dc68912fe162b6": {
641
+ "model_module": "@jupyter-widgets/base",
642
+ "model_name": "LayoutModel",
643
+ "model_module_version": "1.2.0",
644
+ "state": {
645
+ "_model_module": "@jupyter-widgets/base",
646
+ "_model_module_version": "1.2.0",
647
+ "_model_name": "LayoutModel",
648
+ "_view_count": null,
649
+ "_view_module": "@jupyter-widgets/base",
650
+ "_view_module_version": "1.2.0",
651
+ "_view_name": "LayoutView",
652
+ "align_content": null,
653
+ "align_items": null,
654
+ "align_self": null,
655
+ "border": null,
656
+ "bottom": null,
657
+ "display": null,
658
+ "flex": null,
659
+ "flex_flow": null,
660
+ "grid_area": null,
661
+ "grid_auto_columns": null,
662
+ "grid_auto_flow": null,
663
+ "grid_auto_rows": null,
664
+ "grid_column": null,
665
+ "grid_gap": null,
666
+ "grid_row": null,
667
+ "grid_template_areas": null,
668
+ "grid_template_columns": null,
669
+ "grid_template_rows": null,
670
+ "height": null,
671
+ "justify_content": null,
672
+ "justify_items": null,
673
+ "left": null,
674
+ "margin": null,
675
+ "max_height": null,
676
+ "max_width": null,
677
+ "min_height": null,
678
+ "min_width": null,
679
+ "object_fit": null,
680
+ "object_position": null,
681
+ "order": null,
682
+ "overflow": null,
683
+ "overflow_x": null,
684
+ "overflow_y": null,
685
+ "padding": null,
686
+ "right": null,
687
+ "top": null,
688
+ "visibility": null,
689
+ "width": null
690
+ }
691
+ },
692
+ "f3a46d6eebe04dd3894cb893ca8bc58a": {
693
+ "model_module": "@jupyter-widgets/controls",
694
+ "model_name": "DescriptionStyleModel",
695
+ "model_module_version": "1.5.0",
696
+ "state": {
697
+ "_model_module": "@jupyter-widgets/controls",
698
+ "_model_module_version": "1.5.0",
699
+ "_model_name": "DescriptionStyleModel",
700
+ "_view_count": null,
701
+ "_view_module": "@jupyter-widgets/base",
702
+ "_view_module_version": "1.2.0",
703
+ "_view_name": "StyleView",
704
+ "description_width": ""
705
+ }
706
+ },
707
+ "844da948344e4421b32fa41a679fbdb7": {
708
+ "model_module": "@jupyter-widgets/controls",
709
+ "model_name": "HBoxModel",
710
+ "model_module_version": "1.5.0",
711
+ "state": {
712
+ "_dom_classes": [],
713
+ "_model_module": "@jupyter-widgets/controls",
714
+ "_model_module_version": "1.5.0",
715
+ "_model_name": "HBoxModel",
716
+ "_view_count": null,
717
+ "_view_module": "@jupyter-widgets/controls",
718
+ "_view_module_version": "1.5.0",
719
+ "_view_name": "HBoxView",
720
+ "box_style": "",
721
+ "children": [
722
+ "IPY_MODEL_012adaa5fd314a589e7c67e381a26c2c",
723
+ "IPY_MODEL_dea346540d084b5c89d96b992c11c30e",
724
+ "IPY_MODEL_a82b849d29f64d878cd87cba3851b80b"
725
+ ],
726
+ "layout": "IPY_MODEL_fe5a48f5cb2743319c5fcd38a494ff2c"
727
+ }
728
+ },
729
+ "012adaa5fd314a589e7c67e381a26c2c": {
730
+ "model_module": "@jupyter-widgets/controls",
731
+ "model_name": "HTMLModel",
732
+ "model_module_version": "1.5.0",
733
+ "state": {
734
+ "_dom_classes": [],
735
+ "_model_module": "@jupyter-widgets/controls",
736
+ "_model_module_version": "1.5.0",
737
+ "_model_name": "HTMLModel",
738
+ "_view_count": null,
739
+ "_view_module": "@jupyter-widgets/controls",
740
+ "_view_module_version": "1.5.0",
741
+ "_view_name": "HTMLView",
742
+ "description": "",
743
+ "description_tooltip": null,
744
+ "layout": "IPY_MODEL_098dee5390834dba9557964ccde15819",
745
+ "placeholder": "​",
746
+ "style": "IPY_MODEL_8fda24ae999c4da29f2282b7b687d147",
747
+ "value": "Loading weights: 100%"
748
+ }
749
+ },
750
+ "dea346540d084b5c89d96b992c11c30e": {
751
+ "model_module": "@jupyter-widgets/controls",
752
+ "model_name": "FloatProgressModel",
753
+ "model_module_version": "1.5.0",
754
+ "state": {
755
+ "_dom_classes": [],
756
+ "_model_module": "@jupyter-widgets/controls",
757
+ "_model_module_version": "1.5.0",
758
+ "_model_name": "FloatProgressModel",
759
+ "_view_count": null,
760
+ "_view_module": "@jupyter-widgets/controls",
761
+ "_view_module_version": "1.5.0",
762
+ "_view_name": "ProgressView",
763
+ "bar_style": "success",
764
+ "description": "",
765
+ "description_tooltip": null,
766
+ "layout": "IPY_MODEL_4d9edf9c343d4fc4a6381bba2d25ac4b",
767
+ "max": 453,
768
+ "min": 0,
769
+ "orientation": "horizontal",
770
+ "style": "IPY_MODEL_4c77a8efb23a4a44ba22aedcee5e6f16",
771
+ "value": 453
772
+ }
773
+ },
774
+ "a82b849d29f64d878cd87cba3851b80b": {
775
+ "model_module": "@jupyter-widgets/controls",
776
+ "model_name": "HTMLModel",
777
+ "model_module_version": "1.5.0",
778
+ "state": {
779
+ "_dom_classes": [],
780
+ "_model_module": "@jupyter-widgets/controls",
781
+ "_model_module_version": "1.5.0",
782
+ "_model_name": "HTMLModel",
783
+ "_view_count": null,
784
+ "_view_module": "@jupyter-widgets/controls",
785
+ "_view_module_version": "1.5.0",
786
+ "_view_name": "HTMLView",
787
+ "description": "",
788
+ "description_tooltip": null,
789
+ "layout": "IPY_MODEL_7ce7515d20fb4c06a27da6f45e0210d3",
790
+ "placeholder": "​",
791
+ "style": "IPY_MODEL_0daa08754c274d51ac35ef34e3a9457d",
792
+ "value": " 453/453 [00:03<00:00, 144.88it/s, Materializing param=model.layers.31.self_attn.v_proj.weight]"
793
+ }
794
+ },
795
+ "fe5a48f5cb2743319c5fcd38a494ff2c": {
796
+ "model_module": "@jupyter-widgets/base",
797
+ "model_name": "LayoutModel",
798
+ "model_module_version": "1.2.0",
799
+ "state": {
800
+ "_model_module": "@jupyter-widgets/base",
801
+ "_model_module_version": "1.2.0",
802
+ "_model_name": "LayoutModel",
803
+ "_view_count": null,
804
+ "_view_module": "@jupyter-widgets/base",
805
+ "_view_module_version": "1.2.0",
806
+ "_view_name": "LayoutView",
807
+ "align_content": null,
808
+ "align_items": null,
809
+ "align_self": null,
810
+ "border": null,
811
+ "bottom": null,
812
+ "display": null,
813
+ "flex": null,
814
+ "flex_flow": null,
815
+ "grid_area": null,
816
+ "grid_auto_columns": null,
817
+ "grid_auto_flow": null,
818
+ "grid_auto_rows": null,
819
+ "grid_column": null,
820
+ "grid_gap": null,
821
+ "grid_row": null,
822
+ "grid_template_areas": null,
823
+ "grid_template_columns": null,
824
+ "grid_template_rows": null,
825
+ "height": null,
826
+ "justify_content": null,
827
+ "justify_items": null,
828
+ "left": null,
829
+ "margin": null,
830
+ "max_height": null,
831
+ "max_width": null,
832
+ "min_height": null,
833
+ "min_width": null,
834
+ "object_fit": null,
835
+ "object_position": null,
836
+ "order": null,
837
+ "overflow": null,
838
+ "overflow_x": null,
839
+ "overflow_y": null,
840
+ "padding": null,
841
+ "right": null,
842
+ "top": null,
843
+ "visibility": null,
844
+ "width": null
845
+ }
846
+ },
847
+ "098dee5390834dba9557964ccde15819": {
848
+ "model_module": "@jupyter-widgets/base",
849
+ "model_name": "LayoutModel",
850
+ "model_module_version": "1.2.0",
851
+ "state": {
852
+ "_model_module": "@jupyter-widgets/base",
853
+ "_model_module_version": "1.2.0",
854
+ "_model_name": "LayoutModel",
855
+ "_view_count": null,
856
+ "_view_module": "@jupyter-widgets/base",
857
+ "_view_module_version": "1.2.0",
858
+ "_view_name": "LayoutView",
859
+ "align_content": null,
860
+ "align_items": null,
861
+ "align_self": null,
862
+ "border": null,
863
+ "bottom": null,
864
+ "display": null,
865
+ "flex": null,
866
+ "flex_flow": null,
867
+ "grid_area": null,
868
+ "grid_auto_columns": null,
869
+ "grid_auto_flow": null,
870
+ "grid_auto_rows": null,
871
+ "grid_column": null,
872
+ "grid_gap": null,
873
+ "grid_row": null,
874
+ "grid_template_areas": null,
875
+ "grid_template_columns": null,
876
+ "grid_template_rows": null,
877
+ "height": null,
878
+ "justify_content": null,
879
+ "justify_items": null,
880
+ "left": null,
881
+ "margin": null,
882
+ "max_height": null,
883
+ "max_width": null,
884
+ "min_height": null,
885
+ "min_width": null,
886
+ "object_fit": null,
887
+ "object_position": null,
888
+ "order": null,
889
+ "overflow": null,
890
+ "overflow_x": null,
891
+ "overflow_y": null,
892
+ "padding": null,
893
+ "right": null,
894
+ "top": null,
895
+ "visibility": null,
896
+ "width": null
897
+ }
898
+ },
899
+ "8fda24ae999c4da29f2282b7b687d147": {
900
+ "model_module": "@jupyter-widgets/controls",
901
+ "model_name": "DescriptionStyleModel",
902
+ "model_module_version": "1.5.0",
903
+ "state": {
904
+ "_model_module": "@jupyter-widgets/controls",
905
+ "_model_module_version": "1.5.0",
906
+ "_model_name": "DescriptionStyleModel",
907
+ "_view_count": null,
908
+ "_view_module": "@jupyter-widgets/base",
909
+ "_view_module_version": "1.2.0",
910
+ "_view_name": "StyleView",
911
+ "description_width": ""
912
+ }
913
+ },
914
+ "4d9edf9c343d4fc4a6381bba2d25ac4b": {
915
+ "model_module": "@jupyter-widgets/base",
916
+ "model_name": "LayoutModel",
917
+ "model_module_version": "1.2.0",
918
+ "state": {
919
+ "_model_module": "@jupyter-widgets/base",
920
+ "_model_module_version": "1.2.0",
921
+ "_model_name": "LayoutModel",
922
+ "_view_count": null,
923
+ "_view_module": "@jupyter-widgets/base",
924
+ "_view_module_version": "1.2.0",
925
+ "_view_name": "LayoutView",
926
+ "align_content": null,
927
+ "align_items": null,
928
+ "align_self": null,
929
+ "border": null,
930
+ "bottom": null,
931
+ "display": null,
932
+ "flex": null,
933
+ "flex_flow": null,
934
+ "grid_area": null,
935
+ "grid_auto_columns": null,
936
+ "grid_auto_flow": null,
937
+ "grid_auto_rows": null,
938
+ "grid_column": null,
939
+ "grid_gap": null,
940
+ "grid_row": null,
941
+ "grid_template_areas": null,
942
+ "grid_template_columns": null,
943
+ "grid_template_rows": null,
944
+ "height": null,
945
+ "justify_content": null,
946
+ "justify_items": null,
947
+ "left": null,
948
+ "margin": null,
949
+ "max_height": null,
950
+ "max_width": null,
951
+ "min_height": null,
952
+ "min_width": null,
953
+ "object_fit": null,
954
+ "object_position": null,
955
+ "order": null,
956
+ "overflow": null,
957
+ "overflow_x": null,
958
+ "overflow_y": null,
959
+ "padding": null,
960
+ "right": null,
961
+ "top": null,
962
+ "visibility": null,
963
+ "width": null
964
+ }
965
+ },
966
+ "4c77a8efb23a4a44ba22aedcee5e6f16": {
967
+ "model_module": "@jupyter-widgets/controls",
968
+ "model_name": "ProgressStyleModel",
969
+ "model_module_version": "1.5.0",
970
+ "state": {
971
+ "_model_module": "@jupyter-widgets/controls",
972
+ "_model_module_version": "1.5.0",
973
+ "_model_name": "ProgressStyleModel",
974
+ "_view_count": null,
975
+ "_view_module": "@jupyter-widgets/base",
976
+ "_view_module_version": "1.2.0",
977
+ "_view_name": "StyleView",
978
+ "bar_color": null,
979
+ "description_width": ""
980
+ }
981
+ },
982
+ "7ce7515d20fb4c06a27da6f45e0210d3": {
983
+ "model_module": "@jupyter-widgets/base",
984
+ "model_name": "LayoutModel",
985
+ "model_module_version": "1.2.0",
986
+ "state": {
987
+ "_model_module": "@jupyter-widgets/base",
988
+ "_model_module_version": "1.2.0",
989
+ "_model_name": "LayoutModel",
990
+ "_view_count": null,
991
+ "_view_module": "@jupyter-widgets/base",
992
+ "_view_module_version": "1.2.0",
993
+ "_view_name": "LayoutView",
994
+ "align_content": null,
995
+ "align_items": null,
996
+ "align_self": null,
997
+ "border": null,
998
+ "bottom": null,
999
+ "display": null,
1000
+ "flex": null,
1001
+ "flex_flow": null,
1002
+ "grid_area": null,
1003
+ "grid_auto_columns": null,
1004
+ "grid_auto_flow": null,
1005
+ "grid_auto_rows": null,
1006
+ "grid_column": null,
1007
+ "grid_gap": null,
1008
+ "grid_row": null,
1009
+ "grid_template_areas": null,
1010
+ "grid_template_columns": null,
1011
+ "grid_template_rows": null,
1012
+ "height": null,
1013
+ "justify_content": null,
1014
+ "justify_items": null,
1015
+ "left": null,
1016
+ "margin": null,
1017
+ "max_height": null,
1018
+ "max_width": null,
1019
+ "min_height": null,
1020
+ "min_width": null,
1021
+ "object_fit": null,
1022
+ "object_position": null,
1023
+ "order": null,
1024
+ "overflow": null,
1025
+ "overflow_x": null,
1026
+ "overflow_y": null,
1027
+ "padding": null,
1028
+ "right": null,
1029
+ "top": null,
1030
+ "visibility": null,
1031
+ "width": null
1032
+ }
1033
+ },
1034
+ "0daa08754c274d51ac35ef34e3a9457d": {
1035
+ "model_module": "@jupyter-widgets/controls",
1036
+ "model_name": "DescriptionStyleModel",
1037
+ "model_module_version": "1.5.0",
1038
+ "state": {
1039
+ "_model_module": "@jupyter-widgets/controls",
1040
+ "_model_module_version": "1.5.0",
1041
+ "_model_name": "DescriptionStyleModel",
1042
+ "_view_count": null,
1043
+ "_view_module": "@jupyter-widgets/base",
1044
+ "_view_module_version": "1.2.0",
1045
+ "_view_name": "StyleView",
1046
+ "description_width": ""
1047
+ }
1048
+ }
1049
+ }
1050
+ }
1051
+ },
1052
+ "cells": [
1053
+ {
1054
+ "cell_type": "code",
1055
+ "source": [
1056
+ "!pip install -U transformers"
1057
+ ],
1058
+ "metadata": {
1059
+ "colab": {
1060
+ "base_uri": "https://localhost:8080/",
1061
+ "height": 810
1062
+ },
1063
+ "id": "o0zcQycu-UEa",
1064
+ "outputId": "3d82776f-8531-4680-8f2a-5578e708c945"
1065
+ },
1066
+ "execution_count": 23,
1067
+ "outputs": [
1068
+ {
1069
+ "output_type": "stream",
1070
+ "name": "stdout",
1071
+ "text": [
1072
+ "Requirement already satisfied: transformers in /usr/local/lib/python3.12/dist-packages (5.0.0)\n",
1073
+ "Collecting transformers\n",
1074
+ " Downloading transformers-5.8.1-py3-none-any.whl.metadata (33 kB)\n",
1075
+ "Requirement already satisfied: huggingface-hub<2.0,>=1.5.0 in /usr/local/lib/python3.12/dist-packages (from transformers) (1.11.0)\n",
1076
+ "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.12/dist-packages (from transformers) (2.0.2)\n",
1077
+ "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.12/dist-packages (from transformers) (26.1)\n",
1078
+ "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.12/dist-packages (from transformers) (6.0.3)\n",
1079
+ "Requirement already satisfied: regex>=2025.10.22 in /usr/local/lib/python3.12/dist-packages (from transformers) (2025.11.3)\n",
1080
+ "Requirement already satisfied: tokenizers<=0.23.0,>=0.22.0 in /usr/local/lib/python3.12/dist-packages (from transformers) (0.22.2)\n",
1081
+ "Requirement already satisfied: typer in /usr/local/lib/python3.12/dist-packages (from transformers) (0.24.2)\n",
1082
+ "Requirement already satisfied: safetensors>=0.4.3 in /usr/local/lib/python3.12/dist-packages (from transformers) (0.7.0)\n",
1083
+ "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.12/dist-packages (from transformers) (4.67.3)\n",
1084
+ "Requirement already satisfied: filelock>=3.10.0 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub<2.0,>=1.5.0->transformers) (3.29.0)\n",
1085
+ "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub<2.0,>=1.5.0->transformers) (2025.3.0)\n",
1086
+ "Requirement already satisfied: hf-xet<2.0.0,>=1.4.3 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub<2.0,>=1.5.0->transformers) (1.4.3)\n",
1087
+ "Requirement already satisfied: httpx<1,>=0.23.0 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub<2.0,>=1.5.0->transformers) (0.28.1)\n",
1088
+ "Requirement already satisfied: typing-extensions>=4.1.0 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub<2.0,>=1.5.0->transformers) (4.15.0)\n",
1089
+ "Requirement already satisfied: click>=8.2.1 in /usr/local/lib/python3.12/dist-packages (from typer->transformers) (8.3.3)\n",
1090
+ "Requirement already satisfied: shellingham>=1.3.0 in /usr/local/lib/python3.12/dist-packages (from typer->transformers) (1.5.4)\n",
1091
+ "Requirement already satisfied: rich>=12.3.0 in /usr/local/lib/python3.12/dist-packages (from typer->transformers) (13.9.4)\n",
1092
+ "Requirement already satisfied: annotated-doc>=0.0.2 in /usr/local/lib/python3.12/dist-packages (from typer->transformers) (0.0.4)\n",
1093
+ "Requirement already satisfied: anyio in /usr/local/lib/python3.12/dist-packages (from httpx<1,>=0.23.0->huggingface-hub<2.0,>=1.5.0->transformers) (4.13.0)\n",
1094
+ "Requirement already satisfied: certifi in /usr/local/lib/python3.12/dist-packages (from httpx<1,>=0.23.0->huggingface-hub<2.0,>=1.5.0->transformers) (2026.4.22)\n",
1095
+ "Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.12/dist-packages (from httpx<1,>=0.23.0->huggingface-hub<2.0,>=1.5.0->transformers) (1.0.9)\n",
1096
+ "Requirement already satisfied: idna in /usr/local/lib/python3.12/dist-packages (from httpx<1,>=0.23.0->huggingface-hub<2.0,>=1.5.0->transformers) (3.13)\n",
1097
+ "Requirement already satisfied: h11>=0.16 in /usr/local/lib/python3.12/dist-packages (from httpcore==1.*->httpx<1,>=0.23.0->huggingface-hub<2.0,>=1.5.0->transformers) (0.16.0)\n",
1098
+ "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.12/dist-packages (from rich>=12.3.0->typer->transformers) (4.0.0)\n",
1099
+ "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.12/dist-packages (from rich>=12.3.0->typer->transformers) (2.20.0)\n",
1100
+ "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.12/dist-packages (from markdown-it-py>=2.2.0->rich>=12.3.0->typer->transformers) (0.1.2)\n",
1101
+ "Downloading transformers-5.8.1-py3-none-any.whl (10.6 MB)\n",
1102
+ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m10.6/10.6 MB\u001b[0m \u001b[31m61.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
1103
+ "\u001b[?25hInstalling collected packages: transformers\n",
1104
+ " Attempting uninstall: transformers\n",
1105
+ " Found existing installation: transformers 5.0.0\n",
1106
+ " Uninstalling transformers-5.0.0:\n",
1107
+ " Successfully uninstalled transformers-5.0.0\n",
1108
+ "Successfully installed transformers-5.8.1\n"
1109
+ ]
1110
+ },
1111
+ {
1112
+ "output_type": "display_data",
1113
+ "data": {
1114
+ "application/vnd.colab-display-data+json": {
1115
+ "pip_warning": {
1116
+ "packages": [
1117
+ "transformers"
1118
+ ]
1119
+ },
1120
+ "id": "338a67b765ed413081d22a770dd5b35c"
1121
+ }
1122
+ },
1123
+ "metadata": {}
1124
+ }
1125
+ ]
1126
+ },
1127
+ {
1128
+ "cell_type": "markdown",
1129
+ "source": [
1130
+ "## Local Inference on GPU\n",
1131
+ "Model page: https://huggingface.co/microsoft/phi-2\n",
1132
+ "\n",
1133
+ "⚠️ If the generated code snippets do not work, please open an issue on either the [model repo](https://huggingface.co/microsoft/phi-2)\n",
1134
+ "\t\t\tand/or on [huggingface.js](https://github.com/huggingface/huggingface.js/blob/main/packages/tasks/src/model-libraries-snippets.ts) 🙏"
1135
+ ],
1136
+ "metadata": {
1137
+ "id": "qhYDm6yk-UEj"
1138
+ }
1139
+ },
1140
+ {
1141
+ "cell_type": "code",
1142
+ "source": [
1143
+ "# Use a pipeline as a high-level helper\n",
1144
+ "from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM, AutoConfig\n",
1145
+ "import torch\n",
1146
+ "\n",
1147
+ "model_name = \"microsoft/phi-2\"\n",
1148
+ "\n",
1149
+ "# Load tokenizer and set pad_token\n",
1150
+ "tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)\n",
1151
+ "tokenizer.pad_token = tokenizer.eos_token\n",
1152
+ "\n",
1153
+ "# Load model configuration and set pad_token_id\n",
1154
+ "config = AutoConfig.from_pretrained(model_name, trust_remote_code=True)\n",
1155
+ "config.pad_token_id = tokenizer.eos_token_id\n",
1156
+ "\n",
1157
+ "# Load model with the modified configuration\n",
1158
+ "model = AutoModelForCausalLM.from_pretrained(\n",
1159
+ " model_name,\n",
1160
+ " config=config,\n",
1161
+ " trust_remote_code=True,\n",
1162
+ " torch_dtype=torch.float16 # Use float16 for potentially better performance/memory usage\n",
1163
+ ")\n",
1164
+ "\n",
1165
+ "# Create the pipeline with the correctly loaded model and tokenizer\n",
1166
+ "# Check for GPU and move model if available\n",
1167
+ "device = 0 if torch.cuda.is_available() else -1\n",
1168
+ "if torch.cuda.is_available():\n",
1169
+ " model.to('cuda')\n",
1170
+ " print(\"Model moved to GPU.\")\n",
1171
+ "else:\n",
1172
+ " print(\"GPU not available, model will run on CPU.\")\n",
1173
+ "\n",
1174
+ "pipe = pipeline(\"text-generation\", model=model, tokenizer=tokenizer, device=device)\n",
1175
+ "print(\"Pipeline initialized successfully.\")"
1176
+ ],
1177
+ "metadata": {
1178
+ "colab": {
1179
+ "base_uri": "https://localhost:8080/",
1180
+ "height": 96,
1181
+ "referenced_widgets": [
1182
+ "b486eefffb274a1d89c401ee56f0ea7b",
1183
+ "2757c39f0c9a4fa599bd2a7b58c3ad4a",
1184
+ "696a9b10ead84306a3886b2a5853eb7c",
1185
+ "d7684e7d23764317acc7bcc512944758",
1186
+ "e44dbcae75684967ae5a797d20c2ec16",
1187
+ "f318babe826841ab96db9716af5adc5e",
1188
+ "fa14e7cbb0d14d56b5276d77f97f4315",
1189
+ "fd3f39e32b514e1f949a98ebc2922be0",
1190
+ "e94a0224955143e59fb03000dff11208",
1191
+ "51f5cb0a06e84813a224e51e8a11c128",
1192
+ "adc120af345247d6b3de0611e6d44490"
1193
+ ]
1194
+ },
1195
+ "id": "b9Ly2RUM-UFe",
1196
+ "outputId": "f89768a7-caf1-4972-8c24-d088907a31ea"
1197
+ },
1198
+ "execution_count": 25,
1199
+ "outputs": [
1200
+ {
1201
+ "output_type": "display_data",
1202
+ "data": {
1203
+ "text/plain": [
1204
+ "Loading weights: 0%| | 0/453 [00:00<?, ?it/s]"
1205
+ ],
1206
+ "application/vnd.jupyter.widget-view+json": {
1207
+ "version_major": 2,
1208
+ "version_minor": 0,
1209
+ "model_id": "b486eefffb274a1d89c401ee56f0ea7b"
1210
+ }
1211
+ },
1212
+ "metadata": {}
1213
+ },
1214
+ {
1215
+ "output_type": "stream",
1216
+ "name": "stdout",
1217
+ "text": [
1218
+ "GPU not available, model will run on CPU.\n",
1219
+ "Pipeline initialized successfully.\n"
1220
+ ]
1221
+ }
1222
+ ]
1223
+ },
1224
+ {
1225
+ "cell_type": "code",
1226
+ "source": [
1227
+ "from transformers import AutoTokenizer, AutoModelForCausalLM, AutoConfig\n",
1228
+ "import torch\n",
1229
+ "\n",
1230
+ "# Load tokenizer first\n",
1231
+ "tokenizer = AutoTokenizer.from_pretrained(\"microsoft/phi-2\", trust_remote_code=True)\n",
1232
+ "\n",
1233
+ "# Set pad_token for tokenizer using eos_token\n",
1234
+ "tokenizer.pad_token = tokenizer.eos_token\n",
1235
+ "\n",
1236
+ "# Load model configuration separately to ensure pad_token_id is set before model initialization\n",
1237
+ "config = AutoConfig.from_pretrained(\"microsoft/phi-2\", trust_remote_code=True)\n",
1238
+ "\n",
1239
+ "# Explicitly set pad_token_id in the config\n",
1240
+ "config.pad_token_id = tokenizer.eos_token_id\n",
1241
+ "\n",
1242
+ "model = AutoModelForCausalLM.from_pretrained(\n",
1243
+ " \"microsoft/phi-2\",\n",
1244
+ " config=config, # Pass the modified config here\n",
1245
+ " trust_remote_code=True,\n",
1246
+ " torch_dtype=torch.float16 # Use float16 for potentially better performance/memory usage\n",
1247
+ ")"
1248
+ ],
1249
+ "metadata": {
1250
+ "colab": {
1251
+ "base_uri": "https://localhost:8080/",
1252
+ "height": 61,
1253
+ "referenced_widgets": [
1254
+ "1e548b10c6b44b5fb6ea8687d94486f7",
1255
+ "603cb08fbfdf4aa5bb1072da1501116f",
1256
+ "b30d2933522342bb8df152670e068a61",
1257
+ "c04efaac2bd042618f7d4923ec2be8c0",
1258
+ "90559a506ecb4f46a345855a05cfc2d4",
1259
+ "e36f24e96c9a4941a071ad0a10e486af",
1260
+ "e2962aae45854cc39eb90fdbcef0f460",
1261
+ "b004dc925fb64e43ae97d73788648ef7",
1262
+ "c76b9cb1d93b48829805003ed178a2fa",
1263
+ "19103b3d686c4da994dc68912fe162b6",
1264
+ "f3a46d6eebe04dd3894cb893ca8bc58a"
1265
+ ]
1266
+ },
1267
+ "id": "q5AOq1_Z-UFu",
1268
+ "outputId": "e1c11712-860c-40f7-e8eb-f639471858d7"
1269
+ },
1270
+ "execution_count": 39,
1271
+ "outputs": [
1272
+ {
1273
+ "output_type": "display_data",
1274
+ "data": {
1275
+ "text/plain": [
1276
+ "Loading weights: 0%| | 0/453 [00:00<?, ?it/s]"
1277
+ ],
1278
+ "application/vnd.jupyter.widget-view+json": {
1279
+ "version_major": 2,
1280
+ "version_minor": 0,
1281
+ "model_id": "1e548b10c6b44b5fb6ea8687d94486f7"
1282
+ }
1283
+ },
1284
+ "metadata": {}
1285
+ }
1286
+ ]
1287
+ },
1288
+ {
1289
+ "cell_type": "markdown",
1290
+ "source": [
1291
+ "## Remote Inference via Inference Providers\n",
1292
+ "Ensure you have a valid **HF_TOKEN** set in your environment. You can get your token from [your settings page](https://huggingface.co/settings/tokens). Note: running this may incur charges above the free tier.\n",
1293
+ "The following Python example shows how to run the model remotely on HF Inference Providers, automatically selecting an available inference provider for you.\n",
1294
+ "For more information on how to use the Inference Providers, please refer to our [documentation and guides](https://huggingface.co/docs/inference-providers/en/index)."
1295
+ ],
1296
+ "metadata": {
1297
+ "id": "IRyu8RyM-UF-"
1298
+ }
1299
+ },
1300
+ {
1301
+ "cell_type": "markdown",
1302
+ "metadata": {
1303
+ "id": "029ed965"
1304
+ },
1305
+ "source": [
1306
+ "## Gradio Interface for Phi-2 Chat"
1307
+ ]
1308
+ },
1309
+ {
1310
+ "cell_type": "code",
1311
+ "metadata": {
1312
+ "id": "b8b69d12"
1313
+ },
1314
+ "source": [
1315
+ "# Install Gradio library\n",
1316
+ "!pip install gradio -q"
1317
+ ],
1318
+ "execution_count": 27,
1319
+ "outputs": []
1320
+ },
1321
+ {
1322
+ "cell_type": "code",
1323
+ "metadata": {
1324
+ "colab": {
1325
+ "base_uri": "https://localhost:8080/",
1326
+ "height": 113,
1327
+ "referenced_widgets": [
1328
+ "844da948344e4421b32fa41a679fbdb7",
1329
+ "012adaa5fd314a589e7c67e381a26c2c",
1330
+ "dea346540d084b5c89d96b992c11c30e",
1331
+ "a82b849d29f64d878cd87cba3851b80b",
1332
+ "fe5a48f5cb2743319c5fcd38a494ff2c",
1333
+ "098dee5390834dba9557964ccde15819",
1334
+ "8fda24ae999c4da29f2282b7b687d147",
1335
+ "4d9edf9c343d4fc4a6381bba2d25ac4b",
1336
+ "4c77a8efb23a4a44ba22aedcee5e6f16",
1337
+ "7ce7515d20fb4c06a27da6f45e0210d3",
1338
+ "0daa08754c274d51ac35ef34e3a9457d"
1339
+ ]
1340
+ },
1341
+ "id": "b5a619ac",
1342
+ "outputId": "7c85a144-3652-4541-ded7-dce03c49b549"
1343
+ },
1344
+ "source": [
1345
+ "import gradio as gr\n",
1346
+ "from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM, AutoConfig\n",
1347
+ "import torch\n",
1348
+ "\n",
1349
+ "print(\"Loading Phi-2 model and tokenizer...\")\n",
1350
+ "\n",
1351
+ "# Load tokenizer first\n",
1352
+ "tokenizer = AutoTokenizer.from_pretrained(\"microsoft/phi-2\", trust_remote_code=True)\n",
1353
+ "\n",
1354
+ "# Set pad_token for tokenizer using eos_token\n",
1355
+ "tokenizer.pad_token = tokenizer.eos_token\n",
1356
+ "\n",
1357
+ "# Load model configuration separately to ensure pad_token_id is set before model initialization\n",
1358
+ "config = AutoConfig.from_pretrained(\"microsoft/phi-2\", trust_remote_code=True)\n",
1359
+ "\n",
1360
+ "# Explicitly set pad_token_id in the config, as Phi-2's config might not have it by default\n",
1361
+ "# The model's internal structure expects this attribute to be present.\n",
1362
+ "config.pad_token_id = tokenizer.eos_token_id\n",
1363
+ "\n",
1364
+ "model = AutoModelForCausalLM.from_pretrained(\n",
1365
+ " \"microsoft/phi-2\",\n",
1366
+ " config=config, # Pass the modified config here\n",
1367
+ " trust_remote_code=True,\n",
1368
+ " torch_dtype=torch.float16\n",
1369
+ ")\n",
1370
+ "\n",
1371
+ "# Check for GPU and move model if available\n",
1372
+ "if torch.cuda.is_available():\n",
1373
+ " model.to('cuda')\n",
1374
+ " print(\"Model moved to GPU.\")\n",
1375
+ "else:\n",
1376
+ " print(\"GPU not available, model will run on CPU.\")\n",
1377
+ "\n",
1378
+ "# Create a text generation pipeline and rename it to avoid conflict\n",
1379
+ "text_generator_pipeline = pipeline(\"text-generation\", model=model, tokenizer=tokenizer, device=0 if torch.cuda.is_available() else -1)\n",
1380
+ "\n",
1381
+ "print(\"Phi-2 model loaded successfully.\")"
1382
+ ],
1383
+ "execution_count": 28,
1384
+ "outputs": [
1385
+ {
1386
+ "output_type": "stream",
1387
+ "name": "stdout",
1388
+ "text": [
1389
+ "Loading Phi-2 model and tokenizer...\n"
1390
+ ]
1391
+ },
1392
+ {
1393
+ "output_type": "display_data",
1394
+ "data": {
1395
+ "text/plain": [
1396
+ "Loading weights: 0%| | 0/453 [00:00<?, ?it/s]"
1397
+ ],
1398
+ "application/vnd.jupyter.widget-view+json": {
1399
+ "version_major": 2,
1400
+ "version_minor": 0,
1401
+ "model_id": "844da948344e4421b32fa41a679fbdb7"
1402
+ }
1403
+ },
1404
+ "metadata": {}
1405
+ },
1406
+ {
1407
+ "output_type": "stream",
1408
+ "name": "stdout",
1409
+ "text": [
1410
+ "GPU not available, model will run on CPU.\n",
1411
+ "Phi-2 model loaded successfully.\n"
1412
+ ]
1413
+ }
1414
+ ]
1415
+ },
1416
+ {
1417
+ "cell_type": "code",
1418
+ "metadata": {
1419
+ "id": "61f7b058"
1420
+ },
1421
+ "source": [
1422
+ "def predict(message, history):\n",
1423
+ " conversation_history = \"\"\n",
1424
+ " for human, assistant in history:\n",
1425
+ " conversation_history += f\"Human: {human}\\nAssistant: {assistant}\\n\"\n",
1426
+ " conversation_history += f\"Human: {message}\\nAssistant:\"\n",
1427
+ "\n",
1428
+ " outputs = text_generator_pipeline(\n",
1429
+ " conversation_history, # Pass conversation_history directly as a string to the renamed pipeline object\n",
1430
+ " max_new_tokens=200, # Generate up to 200 new tokens\n",
1431
+ " do_sample=True,\n",
1432
+ " temperature=0.7,\n",
1433
+ " top_k=50,\n",
1434
+ " top_p=0.95,\n",
1435
+ " eos_token_id=tokenizer.eos_token_id # Stop generation at end-of-sequence token\n",
1436
+ " )\n",
1437
+ " generated_text = outputs[0]['generated_text']\n",
1438
+ "\n",
1439
+ " # Extract only the assistant's response part\n",
1440
+ " assistant_response = generated_text.split(\"Assistant:\")[-1].strip()\n",
1441
+ " # Remove the last user input from the response if the model repeats it\n",
1442
+ " if assistant_response.startswith(message):\n",
1443
+ " assistant_response = assistant_response[len(message):].strip()\n",
1444
+ "\n",
1445
+ " return assistant_response"
1446
+ ],
1447
+ "execution_count": 29,
1448
+ "outputs": []
1449
+ },
1450
+ {
1451
+ "cell_type": "markdown",
1452
+ "metadata": {
1453
+ "id": "cbdf81f5"
1454
+ },
1455
+ "source": [
1456
+ "Now, let's launch the Gradio chat interface. Click the public URL to interact with the model."
1457
+ ]
1458
+ },
1459
+ {
1460
+ "cell_type": "code",
1461
+ "metadata": {
1462
+ "colab": {
1463
+ "base_uri": "https://localhost:8080/",
1464
+ "height": 1000
1465
+ },
1466
+ "id": "63e656fe",
1467
+ "outputId": "cc1a646b-cc0a-4f68-e309-2ea3660104b8"
1468
+ },
1469
+ "source": [
1470
+ "gr.ChatInterface(\n",
1471
+ " predict,\n",
1472
+ " chatbot=gr.Chatbot(height=500), # Make the chatbot window larger\n",
1473
+ " textbox=gr.Textbox(placeholder=\"Ask me a question\", container=False, scale=7),\n",
1474
+ " title=\"Chat with Phi-2\",\n",
1475
+ " description=\"Interact with the Microsoft Phi-2 model. Ask questions, have conversations, or experiment with its generative capabilities!\",\n",
1476
+ " theme=\"soft\", # A pleasant theme\n",
1477
+ " examples=[\"Tell me a short story.\", \"Explain quantum physics simply.\", \"What is the capital of France?\"],\n",
1478
+ " cache_examples=False\n",
1479
+ ").launch(debug=True, share=True)"
1480
+ ],
1481
+ "execution_count": 36,
1482
+ "outputs": [
1483
+ {
1484
+ "output_type": "stream",
1485
+ "name": "stderr",
1486
+ "text": [
1487
+ "/tmp/ipykernel_3691/638742562.py:3: UserWarning: You have not specified a value for the `type` parameter. Defaulting to the 'tuples' format for chatbot messages, but this is deprecated and will be removed in a future version of Gradio. Please set type='messages' instead, which uses openai-style dictionaries with 'role' and 'content' keys.\n",
1488
+ " chatbot=gr.Chatbot(height=500), # Make the chatbot window larger\n",
1489
+ "/tmp/ipykernel_3691/638742562.py:3: DeprecationWarning: The default value of 'allow_tags' in gr.Chatbot will be changed from False to True in Gradio 6.0. You will need to explicitly set allow_tags=False if you want to disable tags in your chatbot.\n",
1490
+ " chatbot=gr.Chatbot(height=500), # Make the chatbot window larger\n",
1491
+ "/usr/local/lib/python3.12/dist-packages/gradio/chat_interface.py:330: UserWarning: The gr.ChatInterface was not provided with a type, so the type of the gr.Chatbot, 'tuples', will be used.\n",
1492
+ " warnings.warn(\n"
1493
+ ]
1494
+ },
1495
+ {
1496
+ "output_type": "stream",
1497
+ "name": "stdout",
1498
+ "text": [
1499
+ "Colab notebook detected. This cell will run indefinitely so that you can see errors and logs. To turn off, set debug=False in launch().\n",
1500
+ "* Running on public URL: https://65e2f7deee45e031ef.gradio.live\n",
1501
+ "\n",
1502
+ "This share link expires in 1 week. For free permanent hosting and GPU upgrades, run `gradio deploy` from the terminal in the working directory to deploy to Hugging Face Spaces (https://huggingface.co/spaces)\n"
1503
+ ]
1504
+ },
1505
+ {
1506
+ "output_type": "display_data",
1507
+ "data": {
1508
+ "text/plain": [
1509
+ "<IPython.core.display.HTML object>"
1510
+ ],
1511
+ "text/html": [
1512
+ "<div><iframe src=\"https://65e2f7deee45e031ef.gradio.live\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
1513
+ ]
1514
+ },
1515
+ "metadata": {}
1516
+ },
1517
+ {
1518
+ "output_type": "stream",
1519
+ "name": "stderr",
1520
+ "text": [
1521
+ "Both `max_new_tokens` (=200) and `max_length`(=20) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n",
1522
+ "Both `max_new_tokens` (=200) and `max_length`(=20) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n",
1523
+ "Both `max_new_tokens` (=200) and `max_length`(=20) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n",
1524
+ "Both `max_new_tokens` (=200) and `max_length`(=20) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n",
1525
+ "Both `max_new_tokens` (=200) and `max_length`(=20) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n",
1526
+ "Both `max_new_tokens` (=200) and `max_length`(=20) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n",
1527
+ "Both `max_new_tokens` (=200) and `max_length`(=20) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n",
1528
+ "Both `max_new_tokens` (=200) and `max_length`(=20) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n",
1529
+ "Both `max_new_tokens` (=200) and `max_length`(=20) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n",
1530
+ "Both `max_new_tokens` (=200) and `max_length`(=20) seem to have been set. `max_new_tokens` will take precedence. Please refer to the documentation for more information. (https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)\n"
1531
+ ]
1532
+ },
1533
+ {
1534
+ "output_type": "stream",
1535
+ "name": "stdout",
1536
+ "text": [
1537
+ "Keyboard interruption in main thread... closing server.\n"
1538
+ ]
1539
+ },
1540
+ {
1541
+ "output_type": "error",
1542
+ "ename": "KeyboardInterrupt",
1543
+ "evalue": "",
1544
+ "traceback": [
1545
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
1546
+ "\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
1547
+ "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/gradio/blocks.py\u001b[0m in \u001b[0;36mblock_thread\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 3042\u001b[0m \u001b[0;32mwhile\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3043\u001b[0;31m \u001b[0mtime\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msleep\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m0.1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3044\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mKeyboardInterrupt\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mOSError\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
1548
+ "\u001b[0;31mKeyboardInterrupt\u001b[0m: ",
1549
+ "\nDuring handling of the above exception, another exception occurred:\n",
1550
+ "\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
1551
+ "\u001b[0;32m/tmp/ipykernel_3691/638742562.py\u001b[0m in \u001b[0;36m<cell line: 0>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 8\u001b[0m \u001b[0mexamples\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"Tell me a short story.\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"Explain quantum physics simply.\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"What is the capital of France?\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 9\u001b[0m \u001b[0mcache_examples\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 10\u001b[0;31m ).launch(debug=True, share=True)\n\u001b[0m",
1552
+ "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/gradio/blocks.py\u001b[0m in \u001b[0;36mlaunch\u001b[0;34m(self, inline, inbrowser, share, debug, max_threads, auth, auth_message, prevent_thread_lock, show_error, server_name, server_port, height, width, favicon_path, ssl_keyfile, ssl_certfile, ssl_keyfile_password, ssl_verify, quiet, show_api, allowed_paths, blocked_paths, root_path, app_kwargs, state_session_capacity, share_server_address, share_server_protocol, share_server_tls_certificate, auth_dependency, max_file_size, enable_monitoring, strict_cors, node_server_name, node_port, ssr_mode, pwa, mcp_server, _frontend, i18n)\u001b[0m\n\u001b[1;32m 2948\u001b[0m )\n\u001b[1;32m 2949\u001b[0m ):\n\u001b[0;32m-> 2950\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mblock_thread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2951\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2952\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mTupleNoPrint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mserver_app\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlocal_url\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshare_url\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# type: ignore\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
1553
+ "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/gradio/blocks.py\u001b[0m in \u001b[0;36mblock_thread\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 3045\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Keyboard interruption in main thread... closing server.\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3046\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mserver\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3047\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mserver\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mclose\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3048\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mtunnel\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mCURRENT_TUNNELS\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3049\u001b[0m \u001b[0mtunnel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mkill\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
1554
+ "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/gradio/http_server.py\u001b[0m in \u001b[0;36mclose\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 67\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreloader\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstop\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 68\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwatch_thread\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 69\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mthread\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m5\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 70\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 71\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
1555
+ "\u001b[0;32m/usr/lib/python3.12/threading.py\u001b[0m in \u001b[0;36mjoin\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m 1151\u001b[0m \u001b[0;31m# the behavior of a negative timeout isn't documented, but\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1152\u001b[0m \u001b[0;31m# historically .join(timeout=x) for x<0 has acted as if timeout=0\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1153\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_wait_for_tstate_lock\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmax\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1154\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1155\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_wait_for_tstate_lock\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mblock\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtimeout\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
1556
+ "\u001b[0;32m/usr/lib/python3.12/threading.py\u001b[0m in \u001b[0;36m_wait_for_tstate_lock\u001b[0;34m(self, block, timeout)\u001b[0m\n\u001b[1;32m 1167\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1168\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1169\u001b[0;31m \u001b[0;32mif\u001b[0m \u001b[0mlock\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0macquire\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mblock\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtimeout\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1170\u001b[0m \u001b[0mlock\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrelease\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1171\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_stop\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
1557
+ "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
1558
+ ]
1559
+ }
1560
+ ]
1561
+ },
1562
+ {
1563
+ "cell_type": "code",
1564
+ "metadata": {
1565
+ "id": "61f7b008"
1566
+ },
1567
+ "source": [
1568
+ "def predict(message, history):\n",
1569
+ " conversation_history = \"\"\n",
1570
+ " for human, assistant in history:\n",
1571
+ " conversation_history += f\"Human: {human}\\nAssistant: {assistant}\\n\"\n",
1572
+ " conversation_history += f\"Human: {message}\\nAssistant:\"\n",
1573
+ "\n",
1574
+ " outputs = pipe(\n",
1575
+ " conversation_history, # Pass conversation_history directly as a string\n",
1576
+ " max_new_tokens=200, # Generate up to 200 new tokens\n",
1577
+ " do_sample=True,\n",
1578
+ " temperature=0.7,\n",
1579
+ " top_k=50,\n",
1580
+ " top_p=0.95,\n",
1581
+ " eos_token_id=tokenizer.eos_token_id # Stop generation at end-of-sequence token\n",
1582
+ " )\n",
1583
+ " generated_text = outputs[0]['generated_text']\n",
1584
+ "\n",
1585
+ " # Extract only the assistant's response part\n",
1586
+ " assistant_response = generated_text.split(\"Assistant:\")[-1].strip()\n",
1587
+ " # Remove the last user input from the response if the model repeats it\n",
1588
+ " if assistant_response.startswith(message):\n",
1589
+ " assistant_response = assistant_response[len(message):].strip()\n",
1590
+ "\n",
1591
+ " return assistant_response"
1592
+ ],
1593
+ "execution_count": 35,
1594
+ "outputs": []
1595
+ },
1596
+ {
1597
+ "cell_type": "code",
1598
+ "source": [
1599
+ "import os\n",
1600
+ "os.environ['HF_TOKEN'] = 'YOUR_TOKEN_HERE'"
1601
+ ],
1602
+ "metadata": {
1603
+ "id": "leeUFqBD-UF-"
1604
+ },
1605
+ "execution_count": 32,
1606
+ "outputs": []
1607
+ },
1608
+ {
1609
+ "cell_type": "code",
1610
+ "source": [
1611
+ "import os\n",
1612
+ "from huggingface_hub import InferenceClient\n",
1613
+ "\n",
1614
+ "client = InferenceClient(\n",
1615
+ " provider=\"auto\",\n",
1616
+ " api_key=os.environ[\"HF_TOKEN\"],\n",
1617
+ ")\n",
1618
+ "\n",
1619
+ "completion = client.chat.completions.create(\n",
1620
+ " model=\"microsoft/phi-2\",\n",
1621
+ " messages=\"\\\"Can you please let us know more details about your \\\"\",\n",
1622
+ ")\n",
1623
+ "\n",
1624
+ "print(completion.choices[0].message)"
1625
+ ],
1626
+ "metadata": {
1627
+ "colab": {
1628
+ "base_uri": "https://localhost:8080/",
1629
+ "height": 512
1630
+ },
1631
+ "id": "Zmof51oV-UGN",
1632
+ "outputId": "7cf7ce76-f57b-44ee-9f06-5f3191182924"
1633
+ },
1634
+ "execution_count": 37,
1635
+ "outputs": [
1636
+ {
1637
+ "output_type": "error",
1638
+ "ename": "ValueError",
1639
+ "evalue": "Cannot select auto-router when using non-Hugging Face API key.",
1640
+ "traceback": [
1641
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
1642
+ "\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)",
1643
+ "\u001b[0;32m/tmp/ipykernel_3691/2505081652.py\u001b[0m in \u001b[0;36m<cell line: 0>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 7\u001b[0m )\n\u001b[1;32m 8\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 9\u001b[0;31m completion = client.chat.completions.create(\n\u001b[0m\u001b[1;32m 10\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"microsoft/phi-2\"\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 11\u001b[0m \u001b[0mmessages\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"\\\"Can you please let us know more details about your \\\"\"\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
1644
+ "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/huggingface_hub/inference/_client.py\u001b[0m in \u001b[0;36mchat_completion\u001b[0;34m(self, messages, model, stream, frequency_penalty, logit_bias, logprobs, max_tokens, n, presence_penalty, response_format, seed, stop, stream_options, temperature, tool_choice, tool_prompt, tools, top_logprobs, top_p, extra_body)\u001b[0m\n\u001b[1;32m 920\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mextra_body\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0;34m{\u001b[0m\u001b[0;34m}\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 921\u001b[0m }\n\u001b[0;32m--> 922\u001b[0;31m request_parameters = provider_helper.prepare_request(\n\u001b[0m\u001b[1;32m 923\u001b[0m \u001b[0minputs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmessages\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 924\u001b[0m \u001b[0mparameters\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mparameters\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
1645
+ "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/huggingface_hub/inference/_providers/_common.py\u001b[0m in \u001b[0;36mprepare_request\u001b[0;34m(self, inputs, parameters, headers, model, api_key, extra_payload)\u001b[0m\n\u001b[1;32m 100\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 101\u001b[0m \u001b[0;31m# routed URL if HF token, or direct URL (to customize in '_prepare_route' in subclasses)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 102\u001b[0;31m \u001b[0murl\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_prepare_url\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mapi_key\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mprovider_mapping_info\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mprovider_id\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 103\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 104\u001b[0m \u001b[0;31m# prepare payload (to customize in subclasses)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
1646
+ "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/huggingface_hub/inference/_providers/_common.py\u001b[0m in \u001b[0;36m_prepare_url\u001b[0;34m(self, api_key, mapped_model)\u001b[0m\n\u001b[1;32m 214\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 215\u001b[0m Usually not overwritten in subclasses.\"\"\"\n\u001b[0;32m--> 216\u001b[0;31m \u001b[0mbase_url\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_prepare_base_url\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mapi_key\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 217\u001b[0m \u001b[0mroute\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_prepare_route\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmapped_model\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mapi_key\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 218\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0;34mf\"{base_url.rstrip('/')}/{route.lstrip('/')}\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
1647
+ "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/huggingface_hub/inference/_providers/_common.py\u001b[0m in \u001b[0;36m_prepare_base_url\u001b[0;34m(self, api_key)\u001b[0m\n\u001b[1;32m 300\u001b[0m \u001b[0;31m# Route to the proxy if the api_key is a HF TOKEN\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 301\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mapi_key\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstartswith\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"hf_\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 302\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Cannot select auto-router when using non-Hugging Face API key.\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 303\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 304\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbase_url\u001b[0m \u001b[0;31m# No `/auto` suffix in the URL\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
1648
+ "\u001b[0;31mValueError\u001b[0m: Cannot select auto-router when using non-Hugging Face API key."
1649
+ ]
1650
+ }
1651
+ ]
1652
+ }
1653
+ ]
1654
+ }