Hugging Face's logo

kordelfrance
/
Olfaction-Vision-Language-Embeddings

Robotics
English
embeddings
multimodal
olfaction-vision-language
olfaction
olfactory
scentience
neural-network
graph-neural-network
gnn
vision-language
vision
language
smell
clip
siglip
Model card Files
xet
Community
kordelfrance commited on
Commit
7b355cc
·
verified ·
1 Parent(s): 2ae48c5

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. model/train_colip.py +0 -0
  2. notebooks/colip-inference.ipynb +1440 -0
  3. notebooks/colip-train.py +3 -0
model/train_colip.py ADDED
File without changes
notebooks/colip-inference.ipynb ADDED
@@ -0,0 +1,1440 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "nbformat": 4,
3
+ "nbformat_minor": 0,
4
+ "metadata": {
5
+ "colab": {
6
+ "provenance": [],
7
+ "gpuType": "A100"
8
+ },
9
+ "kernelspec": {
10
+ "name": "python3",
11
+ "display_name": "Python 3"
12
+ },
13
+ "language_info": {
14
+ "name": "python"
15
+ },
16
+ "accelerator": "GPU",
17
+ "widgets": {
18
+ "application/vnd.jupyter.widget-state+json": {
19
+ "223fd629da554a4ea5d92c4ac9ee7015": {
20
+ "model_module": "@jupyter-widgets/controls",
21
+ "model_name": "HBoxModel",
22
+ "model_module_version": "1.5.0",
23
+ "state": {
24
+ "_dom_classes": [],
25
+ "_model_module": "@jupyter-widgets/controls",
26
+ "_model_module_version": "1.5.0",
27
+ "_model_name": "HBoxModel",
28
+ "_view_count": null,
29
+ "_view_module": "@jupyter-widgets/controls",
30
+ "_view_module_version": "1.5.0",
31
+ "_view_name": "HBoxView",
32
+ "box_style": "",
33
+ "children": [
34
+ "IPY_MODEL_6e64f85042bf4ff7bffe79e497f551b0",
35
+ "IPY_MODEL_a423f941a72f4471a931786aa9cf5c94",
36
+ "IPY_MODEL_b31572193fac429aa4968b11aa064b01"
37
+ ],
38
+ "layout": "IPY_MODEL_fda77430f2994fe7aae8037e331e3af9"
39
+ }
40
+ },
41
+ "6e64f85042bf4ff7bffe79e497f551b0": {
42
+ "model_module": "@jupyter-widgets/controls",
43
+ "model_name": "HTMLModel",
44
+ "model_module_version": "1.5.0",
45
+ "state": {
46
+ "_dom_classes": [],
47
+ "_model_module": "@jupyter-widgets/controls",
48
+ "_model_module_version": "1.5.0",
49
+ "_model_name": "HTMLModel",
50
+ "_view_count": null,
51
+ "_view_module": "@jupyter-widgets/controls",
52
+ "_view_module_version": "1.5.0",
53
+ "_view_name": "HTMLView",
54
+ "description": "",
55
+ "description_tooltip": null,
56
+ "layout": "IPY_MODEL_ecdb8b1d43324bf499a4e7730b62aa5a",
57
+ "placeholder": "​",
58
+ "style": "IPY_MODEL_20192df92fbc42a88bd2c5bbc01919a5",
59
+ "value": "config.json: "
60
+ }
61
+ },
62
+ "a423f941a72f4471a931786aa9cf5c94": {
63
+ "model_module": "@jupyter-widgets/controls",
64
+ "model_name": "FloatProgressModel",
65
+ "model_module_version": "1.5.0",
66
+ "state": {
67
+ "_dom_classes": [],
68
+ "_model_module": "@jupyter-widgets/controls",
69
+ "_model_module_version": "1.5.0",
70
+ "_model_name": "FloatProgressModel",
71
+ "_view_count": null,
72
+ "_view_module": "@jupyter-widgets/controls",
73
+ "_view_module_version": "1.5.0",
74
+ "_view_name": "ProgressView",
75
+ "bar_style": "success",
76
+ "description": "",
77
+ "description_tooltip": null,
78
+ "layout": "IPY_MODEL_ef094a0536c5451892124ad9be6167b5",
79
+ "max": 1,
80
+ "min": 0,
81
+ "orientation": "horizontal",
82
+ "style": "IPY_MODEL_34ed901250b34589b4877ba9798b1fb5",
83
+ "value": 1
84
+ }
85
+ },
86
+ "b31572193fac429aa4968b11aa064b01": {
87
+ "model_module": "@jupyter-widgets/controls",
88
+ "model_name": "HTMLModel",
89
+ "model_module_version": "1.5.0",
90
+ "state": {
91
+ "_dom_classes": [],
92
+ "_model_module": "@jupyter-widgets/controls",
93
+ "_model_module_version": "1.5.0",
94
+ "_model_name": "HTMLModel",
95
+ "_view_count": null,
96
+ "_view_module": "@jupyter-widgets/controls",
97
+ "_view_module_version": "1.5.0",
98
+ "_view_name": "HTMLView",
99
+ "description": "",
100
+ "description_tooltip": null,
101
+ "layout": "IPY_MODEL_29298d34157745aaa7a8174602969963",
102
+ "placeholder": "​",
103
+ "style": "IPY_MODEL_45f8a7e85af145a785f3a500973891a3",
104
+ "value": " 4.19k/? [00:00<00:00, 481kB/s]"
105
+ }
106
+ },
107
+ "fda77430f2994fe7aae8037e331e3af9": {
108
+ "model_module": "@jupyter-widgets/base",
109
+ "model_name": "LayoutModel",
110
+ "model_module_version": "1.2.0",
111
+ "state": {
112
+ "_model_module": "@jupyter-widgets/base",
113
+ "_model_module_version": "1.2.0",
114
+ "_model_name": "LayoutModel",
115
+ "_view_count": null,
116
+ "_view_module": "@jupyter-widgets/base",
117
+ "_view_module_version": "1.2.0",
118
+ "_view_name": "LayoutView",
119
+ "align_content": null,
120
+ "align_items": null,
121
+ "align_self": null,
122
+ "border": null,
123
+ "bottom": null,
124
+ "display": null,
125
+ "flex": null,
126
+ "flex_flow": null,
127
+ "grid_area": null,
128
+ "grid_auto_columns": null,
129
+ "grid_auto_flow": null,
130
+ "grid_auto_rows": null,
131
+ "grid_column": null,
132
+ "grid_gap": null,
133
+ "grid_row": null,
134
+ "grid_template_areas": null,
135
+ "grid_template_columns": null,
136
+ "grid_template_rows": null,
137
+ "height": null,
138
+ "justify_content": null,
139
+ "justify_items": null,
140
+ "left": null,
141
+ "margin": null,
142
+ "max_height": null,
143
+ "max_width": null,
144
+ "min_height": null,
145
+ "min_width": null,
146
+ "object_fit": null,
147
+ "object_position": null,
148
+ "order": null,
149
+ "overflow": null,
150
+ "overflow_x": null,
151
+ "overflow_y": null,
152
+ "padding": null,
153
+ "right": null,
154
+ "top": null,
155
+ "visibility": null,
156
+ "width": null
157
+ }
158
+ },
159
+ "ecdb8b1d43324bf499a4e7730b62aa5a": {
160
+ "model_module": "@jupyter-widgets/base",
161
+ "model_name": "LayoutModel",
162
+ "model_module_version": "1.2.0",
163
+ "state": {
164
+ "_model_module": "@jupyter-widgets/base",
165
+ "_model_module_version": "1.2.0",
166
+ "_model_name": "LayoutModel",
167
+ "_view_count": null,
168
+ "_view_module": "@jupyter-widgets/base",
169
+ "_view_module_version": "1.2.0",
170
+ "_view_name": "LayoutView",
171
+ "align_content": null,
172
+ "align_items": null,
173
+ "align_self": null,
174
+ "border": null,
175
+ "bottom": null,
176
+ "display": null,
177
+ "flex": null,
178
+ "flex_flow": null,
179
+ "grid_area": null,
180
+ "grid_auto_columns": null,
181
+ "grid_auto_flow": null,
182
+ "grid_auto_rows": null,
183
+ "grid_column": null,
184
+ "grid_gap": null,
185
+ "grid_row": null,
186
+ "grid_template_areas": null,
187
+ "grid_template_columns": null,
188
+ "grid_template_rows": null,
189
+ "height": null,
190
+ "justify_content": null,
191
+ "justify_items": null,
192
+ "left": null,
193
+ "margin": null,
194
+ "max_height": null,
195
+ "max_width": null,
196
+ "min_height": null,
197
+ "min_width": null,
198
+ "object_fit": null,
199
+ "object_position": null,
200
+ "order": null,
201
+ "overflow": null,
202
+ "overflow_x": null,
203
+ "overflow_y": null,
204
+ "padding": null,
205
+ "right": null,
206
+ "top": null,
207
+ "visibility": null,
208
+ "width": null
209
+ }
210
+ },
211
+ "20192df92fbc42a88bd2c5bbc01919a5": {
212
+ "model_module": "@jupyter-widgets/controls",
213
+ "model_name": "DescriptionStyleModel",
214
+ "model_module_version": "1.5.0",
215
+ "state": {
216
+ "_model_module": "@jupyter-widgets/controls",
217
+ "_model_module_version": "1.5.0",
218
+ "_model_name": "DescriptionStyleModel",
219
+ "_view_count": null,
220
+ "_view_module": "@jupyter-widgets/base",
221
+ "_view_module_version": "1.2.0",
222
+ "_view_name": "StyleView",
223
+ "description_width": ""
224
+ }
225
+ },
226
+ "ef094a0536c5451892124ad9be6167b5": {
227
+ "model_module": "@jupyter-widgets/base",
228
+ "model_name": "LayoutModel",
229
+ "model_module_version": "1.2.0",
230
+ "state": {
231
+ "_model_module": "@jupyter-widgets/base",
232
+ "_model_module_version": "1.2.0",
233
+ "_model_name": "LayoutModel",
234
+ "_view_count": null,
235
+ "_view_module": "@jupyter-widgets/base",
236
+ "_view_module_version": "1.2.0",
237
+ "_view_name": "LayoutView",
238
+ "align_content": null,
239
+ "align_items": null,
240
+ "align_self": null,
241
+ "border": null,
242
+ "bottom": null,
243
+ "display": null,
244
+ "flex": null,
245
+ "flex_flow": null,
246
+ "grid_area": null,
247
+ "grid_auto_columns": null,
248
+ "grid_auto_flow": null,
249
+ "grid_auto_rows": null,
250
+ "grid_column": null,
251
+ "grid_gap": null,
252
+ "grid_row": null,
253
+ "grid_template_areas": null,
254
+ "grid_template_columns": null,
255
+ "grid_template_rows": null,
256
+ "height": null,
257
+ "justify_content": null,
258
+ "justify_items": null,
259
+ "left": null,
260
+ "margin": null,
261
+ "max_height": null,
262
+ "max_width": null,
263
+ "min_height": null,
264
+ "min_width": null,
265
+ "object_fit": null,
266
+ "object_position": null,
267
+ "order": null,
268
+ "overflow": null,
269
+ "overflow_x": null,
270
+ "overflow_y": null,
271
+ "padding": null,
272
+ "right": null,
273
+ "top": null,
274
+ "visibility": null,
275
+ "width": "20px"
276
+ }
277
+ },
278
+ "34ed901250b34589b4877ba9798b1fb5": {
279
+ "model_module": "@jupyter-widgets/controls",
280
+ "model_name": "ProgressStyleModel",
281
+ "model_module_version": "1.5.0",
282
+ "state": {
283
+ "_model_module": "@jupyter-widgets/controls",
284
+ "_model_module_version": "1.5.0",
285
+ "_model_name": "ProgressStyleModel",
286
+ "_view_count": null,
287
+ "_view_module": "@jupyter-widgets/base",
288
+ "_view_module_version": "1.2.0",
289
+ "_view_name": "StyleView",
290
+ "bar_color": null,
291
+ "description_width": ""
292
+ }
293
+ },
294
+ "29298d34157745aaa7a8174602969963": {
295
+ "model_module": "@jupyter-widgets/base",
296
+ "model_name": "LayoutModel",
297
+ "model_module_version": "1.2.0",
298
+ "state": {
299
+ "_model_module": "@jupyter-widgets/base",
300
+ "_model_module_version": "1.2.0",
301
+ "_model_name": "LayoutModel",
302
+ "_view_count": null,
303
+ "_view_module": "@jupyter-widgets/base",
304
+ "_view_module_version": "1.2.0",
305
+ "_view_name": "LayoutView",
306
+ "align_content": null,
307
+ "align_items": null,
308
+ "align_self": null,
309
+ "border": null,
310
+ "bottom": null,
311
+ "display": null,
312
+ "flex": null,
313
+ "flex_flow": null,
314
+ "grid_area": null,
315
+ "grid_auto_columns": null,
316
+ "grid_auto_flow": null,
317
+ "grid_auto_rows": null,
318
+ "grid_column": null,
319
+ "grid_gap": null,
320
+ "grid_row": null,
321
+ "grid_template_areas": null,
322
+ "grid_template_columns": null,
323
+ "grid_template_rows": null,
324
+ "height": null,
325
+ "justify_content": null,
326
+ "justify_items": null,
327
+ "left": null,
328
+ "margin": null,
329
+ "max_height": null,
330
+ "max_width": null,
331
+ "min_height": null,
332
+ "min_width": null,
333
+ "object_fit": null,
334
+ "object_position": null,
335
+ "order": null,
336
+ "overflow": null,
337
+ "overflow_x": null,
338
+ "overflow_y": null,
339
+ "padding": null,
340
+ "right": null,
341
+ "top": null,
342
+ "visibility": null,
343
+ "width": null
344
+ }
345
+ },
346
+ "45f8a7e85af145a785f3a500973891a3": {
347
+ "model_module": "@jupyter-widgets/controls",
348
+ "model_name": "DescriptionStyleModel",
349
+ "model_module_version": "1.5.0",
350
+ "state": {
351
+ "_model_module": "@jupyter-widgets/controls",
352
+ "_model_module_version": "1.5.0",
353
+ "_model_name": "DescriptionStyleModel",
354
+ "_view_count": null,
355
+ "_view_module": "@jupyter-widgets/base",
356
+ "_view_module_version": "1.2.0",
357
+ "_view_name": "StyleView",
358
+ "description_width": ""
359
+ }
360
+ },
361
+ "e00e2e153c93415cb0c790f5863d54d1": {
362
+ "model_module": "@jupyter-widgets/controls",
363
+ "model_name": "HBoxModel",
364
+ "model_module_version": "1.5.0",
365
+ "state": {
366
+ "_dom_classes": [],
367
+ "_model_module": "@jupyter-widgets/controls",
368
+ "_model_module_version": "1.5.0",
369
+ "_model_name": "HBoxModel",
370
+ "_view_count": null,
371
+ "_view_module": "@jupyter-widgets/controls",
372
+ "_view_module_version": "1.5.0",
373
+ "_view_name": "HBoxView",
374
+ "box_style": "",
375
+ "children": [
376
+ "IPY_MODEL_e83efa1549434c25876a610196c1ccec",
377
+ "IPY_MODEL_aed3b64d965243e18b175639fc7ae4bb",
378
+ "IPY_MODEL_02c0bcc081ca4ace906bd6a78c12f535"
379
+ ],
380
+ "layout": "IPY_MODEL_3da233a9127045548eb7e7d288e737de"
381
+ }
382
+ },
383
+ "e83efa1549434c25876a610196c1ccec": {
384
+ "model_module": "@jupyter-widgets/controls",
385
+ "model_name": "HTMLModel",
386
+ "model_module_version": "1.5.0",
387
+ "state": {
388
+ "_dom_classes": [],
389
+ "_model_module": "@jupyter-widgets/controls",
390
+ "_model_module_version": "1.5.0",
391
+ "_model_name": "HTMLModel",
392
+ "_view_count": null,
393
+ "_view_module": "@jupyter-widgets/controls",
394
+ "_view_module_version": "1.5.0",
395
+ "_view_name": "HTMLView",
396
+ "description": "",
397
+ "description_tooltip": null,
398
+ "layout": "IPY_MODEL_8c4c489272b54a3e87291136cedc3b56",
399
+ "placeholder": "​",
400
+ "style": "IPY_MODEL_017bcd4342b94ea8b28cdfeb6cd4cb69",
401
+ "value": "pytorch_model.bin: 100%"
402
+ }
403
+ },
404
+ "aed3b64d965243e18b175639fc7ae4bb": {
405
+ "model_module": "@jupyter-widgets/controls",
406
+ "model_name": "FloatProgressModel",
407
+ "model_module_version": "1.5.0",
408
+ "state": {
409
+ "_dom_classes": [],
410
+ "_model_module": "@jupyter-widgets/controls",
411
+ "_model_module_version": "1.5.0",
412
+ "_model_name": "FloatProgressModel",
413
+ "_view_count": null,
414
+ "_view_module": "@jupyter-widgets/controls",
415
+ "_view_module_version": "1.5.0",
416
+ "_view_name": "ProgressView",
417
+ "bar_style": "success",
418
+ "description": "",
419
+ "description_tooltip": null,
420
+ "layout": "IPY_MODEL_83c0aa9c35574cd3bf685d17038e6db2",
421
+ "max": 605247071,
422
+ "min": 0,
423
+ "orientation": "horizontal",
424
+ "style": "IPY_MODEL_b1433237d5ee478e89fc8f9dca90b212",
425
+ "value": 605247071
426
+ }
427
+ },
428
+ "02c0bcc081ca4ace906bd6a78c12f535": {
429
+ "model_module": "@jupyter-widgets/controls",
430
+ "model_name": "HTMLModel",
431
+ "model_module_version": "1.5.0",
432
+ "state": {
433
+ "_dom_classes": [],
434
+ "_model_module": "@jupyter-widgets/controls",
435
+ "_model_module_version": "1.5.0",
436
+ "_model_name": "HTMLModel",
437
+ "_view_count": null,
438
+ "_view_module": "@jupyter-widgets/controls",
439
+ "_view_module_version": "1.5.0",
440
+ "_view_name": "HTMLView",
441
+ "description": "",
442
+ "description_tooltip": null,
443
+ "layout": "IPY_MODEL_7e0de4dd998146fe86b943bbc9a92733",
444
+ "placeholder": "​",
445
+ "style": "IPY_MODEL_0dddf5988a3646fda9d38367b322da4d",
446
+ "value": " 605M/605M [00:03<00:00, 346MB/s]"
447
+ }
448
+ },
449
+ "3da233a9127045548eb7e7d288e737de": {
450
+ "model_module": "@jupyter-widgets/base",
451
+ "model_name": "LayoutModel",
452
+ "model_module_version": "1.2.0",
453
+ "state": {
454
+ "_model_module": "@jupyter-widgets/base",
455
+ "_model_module_version": "1.2.0",
456
+ "_model_name": "LayoutModel",
457
+ "_view_count": null,
458
+ "_view_module": "@jupyter-widgets/base",
459
+ "_view_module_version": "1.2.0",
460
+ "_view_name": "LayoutView",
461
+ "align_content": null,
462
+ "align_items": null,
463
+ "align_self": null,
464
+ "border": null,
465
+ "bottom": null,
466
+ "display": null,
467
+ "flex": null,
468
+ "flex_flow": null,
469
+ "grid_area": null,
470
+ "grid_auto_columns": null,
471
+ "grid_auto_flow": null,
472
+ "grid_auto_rows": null,
473
+ "grid_column": null,
474
+ "grid_gap": null,
475
+ "grid_row": null,
476
+ "grid_template_areas": null,
477
+ "grid_template_columns": null,
478
+ "grid_template_rows": null,
479
+ "height": null,
480
+ "justify_content": null,
481
+ "justify_items": null,
482
+ "left": null,
483
+ "margin": null,
484
+ "max_height": null,
485
+ "max_width": null,
486
+ "min_height": null,
487
+ "min_width": null,
488
+ "object_fit": null,
489
+ "object_position": null,
490
+ "order": null,
491
+ "overflow": null,
492
+ "overflow_x": null,
493
+ "overflow_y": null,
494
+ "padding": null,
495
+ "right": null,
496
+ "top": null,
497
+ "visibility": null,
498
+ "width": null
499
+ }
500
+ },
501
+ "8c4c489272b54a3e87291136cedc3b56": {
502
+ "model_module": "@jupyter-widgets/base",
503
+ "model_name": "LayoutModel",
504
+ "model_module_version": "1.2.0",
505
+ "state": {
506
+ "_model_module": "@jupyter-widgets/base",
507
+ "_model_module_version": "1.2.0",
508
+ "_model_name": "LayoutModel",
509
+ "_view_count": null,
510
+ "_view_module": "@jupyter-widgets/base",
511
+ "_view_module_version": "1.2.0",
512
+ "_view_name": "LayoutView",
513
+ "align_content": null,
514
+ "align_items": null,
515
+ "align_self": null,
516
+ "border": null,
517
+ "bottom": null,
518
+ "display": null,
519
+ "flex": null,
520
+ "flex_flow": null,
521
+ "grid_area": null,
522
+ "grid_auto_columns": null,
523
+ "grid_auto_flow": null,
524
+ "grid_auto_rows": null,
525
+ "grid_column": null,
526
+ "grid_gap": null,
527
+ "grid_row": null,
528
+ "grid_template_areas": null,
529
+ "grid_template_columns": null,
530
+ "grid_template_rows": null,
531
+ "height": null,
532
+ "justify_content": null,
533
+ "justify_items": null,
534
+ "left": null,
535
+ "margin": null,
536
+ "max_height": null,
537
+ "max_width": null,
538
+ "min_height": null,
539
+ "min_width": null,
540
+ "object_fit": null,
541
+ "object_position": null,
542
+ "order": null,
543
+ "overflow": null,
544
+ "overflow_x": null,
545
+ "overflow_y": null,
546
+ "padding": null,
547
+ "right": null,
548
+ "top": null,
549
+ "visibility": null,
550
+ "width": null
551
+ }
552
+ },
553
+ "017bcd4342b94ea8b28cdfeb6cd4cb69": {
554
+ "model_module": "@jupyter-widgets/controls",
555
+ "model_name": "DescriptionStyleModel",
556
+ "model_module_version": "1.5.0",
557
+ "state": {
558
+ "_model_module": "@jupyter-widgets/controls",
559
+ "_model_module_version": "1.5.0",
560
+ "_model_name": "DescriptionStyleModel",
561
+ "_view_count": null,
562
+ "_view_module": "@jupyter-widgets/base",
563
+ "_view_module_version": "1.2.0",
564
+ "_view_name": "StyleView",
565
+ "description_width": ""
566
+ }
567
+ },
568
+ "83c0aa9c35574cd3bf685d17038e6db2": {
569
+ "model_module": "@jupyter-widgets/base",
570
+ "model_name": "LayoutModel",
571
+ "model_module_version": "1.2.0",
572
+ "state": {
573
+ "_model_module": "@jupyter-widgets/base",
574
+ "_model_module_version": "1.2.0",
575
+ "_model_name": "LayoutModel",
576
+ "_view_count": null,
577
+ "_view_module": "@jupyter-widgets/base",
578
+ "_view_module_version": "1.2.0",
579
+ "_view_name": "LayoutView",
580
+ "align_content": null,
581
+ "align_items": null,
582
+ "align_self": null,
583
+ "border": null,
584
+ "bottom": null,
585
+ "display": null,
586
+ "flex": null,
587
+ "flex_flow": null,
588
+ "grid_area": null,
589
+ "grid_auto_columns": null,
590
+ "grid_auto_flow": null,
591
+ "grid_auto_rows": null,
592
+ "grid_column": null,
593
+ "grid_gap": null,
594
+ "grid_row": null,
595
+ "grid_template_areas": null,
596
+ "grid_template_columns": null,
597
+ "grid_template_rows": null,
598
+ "height": null,
599
+ "justify_content": null,
600
+ "justify_items": null,
601
+ "left": null,
602
+ "margin": null,
603
+ "max_height": null,
604
+ "max_width": null,
605
+ "min_height": null,
606
+ "min_width": null,
607
+ "object_fit": null,
608
+ "object_position": null,
609
+ "order": null,
610
+ "overflow": null,
611
+ "overflow_x": null,
612
+ "overflow_y": null,
613
+ "padding": null,
614
+ "right": null,
615
+ "top": null,
616
+ "visibility": null,
617
+ "width": null
618
+ }
619
+ },
620
+ "b1433237d5ee478e89fc8f9dca90b212": {
621
+ "model_module": "@jupyter-widgets/controls",
622
+ "model_name": "ProgressStyleModel",
623
+ "model_module_version": "1.5.0",
624
+ "state": {
625
+ "_model_module": "@jupyter-widgets/controls",
626
+ "_model_module_version": "1.5.0",
627
+ "_model_name": "ProgressStyleModel",
628
+ "_view_count": null,
629
+ "_view_module": "@jupyter-widgets/base",
630
+ "_view_module_version": "1.2.0",
631
+ "_view_name": "StyleView",
632
+ "bar_color": null,
633
+ "description_width": ""
634
+ }
635
+ },
636
+ "7e0de4dd998146fe86b943bbc9a92733": {
637
+ "model_module": "@jupyter-widgets/base",
638
+ "model_name": "LayoutModel",
639
+ "model_module_version": "1.2.0",
640
+ "state": {
641
+ "_model_module": "@jupyter-widgets/base",
642
+ "_model_module_version": "1.2.0",
643
+ "_model_name": "LayoutModel",
644
+ "_view_count": null,
645
+ "_view_module": "@jupyter-widgets/base",
646
+ "_view_module_version": "1.2.0",
647
+ "_view_name": "LayoutView",
648
+ "align_content": null,
649
+ "align_items": null,
650
+ "align_self": null,
651
+ "border": null,
652
+ "bottom": null,
653
+ "display": null,
654
+ "flex": null,
655
+ "flex_flow": null,
656
+ "grid_area": null,
657
+ "grid_auto_columns": null,
658
+ "grid_auto_flow": null,
659
+ "grid_auto_rows": null,
660
+ "grid_column": null,
661
+ "grid_gap": null,
662
+ "grid_row": null,
663
+ "grid_template_areas": null,
664
+ "grid_template_columns": null,
665
+ "grid_template_rows": null,
666
+ "height": null,
667
+ "justify_content": null,
668
+ "justify_items": null,
669
+ "left": null,
670
+ "margin": null,
671
+ "max_height": null,
672
+ "max_width": null,
673
+ "min_height": null,
674
+ "min_width": null,
675
+ "object_fit": null,
676
+ "object_position": null,
677
+ "order": null,
678
+ "overflow": null,
679
+ "overflow_x": null,
680
+ "overflow_y": null,
681
+ "padding": null,
682
+ "right": null,
683
+ "top": null,
684
+ "visibility": null,
685
+ "width": null
686
+ }
687
+ },
688
+ "0dddf5988a3646fda9d38367b322da4d": {
689
+ "model_module": "@jupyter-widgets/controls",
690
+ "model_name": "DescriptionStyleModel",
691
+ "model_module_version": "1.5.0",
692
+ "state": {
693
+ "_model_module": "@jupyter-widgets/controls",
694
+ "_model_module_version": "1.5.0",
695
+ "_model_name": "DescriptionStyleModel",
696
+ "_view_count": null,
697
+ "_view_module": "@jupyter-widgets/base",
698
+ "_view_module_version": "1.2.0",
699
+ "_view_name": "StyleView",
700
+ "description_width": ""
701
+ }
702
+ },
703
+ "00b6df6c5c034199b1eab78b51dcf6ad": {
704
+ "model_module": "@jupyter-widgets/controls",
705
+ "model_name": "HBoxModel",
706
+ "model_module_version": "1.5.0",
707
+ "state": {
708
+ "_dom_classes": [],
709
+ "_model_module": "@jupyter-widgets/controls",
710
+ "_model_module_version": "1.5.0",
711
+ "_model_name": "HBoxModel",
712
+ "_view_count": null,
713
+ "_view_module": "@jupyter-widgets/controls",
714
+ "_view_module_version": "1.5.0",
715
+ "_view_name": "HBoxView",
716
+ "box_style": "",
717
+ "children": [
718
+ "IPY_MODEL_cc0dce6199e94c038903e678fa3ccaba",
719
+ "IPY_MODEL_af20d025ec884ec3812a57b92af74e9c",
720
+ "IPY_MODEL_306e5c358b204eee95935f948d3c3e49"
721
+ ],
722
+ "layout": "IPY_MODEL_1798886e358142048bc0bc25e340566b"
723
+ }
724
+ },
725
+ "cc0dce6199e94c038903e678fa3ccaba": {
726
+ "model_module": "@jupyter-widgets/controls",
727
+ "model_name": "HTMLModel",
728
+ "model_module_version": "1.5.0",
729
+ "state": {
730
+ "_dom_classes": [],
731
+ "_model_module": "@jupyter-widgets/controls",
732
+ "_model_module_version": "1.5.0",
733
+ "_model_name": "HTMLModel",
734
+ "_view_count": null,
735
+ "_view_module": "@jupyter-widgets/controls",
736
+ "_view_module_version": "1.5.0",
737
+ "_view_name": "HTMLView",
738
+ "description": "",
739
+ "description_tooltip": null,
740
+ "layout": "IPY_MODEL_442fb85c972946ef92fe98e35a4c6566",
741
+ "placeholder": "​",
742
+ "style": "IPY_MODEL_e7fc0e67a3c740458cc7ce4ebf3fcba8",
743
+ "value": "model.safetensors: 100%"
744
+ }
745
+ },
746
+ "af20d025ec884ec3812a57b92af74e9c": {
747
+ "model_module": "@jupyter-widgets/controls",
748
+ "model_name": "FloatProgressModel",
749
+ "model_module_version": "1.5.0",
750
+ "state": {
751
+ "_dom_classes": [],
752
+ "_model_module": "@jupyter-widgets/controls",
753
+ "_model_module_version": "1.5.0",
754
+ "_model_name": "FloatProgressModel",
755
+ "_view_count": null,
756
+ "_view_module": "@jupyter-widgets/controls",
757
+ "_view_module_version": "1.5.0",
758
+ "_view_name": "ProgressView",
759
+ "bar_style": "success",
760
+ "description": "",
761
+ "description_tooltip": null,
762
+ "layout": "IPY_MODEL_5572cce8c8a44f718dbf38d0b18abeb5",
763
+ "max": 605157884,
764
+ "min": 0,
765
+ "orientation": "horizontal",
766
+ "style": "IPY_MODEL_bd2b1a63e41949cbb2b34a53e177ea75",
767
+ "value": 605157884
768
+ }
769
+ },
770
+ "306e5c358b204eee95935f948d3c3e49": {
771
+ "model_module": "@jupyter-widgets/controls",
772
+ "model_name": "HTMLModel",
773
+ "model_module_version": "1.5.0",
774
+ "state": {
775
+ "_dom_classes": [],
776
+ "_model_module": "@jupyter-widgets/controls",
777
+ "_model_module_version": "1.5.0",
778
+ "_model_name": "HTMLModel",
779
+ "_view_count": null,
780
+ "_view_module": "@jupyter-widgets/controls",
781
+ "_view_module_version": "1.5.0",
782
+ "_view_name": "HTMLView",
783
+ "description": "",
784
+ "description_tooltip": null,
785
+ "layout": "IPY_MODEL_a59ed417d5b746ff95c9b6c694bc3abb",
786
+ "placeholder": "​",
787
+ "style": "IPY_MODEL_22865f4d771241239b948317bbf60a91",
788
+ "value": " 605M/605M [00:04<00:00, 214MB/s]"
789
+ }
790
+ },
791
+ "1798886e358142048bc0bc25e340566b": {
792
+ "model_module": "@jupyter-widgets/base",
793
+ "model_name": "LayoutModel",
794
+ "model_module_version": "1.2.0",
795
+ "state": {
796
+ "_model_module": "@jupyter-widgets/base",
797
+ "_model_module_version": "1.2.0",
798
+ "_model_name": "LayoutModel",
799
+ "_view_count": null,
800
+ "_view_module": "@jupyter-widgets/base",
801
+ "_view_module_version": "1.2.0",
802
+ "_view_name": "LayoutView",
803
+ "align_content": null,
804
+ "align_items": null,
805
+ "align_self": null,
806
+ "border": null,
807
+ "bottom": null,
808
+ "display": null,
809
+ "flex": null,
810
+ "flex_flow": null,
811
+ "grid_area": null,
812
+ "grid_auto_columns": null,
813
+ "grid_auto_flow": null,
814
+ "grid_auto_rows": null,
815
+ "grid_column": null,
816
+ "grid_gap": null,
817
+ "grid_row": null,
818
+ "grid_template_areas": null,
819
+ "grid_template_columns": null,
820
+ "grid_template_rows": null,
821
+ "height": null,
822
+ "justify_content": null,
823
+ "justify_items": null,
824
+ "left": null,
825
+ "margin": null,
826
+ "max_height": null,
827
+ "max_width": null,
828
+ "min_height": null,
829
+ "min_width": null,
830
+ "object_fit": null,
831
+ "object_position": null,
832
+ "order": null,
833
+ "overflow": null,
834
+ "overflow_x": null,
835
+ "overflow_y": null,
836
+ "padding": null,
837
+ "right": null,
838
+ "top": null,
839
+ "visibility": null,
840
+ "width": null
841
+ }
842
+ },
843
+ "442fb85c972946ef92fe98e35a4c6566": {
844
+ "model_module": "@jupyter-widgets/base",
845
+ "model_name": "LayoutModel",
846
+ "model_module_version": "1.2.0",
847
+ "state": {
848
+ "_model_module": "@jupyter-widgets/base",
849
+ "_model_module_version": "1.2.0",
850
+ "_model_name": "LayoutModel",
851
+ "_view_count": null,
852
+ "_view_module": "@jupyter-widgets/base",
853
+ "_view_module_version": "1.2.0",
854
+ "_view_name": "LayoutView",
855
+ "align_content": null,
856
+ "align_items": null,
857
+ "align_self": null,
858
+ "border": null,
859
+ "bottom": null,
860
+ "display": null,
861
+ "flex": null,
862
+ "flex_flow": null,
863
+ "grid_area": null,
864
+ "grid_auto_columns": null,
865
+ "grid_auto_flow": null,
866
+ "grid_auto_rows": null,
867
+ "grid_column": null,
868
+ "grid_gap": null,
869
+ "grid_row": null,
870
+ "grid_template_areas": null,
871
+ "grid_template_columns": null,
872
+ "grid_template_rows": null,
873
+ "height": null,
874
+ "justify_content": null,
875
+ "justify_items": null,
876
+ "left": null,
877
+ "margin": null,
878
+ "max_height": null,
879
+ "max_width": null,
880
+ "min_height": null,
881
+ "min_width": null,
882
+ "object_fit": null,
883
+ "object_position": null,
884
+ "order": null,
885
+ "overflow": null,
886
+ "overflow_x": null,
887
+ "overflow_y": null,
888
+ "padding": null,
889
+ "right": null,
890
+ "top": null,
891
+ "visibility": null,
892
+ "width": null
893
+ }
894
+ },
895
+ "e7fc0e67a3c740458cc7ce4ebf3fcba8": {
896
+ "model_module": "@jupyter-widgets/controls",
897
+ "model_name": "DescriptionStyleModel",
898
+ "model_module_version": "1.5.0",
899
+ "state": {
900
+ "_model_module": "@jupyter-widgets/controls",
901
+ "_model_module_version": "1.5.0",
902
+ "_model_name": "DescriptionStyleModel",
903
+ "_view_count": null,
904
+ "_view_module": "@jupyter-widgets/base",
905
+ "_view_module_version": "1.2.0",
906
+ "_view_name": "StyleView",
907
+ "description_width": ""
908
+ }
909
+ },
910
+ "5572cce8c8a44f718dbf38d0b18abeb5": {
911
+ "model_module": "@jupyter-widgets/base",
912
+ "model_name": "LayoutModel",
913
+ "model_module_version": "1.2.0",
914
+ "state": {
915
+ "_model_module": "@jupyter-widgets/base",
916
+ "_model_module_version": "1.2.0",
917
+ "_model_name": "LayoutModel",
918
+ "_view_count": null,
919
+ "_view_module": "@jupyter-widgets/base",
920
+ "_view_module_version": "1.2.0",
921
+ "_view_name": "LayoutView",
922
+ "align_content": null,
923
+ "align_items": null,
924
+ "align_self": null,
925
+ "border": null,
926
+ "bottom": null,
927
+ "display": null,
928
+ "flex": null,
929
+ "flex_flow": null,
930
+ "grid_area": null,
931
+ "grid_auto_columns": null,
932
+ "grid_auto_flow": null,
933
+ "grid_auto_rows": null,
934
+ "grid_column": null,
935
+ "grid_gap": null,
936
+ "grid_row": null,
937
+ "grid_template_areas": null,
938
+ "grid_template_columns": null,
939
+ "grid_template_rows": null,
940
+ "height": null,
941
+ "justify_content": null,
942
+ "justify_items": null,
943
+ "left": null,
944
+ "margin": null,
945
+ "max_height": null,
946
+ "max_width": null,
947
+ "min_height": null,
948
+ "min_width": null,
949
+ "object_fit": null,
950
+ "object_position": null,
951
+ "order": null,
952
+ "overflow": null,
953
+ "overflow_x": null,
954
+ "overflow_y": null,
955
+ "padding": null,
956
+ "right": null,
957
+ "top": null,
958
+ "visibility": null,
959
+ "width": null
960
+ }
961
+ },
962
+ "bd2b1a63e41949cbb2b34a53e177ea75": {
963
+ "model_module": "@jupyter-widgets/controls",
964
+ "model_name": "ProgressStyleModel",
965
+ "model_module_version": "1.5.0",
966
+ "state": {
967
+ "_model_module": "@jupyter-widgets/controls",
968
+ "_model_module_version": "1.5.0",
969
+ "_model_name": "ProgressStyleModel",
970
+ "_view_count": null,
971
+ "_view_module": "@jupyter-widgets/base",
972
+ "_view_module_version": "1.2.0",
973
+ "_view_name": "StyleView",
974
+ "bar_color": null,
975
+ "description_width": ""
976
+ }
977
+ },
978
+ "a59ed417d5b746ff95c9b6c694bc3abb": {
979
+ "model_module": "@jupyter-widgets/base",
980
+ "model_name": "LayoutModel",
981
+ "model_module_version": "1.2.0",
982
+ "state": {
983
+ "_model_module": "@jupyter-widgets/base",
984
+ "_model_module_version": "1.2.0",
985
+ "_model_name": "LayoutModel",
986
+ "_view_count": null,
987
+ "_view_module": "@jupyter-widgets/base",
988
+ "_view_module_version": "1.2.0",
989
+ "_view_name": "LayoutView",
990
+ "align_content": null,
991
+ "align_items": null,
992
+ "align_self": null,
993
+ "border": null,
994
+ "bottom": null,
995
+ "display": null,
996
+ "flex": null,
997
+ "flex_flow": null,
998
+ "grid_area": null,
999
+ "grid_auto_columns": null,
1000
+ "grid_auto_flow": null,
1001
+ "grid_auto_rows": null,
1002
+ "grid_column": null,
1003
+ "grid_gap": null,
1004
+ "grid_row": null,
1005
+ "grid_template_areas": null,
1006
+ "grid_template_columns": null,
1007
+ "grid_template_rows": null,
1008
+ "height": null,
1009
+ "justify_content": null,
1010
+ "justify_items": null,
1011
+ "left": null,
1012
+ "margin": null,
1013
+ "max_height": null,
1014
+ "max_width": null,
1015
+ "min_height": null,
1016
+ "min_width": null,
1017
+ "object_fit": null,
1018
+ "object_position": null,
1019
+ "order": null,
1020
+ "overflow": null,
1021
+ "overflow_x": null,
1022
+ "overflow_y": null,
1023
+ "padding": null,
1024
+ "right": null,
1025
+ "top": null,
1026
+ "visibility": null,
1027
+ "width": null
1028
+ }
1029
+ },
1030
+ "22865f4d771241239b948317bbf60a91": {
1031
+ "model_module": "@jupyter-widgets/controls",
1032
+ "model_name": "DescriptionStyleModel",
1033
+ "model_module_version": "1.5.0",
1034
+ "state": {
1035
+ "_model_module": "@jupyter-widgets/controls",
1036
+ "_model_module_version": "1.5.0",
1037
+ "_model_name": "DescriptionStyleModel",
1038
+ "_view_count": null,
1039
+ "_view_module": "@jupyter-widgets/base",
1040
+ "_view_module_version": "1.2.0",
1041
+ "_view_name": "StyleView",
1042
+ "description_width": ""
1043
+ }
1044
+ }
1045
+ }
1046
+ }
1047
+ },
1048
+ "cells": [
1049
+ {
1050
+ "cell_type": "markdown",
1051
+ "source": [
1052
+ "# Olfaction-Vision-Language-Embeddings"
1053
+ ],
1054
+ "metadata": {
1055
+ "id": "SHn5L_NdNL-V"
1056
+ }
1057
+ },
1058
+ {
1059
+ "cell_type": "markdown",
1060
+ "source": [
1061
+ "This is a quick start on loading the olfaction-vision-language models and getting the joint multimodal embeddings from an olfaction-vision data sample."
1062
+ ],
1063
+ "metadata": {
1064
+ "id": "_40H8e0QNCj_"
1065
+ }
1066
+ },
1067
+ {
1068
+ "cell_type": "markdown",
1069
+ "source": [
1070
+ "### Install Libraries"
1071
+ ],
1072
+ "metadata": {
1073
+ "id": "g0qE7ci4M_V6"
1074
+ }
1075
+ },
1076
+ {
1077
+ "cell_type": "code",
1078
+ "execution_count": 1,
1079
+ "metadata": {
1080
+ "id": "cxabQxw9LSzM",
1081
+ "colab": {
1082
+ "base_uri": "https://localhost:8080/"
1083
+ },
1084
+ "outputId": "956b99fd-1cb5-4382-a8b5-bd7ec2df859b"
1085
+ },
1086
+ "outputs": [
1087
+ {
1088
+ "output_type": "stream",
1089
+ "name": "stdout",
1090
+ "text": [
1091
+ "Requirement already satisfied: transformers in /usr/local/lib/python3.12/dist-packages (4.56.1)\n",
1092
+ "Requirement already satisfied: filelock in /usr/local/lib/python3.12/dist-packages (from transformers) (3.19.1)\n",
1093
+ "Requirement already satisfied: huggingface-hub<1.0,>=0.34.0 in /usr/local/lib/python3.12/dist-packages (from transformers) (0.35.0)\n",
1094
+ "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.12/dist-packages (from transformers) (2.0.2)\n",
1095
+ "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.12/dist-packages (from transformers) (25.0)\n",
1096
+ "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.12/dist-packages (from transformers) (6.0.2)\n",
1097
+ "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.12/dist-packages (from transformers) (2024.11.6)\n",
1098
+ "Requirement already satisfied: requests in /usr/local/lib/python3.12/dist-packages (from transformers) (2.32.4)\n",
1099
+ "Requirement already satisfied: tokenizers<=0.23.0,>=0.22.0 in /usr/local/lib/python3.12/dist-packages (from transformers) (0.22.0)\n",
1100
+ "Requirement already satisfied: safetensors>=0.4.3 in /usr/local/lib/python3.12/dist-packages (from transformers) (0.6.2)\n",
1101
+ "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.12/dist-packages (from transformers) (4.67.1)\n",
1102
+ "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub<1.0,>=0.34.0->transformers) (2025.3.0)\n",
1103
+ "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub<1.0,>=0.34.0->transformers) (4.15.0)\n",
1104
+ "Requirement already satisfied: hf-xet<2.0.0,>=1.1.3 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub<1.0,>=0.34.0->transformers) (1.1.10)\n",
1105
+ "Requirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests->transformers) (3.4.3)\n",
1106
+ "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests->transformers) (3.10)\n",
1107
+ "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests->transformers) (2.5.0)\n",
1108
+ "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests->transformers) (2025.8.3)\n",
1109
+ "Requirement already satisfied: safetensors in /usr/local/lib/python3.12/dist-packages (0.6.2)\n"
1110
+ ]
1111
+ }
1112
+ ],
1113
+ "source": [
1114
+ "!pip install transformers\n",
1115
+ "!pip install safetensors"
1116
+ ]
1117
+ },
1118
+ {
1119
+ "cell_type": "markdown",
1120
+ "source": [
1121
+ "### Import and Configure"
1122
+ ],
1123
+ "metadata": {
1124
+ "id": "7HB6A3RDMrQ0"
1125
+ }
1126
+ },
1127
+ {
1128
+ "cell_type": "code",
1129
+ "source": [
1130
+ "import torch\n",
1131
+ "import torch.nn as nn\n",
1132
+ "from safetensors.torch import load_file\n",
1133
+ "from torchvision import transforms\n",
1134
+ "from transformers import CLIPProcessor, CLIPModel\n",
1135
+ "from PIL import Image\n",
1136
+ "\n",
1137
+ "\n",
1138
+ "DEVICE = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
1139
+ "EMBED_DIM = 512 # Embedding dims = 512 for small, 2048 for large\n",
1140
+ "ENCODER_FILE_PATH = f\"./olf_encoder_{EMBED_DIM}.pt\"\n",
1141
+ "GNN_FILE_PATH = f\"./gnn_{EMBED_DIM}.pt\""
1142
+ ],
1143
+ "metadata": {
1144
+ "id": "BHUd6n3bLbqo"
1145
+ },
1146
+ "execution_count": 3,
1147
+ "outputs": []
1148
+ },
1149
+ {
1150
+ "cell_type": "markdown",
1151
+ "source": [
1152
+ "### Embeddings Function"
1153
+ ],
1154
+ "metadata": {
1155
+ "id": "Tad9Pu6PMn9g"
1156
+ }
1157
+ },
1158
+ {
1159
+ "cell_type": "code",
1160
+ "source": [
1161
+ "def get_embeddings(clip_model, olf_encoder, graph_model, image, olf_vec):\n",
1162
+ " \"\"\"\n",
1163
+ " Gets joint olfaction-vision-language embeddings for a given image and olfaction vector.\n",
1164
+ "\n",
1165
+ " :param clip_model: vision-language model\n",
1166
+ " :param olf_encoder: olfactory encoder from aromas/molecules\n",
1167
+ " :param graph_model: cross-modal associator\n",
1168
+ " :param image: PIL image\n",
1169
+ " :param olf_vec: olfaction vector\n",
1170
+ " :return: joint olfaction-vision-language embeddings\n",
1171
+ " \"\"\"\n",
1172
+ " clip_model.eval()\n",
1173
+ " olf_encoder.eval()\n",
1174
+ " graph_model.eval()\n",
1175
+ "\n",
1176
+ " transform = transforms.Compose([\n",
1177
+ " transforms.Resize((224, 224)),\n",
1178
+ " transforms.ToTensor(),\n",
1179
+ " ])\n",
1180
+ "\n",
1181
+ " image_tensor = transform(image).unsqueeze(0).to(DEVICE)\n",
1182
+ " olf_tensor = torch.tensor(olf_vec, dtype=torch.float32).unsqueeze(0).to(DEVICE)\n",
1183
+ "\n",
1184
+ " with torch.no_grad():\n",
1185
+ " vision_embeds = clip_model.get_image_features(pixel_values=image_tensor)\n",
1186
+ " if EMBED_DIM != 768 and EMBED_DIM != 512:\n",
1187
+ " projection = nn.Linear(vision_embeds.shape[-1], EMBED_DIM).to(DEVICE)\n",
1188
+ " vision_embeds = projection(vision_embeds).to(DEVICE)\n",
1189
+ " vision_embeds = vision_embeds.to(DEVICE)\n",
1190
+ " olf_embeds = olf_encoder(olf_tensor).to(DEVICE)\n",
1191
+ " ovl_embeds = graph_model(vision_embeds, olf_embeds).squeeze()\n",
1192
+ "\n",
1193
+ " return ovl_embeds"
1194
+ ],
1195
+ "metadata": {
1196
+ "id": "UzhGG8CzMmBs"
1197
+ },
1198
+ "execution_count": 4,
1199
+ "outputs": []
1200
+ },
1201
+ {
1202
+ "cell_type": "markdown",
1203
+ "source": [
1204
+ "### Get Joint Embeddings from a Data Sample"
1205
+ ],
1206
+ "metadata": {
1207
+ "id": "fQIb0yeiMwRN"
1208
+ }
1209
+ },
1210
+ {
1211
+ "cell_type": "code",
1212
+ "source": [
1213
+ "# Load the models\n",
1214
+ "olf_encoder = torch.jit.load(ENCODER_FILE_PATH)\n",
1215
+ "graph_model = torch.jit.load(GNN_FILE_PATH)\n",
1216
+ "clip_model = CLIPModel.from_pretrained(\"openai/clip-vit-base-patch32\").to(DEVICE)\n",
1217
+ "\n",
1218
+ "# Build example vision-olfaction sample with dummy data\n",
1219
+ "example_image = Image.new('RGB', (224, 224))\n",
1220
+ "example_image.save(f\"/tmp/image_example.jpg\")\n",
1221
+ "example_olf_vec = torch.randn(112)\n",
1222
+ "\n",
1223
+ "# Run inference\n",
1224
+ "embeddings = get_embeddings(\n",
1225
+ " clip_model,\n",
1226
+ " olf_encoder,\n",
1227
+ " graph_model,\n",
1228
+ " example_image,\n",
1229
+ " example_olf_vec\n",
1230
+ ")\n",
1231
+ "print(\"Embeddings\", embeddings)"
1232
+ ],
1233
+ "metadata": {
1234
+ "id": "_U5qqxn8Mibo",
1235
+ "colab": {
1236
+ "base_uri": "https://localhost:8080/",
1237
+ "height": 1000,
1238
+ "referenced_widgets": [
1239
+ "223fd629da554a4ea5d92c4ac9ee7015",
1240
+ "6e64f85042bf4ff7bffe79e497f551b0",
1241
+ "a423f941a72f4471a931786aa9cf5c94",
1242
+ "b31572193fac429aa4968b11aa064b01",
1243
+ "fda77430f2994fe7aae8037e331e3af9",
1244
+ "ecdb8b1d43324bf499a4e7730b62aa5a",
1245
+ "20192df92fbc42a88bd2c5bbc01919a5",
1246
+ "ef094a0536c5451892124ad9be6167b5",
1247
+ "34ed901250b34589b4877ba9798b1fb5",
1248
+ "29298d34157745aaa7a8174602969963",
1249
+ "45f8a7e85af145a785f3a500973891a3",
1250
+ "e00e2e153c93415cb0c790f5863d54d1",
1251
+ "e83efa1549434c25876a610196c1ccec",
1252
+ "aed3b64d965243e18b175639fc7ae4bb",
1253
+ "02c0bcc081ca4ace906bd6a78c12f535",
1254
+ "3da233a9127045548eb7e7d288e737de",
1255
+ "8c4c489272b54a3e87291136cedc3b56",
1256
+ "017bcd4342b94ea8b28cdfeb6cd4cb69",
1257
+ "83c0aa9c35574cd3bf685d17038e6db2",
1258
+ "b1433237d5ee478e89fc8f9dca90b212",
1259
+ "7e0de4dd998146fe86b943bbc9a92733",
1260
+ "0dddf5988a3646fda9d38367b322da4d",
1261
+ "00b6df6c5c034199b1eab78b51dcf6ad",
1262
+ "cc0dce6199e94c038903e678fa3ccaba",
1263
+ "af20d025ec884ec3812a57b92af74e9c",
1264
+ "306e5c358b204eee95935f948d3c3e49",
1265
+ "1798886e358142048bc0bc25e340566b",
1266
+ "442fb85c972946ef92fe98e35a4c6566",
1267
+ "e7fc0e67a3c740458cc7ce4ebf3fcba8",
1268
+ "5572cce8c8a44f718dbf38d0b18abeb5",
1269
+ "bd2b1a63e41949cbb2b34a53e177ea75",
1270
+ "a59ed417d5b746ff95c9b6c694bc3abb",
1271
+ "22865f4d771241239b948317bbf60a91"
1272
+ ]
1273
+ },
1274
+ "outputId": "c73f8e1b-f680-4d0b-a064-e190678afa30"
1275
+ },
1276
+ "execution_count": 5,
1277
+ "outputs": [
1278
+ {
1279
+ "output_type": "display_data",
1280
+ "data": {
1281
+ "text/plain": [
1282
+ "config.json: 0.00B [00:00, ?B/s]"
1283
+ ],
1284
+ "application/vnd.jupyter.widget-view+json": {
1285
+ "version_major": 2,
1286
+ "version_minor": 0,
1287
+ "model_id": "223fd629da554a4ea5d92c4ac9ee7015"
1288
+ }
1289
+ },
1290
+ "metadata": {}
1291
+ },
1292
+ {
1293
+ "output_type": "display_data",
1294
+ "data": {
1295
+ "text/plain": [
1296
+ "pytorch_model.bin: 0%| | 0.00/605M [00:00<?, ?B/s]"
1297
+ ],
1298
+ "application/vnd.jupyter.widget-view+json": {
1299
+ "version_major": 2,
1300
+ "version_minor": 0,
1301
+ "model_id": "e00e2e153c93415cb0c790f5863d54d1"
1302
+ }
1303
+ },
1304
+ "metadata": {}
1305
+ },
1306
+ {
1307
+ "output_type": "stream",
1308
+ "name": "stderr",
1309
+ "text": [
1310
+ "/tmp/ipython-input-3371101550.py:22: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.detach().clone() or sourceTensor.detach().clone().requires_grad_(True), rather than torch.tensor(sourceTensor).\n",
1311
+ " olf_tensor = torch.tensor(olf_vec, dtype=torch.float32).unsqueeze(0).to(DEVICE)\n"
1312
+ ]
1313
+ },
1314
+ {
1315
+ "output_type": "display_data",
1316
+ "data": {
1317
+ "text/plain": [
1318
+ "model.safetensors: 0%| | 0.00/605M [00:00<?, ?B/s]"
1319
+ ],
1320
+ "application/vnd.jupyter.widget-view+json": {
1321
+ "version_major": 2,
1322
+ "version_minor": 0,
1323
+ "model_id": "00b6df6c5c034199b1eab78b51dcf6ad"
1324
+ }
1325
+ },
1326
+ "metadata": {}
1327
+ },
1328
+ {
1329
+ "output_type": "stream",
1330
+ "name": "stdout",
1331
+ "text": [
1332
+ "Embeddings tensor([-1.2382e-02, 2.3777e-02, -9.0558e-03, -2.7979e-02, -5.9549e-03,\n",
1333
+ " 1.4678e-02, 1.2424e-02, 2.2361e-02, 2.6167e-02, 4.0972e-02,\n",
1334
+ " -2.1756e-02, 3.2277e-02, -1.7444e-02, 5.4060e-03, 1.0332e-02,\n",
1335
+ " 5.6603e-02, -1.3966e-02, 7.7477e-03, -1.8678e-03, 9.0651e-03,\n",
1336
+ " 2.6837e-02, 9.8322e-03, 1.3258e-02, -3.7714e-02, -5.1809e-02,\n",
1337
+ " 5.2755e-02, 1.2107e-02, -1.3018e-02, 1.8774e-02, -5.6916e-02,\n",
1338
+ " -2.9328e-02, -2.7885e-02, 1.4422e-03, 2.0761e-02, -2.9871e-02,\n",
1339
+ " 2.7381e-02, 2.2001e-02, -2.1286e-02, 2.1925e-02, -2.4814e-03,\n",
1340
+ " -5.7491e-03, 9.8888e-03, -3.1911e-02, -3.9359e-02, 2.4043e-02,\n",
1341
+ " 2.1701e-02, 6.7535e-04, -3.9431e-02, 3.2242e-02, 3.3601e-02,\n",
1342
+ " 2.4195e-02, 1.9859e-02, 2.0833e-02, -4.2177e-03, -6.6240e-02,\n",
1343
+ " 5.9470e-02, 1.4912e-02, -4.3088e-02, -4.2664e-02, -7.2853e-02,\n",
1344
+ " -4.0203e-02, -2.0882e-02, 2.9648e-02, 1.9767e-02, 4.8396e-02,\n",
1345
+ " -2.9807e-02, 3.1730e-02, -2.0178e-02, 1.2190e-02, 3.3228e-02,\n",
1346
+ " -5.9983e-03, 4.8417e-02, -4.6937e-03, 2.4826e-03, -3.7397e-04,\n",
1347
+ " 5.4107e-02, -4.2169e-02, -1.6809e-02, -1.1600e-02, -9.0205e-03,\n",
1348
+ " -1.3506e-02, -3.4119e-02, 3.3122e-02, -1.7371e-02, -4.5487e-03,\n",
1349
+ " -3.7503e-02, 3.5954e-02, 3.3404e-02, -2.8282e-03, 3.8558e-03,\n",
1350
+ " 5.0639e-03, -3.4529e-02, 1.9940e-03, -1.6765e-02, -1.7187e-02,\n",
1351
+ " -3.2748e-03, 8.9541e-03, 3.8199e-02, -1.3884e-02, -7.5526e-03,\n",
1352
+ " -4.5498e-03, 7.6342e-03, -3.7529e-02, -3.4182e-02, 2.5023e-02,\n",
1353
+ " 3.0976e-02, 3.9224e-02, 2.9111e-02, -1.7261e-02, -4.4526e-02,\n",
1354
+ " -3.5593e-02, 3.7600e-02, -2.4578e-02, 2.5630e-02, -2.5645e-02,\n",
1355
+ " 6.5666e-03, -2.6352e-02, -4.3273e-02, 1.3548e-02, -3.4678e-03,\n",
1356
+ " -1.0264e-03, -4.2819e-02, -7.5583e-03, -3.0166e-02, -2.9065e-02,\n",
1357
+ " -4.2232e-02, 9.9019e-03, 3.9737e-02, 2.5266e-02, -4.4397e-04,\n",
1358
+ " 5.2273e-02, -2.0658e-02, 2.2354e-02, -3.5845e-03, -3.0547e-02,\n",
1359
+ " 1.2285e-02, -2.4526e-02, -2.1744e-02, -6.5099e-03, 3.2656e-02,\n",
1360
+ " -4.7543e-02, 2.8927e-02, -3.9135e-02, 2.9562e-02, 2.8449e-02,\n",
1361
+ " -1.1029e-02, -4.2456e-02, -1.7066e-02, 6.6891e-03, -3.9591e-02,\n",
1362
+ " -2.8447e-02, 6.1454e-02, 6.3333e-03, -1.9346e-02, 3.7102e-02,\n",
1363
+ " -3.1053e-02, -8.0344e-03, 2.0000e-03, 1.0855e-02, 1.8613e-02,\n",
1364
+ " -3.3279e-02, -5.1925e-02, -2.7866e-02, 7.7725e-03, -2.1239e-02,\n",
1365
+ " -4.3440e-02, 9.6087e-03, 4.1832e-02, 3.6421e-02, -6.0077e-02,\n",
1366
+ " -1.9795e-03, 2.7103e-02, 1.8832e-03, -6.6289e-03, 2.3974e-02,\n",
1367
+ " -1.5727e-02, -3.0777e-02, -3.2689e-02, 4.0718e-02, -1.3944e-02,\n",
1368
+ " 4.3132e-02, 5.9605e-03, 1.6858e-02, 4.6465e-02, -2.5641e-02,\n",
1369
+ " 4.5649e-02, 4.6381e-02, -1.8201e-04, 3.5800e-03, 3.1351e-03,\n",
1370
+ " 6.5669e-03, 7.6069e-03, 7.9719e-03, -2.6041e-02, 2.3622e-02,\n",
1371
+ " -2.8072e-02, -2.7961e-02, -2.8523e-02, 3.3419e-02, 5.5684e-03,\n",
1372
+ " 2.3050e-02, 4.0895e-03, 2.0882e-02, 4.3363e-02, -3.0487e-02,\n",
1373
+ " 2.1326e-02, -4.9993e-02, -5.8958e-02, -1.4975e-02, 2.1988e-02,\n",
1374
+ " -9.1418e-03, 4.1744e-02, 1.9009e-02, -6.1899e-03, 2.2247e-02,\n",
1375
+ " -1.4604e-02, -8.4233e-03, 2.3490e-02, -5.1141e-02, -1.1100e-02,\n",
1376
+ " -2.4043e-02, -3.9606e-03, -5.6764e-03, 4.0223e-02, -3.2318e-02,\n",
1377
+ " -6.5682e-03, 8.3425e-03, 3.6913e-03, 4.2698e-02, 3.8317e-02,\n",
1378
+ " -3.7985e-02, -5.4935e-02, -1.2818e-02, -3.6124e-02, -4.1422e-02,\n",
1379
+ " 6.4659e-02, 5.0291e-02, -4.0138e-03, 6.1792e-02, 1.5178e-02,\n",
1380
+ " -3.4059e-02, -2.4185e-02, 2.6992e-02, 3.0114e-02, -4.8037e-02,\n",
1381
+ " -4.7263e-02, -2.9531e-02, -2.3112e-02, 3.5940e-02, -4.2610e-03,\n",
1382
+ " -3.3441e-02, -4.3660e-02, -2.9882e-02, -3.3037e-02, -6.8088e-03,\n",
1383
+ " 4.2448e-02, -3.7456e-02, -2.4145e-02, -4.3904e-03, -5.2699e-02,\n",
1384
+ " 2.6015e-02, 4.7213e-02, 1.5600e-02, -3.9699e-02, 3.0559e-02,\n",
1385
+ " 1.8667e-02, -5.8278e-02, -4.3806e-02, 3.9975e-02, -9.3888e-03,\n",
1386
+ " 2.9018e-02, 6.5261e-03, -2.1493e-02, 2.0437e-02, -1.2037e-02,\n",
1387
+ " -8.7288e-03, 1.2760e-02, 1.9282e-02, 4.9413e-02, 5.9918e-02,\n",
1388
+ " 1.2549e-02, -1.7312e-02, -6.2129e-03, 1.7699e-02, 1.1891e-02,\n",
1389
+ " 4.9743e-02, -2.4807e-03, -1.0995e-02, -1.6377e-02, -1.9123e-02,\n",
1390
+ " 3.1563e-02, 2.2353e-02, -2.1580e-02, -2.2945e-03, 1.1060e-02,\n",
1391
+ " -4.2183e-02, 1.4179e-02, -1.3403e-02, -2.9810e-02, -5.6903e-04,\n",
1392
+ " 4.9318e-03, 1.2199e-02, 2.3815e-02, 3.7348e-02, -1.1329e-02,\n",
1393
+ " 3.4192e-02, 2.4700e-02, -6.9127e-03, -2.9401e-02, 4.9456e-02,\n",
1394
+ " -4.4161e-02, -2.2464e-02, 1.5216e-02, 3.2801e-02, 7.9586e-03,\n",
1395
+ " -2.8726e-02, -2.4531e-02, 9.3998e-04, -1.8076e-02, 2.5756e-02,\n",
1396
+ " 3.5562e-02, 3.9687e-02, -9.6016e-03, 1.9454e-02, -2.7492e-02,\n",
1397
+ " 2.4521e-02, 6.3319e-03, 1.1923e-02, -4.0261e-02, -4.9173e-02,\n",
1398
+ " 1.5397e-02, -1.1105e-02, 3.9296e-03, -4.1732e-02, 3.2394e-03,\n",
1399
+ " 1.6069e-02, -4.7499e-03, 3.7496e-02, 5.5341e-03, -4.7040e-03,\n",
1400
+ " 5.8950e-03, 1.3983e-02, -3.1098e-02, 1.4663e-02, 5.6128e-03,\n",
1401
+ " 3.0729e-02, -2.0301e-02, -1.5031e-02, -3.2706e-02, 5.2713e-03,\n",
1402
+ " 1.0875e-02, -2.1647e-03, -1.2785e-02, 3.1341e-02, -4.1358e-03,\n",
1403
+ " -1.2224e-02, -2.1684e-02, -1.9019e-02, -1.0635e-02, -1.8336e-02,\n",
1404
+ " -4.1044e-02, 6.2476e-02, 1.5445e-02, -1.1915e-02, -2.7653e-02,\n",
1405
+ " 2.9938e-02, -1.7454e-02, -4.0212e-02, -4.8854e-02, -2.9648e-02,\n",
1406
+ " -4.2355e-03, 4.2125e-02, 4.2479e-02, 2.9639e-02, 4.6756e-02,\n",
1407
+ " -3.9440e-02, 1.5966e-02, 4.1328e-02, 6.0198e-03, -2.8606e-03,\n",
1408
+ " -3.4569e-02, 3.8376e-02, -4.4300e-02, -1.1705e-02, 2.4567e-02,\n",
1409
+ " -5.3427e-02, 3.0413e-02, -2.2874e-02, 8.2115e-03, -9.2121e-03,\n",
1410
+ " -1.8470e-02, 1.9797e-02, -1.6544e-02, 3.9609e-02, -2.1346e-02,\n",
1411
+ " -1.1476e-02, -1.4558e-02, -2.0425e-02, -4.0206e-02, 2.7925e-02,\n",
1412
+ " -4.5171e-02, -3.0734e-02, 1.3843e-03, 1.4165e-03, 3.6692e-02,\n",
1413
+ " -1.0316e-02, -8.4574e-03, 9.1044e-03, 6.3539e-03, 5.8177e-02,\n",
1414
+ " -6.0673e-02, 2.0486e-02, 2.1275e-03, 2.1331e-02, -2.9459e-02,\n",
1415
+ " -1.7506e-02, -3.9725e-02, -3.5125e-02, 1.7009e-02, -2.2607e-02,\n",
1416
+ " 2.5613e-02, -1.7191e-02, 2.4924e-02, 1.1381e-02, 5.0210e-02,\n",
1417
+ " 1.6133e-02, -3.4101e-02, 4.3127e-02, -2.6115e-02, -2.4310e-02,\n",
1418
+ " 1.4836e-02, 2.9488e-03, -1.9305e-02, 1.7551e-02, -4.3856e-03,\n",
1419
+ " 2.7736e-03, -3.5622e-02, 2.7643e-02, -1.0981e-02, 2.4715e-02,\n",
1420
+ " -5.5604e-02, 4.1159e-03, 2.6200e-03, 1.7816e-02, -4.0692e-02,\n",
1421
+ " 1.4501e-02, -1.0926e-02, 1.0430e-02, 1.0014e-02, -1.4574e-03,\n",
1422
+ " -2.0643e-02, -4.6965e-05, 2.9224e-02, 2.0517e-02, 1.5342e-02,\n",
1423
+ " -4.6140e-02, 3.6729e-02, -2.8712e-02, -3.4549e-02, 3.6401e-02,\n",
1424
+ " 2.0951e-04, 3.6749e-02, 2.4448e-02, -2.1573e-02, -2.2042e-02,\n",
1425
+ " 1.5533e-02, -3.5143e-02, -1.2829e-03, -1.4106e-02, -7.1603e-03,\n",
1426
+ " 1.9629e-02, 1.5547e-02, -2.0665e-02, -7.8915e-03, -2.2204e-02,\n",
1427
+ " 2.3729e-02, -3.4803e-02, -8.8258e-03, 4.5064e-03, 1.0267e-02,\n",
1428
+ " 3.4312e-02, 4.9433e-03, 1.2649e-02, 2.6544e-02, 4.4002e-02,\n",
1429
+ " 3.2077e-02, -5.1173e-03, 2.9450e-02, -2.0400e-02, -5.0544e-03,\n",
1430
+ " -4.3809e-03, 3.6011e-02, -1.3025e-02, 3.2278e-02, 2.6285e-02,\n",
1431
+ " -4.6947e-02, 2.6550e-02, -1.3451e-02, 4.3941e-02, 2.7320e-02,\n",
1432
+ " 4.8139e-02, 2.0404e-02, -2.0632e-02, -1.2376e-02, -2.7625e-02,\n",
1433
+ " -2.4838e-02, -1.0411e-03, 1.4996e-02, 1.5229e-02, 2.0967e-02,\n",
1434
+ " -2.5330e-02, -2.1693e-02], device='cuda:0')\n"
1435
+ ]
1436
+ }
1437
+ ]
1438
+ }
1439
+ ]
1440
+ }
notebooks/colip-train.py ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ # Full code for replicating model training coming soon.
2
+ # Training data available here: https://huggingface.co/datasets/kordelfrance/olfaction-vision-language-dataset
3
+