Hugging Face's logo

zeromodels
/
metaclip2_worldwide_m16_224

Zero-Shot Image Classification
ZeroModels
Keras
PyTorch
JAX
TensorFlow
metaclip2
vision
Model card Files
xet
 Community
IMvision12 commited on
Commit
8ccb86c
·
verified ·
1 Parent(s): 6398536

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. .gitattributes +1 -0
  2. README.md +19 -0
  3. model.weights.json +602 -0
  4. model_00000.weights.h5 +3 -0
  5. model_00001.weights.h5 +3 -0
  6. tokenizer.json +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ pipeline_tag: zero-shot-image-classification
3
+ license: cc-by-nc-4.0
4
+ library_name: kerasformers
5
+ tags:
6
+ - keras
7
+ - kerasformers
8
+ - metaclip2
9
+ ---
10
+
11
+ # metaclip2_worldwide_m16_224 (Keras 3)
12
+
13
+ Pure-Keras 3 weights for [kerasformers](https://github.com/IMvision12/KerasFormers), mirrored from the GitHub release. License: `cc-by-nc-4.0`.
14
+
15
+ ```python
16
+ from kerasformers.models.metaclip2 import MetaClip2Model, MetaClip2Tokenizer
17
+ model = MetaClip2Model.from_weights("metaclip2_worldwide_m16_224")
18
+ tokenizer = MetaClip2Tokenizer.from_weights("metaclip2_worldwide_m16_224")
19
+ ```
model.weights.json ADDED
@@ -0,0 +1,602 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 2153410580.25
4
+ },
5
+ "weight_map": {
6
+ "/layers/conv2d/vars": "model_00000.weights.h5",
7
+ "/layers/clip_text_model_embedding/position_embedding/vars": "model_00000.weights.h5",
8
+ "/layers/clip_text_model_embedding/token_embedding/vars": "model_00000.weights.h5",
9
+ "/layers/clip_vision_model_embedding/vars": "model_00000.weights.h5",
10
+ "/layers/clip_vision_model_embedding/position_embs/vars": [
11
+ "model_00000.weights.h5"
12
+ ],
13
+ "/layers/layer_normalization/vars": [
14
+ "model_00000.weights.h5"
15
+ ],
16
+ "/layers/layer_normalization_1/vars": [
17
+ "model_00000.weights.h5"
18
+ ],
19
+ "/layers/clip_attention/k_proj/vars": [
20
+ "model_00000.weights.h5"
21
+ ],
22
+ "/layers/clip_attention/out_proj/vars": [
23
+ "model_00000.weights.h5"
24
+ ],
25
+ "/layers/clip_attention/q_proj/vars": [
26
+ "model_00000.weights.h5"
27
+ ],
28
+ "/layers/clip_attention/v_proj/vars": [
29
+ "model_00000.weights.h5"
30
+ ],
31
+ "/layers/layer_normalization_2/vars": [
32
+ "model_00000.weights.h5"
33
+ ],
34
+ "/layers/clip_attention_1/k_proj/vars": [
35
+ "model_00000.weights.h5"
36
+ ],
37
+ "/layers/clip_attention_1/out_proj/vars": [
38
+ "model_00000.weights.h5"
39
+ ],
40
+ "/layers/clip_attention_1/q_proj/vars": [
41
+ "model_00000.weights.h5"
42
+ ],
43
+ "/layers/clip_attention_1/v_proj/vars": [
44
+ "model_00000.weights.h5"
45
+ ],
46
+ "/layers/layer_normalization_3/vars": [
47
+ "model_00000.weights.h5"
48
+ ],
49
+ "/layers/dense/vars": [
50
+ "model_00000.weights.h5"
51
+ ],
52
+ "/layers/layer_normalization_4/vars": [
53
+ "model_00000.weights.h5"
54
+ ],
55
+ "/layers/dense_1/vars": [
56
+ "model_00000.weights.h5"
57
+ ],
58
+ "/layers/dense_2/vars": [
59
+ "model_00000.weights.h5"
60
+ ],
61
+ "/layers/dense_3/vars": [
62
+ "model_00000.weights.h5"
63
+ ],
64
+ "/layers/layer_normalization_5/vars": [
65
+ "model_00000.weights.h5"
66
+ ],
67
+ "/layers/clip_attention_2/k_proj/vars": [
68
+ "model_00000.weights.h5"
69
+ ],
70
+ "/layers/clip_attention_2/out_proj/vars": [
71
+ "model_00000.weights.h5"
72
+ ],
73
+ "/layers/clip_attention_2/q_proj/vars": [
74
+ "model_00000.weights.h5"
75
+ ],
76
+ "/layers/clip_attention_2/v_proj/vars": [
77
+ "model_00000.weights.h5"
78
+ ],
79
+ "/layers/layer_normalization_6/vars": [
80
+ "model_00000.weights.h5"
81
+ ],
82
+ "/layers/clip_attention_3/k_proj/vars": [
83
+ "model_00000.weights.h5"
84
+ ],
85
+ "/layers/clip_attention_3/out_proj/vars": [
86
+ "model_00000.weights.h5"
87
+ ],
88
+ "/layers/clip_attention_3/q_proj/vars": [
89
+ "model_00000.weights.h5"
90
+ ],
91
+ "/layers/clip_attention_3/v_proj/vars": [
92
+ "model_00000.weights.h5"
93
+ ],
94
+ "/layers/layer_normalization_7/vars": [
95
+ "model_00000.weights.h5"
96
+ ],
97
+ "/layers/dense_4/vars": [
98
+ "model_00000.weights.h5"
99
+ ],
100
+ "/layers/layer_normalization_8/vars": [
101
+ "model_00000.weights.h5"
102
+ ],
103
+ "/layers/dense_5/vars": [
104
+ "model_00000.weights.h5"
105
+ ],
106
+ "/layers/dense_6/vars": [
107
+ "model_00000.weights.h5"
108
+ ],
109
+ "/layers/dense_7/vars": [
110
+ "model_00000.weights.h5"
111
+ ],
112
+ "/layers/layer_normalization_9/vars": [
113
+ "model_00000.weights.h5"
114
+ ],
115
+ "/layers/clip_attention_4/k_proj/vars": [
116
+ "model_00000.weights.h5"
117
+ ],
118
+ "/layers/clip_attention_4/out_proj/vars": [
119
+ "model_00000.weights.h5"
120
+ ],
121
+ "/layers/clip_attention_4/q_proj/vars": [
122
+ "model_00000.weights.h5"
123
+ ],
124
+ "/layers/clip_attention_4/v_proj/vars": [
125
+ "model_00000.weights.h5"
126
+ ],
127
+ "/layers/layer_normalization_10/vars": [
128
+ "model_00000.weights.h5"
129
+ ],
130
+ "/layers/clip_attention_5/k_proj/vars": [
131
+ "model_00000.weights.h5"
132
+ ],
133
+ "/layers/clip_attention_5/out_proj/vars": [
134
+ "model_00000.weights.h5"
135
+ ],
136
+ "/layers/clip_attention_5/q_proj/vars": [
137
+ "model_00000.weights.h5"
138
+ ],
139
+ "/layers/clip_attention_5/v_proj/vars": [
140
+ "model_00000.weights.h5"
141
+ ],
142
+ "/layers/layer_normalization_11/vars": [
143
+ "model_00000.weights.h5"
144
+ ],
145
+ "/layers/dense_8/vars": [
146
+ "model_00000.weights.h5"
147
+ ],
148
+ "/layers/layer_normalization_12/vars": [
149
+ "model_00000.weights.h5"
150
+ ],
151
+ "/layers/dense_9/vars": [
152
+ "model_00000.weights.h5"
153
+ ],
154
+ "/layers/dense_10/vars": [
155
+ "model_00000.weights.h5"
156
+ ],
157
+ "/layers/dense_11/vars": [
158
+ "model_00000.weights.h5"
159
+ ],
160
+ "/layers/layer_normalization_13/vars": [
161
+ "model_00000.weights.h5"
162
+ ],
163
+ "/layers/clip_attention_6/k_proj/vars": [
164
+ "model_00000.weights.h5"
165
+ ],
166
+ "/layers/clip_attention_6/out_proj/vars": [
167
+ "model_00000.weights.h5"
168
+ ],
169
+ "/layers/clip_attention_6/q_proj/vars": [
170
+ "model_00000.weights.h5"
171
+ ],
172
+ "/layers/clip_attention_6/v_proj/vars": [
173
+ "model_00000.weights.h5"
174
+ ],
175
+ "/layers/layer_normalization_14/vars": [
176
+ "model_00000.weights.h5"
177
+ ],
178
+ "/layers/clip_attention_7/k_proj/vars": [
179
+ "model_00000.weights.h5"
180
+ ],
181
+ "/layers/clip_attention_7/out_proj/vars": [
182
+ "model_00000.weights.h5"
183
+ ],
184
+ "/layers/clip_attention_7/q_proj/vars": [
185
+ "model_00000.weights.h5"
186
+ ],
187
+ "/layers/clip_attention_7/v_proj/vars": [
188
+ "model_00001.weights.h5"
189
+ ],
190
+ "/layers/layer_normalization_15/vars": [
191
+ "model_00001.weights.h5"
192
+ ],
193
+ "/layers/dense_12/vars": [
194
+ "model_00001.weights.h5"
195
+ ],
196
+ "/layers/layer_normalization_16/vars": [
197
+ "model_00001.weights.h5"
198
+ ],
199
+ "/layers/dense_13/vars": [
200
+ "model_00001.weights.h5"
201
+ ],
202
+ "/layers/dense_14/vars": [
203
+ "model_00001.weights.h5"
204
+ ],
205
+ "/layers/dense_15/vars": [
206
+ "model_00001.weights.h5"
207
+ ],
208
+ "/layers/layer_normalization_17/vars": [
209
+ "model_00001.weights.h5"
210
+ ],
211
+ "/layers/clip_attention_8/k_proj/vars": [
212
+ "model_00001.weights.h5"
213
+ ],
214
+ "/layers/clip_attention_8/out_proj/vars": [
215
+ "model_00001.weights.h5"
216
+ ],
217
+ "/layers/clip_attention_8/q_proj/vars": [
218
+ "model_00001.weights.h5"
219
+ ],
220
+ "/layers/clip_attention_8/v_proj/vars": [
221
+ "model_00001.weights.h5"
222
+ ],
223
+ "/layers/layer_normalization_18/vars": [
224
+ "model_00001.weights.h5"
225
+ ],
226
+ "/layers/clip_attention_9/k_proj/vars": [
227
+ "model_00001.weights.h5"
228
+ ],
229
+ "/layers/clip_attention_9/out_proj/vars": [
230
+ "model_00001.weights.h5"
231
+ ],
232
+ "/layers/clip_attention_9/q_proj/vars": [
233
+ "model_00001.weights.h5"
234
+ ],
235
+ "/layers/clip_attention_9/v_proj/vars": [
236
+ "model_00001.weights.h5"
237
+ ],
238
+ "/layers/layer_normalization_19/vars": [
239
+ "model_00001.weights.h5"
240
+ ],
241
+ "/layers/dense_16/vars": [
242
+ "model_00001.weights.h5"
243
+ ],
244
+ "/layers/layer_normalization_20/vars": [
245
+ "model_00001.weights.h5"
246
+ ],
247
+ "/layers/dense_17/vars": [
248
+ "model_00001.weights.h5"
249
+ ],
250
+ "/layers/dense_18/vars": [
251
+ "model_00001.weights.h5"
252
+ ],
253
+ "/layers/dense_19/vars": [
254
+ "model_00001.weights.h5"
255
+ ],
256
+ "/layers/layer_normalization_21/vars": [
257
+ "model_00001.weights.h5"
258
+ ],
259
+ "/layers/clip_attention_10/k_proj/vars": [
260
+ "model_00001.weights.h5"
261
+ ],
262
+ "/layers/clip_attention_10/out_proj/vars": [
263
+ "model_00001.weights.h5"
264
+ ],
265
+ "/layers/clip_attention_10/q_proj/vars": [
266
+ "model_00001.weights.h5"
267
+ ],
268
+ "/layers/clip_attention_10/v_proj/vars": [
269
+ "model_00001.weights.h5"
270
+ ],
271
+ "/layers/layer_normalization_22/vars": [
272
+ "model_00001.weights.h5"
273
+ ],
274
+ "/layers/clip_attention_11/k_proj/vars": [
275
+ "model_00001.weights.h5"
276
+ ],
277
+ "/layers/clip_attention_11/out_proj/vars": [
278
+ "model_00001.weights.h5"
279
+ ],
280
+ "/layers/clip_attention_11/q_proj/vars": [
281
+ "model_00001.weights.h5"
282
+ ],
283
+ "/layers/clip_attention_11/v_proj/vars": [
284
+ "model_00001.weights.h5"
285
+ ],
286
+ "/layers/layer_normalization_23/vars": [
287
+ "model_00001.weights.h5"
288
+ ],
289
+ "/layers/dense_20/vars": [
290
+ "model_00001.weights.h5"
291
+ ],
292
+ "/layers/layer_normalization_24/vars": [
293
+ "model_00001.weights.h5"
294
+ ],
295
+ "/layers/dense_21/vars": [
296
+ "model_00001.weights.h5"
297
+ ],
298
+ "/layers/dense_22/vars": [
299
+ "model_00001.weights.h5"
300
+ ],
301
+ "/layers/dense_23/vars": [
302
+ "model_00001.weights.h5"
303
+ ],
304
+ "/layers/layer_normalization_25/vars": [
305
+ "model_00001.weights.h5"
306
+ ],
307
+ "/layers/clip_attention_12/k_proj/vars": [
308
+ "model_00001.weights.h5"
309
+ ],
310
+ "/layers/clip_attention_12/out_proj/vars": [
311
+ "model_00001.weights.h5"
312
+ ],
313
+ "/layers/clip_attention_12/q_proj/vars": [
314
+ "model_00001.weights.h5"
315
+ ],
316
+ "/layers/clip_attention_12/v_proj/vars": [
317
+ "model_00001.weights.h5"
318
+ ],
319
+ "/layers/layer_normalization_26/vars": [
320
+ "model_00001.weights.h5"
321
+ ],
322
+ "/layers/clip_attention_13/k_proj/vars": [
323
+ "model_00001.weights.h5"
324
+ ],
325
+ "/layers/clip_attention_13/out_proj/vars": [
326
+ "model_00001.weights.h5"
327
+ ],
328
+ "/layers/clip_attention_13/q_proj/vars": [
329
+ "model_00001.weights.h5"
330
+ ],
331
+ "/layers/clip_attention_13/v_proj/vars": [
332
+ "model_00001.weights.h5"
333
+ ],
334
+ "/layers/layer_normalization_27/vars": [
335
+ "model_00001.weights.h5"
336
+ ],
337
+ "/layers/dense_24/vars": [
338
+ "model_00001.weights.h5"
339
+ ],
340
+ "/layers/layer_normalization_28/vars": [
341
+ "model_00001.weights.h5"
342
+ ],
343
+ "/layers/dense_25/vars": [
344
+ "model_00001.weights.h5"
345
+ ],
346
+ "/layers/dense_26/vars": [
347
+ "model_00001.weights.h5"
348
+ ],
349
+ "/layers/dense_27/vars": [
350
+ "model_00001.weights.h5"
351
+ ],
352
+ "/layers/layer_normalization_29/vars": [
353
+ "model_00001.weights.h5"
354
+ ],
355
+ "/layers/clip_attention_14/k_proj/vars": [
356
+ "model_00001.weights.h5"
357
+ ],
358
+ "/layers/clip_attention_14/out_proj/vars": [
359
+ "model_00001.weights.h5"
360
+ ],
361
+ "/layers/clip_attention_14/q_proj/vars": [
362
+ "model_00001.weights.h5"
363
+ ],
364
+ "/layers/clip_attention_14/v_proj/vars": [
365
+ "model_00001.weights.h5"
366
+ ],
367
+ "/layers/layer_normalization_30/vars": [
368
+ "model_00001.weights.h5"
369
+ ],
370
+ "/layers/clip_attention_15/k_proj/vars": [
371
+ "model_00001.weights.h5"
372
+ ],
373
+ "/layers/clip_attention_15/out_proj/vars": [
374
+ "model_00001.weights.h5"
375
+ ],
376
+ "/layers/clip_attention_15/q_proj/vars": [
377
+ "model_00001.weights.h5"
378
+ ],
379
+ "/layers/clip_attention_15/v_proj/vars": [
380
+ "model_00001.weights.h5"
381
+ ],
382
+ "/layers/layer_normalization_31/vars": [
383
+ "model_00001.weights.h5"
384
+ ],
385
+ "/layers/dense_28/vars": [
386
+ "model_00001.weights.h5"
387
+ ],
388
+ "/layers/layer_normalization_32/vars": [
389
+ "model_00001.weights.h5"
390
+ ],
391
+ "/layers/dense_29/vars": [
392
+ "model_00001.weights.h5"
393
+ ],
394
+ "/layers/dense_30/vars": [
395
+ "model_00001.weights.h5"
396
+ ],
397
+ "/layers/dense_31/vars": [
398
+ "model_00001.weights.h5"
399
+ ],
400
+ "/layers/layer_normalization_33/vars": [
401
+ "model_00001.weights.h5"
402
+ ],
403
+ "/layers/clip_attention_16/k_proj/vars": [
404
+ "model_00001.weights.h5"
405
+ ],
406
+ "/layers/clip_attention_16/out_proj/vars": [
407
+ "model_00001.weights.h5"
408
+ ],
409
+ "/layers/clip_attention_16/q_proj/vars": [
410
+ "model_00001.weights.h5"
411
+ ],
412
+ "/layers/clip_attention_16/v_proj/vars": [
413
+ "model_00001.weights.h5"
414
+ ],
415
+ "/layers/layer_normalization_34/vars": [
416
+ "model_00001.weights.h5"
417
+ ],
418
+ "/layers/clip_attention_17/k_proj/vars": [
419
+ "model_00001.weights.h5"
420
+ ],
421
+ "/layers/clip_attention_17/out_proj/vars": [
422
+ "model_00001.weights.h5"
423
+ ],
424
+ "/layers/clip_attention_17/q_proj/vars": [
425
+ "model_00001.weights.h5"
426
+ ],
427
+ "/layers/clip_attention_17/v_proj/vars": [
428
+ "model_00001.weights.h5"
429
+ ],
430
+ "/layers/layer_normalization_35/vars": [
431
+ "model_00001.weights.h5"
432
+ ],
433
+ "/layers/dense_32/vars": [
434
+ "model_00001.weights.h5"
435
+ ],
436
+ "/layers/layer_normalization_36/vars": [
437
+ "model_00001.weights.h5"
438
+ ],
439
+ "/layers/dense_33/vars": [
440
+ "model_00001.weights.h5"
441
+ ],
442
+ "/layers/dense_34/vars": [
443
+ "model_00001.weights.h5"
444
+ ],
445
+ "/layers/dense_35/vars": [
446
+ "model_00001.weights.h5"
447
+ ],
448
+ "/layers/layer_normalization_37/vars": [
449
+ "model_00001.weights.h5"
450
+ ],
451
+ "/layers/clip_attention_18/k_proj/vars": [
452
+ "model_00001.weights.h5"
453
+ ],
454
+ "/layers/clip_attention_18/out_proj/vars": [
455
+ "model_00001.weights.h5"
456
+ ],
457
+ "/layers/clip_attention_18/q_proj/vars": [
458
+ "model_00001.weights.h5"
459
+ ],
460
+ "/layers/clip_attention_18/v_proj/vars": [
461
+ "model_00001.weights.h5"
462
+ ],
463
+ "/layers/layer_normalization_38/vars": [
464
+ "model_00001.weights.h5"
465
+ ],
466
+ "/layers/clip_attention_19/k_proj/vars": [
467
+ "model_00001.weights.h5"
468
+ ],
469
+ "/layers/clip_attention_19/out_proj/vars": [
470
+ "model_00001.weights.h5"
471
+ ],
472
+ "/layers/clip_attention_19/q_proj/vars": [
473
+ "model_00001.weights.h5"
474
+ ],
475
+ "/layers/clip_attention_19/v_proj/vars": [
476
+ "model_00001.weights.h5"
477
+ ],
478
+ "/layers/layer_normalization_39/vars": [
479
+ "model_00001.weights.h5"
480
+ ],
481
+ "/layers/dense_36/vars": [
482
+ "model_00001.weights.h5"
483
+ ],
484
+ "/layers/layer_normalization_40/vars": [
485
+ "model_00001.weights.h5"
486
+ ],
487
+ "/layers/dense_37/vars": [
488
+ "model_00001.weights.h5"
489
+ ],
490
+ "/layers/dense_38/vars": [
491
+ "model_00001.weights.h5"
492
+ ],
493
+ "/layers/dense_39/vars": [
494
+ "model_00001.weights.h5"
495
+ ],
496
+ "/layers/layer_normalization_41/vars": [
497
+ "model_00001.weights.h5"
498
+ ],
499
+ "/layers/clip_attention_20/k_proj/vars": [
500
+ "model_00001.weights.h5"
501
+ ],
502
+ "/layers/clip_attention_20/out_proj/vars": [
503
+ "model_00001.weights.h5"
504
+ ],
505
+ "/layers/clip_attention_20/q_proj/vars": [
506
+ "model_00001.weights.h5"
507
+ ],
508
+ "/layers/clip_attention_20/v_proj/vars": [
509
+ "model_00001.weights.h5"
510
+ ],
511
+ "/layers/layer_normalization_42/vars": [
512
+ "model_00001.weights.h5"
513
+ ],
514
+ "/layers/clip_attention_21/k_proj/vars": [
515
+ "model_00001.weights.h5"
516
+ ],
517
+ "/layers/clip_attention_21/out_proj/vars": [
518
+ "model_00001.weights.h5"
519
+ ],
520
+ "/layers/clip_attention_21/q_proj/vars": [
521
+ "model_00001.weights.h5"
522
+ ],
523
+ "/layers/clip_attention_21/v_proj/vars": [
524
+ "model_00001.weights.h5"
525
+ ],
526
+ "/layers/layer_normalization_43/vars": [
527
+ "model_00001.weights.h5"
528
+ ],
529
+ "/layers/dense_40/vars": [
530
+ "model_00001.weights.h5"
531
+ ],
532
+ "/layers/layer_normalization_44/vars": [
533
+ "model_00001.weights.h5"
534
+ ],
535
+ "/layers/dense_41/vars": [
536
+ "model_00001.weights.h5"
537
+ ],
538
+ "/layers/dense_42/vars": [
539
+ "model_00001.weights.h5"
540
+ ],
541
+ "/layers/dense_43/vars": [
542
+ "model_00001.weights.h5"
543
+ ],
544
+ "/layers/layer_normalization_45/vars": [
545
+ "model_00001.weights.h5"
546
+ ],
547
+ "/layers/clip_attention_22/k_proj/vars": [
548
+ "model_00001.weights.h5"
549
+ ],
550
+ "/layers/clip_attention_22/out_proj/vars": [
551
+ "model_00001.weights.h5"
552
+ ],
553
+ "/layers/clip_attention_22/q_proj/vars": [
554
+ "model_00001.weights.h5"
555
+ ],
556
+ "/layers/clip_attention_22/v_proj/vars": [
557
+ "model_00001.weights.h5"
558
+ ],
559
+ "/layers/layer_normalization_46/vars": [
560
+ "model_00001.weights.h5"
561
+ ],
562
+ "/layers/clip_attention_23/k_proj/vars": [
563
+ "model_00001.weights.h5"
564
+ ],
565
+ "/layers/clip_attention_23/out_proj/vars": [
566
+ "model_00001.weights.h5"
567
+ ],
568
+ "/layers/clip_attention_23/q_proj/vars": [
569
+ "model_00001.weights.h5"
570
+ ],
571
+ "/layers/clip_attention_23/v_proj/vars": [
572
+ "model_00001.weights.h5"
573
+ ],
574
+ "/layers/layer_normalization_47/vars": [
575
+ "model_00001.weights.h5"
576
+ ],
577
+ "/layers/dense_44/vars": [
578
+ "model_00001.weights.h5"
579
+ ],
580
+ "/layers/layer_normalization_48/vars": [
581
+ "model_00001.weights.h5"
582
+ ],
583
+ "/layers/dense_45/vars": [
584
+ "model_00001.weights.h5"
585
+ ],
586
+ "/layers/dense_46/vars": [
587
+ "model_00001.weights.h5"
588
+ ],
589
+ "/layers/dense_47/vars": [
590
+ "model_00001.weights.h5"
591
+ ],
592
+ "/layers/layer_normalization_49/vars": [
593
+ "model_00001.weights.h5"
594
+ ],
595
+ "/layers/layer_normalization_50/vars": [
596
+ "model_00001.weights.h5"
597
+ ],
598
+ "/layers/dense_48/vars": "model_00001.weights.h5",
599
+ "/layers/dense_49/vars": "model_00001.weights.h5",
600
+ "/layers/clip_logit_scale/vars": "model_00001.weights.h5"
601
+ }
602
+ }
model_00000.weights.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3917d451a32a639bf322b1f7109ecad08f53cbf6bf46d43d973f862984f4397
3
+ size 1931943232
model_00001.weights.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d57a9c15502290311ebc602f2a6364e6fbd562ddd1e03ac4b7964c9ed402a8a
3
+ size 222250068
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9b777521f1113c9a64cdbd2bccbc890c17d7b4d451777cd67839cd45760da83
3
+ size 61333880