diego281010 commited on
Commit
2e28044
·
verified ·
1 Parent(s): 9baeae0

Retira los pesos de SAM 3 (cada uno los descarga de Meta) y el LightGBM de peso entrenado con EMMa (uso solo academico)

Browse files
Files changed (16) hide show
  1. modelos_entrenados/models--facebook--sam3/.no_exist/3c879f39826c281e95690f02c7821c4de09afae7/added_tokens.json +0 -0
  2. modelos_entrenados/models--facebook--sam3/.no_exist/3c879f39826c281e95690f02c7821c4de09afae7/audio_tokenizer_config.json +0 -0
  3. modelos_entrenados/models--facebook--sam3/.no_exist/3c879f39826c281e95690f02c7821c4de09afae7/chat_template.jinja +0 -0
  4. modelos_entrenados/models--facebook--sam3/.no_exist/3c879f39826c281e95690f02c7821c4de09afae7/chat_template.json +0 -0
  5. modelos_entrenados/models--facebook--sam3/.no_exist/3c879f39826c281e95690f02c7821c4de09afae7/preprocessor_config.json +0 -0
  6. modelos_entrenados/models--facebook--sam3/refs/main +0 -1
  7. modelos_entrenados/models--facebook--sam3/snapshots/3c879f39826c281e95690f02c7821c4de09afae7/config.json +0 -896
  8. modelos_entrenados/models--facebook--sam3/snapshots/3c879f39826c281e95690f02c7821c4de09afae7/merges.txt +0 -0
  9. modelos_entrenados/models--facebook--sam3/snapshots/3c879f39826c281e95690f02c7821c4de09afae7/model.safetensors +0 -3
  10. modelos_entrenados/models--facebook--sam3/snapshots/3c879f39826c281e95690f02c7821c4de09afae7/processor_config.json +0 -80
  11. modelos_entrenados/models--facebook--sam3/snapshots/3c879f39826c281e95690f02c7821c4de09afae7/special_tokens_map.json +0 -30
  12. modelos_entrenados/models--facebook--sam3/snapshots/3c879f39826c281e95690f02c7821c4de09afae7/tokenizer.json +0 -0
  13. modelos_entrenados/models--facebook--sam3/snapshots/3c879f39826c281e95690f02c7821c4de09afae7/tokenizer_config.json +0 -33
  14. modelos_entrenados/models--facebook--sam3/snapshots/3c879f39826c281e95690f02c7821c4de09afae7/vocab.json +0 -0
  15. modelos_entrenados/models--facebook--sam3/snapshots/image.png +0 -3
  16. modelos_entrenados/peso/lgbm_peso.joblib +0 -3
modelos_entrenados/models--facebook--sam3/.no_exist/3c879f39826c281e95690f02c7821c4de09afae7/added_tokens.json DELETED
File without changes
modelos_entrenados/models--facebook--sam3/.no_exist/3c879f39826c281e95690f02c7821c4de09afae7/audio_tokenizer_config.json DELETED
File without changes
modelos_entrenados/models--facebook--sam3/.no_exist/3c879f39826c281e95690f02c7821c4de09afae7/chat_template.jinja DELETED
File without changes
modelos_entrenados/models--facebook--sam3/.no_exist/3c879f39826c281e95690f02c7821c4de09afae7/chat_template.json DELETED
File without changes
modelos_entrenados/models--facebook--sam3/.no_exist/3c879f39826c281e95690f02c7821c4de09afae7/preprocessor_config.json DELETED
File without changes
modelos_entrenados/models--facebook--sam3/refs/main DELETED
@@ -1 +0,0 @@
1
- 3c879f39826c281e95690f02c7821c4de09afae7
 
 
modelos_entrenados/models--facebook--sam3/snapshots/3c879f39826c281e95690f02c7821c4de09afae7/config.json DELETED
@@ -1,896 +0,0 @@
1
- {
2
- "architectures": [
3
- "Sam3VideoModel"
4
- ],
5
- "assoc_iou_thresh": 0.1,
6
- "decrease_trk_keep_alive_for_empty_masklets": false,
7
- "det_nms_thresh": 0.1,
8
- "detector_config": {
9
- "detr_decoder_config": {
10
- "_name_or_path": "",
11
- "add_cross_attention": false,
12
- "architectures": null,
13
- "bad_words_ids": null,
14
- "begin_suppress_tokens": null,
15
- "bos_token_id": null,
16
- "box_rpb_mode": "log",
17
- "chunk_size_feed_forward": 0,
18
- "cross_attention_hidden_size": null,
19
- "decoder_start_token_id": null,
20
- "diversity_penalty": 0.0,
21
- "do_sample": false,
22
- "dropout": 0.1,
23
- "dtype": null,
24
- "early_stopping": false,
25
- "encoder_no_repeat_ngram_size": 0,
26
- "eos_token_id": null,
27
- "exponential_decay_length_penalty": null,
28
- "finetuning_task": null,
29
- "forced_bos_token_id": null,
30
- "forced_eos_token_id": null,
31
- "hidden_act": "relu",
32
- "hidden_dropout": 0.0,
33
- "hidden_size": 256,
34
- "id2label": {
35
- "0": "LABEL_0",
36
- "1": "LABEL_1"
37
- },
38
- "initializer_range": 0.02,
39
- "intermediate_size": 2048,
40
- "is_decoder": false,
41
- "is_encoder_decoder": false,
42
- "label2id": {
43
- "LABEL_0": 0,
44
- "LABEL_1": 1
45
- },
46
- "layer_norm_eps": 1e-06,
47
- "length_penalty": 1.0,
48
- "max_length": 20,
49
- "min_length": 0,
50
- "model_type": "sam3_detr_decoder",
51
- "no_repeat_ngram_size": 0,
52
- "num_attention_heads": 8,
53
- "num_beam_groups": 1,
54
- "num_beams": 1,
55
- "num_layers": 6,
56
- "num_queries": 200,
57
- "num_return_sequences": 1,
58
- "output_attentions": false,
59
- "output_hidden_states": false,
60
- "output_scores": false,
61
- "pad_token_id": null,
62
- "prefix": null,
63
- "problem_type": null,
64
- "remove_invalid_values": false,
65
- "repetition_penalty": 1.0,
66
- "return_dict": true,
67
- "return_dict_in_generate": false,
68
- "sep_token_id": null,
69
- "suppress_tokens": null,
70
- "task_specific_params": null,
71
- "temperature": 1.0,
72
- "tie_encoder_decoder": false,
73
- "tie_word_embeddings": true,
74
- "tokenizer_class": null,
75
- "top_k": 50,
76
- "top_p": 1.0,
77
- "typical_p": 1.0,
78
- "use_presence_token": true
79
- },
80
- "detr_encoder_config": {
81
- "_name_or_path": "",
82
- "add_cross_attention": false,
83
- "architectures": null,
84
- "bad_words_ids": null,
85
- "begin_suppress_tokens": null,
86
- "bos_token_id": null,
87
- "chunk_size_feed_forward": 0,
88
- "cross_attention_hidden_size": null,
89
- "decoder_start_token_id": null,
90
- "diversity_penalty": 0.0,
91
- "do_sample": false,
92
- "dropout": 0.1,
93
- "dtype": null,
94
- "early_stopping": false,
95
- "encoder_no_repeat_ngram_size": 0,
96
- "eos_token_id": null,
97
- "exponential_decay_length_penalty": null,
98
- "finetuning_task": null,
99
- "forced_bos_token_id": null,
100
- "forced_eos_token_id": null,
101
- "hidden_act": "relu",
102
- "hidden_dropout": 0.0,
103
- "hidden_size": 256,
104
- "id2label": {
105
- "0": "LABEL_0",
106
- "1": "LABEL_1"
107
- },
108
- "initializer_range": 0.02,
109
- "intermediate_size": 2048,
110
- "is_decoder": false,
111
- "is_encoder_decoder": false,
112
- "label2id": {
113
- "LABEL_0": 0,
114
- "LABEL_1": 1
115
- },
116
- "layer_norm_eps": 1e-06,
117
- "length_penalty": 1.0,
118
- "max_length": 20,
119
- "min_length": 0,
120
- "model_type": "sam3_detr_encoder",
121
- "no_repeat_ngram_size": 0,
122
- "num_attention_heads": 8,
123
- "num_beam_groups": 1,
124
- "num_beams": 1,
125
- "num_layers": 6,
126
- "num_return_sequences": 1,
127
- "output_attentions": false,
128
- "output_hidden_states": false,
129
- "output_scores": false,
130
- "pad_token_id": null,
131
- "prefix": null,
132
- "problem_type": null,
133
- "remove_invalid_values": false,
134
- "repetition_penalty": 1.0,
135
- "return_dict": true,
136
- "return_dict_in_generate": false,
137
- "sep_token_id": null,
138
- "suppress_tokens": null,
139
- "task_specific_params": null,
140
- "temperature": 1.0,
141
- "tie_encoder_decoder": false,
142
- "tie_word_embeddings": true,
143
- "tokenizer_class": null,
144
- "top_k": 50,
145
- "top_p": 1.0,
146
- "typical_p": 1.0
147
- },
148
- "geometry_encoder_config": {
149
- "_name_or_path": "",
150
- "add_cross_attention": false,
151
- "architectures": null,
152
- "bad_words_ids": null,
153
- "begin_suppress_tokens": null,
154
- "bos_token_id": null,
155
- "chunk_size_feed_forward": 0,
156
- "cross_attention_hidden_size": null,
157
- "decoder_start_token_id": null,
158
- "diversity_penalty": 0.0,
159
- "do_sample": false,
160
- "dropout": 0.1,
161
- "dtype": null,
162
- "early_stopping": false,
163
- "encoder_no_repeat_ngram_size": 0,
164
- "eos_token_id": null,
165
- "exponential_decay_length_penalty": null,
166
- "finetuning_task": null,
167
- "forced_bos_token_id": null,
168
- "forced_eos_token_id": null,
169
- "hidden_act": "relu",
170
- "hidden_dropout": 0.0,
171
- "hidden_size": 256,
172
- "id2label": {
173
- "0": "LABEL_0",
174
- "1": "LABEL_1"
175
- },
176
- "initializer_range": 0.02,
177
- "intermediate_size": 2048,
178
- "is_decoder": false,
179
- "is_encoder_decoder": false,
180
- "label2id": {
181
- "LABEL_0": 0,
182
- "LABEL_1": 1
183
- },
184
- "layer_norm_eps": 1e-06,
185
- "length_penalty": 1.0,
186
- "max_length": 20,
187
- "min_length": 0,
188
- "model_type": "sam3_geometry_encoder",
189
- "no_repeat_ngram_size": 0,
190
- "num_attention_heads": 8,
191
- "num_beam_groups": 1,
192
- "num_beams": 1,
193
- "num_layers": 3,
194
- "num_return_sequences": 1,
195
- "output_attentions": false,
196
- "output_hidden_states": false,
197
- "output_scores": false,
198
- "pad_token_id": null,
199
- "prefix": null,
200
- "problem_type": null,
201
- "remove_invalid_values": false,
202
- "repetition_penalty": 1.0,
203
- "return_dict": true,
204
- "return_dict_in_generate": false,
205
- "roi_size": 7,
206
- "sep_token_id": null,
207
- "suppress_tokens": null,
208
- "task_specific_params": null,
209
- "temperature": 1.0,
210
- "tie_encoder_decoder": false,
211
- "tie_word_embeddings": true,
212
- "tokenizer_class": null,
213
- "top_k": 50,
214
- "top_p": 1.0,
215
- "typical_p": 1.0
216
- },
217
- "initializer_range": 0.02,
218
- "mask_decoder_config": {
219
- "_name_or_path": "",
220
- "add_cross_attention": false,
221
- "architectures": null,
222
- "bad_words_ids": null,
223
- "begin_suppress_tokens": null,
224
- "bos_token_id": null,
225
- "chunk_size_feed_forward": 0,
226
- "cross_attention_hidden_size": null,
227
- "decoder_start_token_id": null,
228
- "diversity_penalty": 0.0,
229
- "do_sample": false,
230
- "dropout": 0.0,
231
- "dtype": null,
232
- "early_stopping": false,
233
- "encoder_no_repeat_ngram_size": 0,
234
- "eos_token_id": null,
235
- "exponential_decay_length_penalty": null,
236
- "finetuning_task": null,
237
- "forced_bos_token_id": null,
238
- "forced_eos_token_id": null,
239
- "hidden_size": 256,
240
- "id2label": {
241
- "0": "LABEL_0",
242
- "1": "LABEL_1"
243
- },
244
- "initializer_range": 0.02,
245
- "is_decoder": false,
246
- "is_encoder_decoder": false,
247
- "label2id": {
248
- "LABEL_0": 0,
249
- "LABEL_1": 1
250
- },
251
- "layer_norm_eps": 1e-06,
252
- "length_penalty": 1.0,
253
- "max_length": 20,
254
- "min_length": 0,
255
- "model_type": "sam3_mask_decoder",
256
- "no_repeat_ngram_size": 0,
257
- "num_attention_heads": 8,
258
- "num_beam_groups": 1,
259
- "num_beams": 1,
260
- "num_return_sequences": 1,
261
- "num_upsampling_stages": 3,
262
- "output_attentions": false,
263
- "output_hidden_states": false,
264
- "output_scores": false,
265
- "pad_token_id": null,
266
- "prefix": null,
267
- "problem_type": null,
268
- "remove_invalid_values": false,
269
- "repetition_penalty": 1.0,
270
- "return_dict": true,
271
- "return_dict_in_generate": false,
272
- "sep_token_id": null,
273
- "suppress_tokens": null,
274
- "task_specific_params": null,
275
- "temperature": 1.0,
276
- "tie_encoder_decoder": false,
277
- "tie_word_embeddings": true,
278
- "tokenizer_class": null,
279
- "top_k": 50,
280
- "top_p": 1.0,
281
- "typical_p": 1.0
282
- },
283
- "model_type": "sam3",
284
- "text_config": {
285
- "_name_or_path": "",
286
- "add_cross_attention": false,
287
- "architectures": null,
288
- "attention_dropout": 0.0,
289
- "bad_words_ids": null,
290
- "begin_suppress_tokens": null,
291
- "bos_token_id": 49406,
292
- "chunk_size_feed_forward": 0,
293
- "cross_attention_hidden_size": null,
294
- "decoder_start_token_id": null,
295
- "diversity_penalty": 0.0,
296
- "do_sample": false,
297
- "dtype": null,
298
- "early_stopping": false,
299
- "encoder_no_repeat_ngram_size": 0,
300
- "eos_token_id": 49407,
301
- "exponential_decay_length_penalty": null,
302
- "finetuning_task": null,
303
- "forced_bos_token_id": null,
304
- "forced_eos_token_id": null,
305
- "hidden_act": "gelu",
306
- "hidden_size": 1024,
307
- "id2label": {
308
- "0": "LABEL_0",
309
- "1": "LABEL_1"
310
- },
311
- "initializer_factor": 1.0,
312
- "initializer_range": 0.02,
313
- "intermediate_size": 4096,
314
- "is_decoder": false,
315
- "is_encoder_decoder": false,
316
- "label2id": {
317
- "LABEL_0": 0,
318
- "LABEL_1": 1
319
- },
320
- "layer_norm_eps": 1e-05,
321
- "length_penalty": 1.0,
322
- "max_length": 20,
323
- "max_position_embeddings": 32,
324
- "min_length": 0,
325
- "model_type": "clip_text_model",
326
- "no_repeat_ngram_size": 0,
327
- "num_attention_heads": 16,
328
- "num_beam_groups": 1,
329
- "num_beams": 1,
330
- "num_hidden_layers": 24,
331
- "num_return_sequences": 1,
332
- "output_attentions": false,
333
- "output_hidden_states": false,
334
- "output_scores": false,
335
- "pad_token_id": 1,
336
- "prefix": null,
337
- "problem_type": null,
338
- "projection_dim": 512,
339
- "remove_invalid_values": false,
340
- "repetition_penalty": 1.0,
341
- "return_dict": true,
342
- "return_dict_in_generate": false,
343
- "sep_token_id": null,
344
- "suppress_tokens": null,
345
- "task_specific_params": null,
346
- "temperature": 1.0,
347
- "tie_encoder_decoder": false,
348
- "tie_word_embeddings": true,
349
- "tokenizer_class": null,
350
- "top_k": 50,
351
- "top_p": 1.0,
352
- "typical_p": 1.0,
353
- "vocab_size": 49408
354
- },
355
- "vision_config": {
356
- "_name_or_path": "",
357
- "add_cross_attention": false,
358
- "architectures": null,
359
- "backbone_config": {
360
- "_name_or_path": "",
361
- "add_cross_attention": false,
362
- "architectures": null,
363
- "attention_dropout": 0.0,
364
- "bad_words_ids": null,
365
- "begin_suppress_tokens": null,
366
- "bos_token_id": null,
367
- "chunk_size_feed_forward": 0,
368
- "cross_attention_hidden_size": null,
369
- "decoder_start_token_id": null,
370
- "diversity_penalty": 0.0,
371
- "do_sample": false,
372
- "dtype": null,
373
- "early_stopping": false,
374
- "encoder_no_repeat_ngram_size": 0,
375
- "eos_token_id": null,
376
- "exponential_decay_length_penalty": null,
377
- "finetuning_task": null,
378
- "forced_bos_token_id": null,
379
- "forced_eos_token_id": null,
380
- "global_attn_indexes": [
381
- 7,
382
- 15,
383
- 23,
384
- 31
385
- ],
386
- "hidden_act": "gelu",
387
- "hidden_dropout": 0.0,
388
- "hidden_size": 1024,
389
- "id2label": {
390
- "0": "LABEL_0",
391
- "1": "LABEL_1"
392
- },
393
- "image_size": 1008,
394
- "initializer_range": 0.02,
395
- "intermediate_size": 4736,
396
- "is_decoder": false,
397
- "is_encoder_decoder": false,
398
- "label2id": {
399
- "LABEL_0": 0,
400
- "LABEL_1": 1
401
- },
402
- "layer_norm_eps": 1e-06,
403
- "layer_scale_init_value": null,
404
- "length_penalty": 1.0,
405
- "max_length": 20,
406
- "min_length": 0,
407
- "model_type": "sam3_vit_model",
408
- "no_repeat_ngram_size": 0,
409
- "num_attention_heads": 16,
410
- "num_beam_groups": 1,
411
- "num_beams": 1,
412
- "num_channels": 3,
413
- "num_hidden_layers": 32,
414
- "num_return_sequences": 1,
415
- "output_attentions": false,
416
- "output_hidden_states": false,
417
- "output_scores": false,
418
- "pad_token_id": null,
419
- "patch_size": 14,
420
- "prefix": null,
421
- "pretrain_image_size": 336,
422
- "problem_type": null,
423
- "qkv_bias": true,
424
- "remove_invalid_values": false,
425
- "repetition_penalty": 1.0,
426
- "return_dict": true,
427
- "return_dict_in_generate": false,
428
- "rope_theta": 10000.0,
429
- "sep_token_id": null,
430
- "suppress_tokens": null,
431
- "task_specific_params": null,
432
- "temperature": 1.0,
433
- "tie_encoder_decoder": false,
434
- "tie_word_embeddings": true,
435
- "tokenizer_class": null,
436
- "top_k": 50,
437
- "top_p": 1.0,
438
- "typical_p": 1.0,
439
- "window_size": 24
440
- },
441
- "backbone_feature_sizes": [
442
- [
443
- 288,
444
- 288
445
- ],
446
- [
447
- 144,
448
- 144
449
- ],
450
- [
451
- 72,
452
- 72
453
- ]
454
- ],
455
- "bad_words_ids": null,
456
- "begin_suppress_tokens": null,
457
- "bos_token_id": null,
458
- "chunk_size_feed_forward": 0,
459
- "cross_attention_hidden_size": null,
460
- "decoder_start_token_id": null,
461
- "diversity_penalty": 0.0,
462
- "do_sample": false,
463
- "dtype": null,
464
- "early_stopping": false,
465
- "encoder_no_repeat_ngram_size": 0,
466
- "eos_token_id": null,
467
- "exponential_decay_length_penalty": null,
468
- "finetuning_task": null,
469
- "forced_bos_token_id": null,
470
- "forced_eos_token_id": null,
471
- "fpn_hidden_size": 256,
472
- "fpn_kernel_size": 2,
473
- "fpn_stride": 2,
474
- "hidden_act": "gelu",
475
- "id2label": {
476
- "0": "LABEL_0",
477
- "1": "LABEL_1"
478
- },
479
- "initializer_range": 0.02,
480
- "is_decoder": false,
481
- "is_encoder_decoder": false,
482
- "label2id": {
483
- "LABEL_0": 0,
484
- "LABEL_1": 1
485
- },
486
- "layer_norm_eps": 1e-06,
487
- "length_penalty": 1.0,
488
- "max_length": 20,
489
- "min_length": 0,
490
- "model_type": "sam3_vision_model",
491
- "no_repeat_ngram_size": 0,
492
- "num_beam_groups": 1,
493
- "num_beams": 1,
494
- "num_feature_levels": 3,
495
- "num_return_sequences": 1,
496
- "output_attentions": false,
497
- "output_hidden_states": false,
498
- "output_scores": false,
499
- "pad_token_id": null,
500
- "prefix": null,
501
- "problem_type": null,
502
- "remove_invalid_values": false,
503
- "repetition_penalty": 1.0,
504
- "return_dict": true,
505
- "return_dict_in_generate": false,
506
- "scale_factors": [
507
- 4.0,
508
- 2.0,
509
- 1.0,
510
- 0.5
511
- ],
512
- "sep_token_id": null,
513
- "suppress_tokens": null,
514
- "task_specific_params": null,
515
- "temperature": 1.0,
516
- "tie_encoder_decoder": false,
517
- "tie_word_embeddings": true,
518
- "tokenizer_class": null,
519
- "top_k": 50,
520
- "top_p": 1.0,
521
- "typical_p": 1.0
522
- }
523
- },
524
- "dtype": "float32",
525
- "fill_hole_area": 16,
526
- "high_conf_thresh": 0.8,
527
- "high_iou_thresh": 0.8,
528
- "hotstart_delay": 15,
529
- "hotstart_dup_thresh": 8,
530
- "hotstart_unmatch_thresh": 8,
531
- "init_trk_keep_alive": 30,
532
- "initializer_range": 0.02,
533
- "low_res_mask_size": 288,
534
- "max_num_objects": 10000,
535
- "max_trk_keep_alive": 30,
536
- "min_trk_keep_alive": -1,
537
- "model_type": "sam3_video",
538
- "new_det_thresh": 0.7,
539
- "recondition_every_nth_frame": 16,
540
- "recondition_on_trk_masks": false,
541
- "score_threshold_detection": 0.5,
542
- "suppress_overlapping_based_on_recent_occlusion_threshold": 0.7,
543
- "suppress_unmatched_only_within_hotstart": true,
544
- "tracker_config": {
545
- "enable_occlusion_spatial_embedding": true,
546
- "enable_temporal_pos_encoding_for_object_pointers": true,
547
- "image_size": 1008,
548
- "initializer_range": 0.02,
549
- "mask_decoder_config": {
550
- "_name_or_path": "",
551
- "add_cross_attention": false,
552
- "architectures": null,
553
- "attention_downsample_rate": 2,
554
- "bad_words_ids": null,
555
- "begin_suppress_tokens": null,
556
- "bos_token_id": null,
557
- "chunk_size_feed_forward": 0,
558
- "cross_attention_hidden_size": null,
559
- "decoder_start_token_id": null,
560
- "diversity_penalty": 0.0,
561
- "do_sample": false,
562
- "dtype": null,
563
- "dynamic_multimask_stability_delta": 0.05,
564
- "dynamic_multimask_stability_thresh": 0.98,
565
- "dynamic_multimask_via_stability": true,
566
- "early_stopping": false,
567
- "encoder_no_repeat_ngram_size": 0,
568
- "eos_token_id": null,
569
- "exponential_decay_length_penalty": null,
570
- "finetuning_task": null,
571
- "forced_bos_token_id": null,
572
- "forced_eos_token_id": null,
573
- "hidden_act": "gelu",
574
- "hidden_size": 256,
575
- "id2label": {
576
- "0": "LABEL_0",
577
- "1": "LABEL_1"
578
- },
579
- "iou_head_depth": 3,
580
- "iou_head_hidden_dim": 256,
581
- "is_decoder": false,
582
- "is_encoder_decoder": false,
583
- "label2id": {
584
- "LABEL_0": 0,
585
- "LABEL_1": 1
586
- },
587
- "length_penalty": 1.0,
588
- "max_length": 20,
589
- "min_length": 0,
590
- "mlp_dim": 2048,
591
- "model_type": "",
592
- "no_repeat_ngram_size": 0,
593
- "num_attention_heads": 8,
594
- "num_beam_groups": 1,
595
- "num_beams": 1,
596
- "num_hidden_layers": 2,
597
- "num_multimask_outputs": 3,
598
- "num_return_sequences": 1,
599
- "output_attentions": false,
600
- "output_hidden_states": false,
601
- "output_scores": false,
602
- "pad_token_id": null,
603
- "prefix": null,
604
- "problem_type": null,
605
- "remove_invalid_values": false,
606
- "repetition_penalty": 1.0,
607
- "return_dict": true,
608
- "return_dict_in_generate": false,
609
- "sep_token_id": null,
610
- "suppress_tokens": null,
611
- "task_specific_params": null,
612
- "temperature": 1.0,
613
- "tie_encoder_decoder": false,
614
- "tie_word_embeddings": true,
615
- "tokenizer_class": null,
616
- "top_k": 50,
617
- "top_p": 1.0,
618
- "typical_p": 1.0
619
- },
620
- "mask_downsampler_embed_dim": 256,
621
- "mask_downsampler_hidden_act": "gelu",
622
- "mask_downsampler_kernel_size": 3,
623
- "mask_downsampler_padding": 1,
624
- "mask_downsampler_stride": 2,
625
- "mask_downsampler_total_stride": 16,
626
- "max_cond_frame_num": 4,
627
- "max_object_pointers_in_encoder": 16,
628
- "memory_attention_downsample_rate": 1,
629
- "memory_attention_dropout": 0.1,
630
- "memory_attention_feed_forward_hidden_act": "relu",
631
- "memory_attention_feed_forward_hidden_size": 2048,
632
- "memory_attention_hidden_size": 256,
633
- "memory_attention_num_attention_heads": 1,
634
- "memory_attention_num_layers": 4,
635
- "memory_attention_rope_dropout": 0.1,
636
- "memory_attention_rope_feat_sizes": [
637
- 72,
638
- 72
639
- ],
640
- "memory_attention_rope_theta": 10000,
641
- "memory_encoder_hidden_size": 256,
642
- "memory_encoder_output_channels": 64,
643
- "memory_fuser_embed_dim": 256,
644
- "memory_fuser_hidden_act": "gelu",
645
- "memory_fuser_intermediate_dim": 1024,
646
- "memory_fuser_kernel_size": 7,
647
- "memory_fuser_layer_scale_init_value": 1e-06,
648
- "memory_fuser_num_layers": 2,
649
- "memory_fuser_padding": 3,
650
- "model_type": "sam3_tracker_video",
651
- "multimask_max_pt_num": 1,
652
- "multimask_min_pt_num": 0,
653
- "multimask_output_for_tracking": true,
654
- "multimask_output_in_sam": true,
655
- "num_maskmem": 7,
656
- "prompt_encoder_config": {
657
- "_name_or_path": "",
658
- "add_cross_attention": false,
659
- "architectures": null,
660
- "bad_words_ids": null,
661
- "begin_suppress_tokens": null,
662
- "bos_token_id": null,
663
- "chunk_size_feed_forward": 0,
664
- "cross_attention_hidden_size": null,
665
- "decoder_start_token_id": null,
666
- "diversity_penalty": 0.0,
667
- "do_sample": false,
668
- "dtype": null,
669
- "early_stopping": false,
670
- "encoder_no_repeat_ngram_size": 0,
671
- "eos_token_id": null,
672
- "exponential_decay_length_penalty": null,
673
- "finetuning_task": null,
674
- "forced_bos_token_id": null,
675
- "forced_eos_token_id": null,
676
- "hidden_act": "gelu",
677
- "hidden_size": 256,
678
- "id2label": {
679
- "0": "LABEL_0",
680
- "1": "LABEL_1"
681
- },
682
- "image_size": 1008,
683
- "is_decoder": false,
684
- "is_encoder_decoder": false,
685
- "label2id": {
686
- "LABEL_0": 0,
687
- "LABEL_1": 1
688
- },
689
- "layer_norm_eps": 1e-06,
690
- "length_penalty": 1.0,
691
- "mask_input_channels": 16,
692
- "max_length": 20,
693
- "min_length": 0,
694
- "model_type": "",
695
- "no_repeat_ngram_size": 0,
696
- "num_beam_groups": 1,
697
- "num_beams": 1,
698
- "num_point_embeddings": 4,
699
- "num_return_sequences": 1,
700
- "output_attentions": false,
701
- "output_hidden_states": false,
702
- "output_scores": false,
703
- "pad_token_id": null,
704
- "patch_size": 14,
705
- "prefix": null,
706
- "problem_type": null,
707
- "remove_invalid_values": false,
708
- "repetition_penalty": 1.0,
709
- "return_dict": true,
710
- "return_dict_in_generate": false,
711
- "scale": 1,
712
- "sep_token_id": null,
713
- "suppress_tokens": null,
714
- "task_specific_params": null,
715
- "temperature": 1.0,
716
- "tie_encoder_decoder": false,
717
- "tie_word_embeddings": true,
718
- "tokenizer_class": null,
719
- "top_k": 50,
720
- "top_p": 1.0,
721
- "typical_p": 1.0
722
- },
723
- "sigmoid_bias_for_mem_enc": -10.0,
724
- "sigmoid_scale_for_mem_enc": 20.0,
725
- "vision_config": {
726
- "_name_or_path": "",
727
- "add_cross_attention": false,
728
- "architectures": null,
729
- "backbone_config": {
730
- "_name_or_path": "",
731
- "add_cross_attention": false,
732
- "architectures": null,
733
- "attention_dropout": 0.0,
734
- "bad_words_ids": null,
735
- "begin_suppress_tokens": null,
736
- "bos_token_id": null,
737
- "chunk_size_feed_forward": 0,
738
- "cross_attention_hidden_size": null,
739
- "decoder_start_token_id": null,
740
- "diversity_penalty": 0.0,
741
- "do_sample": false,
742
- "dtype": null,
743
- "early_stopping": false,
744
- "encoder_no_repeat_ngram_size": 0,
745
- "eos_token_id": null,
746
- "exponential_decay_length_penalty": null,
747
- "finetuning_task": null,
748
- "forced_bos_token_id": null,
749
- "forced_eos_token_id": null,
750
- "global_attn_indexes": [
751
- 7,
752
- 15,
753
- 23,
754
- 31
755
- ],
756
- "hidden_act": "gelu",
757
- "hidden_dropout": 0.0,
758
- "hidden_size": 1024,
759
- "id2label": {
760
- "0": "LABEL_0",
761
- "1": "LABEL_1"
762
- },
763
- "image_size": 1008,
764
- "initializer_range": 0.02,
765
- "intermediate_size": 4736,
766
- "is_decoder": false,
767
- "is_encoder_decoder": false,
768
- "label2id": {
769
- "LABEL_0": 0,
770
- "LABEL_1": 1
771
- },
772
- "layer_norm_eps": 1e-06,
773
- "layer_scale_init_value": null,
774
- "length_penalty": 1.0,
775
- "max_length": 20,
776
- "min_length": 0,
777
- "model_type": "sam3_vit_model",
778
- "no_repeat_ngram_size": 0,
779
- "num_attention_heads": 16,
780
- "num_beam_groups": 1,
781
- "num_beams": 1,
782
- "num_channels": 3,
783
- "num_hidden_layers": 32,
784
- "num_return_sequences": 1,
785
- "output_attentions": false,
786
- "output_hidden_states": false,
787
- "output_scores": false,
788
- "pad_token_id": null,
789
- "patch_size": 14,
790
- "prefix": null,
791
- "pretrain_image_size": 336,
792
- "problem_type": null,
793
- "qkv_bias": true,
794
- "remove_invalid_values": false,
795
- "repetition_penalty": 1.0,
796
- "return_dict": true,
797
- "return_dict_in_generate": false,
798
- "rope_theta": 10000.0,
799
- "sep_token_id": null,
800
- "suppress_tokens": null,
801
- "task_specific_params": null,
802
- "temperature": 1.0,
803
- "tie_encoder_decoder": false,
804
- "tie_word_embeddings": true,
805
- "tokenizer_class": null,
806
- "top_k": 50,
807
- "top_p": 1.0,
808
- "typical_p": 1.0,
809
- "window_size": 24
810
- },
811
- "backbone_feature_sizes": [
812
- [
813
- 288,
814
- 288
815
- ],
816
- [
817
- 144,
818
- 144
819
- ],
820
- [
821
- 72,
822
- 72
823
- ]
824
- ],
825
- "bad_words_ids": null,
826
- "begin_suppress_tokens": null,
827
- "bos_token_id": null,
828
- "chunk_size_feed_forward": 0,
829
- "cross_attention_hidden_size": null,
830
- "decoder_start_token_id": null,
831
- "diversity_penalty": 0.0,
832
- "do_sample": false,
833
- "dtype": null,
834
- "early_stopping": false,
835
- "encoder_no_repeat_ngram_size": 0,
836
- "eos_token_id": null,
837
- "exponential_decay_length_penalty": null,
838
- "finetuning_task": null,
839
- "forced_bos_token_id": null,
840
- "forced_eos_token_id": null,
841
- "fpn_hidden_size": 256,
842
- "fpn_kernel_size": 2,
843
- "fpn_stride": 2,
844
- "hidden_act": "gelu",
845
- "id2label": {
846
- "0": "LABEL_0",
847
- "1": "LABEL_1"
848
- },
849
- "initializer_range": 0.02,
850
- "is_decoder": false,
851
- "is_encoder_decoder": false,
852
- "label2id": {
853
- "LABEL_0": 0,
854
- "LABEL_1": 1
855
- },
856
- "layer_norm_eps": 1e-06,
857
- "length_penalty": 1.0,
858
- "max_length": 20,
859
- "min_length": 0,
860
- "model_type": "sam3_vision_model",
861
- "no_repeat_ngram_size": 0,
862
- "num_beam_groups": 1,
863
- "num_beams": 1,
864
- "num_feature_levels": 3,
865
- "num_return_sequences": 1,
866
- "output_attentions": false,
867
- "output_hidden_states": false,
868
- "output_scores": false,
869
- "pad_token_id": null,
870
- "prefix": null,
871
- "problem_type": null,
872
- "remove_invalid_values": false,
873
- "repetition_penalty": 1.0,
874
- "return_dict": true,
875
- "return_dict_in_generate": false,
876
- "scale_factors": [
877
- 4.0,
878
- 2.0,
879
- 1.0,
880
- 0.5
881
- ],
882
- "sep_token_id": null,
883
- "suppress_tokens": null,
884
- "task_specific_params": null,
885
- "temperature": 1.0,
886
- "tie_encoder_decoder": false,
887
- "tie_word_embeddings": true,
888
- "tokenizer_class": null,
889
- "top_k": 50,
890
- "top_p": 1.0,
891
- "typical_p": 1.0
892
- }
893
- },
894
- "transformers_version": "5.0.0.dev0",
895
- "trk_assoc_iou_thresh": 0.5
896
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
modelos_entrenados/models--facebook--sam3/snapshots/3c879f39826c281e95690f02c7821c4de09afae7/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
modelos_entrenados/models--facebook--sam3/snapshots/3c879f39826c281e95690f02c7821c4de09afae7/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d06f0a5f84e435071fe6603e61d0b4cc7b40e0d39d487cfd4d67d8cc11cc14a
3
- size 3439938512
 
 
 
 
modelos_entrenados/models--facebook--sam3/snapshots/3c879f39826c281e95690f02c7821c4de09afae7/processor_config.json DELETED
@@ -1,80 +0,0 @@
1
- {
2
- "image_processor": {
3
- "crop_size": null,
4
- "data_format": "channels_first",
5
- "device": null,
6
- "disable_grouping": null,
7
- "do_center_crop": null,
8
- "do_convert_rgb": true,
9
- "do_normalize": true,
10
- "do_pad": null,
11
- "do_rescale": true,
12
- "do_resize": true,
13
- "image_mean": [
14
- 0.5,
15
- 0.5,
16
- 0.5
17
- ],
18
- "image_processor_type": "Sam3ImageProcessorFast",
19
- "image_seq_length": null,
20
- "image_std": [
21
- 0.5,
22
- 0.5,
23
- 0.5
24
- ],
25
- "input_data_format": null,
26
- "mask_size": {
27
- "height": 288,
28
- "width": 288
29
- },
30
- "pad_size": null,
31
- "processor_class": "Sam3VideoProcessor",
32
- "resample": 2,
33
- "rescale_factor": 0.00392156862745098,
34
- "return_tensors": null,
35
- "size": {
36
- "height": 1008,
37
- "width": 1008
38
- }
39
- },
40
- "processor_class": "Sam3VideoProcessor",
41
- "target_size": 1008,
42
- "video_processor": {
43
- "crop_size": null,
44
- "data_format": "channels_first",
45
- "default_to_square": true,
46
- "device": null,
47
- "do_center_crop": null,
48
- "do_convert_rgb": true,
49
- "do_normalize": true,
50
- "do_pad": null,
51
- "do_rescale": true,
52
- "do_resize": true,
53
- "do_sample_frames": null,
54
- "fps": null,
55
- "image_mean": [
56
- 0.5,
57
- 0.5,
58
- 0.5
59
- ],
60
- "image_std": [
61
- 0.5,
62
- 0.5,
63
- 0.5
64
- ],
65
- "input_data_format": null,
66
- "num_frames": null,
67
- "pad_size": null,
68
- "processor_class": "Sam3VideoProcessor",
69
- "resample": 2,
70
- "rescale_factor": 0.00392156862745098,
71
- "return_metadata": false,
72
- "return_tensors": null,
73
- "size": {
74
- "height": 1008,
75
- "width": 1008
76
- },
77
- "video_metadata": null,
78
- "video_processor_type": "Sam2VideoVideoProcessor"
79
- }
80
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
modelos_entrenados/models--facebook--sam3/snapshots/3c879f39826c281e95690f02c7821c4de09afae7/special_tokens_map.json DELETED
@@ -1,30 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<|startoftext|>",
4
- "lstrip": false,
5
- "normalized": true,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "<|endoftext|>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": {
17
- "content": "<|endoftext|>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "unk_token": {
24
- "content": "<|endoftext|>",
25
- "lstrip": false,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- }
30
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
modelos_entrenados/models--facebook--sam3/snapshots/3c879f39826c281e95690f02c7821c4de09afae7/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
modelos_entrenados/models--facebook--sam3/snapshots/3c879f39826c281e95690f02c7821c4de09afae7/tokenizer_config.json DELETED
@@ -1,33 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "49406": {
5
- "content": "<|startoftext|>",
6
- "lstrip": false,
7
- "normalized": true,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "49407": {
13
- "content": "<|endoftext|>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- }
20
- },
21
- "bos_token": "<|startoftext|>",
22
- "clean_up_tokenization_spaces": false,
23
- "do_lower_case": true,
24
- "eos_token": "<|endoftext|>",
25
- "errors": "replace",
26
- "extra_special_tokens": {},
27
- "max_length": 32,
28
- "model_max_length": 32,
29
- "pad_token": "<|endoftext|>",
30
- "processor_class": "Sam3VideoProcessor",
31
- "tokenizer_class": "CLIPTokenizer",
32
- "unk_token": "<|endoftext|>"
33
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
modelos_entrenados/models--facebook--sam3/snapshots/3c879f39826c281e95690f02c7821c4de09afae7/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
modelos_entrenados/models--facebook--sam3/snapshots/image.png DELETED

Git LFS Details

  • SHA256: 66666809d4998cbf0d6144605920b759c0391eb757ba714e35de760b81867b0d
  • Pointer size: 132 Bytes
  • Size of remote file: 1.04 MB
modelos_entrenados/peso/lgbm_peso.joblib DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:33ad6dbdfa3b8d495dcd7b7162b070c7ed00436c54df7637fe5fe402230d80f0
3
- size 3428815