File size: 16,945 Bytes
5f70891
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
{
  "english": {
    "return_dict": true,
    "output_hidden_states": false,
    "torchscript": false,
    "dtype": "float32",
    "pruned_heads": {},
    "tie_word_embeddings": false,
    "chunk_size_feed_forward": 0,
    "is_encoder_decoder": true,
    "is_decoder": false,
    "cross_attention_hidden_size": null,
    "add_cross_attention": false,
    "tie_encoder_decoder": false,
    "architectures": [
      "VisionEncoderDecoderModel"
    ],
    "finetuning_task": null,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "task_specific_params": null,
    "problem_type": null,
    "tokenizer_class": null,
    "prefix": null,
    "bos_token_id": null,
    "pad_token_id": null,
    "eos_token_id": 2,
    "sep_token_id": null,
    "decoder_start_token_id": null,
    "max_length": 20,
    "min_length": 0,
    "do_sample": false,
    "early_stopping": false,
    "num_beams": 1,
    "temperature": 1.0,
    "top_k": 50,
    "top_p": 1.0,
    "typical_p": 1.0,
    "repetition_penalty": 1.0,
    "length_penalty": 1.0,
    "no_repeat_ngram_size": 0,
    "encoder_no_repeat_ngram_size": 0,
    "bad_words_ids": null,
    "num_return_sequences": 1,
    "output_scores": false,
    "return_dict_in_generate": false,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "remove_invalid_values": false,
    "exponential_decay_length_penalty": null,
    "suppress_tokens": null,
    "begin_suppress_tokens": null,
    "num_beam_groups": 1,
    "diversity_penalty": 0.0,
    "_name_or_path": "/home/ampixa/ocr/models/trocr-small-handwritten-b4648cfa",
    "transformers_version": "4.57.6",
    "decoder": {
      "vocab_size": 64044,
      "d_model": 256,
      "decoder_layers": 6,
      "decoder_attention_heads": 8,
      "decoder_ffn_dim": 1024,
      "activation_function": "relu",
      "max_position_embeddings": 512,
      "dropout": 0.1,
      "attention_dropout": 0.0,
      "activation_dropout": 0.0,
      "init_std": 0.02,
      "decoder_layerdrop": 0.0,
      "use_cache": false,
      "scale_embedding": true,
      "use_learned_position_embeddings": true,
      "layernorm_embedding": true,
      "return_dict": true,
      "output_hidden_states": false,
      "torchscript": false,
      "dtype": "float32",
      "pruned_heads": {},
      "tie_word_embeddings": false,
      "chunk_size_feed_forward": 0,
      "is_encoder_decoder": false,
      "is_decoder": true,
      "cross_attention_hidden_size": 384,
      "add_cross_attention": true,
      "tie_encoder_decoder": false,
      "architectures": null,
      "finetuning_task": null,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "task_specific_params": null,
      "problem_type": null,
      "tokenizer_class": null,
      "prefix": null,
      "bos_token_id": 0,
      "pad_token_id": 1,
      "eos_token_id": 2,
      "sep_token_id": null,
      "decoder_start_token_id": 2,
      "max_length": 20,
      "min_length": 0,
      "do_sample": false,
      "early_stopping": false,
      "num_beams": 1,
      "temperature": 1.0,
      "top_k": 50,
      "top_p": 1.0,
      "typical_p": 1.0,
      "repetition_penalty": 1.0,
      "length_penalty": 1.0,
      "no_repeat_ngram_size": 0,
      "encoder_no_repeat_ngram_size": 0,
      "bad_words_ids": null,
      "num_return_sequences": 1,
      "output_scores": false,
      "return_dict_in_generate": false,
      "forced_bos_token_id": null,
      "forced_eos_token_id": null,
      "remove_invalid_values": false,
      "exponential_decay_length_penalty": null,
      "suppress_tokens": null,
      "begin_suppress_tokens": null,
      "num_beam_groups": 1,
      "diversity_penalty": 0.0,
      "_name_or_path": "",
      "classifier_dropout": 0.0,
      "use_bfloat16": false,
      "tf_legacy_loss": false,
      "model_type": "trocr",
      "output_attentions": false
    },
    "encoder": {
      "return_dict": true,
      "output_hidden_states": false,
      "torchscript": false,
      "dtype": "float32",
      "pruned_heads": {},
      "tie_word_embeddings": true,
      "chunk_size_feed_forward": 0,
      "is_encoder_decoder": false,
      "is_decoder": false,
      "cross_attention_hidden_size": null,
      "add_cross_attention": false,
      "tie_encoder_decoder": false,
      "architectures": null,
      "finetuning_task": null,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "task_specific_params": null,
      "problem_type": null,
      "tokenizer_class": null,
      "prefix": null,
      "bos_token_id": null,
      "pad_token_id": null,
      "eos_token_id": null,
      "sep_token_id": null,
      "decoder_start_token_id": null,
      "max_length": 20,
      "min_length": 0,
      "do_sample": false,
      "early_stopping": false,
      "num_beams": 1,
      "temperature": 1.0,
      "top_k": 50,
      "top_p": 1.0,
      "typical_p": 1.0,
      "repetition_penalty": 1.0,
      "length_penalty": 1.0,
      "no_repeat_ngram_size": 0,
      "encoder_no_repeat_ngram_size": 0,
      "bad_words_ids": null,
      "num_return_sequences": 1,
      "output_scores": false,
      "return_dict_in_generate": false,
      "forced_bos_token_id": null,
      "forced_eos_token_id": null,
      "remove_invalid_values": false,
      "exponential_decay_length_penalty": null,
      "suppress_tokens": null,
      "begin_suppress_tokens": null,
      "num_beam_groups": 1,
      "diversity_penalty": 0.0,
      "_name_or_path": "",
      "use_bfloat16": false,
      "tf_legacy_loss": false,
      "hidden_size": 384,
      "num_hidden_layers": 12,
      "num_attention_heads": 6,
      "intermediate_size": 1536,
      "hidden_act": "gelu",
      "hidden_dropout_prob": 0.0,
      "attention_probs_dropout_prob": 0.0,
      "initializer_range": 0.02,
      "layer_norm_eps": 1e-12,
      "image_size": 384,
      "patch_size": 16,
      "num_channels": 3,
      "qkv_bias": true,
      "encoder_stride": 16,
      "pooler_output_size": 384,
      "pooler_act": "tanh",
      "model_type": "deit",
      "output_attentions": false
    },
    "model_type": "vision-encoder-decoder",
    "tf_legacy_loss": false,
    "use_bfloat16": false,
    "output_attentions": false
  },
  "character": {
    "return_dict": true,
    "output_hidden_states": false,
    "torchscript": false,
    "dtype": "float32",
    "pruned_heads": {},
    "tie_word_embeddings": false,
    "chunk_size_feed_forward": 0,
    "is_encoder_decoder": true,
    "is_decoder": false,
    "cross_attention_hidden_size": null,
    "add_cross_attention": false,
    "tie_encoder_decoder": false,
    "architectures": [
      "VisionEncoderDecoderModel"
    ],
    "finetuning_task": null,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "task_specific_params": null,
    "problem_type": null,
    "tokenizer_class": null,
    "prefix": null,
    "bos_token_id": null,
    "pad_token_id": null,
    "eos_token_id": 2,
    "sep_token_id": null,
    "decoder_start_token_id": null,
    "max_length": 20,
    "min_length": 0,
    "do_sample": false,
    "early_stopping": false,
    "num_beams": 1,
    "temperature": 1.0,
    "top_k": 50,
    "top_p": 1.0,
    "typical_p": 1.0,
    "repetition_penalty": 1.0,
    "length_penalty": 1.0,
    "no_repeat_ngram_size": 0,
    "encoder_no_repeat_ngram_size": 0,
    "bad_words_ids": null,
    "num_return_sequences": 1,
    "output_scores": false,
    "return_dict_in_generate": false,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "remove_invalid_values": false,
    "exponential_decay_length_penalty": null,
    "suppress_tokens": null,
    "begin_suppress_tokens": null,
    "num_beam_groups": 1,
    "diversity_penalty": 0.0,
    "_name_or_path": "/home/ampixa/ocr/ocr-deva-ft/runs/trocr-character-full24000-r1-20261021/milestones/24000",
    "transformers_version": "4.57.6",
    "decoder": {
      "vocab_size": 573,
      "d_model": 256,
      "decoder_layers": 6,
      "decoder_attention_heads": 8,
      "decoder_ffn_dim": 1024,
      "activation_function": "relu",
      "max_position_embeddings": 512,
      "dropout": 0.1,
      "attention_dropout": 0.0,
      "activation_dropout": 0.0,
      "init_std": 0.02,
      "decoder_layerdrop": 0.0,
      "use_cache": false,
      "scale_embedding": true,
      "use_learned_position_embeddings": true,
      "layernorm_embedding": true,
      "return_dict": true,
      "output_hidden_states": false,
      "torchscript": false,
      "dtype": "float32",
      "pruned_heads": {},
      "tie_word_embeddings": false,
      "chunk_size_feed_forward": 0,
      "is_encoder_decoder": false,
      "is_decoder": true,
      "cross_attention_hidden_size": 384,
      "add_cross_attention": true,
      "tie_encoder_decoder": false,
      "architectures": null,
      "finetuning_task": null,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "task_specific_params": null,
      "problem_type": null,
      "tokenizer_class": null,
      "prefix": null,
      "bos_token_id": 0,
      "pad_token_id": 1,
      "eos_token_id": 2,
      "sep_token_id": null,
      "decoder_start_token_id": 2,
      "max_length": 20,
      "min_length": 0,
      "do_sample": false,
      "early_stopping": false,
      "num_beams": 1,
      "temperature": 1.0,
      "top_k": 50,
      "top_p": 1.0,
      "typical_p": 1.0,
      "repetition_penalty": 1.0,
      "length_penalty": 1.0,
      "no_repeat_ngram_size": 0,
      "encoder_no_repeat_ngram_size": 0,
      "bad_words_ids": null,
      "num_return_sequences": 1,
      "output_scores": false,
      "return_dict_in_generate": false,
      "forced_bos_token_id": null,
      "forced_eos_token_id": null,
      "remove_invalid_values": false,
      "exponential_decay_length_penalty": null,
      "suppress_tokens": null,
      "begin_suppress_tokens": null,
      "num_beam_groups": 1,
      "diversity_penalty": 0.0,
      "_name_or_path": "",
      "classifier_dropout": 0.0,
      "tf_legacy_loss": false,
      "use_bfloat16": false,
      "model_type": "trocr",
      "output_attentions": false
    },
    "encoder": {
      "return_dict": true,
      "output_hidden_states": false,
      "torchscript": false,
      "dtype": "float32",
      "pruned_heads": {},
      "tie_word_embeddings": true,
      "chunk_size_feed_forward": 0,
      "is_encoder_decoder": false,
      "is_decoder": false,
      "cross_attention_hidden_size": null,
      "add_cross_attention": false,
      "tie_encoder_decoder": false,
      "architectures": null,
      "finetuning_task": null,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "task_specific_params": null,
      "problem_type": null,
      "tokenizer_class": null,
      "prefix": null,
      "bos_token_id": null,
      "pad_token_id": null,
      "eos_token_id": null,
      "sep_token_id": null,
      "decoder_start_token_id": null,
      "max_length": 20,
      "min_length": 0,
      "do_sample": false,
      "early_stopping": false,
      "num_beams": 1,
      "temperature": 1.0,
      "top_k": 50,
      "top_p": 1.0,
      "typical_p": 1.0,
      "repetition_penalty": 1.0,
      "length_penalty": 1.0,
      "no_repeat_ngram_size": 0,
      "encoder_no_repeat_ngram_size": 0,
      "bad_words_ids": null,
      "num_return_sequences": 1,
      "output_scores": false,
      "return_dict_in_generate": false,
      "forced_bos_token_id": null,
      "forced_eos_token_id": null,
      "remove_invalid_values": false,
      "exponential_decay_length_penalty": null,
      "suppress_tokens": null,
      "begin_suppress_tokens": null,
      "num_beam_groups": 1,
      "diversity_penalty": 0.0,
      "_name_or_path": "",
      "tf_legacy_loss": false,
      "use_bfloat16": false,
      "hidden_size": 384,
      "num_hidden_layers": 12,
      "num_attention_heads": 6,
      "intermediate_size": 1536,
      "hidden_act": "gelu",
      "hidden_dropout_prob": 0.0,
      "attention_probs_dropout_prob": 0.0,
      "initializer_range": 0.02,
      "layer_norm_eps": 1e-12,
      "image_size": 384,
      "patch_size": 16,
      "num_channels": 3,
      "qkv_bias": true,
      "encoder_stride": 16,
      "pooler_output_size": 384,
      "pooler_act": "tanh",
      "model_type": "deit",
      "output_attentions": false
    },
    "model_type": "vision-encoder-decoder",
    "tf_legacy_loss": false,
    "use_bfloat16": false,
    "output_attentions": false
  },
  "english_generation": {
    "max_length": 20,
    "max_new_tokens": null,
    "min_length": 0,
    "min_new_tokens": null,
    "early_stopping": false,
    "max_time": null,
    "stop_strings": null,
    "do_sample": false,
    "num_beams": 1,
    "use_cache": false,
    "cache_implementation": null,
    "cache_config": null,
    "return_legacy_cache": null,
    "prefill_chunk_size": null,
    "temperature": 1.0,
    "top_k": 50,
    "top_p": 1.0,
    "min_p": null,
    "typical_p": 1.0,
    "epsilon_cutoff": 0.0,
    "eta_cutoff": 0.0,
    "repetition_penalty": 1.0,
    "encoder_repetition_penalty": 1.0,
    "length_penalty": 1.0,
    "no_repeat_ngram_size": 0,
    "bad_words_ids": null,
    "renormalize_logits": false,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "remove_invalid_values": false,
    "exponential_decay_length_penalty": null,
    "suppress_tokens": null,
    "begin_suppress_tokens": null,
    "sequence_bias": null,
    "token_healing": false,
    "guidance_scale": null,
    "watermarking_config": null,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "output_logits": null,
    "return_dict_in_generate": false,
    "pad_token_id": 1,
    "bos_token_id": 0,
    "eos_token_id": 2,
    "encoder_no_repeat_ngram_size": 0,
    "decoder_start_token_id": 2,
    "is_assistant": false,
    "num_assistant_tokens": 20,
    "num_assistant_tokens_schedule": "constant",
    "assistant_confidence_threshold": 0.4,
    "prompt_lookup_num_tokens": null,
    "max_matching_ngram_size": null,
    "assistant_early_exit": null,
    "assistant_lookbehind": 10,
    "target_lookbehind": 10,
    "disable_compile": false,
    "low_memory": null,
    "penalty_alpha": null,
    "dola_layers": null,
    "diversity_penalty": 0.0,
    "num_beam_groups": 1,
    "constraints": null,
    "force_words_ids": null,
    "_from_model_config": true,
    "transformers_version": "4.57.6"
  },
  "character_generation": {
    "max_length": 20,
    "max_new_tokens": 257,
    "min_length": 0,
    "min_new_tokens": null,
    "early_stopping": false,
    "max_time": null,
    "stop_strings": null,
    "do_sample": false,
    "num_beams": 1,
    "use_cache": false,
    "cache_implementation": null,
    "cache_config": null,
    "return_legacy_cache": null,
    "prefill_chunk_size": null,
    "temperature": 1.0,
    "top_k": 50,
    "top_p": 1.0,
    "min_p": null,
    "typical_p": 1.0,
    "epsilon_cutoff": 0.0,
    "eta_cutoff": 0.0,
    "repetition_penalty": 1.0,
    "encoder_repetition_penalty": 1.0,
    "length_penalty": 1.0,
    "no_repeat_ngram_size": 0,
    "bad_words_ids": null,
    "renormalize_logits": false,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "remove_invalid_values": false,
    "exponential_decay_length_penalty": null,
    "suppress_tokens": [
      0,
      1,
      3
    ],
    "begin_suppress_tokens": null,
    "sequence_bias": null,
    "token_healing": false,
    "guidance_scale": null,
    "watermarking_config": null,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "output_logits": null,
    "return_dict_in_generate": false,
    "pad_token_id": 1,
    "bos_token_id": 0,
    "eos_token_id": 2,
    "encoder_no_repeat_ngram_size": 0,
    "decoder_start_token_id": 2,
    "is_assistant": false,
    "num_assistant_tokens": 20,
    "num_assistant_tokens_schedule": "constant",
    "assistant_confidence_threshold": 0.4,
    "prompt_lookup_num_tokens": null,
    "max_matching_ngram_size": null,
    "assistant_early_exit": null,
    "assistant_lookbehind": 10,
    "target_lookbehind": 10,
    "disable_compile": false,
    "low_memory": null,
    "penalty_alpha": null,
    "dola_layers": null,
    "diversity_penalty": 0.0,
    "num_beam_groups": 1,
    "constraints": null,
    "force_words_ids": null,
    "_from_model_config": true,
    "transformers_version": "4.57.6"
  }
}