Hugging Face's logo

wchai
/
cap_strange

Model card Files Community
cap_strange
File size: 36,600 Bytes 
c7b2255
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
 
SYSTEM = ''
accumulative_counts = 96
allava_cl_data_path = '/data/wenhao/projects/xtuner/data/ALLaVA-4V/ALLaVA-Caption-LAION-4V.jsonl'
allava_cl_dataset = dict(
    dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
    image_folder='/data/wenhao/projects/xtuner/data/ALLaVA-4V',
    image_processor=dict(
        crop_size=378,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=378,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    offline_processed_text_folder=
    '/data/wenhao/projects/xtuner/data/ALLaVA-4V/pre_token_cl_llama31',
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    type='xtuner.dataset.CambrianDataset')
allava_cl_image_folder = '/data/wenhao/projects/xtuner/data/ALLaVA-4V'
allava_cv_data_path = '/data/wenhao/projects/xtuner/data/ALLaVA-4V/ALLaVA-Caption-VFLAN-4V.jsonl'
allava_cv_dataset = dict(
    dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
    image_folder='/data/wenhao/projects/xtuner/data/ALLaVA-4V',
    image_processor=dict(
        crop_size=378,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=378,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    offline_processed_text_folder=
    '/data/wenhao/projects/xtuner/data/ALLaVA-4V/pre_token_cv_llama31',
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    type='xtuner.dataset.CambrianDataset')
allava_data_root = '/data/wenhao/projects/xtuner/data/ALLaVA-4V'
allava_il_data_path = '/data/wenhao/projects/xtuner/data/ALLaVA-4V/ALLaVA-Instruct-LAION-4V.jsonl'
allava_il_dataset = dict(
    dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
    image_folder='/data/wenhao/projects/xtuner/data/ALLaVA-4V',
    image_processor=dict(
        crop_size=378,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=378,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    offline_processed_text_folder=
    '/data/wenhao/projects/xtuner/data/ALLaVA-4V/pre_token_il_llama31',
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    type='xtuner.dataset.CambrianDataset')
allava_il_image_folder = '/data/wenhao/projects/xtuner/data/ALLaVA-4V'
allava_image_folder = '/data/wenhao/projects/xtuner/data/ALLaVA-4V'
allava_iv_data_path = '/data/wenhao/projects/xtuner/data/ALLaVA-4V/ALLaVA-Instruct-VFLAN-4V.jsonl'
allava_iv_dataset = dict(
    dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
    image_folder='/data/wenhao/projects/xtuner/data/ALLaVA-4V',
    image_processor=dict(
        crop_size=378,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=378,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    offline_processed_text_folder=
    '/data/wenhao/projects/xtuner/data/ALLaVA-4V/pre_token_iv_llama31',
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    type='xtuner.dataset.CambrianDataset')
batch_size = 1
betas = (
    0.9,
    0.999,
)
cambrian_data_path = '/data/wenhao/projects/xtuner/data/Cambrian-10M/jsons/Cambrian7M_withsystemprompt.jsonl'
cambrian_data_root = '/data/wenhao/projects/xtuner/data/Cambrian-10M/'
cambrian_dataset = dict(
    dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
    image_folder='/data/wenhao/projects/xtuner/data/Cambrian-10M/',
    image_processor=dict(
        crop_size=378,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=378,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    offline_processed_text_folder=
    '/data/wenhao/projects/xtuner/data/Cambrian-10M/pre_token_llama3',
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    type='xtuner.dataset.CambrianDataset')
cambrian_image_folder = '/data/wenhao/projects/xtuner/data/Cambrian-10M/'
cambrian_processed_text_folder = '/data/wenhao/projects/xtuner/data/Cambrian-10M/pre_token_llama3'
custom_hooks = [
    dict(
        tokenizer=dict(
            padding_side='right',
            pretrained_model_name_or_path='meta-llama/Meta-Llama-3-8B-Instruct',
            trust_remote_code=True,
            type='transformers.AutoTokenizer.from_pretrained'),
        type='xtuner.engine.DatasetInfoHook'),
    dict(
        evaluation_images='https://llava-vl.github.io/static/images/view.jpg',
        evaluation_inputs=[
            '请描述一下这张照片',
            'Please describe this picture',
        ],
        every_n_iters=100,
        image_processor=dict(
            crop_size=378,
            pretrained_model_name_or_path=
            'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
            size=378,
            trust_remote_code=True,
            type='transformers.CLIPImageProcessor.from_pretrained'),
        prompt_template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
        system='',
        tokenizer=dict(
            padding_side='right',
            pretrained_model_name_or_path='meta-llama/Meta-Llama-3-8B-Instruct',
            trust_remote_code=True,
            type='transformers.AutoTokenizer.from_pretrained'),
        type='xtuner.engine.EvaluateChatHook'),
]
dataloader_num_workers = 0
default_hooks = dict(
    checkpoint=dict(
        by_epoch=False,
        interval=200,
        max_keep_ckpts=2,
        type='mmengine.hooks.CheckpointHook'),
    logger=dict(interval=10, type='mmengine.hooks.LoggerHook'),
    param_scheduler=dict(type='mmengine.hooks.ParamSchedulerHook'),
    sampler_seed=dict(type='mmengine.hooks.DistSamplerSeedHook'),
    timer=dict(type='mmengine.hooks.IterTimerHook'))
dense_data_path = '/data/wenhao/projects/xtuner/data/DenseFusion-1M/DenseFusion-1M/DenseFusion-1M-instruct.jsonl'
dense_data_root = '/data/wenhao/projects/xtuner/data/DenseFusion-1M/'
dense_dataset = dict(
    dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
    image_folder='/data/wenhao/projects/xtuner/data/DenseFusion-1M/1M_data',
    image_processor=dict(
        crop_size=378,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=378,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    offline_processed_text_folder=
    '/data/wenhao/projects/xtuner/data/DenseFusion-1M/pre_token_llama3',
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    type='xtuner.dataset.CambrianDataset')
dense_image_folder = '/data/wenhao/projects/xtuner/data/DenseFusion-1M/1M_data'
dense_processed_text_folder = '/data/wenhao/projects/xtuner/data/DenseFusion-1M/pre_token_llama3'
env_cfg = dict(
    cudnn_benchmark=False,
    dist_cfg=dict(backend='nccl'),
    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
evaluation_freq = 100
evaluation_images = 'https://llava-vl.github.io/static/images/view.jpg'
evaluation_inputs = [
    '请描述一下这张照片',
    'Please describe this picture',
]
evol_data_path = '/data/wenhao/projects/xtuner/data/ALLaVA-4V/allava_text/Evol-Instruct-GPT4-Turbo-143K.jsonl'
evol_data_root = '/data/wenhao/projects/xtuner/data/ALLaVA-4V/allava_text/'
evol_dataset = dict(
    dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
    image_folder=
    '/data/wenhao/projects/xtuner/data/ALLaVA-4V/allava_text/images',
    image_processor=dict(
        crop_size=378,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=378,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    offline_processed_text_folder=
    '/data/wenhao/projects/xtuner/data/ALLaVA-4V/pre_token_evol_llama31',
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    type='xtuner.dataset.CambrianDataset')
evol_image_folder = '/data/wenhao/projects/xtuner/data/ALLaVA-4V/allava_text/images'
face_data_path = '/data/wenhao/projects/xtuner/data/FaceCaption-15M/FaceCaption-100K.jsonl'
face_data_root = '/data/wenhao/projects/xtuner/data/FaceCaption-15M/'
face_dataset = dict(
    dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
    image_folder='/data/wenhao/projects/xtuner/data/FaceCaption-15M/full_data',
    image_processor=dict(
        crop_size=378,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=378,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    offline_processed_text_folder=
    '/data/wenhao/projects/xtuner/data/FaceCaption-15M/pre_token_llama3',
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    type='xtuner.dataset.CambrianDataset')
face_image_folder = '/data/wenhao/projects/xtuner/data/FaceCaption-15M/full_data'
face_processed_text_folder = '/data/wenhao/projects/xtuner/data/FaceCaption-15M/pre_token_llama3'
image_processor = dict(
    crop_size=378,
    pretrained_model_name_or_path='laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
    size=378,
    trust_remote_code=True,
    type='transformers.CLIPImageProcessor.from_pretrained')
launcher = 'slurm'
llava_mix_data_path = '/data/wenhao/projects/xtuner/data/LLaVA-Instruct-150K/llava_v1_5_mix665k.jsonl'
llava_mix_data_root = '/data/wenhao/projects/xtuner/data/LLaVA-Instruct-150K/'
llava_mix_dataset = dict(
    dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
    image_folder='/data/wenhao/projects/xtuner/data/LLaVA-Instruct-150K/images',
    image_processor=dict(
        crop_size=378,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=378,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    offline_processed_text_folder=
    '/data/wenhao/projects/xtuner/data/LLaVA-Instruct-150K/pre_token_llama31',
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    type='xtuner.dataset.CambrianDataset')
llava_mix_image_folder = '/data/wenhao/projects/xtuner/data/LLaVA-Instruct-150K/images'
llavanext_data_path = '/data/wenhao/projects/xtuner/data/LLaVA-NeXT-Data/llava_next.jsonl'
llavanext_data_root = '/data/wenhao/projects/xtuner/data/LLaVA-NeXT-Data/'
llavanext_dataset = dict(
    dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
    image_folder='/data/wenhao/projects/xtuner/data/LLaVA-NeXT-Data/images',
    image_processor=dict(
        crop_size=378,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=378,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    offline_processed_text_folder=
    '/data/wenhao/projects/xtuner/data/LLaVA-NeXT-Data/pre_token_llama31',
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    type='xtuner.dataset.CambrianDataset')
llavanext_image_folder = '/data/wenhao/projects/xtuner/data/LLaVA-NeXT-Data/images'
llm_name_or_path = 'meta-llama/Meta-Llama-3-8B-Instruct'
load_from = 'work_dirs/new_image/iter_449600.pth'
log_level = 'INFO'
lr = 1e-05
m4_data_path = '/data/wenhao/projects/xtuner/data/M4-Instruct-Data/m4_instruct_image.jsonl'
m4_data_root = '/data/wenhao/projects/xtuner/data/M4-Instruct-Data/'
m4_dataset = dict(
    dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
    image_folder='/data/wenhao/projects/xtuner/data/M4-Instruct-Data/',
    image_processor=dict(
        crop_size=378,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=378,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    offline_processed_text_folder=
    '/data/wenhao/projects/xtuner/data/M4-Instruct-Data/pre_token_llama31',
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    type='xtuner.dataset.CambrianDataset')
m4_image_folder = '/data/wenhao/projects/xtuner/data/M4-Instruct-Data/'
max_epochs = 1
max_length = 4096
max_norm = 1
model = dict(
    freeze_llm=False,
    freeze_visual_encoder=False,
    llm=dict(
        pretrained_model_name_or_path='meta-llama/Meta-Llama-3-8B-Instruct',
        torch_dtype='torch.float16',
        trust_remote_code=True,
        type='transformers.AutoModelForCausalLM.from_pretrained'),
    llm_lora=dict(
        bias='none',
        lora_alpha=256,
        lora_dropout=0.05,
        r=512,
        task_type='CAUSAL_LM',
        type='peft.LoraConfig'),
    pretrained_pth=
    '/data/wenhao/projects/xtuner/work_dirs/final_new_v/projector',
    type='xtuner.model.PikaModel',
    visual_encoder=dict(
        pretrained_model_name_or_path=
        '/data/wenhao/projects/xtuner/work_dirs/final_new_v/visual_encoder',
        type='xtuner.model.pika.PikaSigVidEncoder.from_pretrained',
        visual_token_merge_ratio=0.1))
optim_type = 'torch.optim.AdamW'
optim_wrapper = dict(
    optimizer=dict(
        betas=(
            0.9,
            0.999,
        ),
        lr=1e-05,
        type='torch.optim.AdamW',
        weight_decay=0),
    type='DeepSpeedOptimWrapper')
param_scheduler = [
    dict(
        begin=0,
        by_epoch=True,
        convert_to_iter_based=True,
        end=0.03,
        start_factor=1e-05,
        type='mmengine.optim.LinearLR'),
    dict(
        T_max=1,
        begin=0.03,
        by_epoch=True,
        convert_to_iter_based=True,
        eta_min=0.0,
        type='mmengine.optim.CosineAnnealingLR'),
]
pretrained_pth = '/data/wenhao/projects/xtuner/work_dirs/final_new_v/projector'
prompt_template = 'xtuner.utils.PROMPT_TEMPLATE.llama3_chat'
randomness = dict(deterministic=False, seed=1416244085)
resume = True
runner_type = 'FlexibleRunner'
save_steps = 200
save_total_limit = 2
sharegpt4v_data_path = '/data/wenhao/projects/xtuner/data/ShareGPT4V/sharegpt4v_instruct_gpt4-vision_cap100k.jsonl'
sharegpt4v_data_root = '/data/wenhao/projects/xtuner/data/ShareGPT4V'
sharegpt4v_dataset = dict(
    dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
    image_folder='/data/wenhao/projects/xtuner/data',
    image_processor=dict(
        crop_size=378,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=378,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    offline_processed_text_folder=
    '/data/wenhao/projects/xtuner/data/ShareGPT4V/pre_token_sharegpt4v_llama31',
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    type='xtuner.dataset.CambrianDataset')
sharegpt4v_image_folder = '/data/wenhao/projects/xtuner/data'
size = 378
strategy = dict(
    config=dict(
        bf16=dict(enabled=True),
        fp16=dict(enabled=False, initial_scale_power=16),
        gradient_accumulation_steps='auto',
        gradient_clipping='auto',
        train_micro_batch_size_per_gpu='auto',
        zero_allow_untested_optimizer=True,
        zero_force_ds_cpu_optimizer=False,
        zero_optimization=dict(overlap_comm=True, stage=2)),
    exclude_frozen_parameters=True,
    gradient_accumulation_steps=96,
    gradient_clipping=1,
    sequence_parallel_size=1,
    train_micro_batch_size_per_gpu=1,
    type='xtuner.engine.DeepSpeedStrategy')
tokenizer = dict(
    padding_side='right',
    pretrained_model_name_or_path='meta-llama/Meta-Llama-3-8B-Instruct',
    trust_remote_code=True,
    type='transformers.AutoTokenizer.from_pretrained')
train_cfg = dict(by_epoch=True, max_epochs=1, val_interval=1)
train_dataloader = dict(
    batch_size=1,
    collate_fn=dict(type='xtuner.dataset.collate_fns.default_collate_fn'),
    dataset=dict(
        datasets=[
            dict(
                dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
                image_folder=
                '/data/wenhao/projects/xtuner/data/M4-Instruct-Data/',
                image_processor=dict(
                    crop_size=378,
                    pretrained_model_name_or_path=
                    'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                    size=378,
                    trust_remote_code=True,
                    type='transformers.CLIPImageProcessor.from_pretrained'),
                max_length=4096,
                offline_processed_text_folder=
                '/data/wenhao/projects/xtuner/data/M4-Instruct-Data/pre_token_llama31',
                pad_image_to_square=True,
                template_map_fn=dict(
                    template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
                    type='xtuner.dataset.map_fns.template_map_fn_factory'),
                type='xtuner.dataset.CambrianDataset'),
            dict(
                dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
                image_folder=
                '/data/wenhao/projects/xtuner/data/LLaVA-NeXT-Data/images',
                image_processor=dict(
                    crop_size=378,
                    pretrained_model_name_or_path=
                    'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                    size=378,
                    trust_remote_code=True,
                    type='transformers.CLIPImageProcessor.from_pretrained'),
                max_length=4096,
                offline_processed_text_folder=
                '/data/wenhao/projects/xtuner/data/LLaVA-NeXT-Data/pre_token_llama31',
                pad_image_to_square=True,
                template_map_fn=dict(
                    template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
                    type='xtuner.dataset.map_fns.template_map_fn_factory'),
                type='xtuner.dataset.CambrianDataset'),
            dict(
                dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
                image_folder='/data/wenhao/projects/xtuner/data/ALLaVA-4V',
                image_processor=dict(
                    crop_size=378,
                    pretrained_model_name_or_path=
                    'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                    size=378,
                    trust_remote_code=True,
                    type='transformers.CLIPImageProcessor.from_pretrained'),
                max_length=4096,
                offline_processed_text_folder=
                '/data/wenhao/projects/xtuner/data/ALLaVA-4V/pre_token_cl_llama31',
                pad_image_to_square=True,
                template_map_fn=dict(
                    template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
                    type='xtuner.dataset.map_fns.template_map_fn_factory'),
                type='xtuner.dataset.CambrianDataset'),
            dict(
                dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
                image_folder='/data/wenhao/projects/xtuner/data/ALLaVA-4V',
                image_processor=dict(
                    crop_size=378,
                    pretrained_model_name_or_path=
                    'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                    size=378,
                    trust_remote_code=True,
                    type='transformers.CLIPImageProcessor.from_pretrained'),
                max_length=4096,
                offline_processed_text_folder=
                '/data/wenhao/projects/xtuner/data/ALLaVA-4V/pre_token_cv_llama31',
                pad_image_to_square=True,
                template_map_fn=dict(
                    template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
                    type='xtuner.dataset.map_fns.template_map_fn_factory'),
                type='xtuner.dataset.CambrianDataset'),
            dict(
                dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
                image_folder='/data/wenhao/projects/xtuner/data/ALLaVA-4V',
                image_processor=dict(
                    crop_size=378,
                    pretrained_model_name_or_path=
                    'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                    size=378,
                    trust_remote_code=True,
                    type='transformers.CLIPImageProcessor.from_pretrained'),
                max_length=4096,
                offline_processed_text_folder=
                '/data/wenhao/projects/xtuner/data/ALLaVA-4V/pre_token_il_llama31',
                pad_image_to_square=True,
                template_map_fn=dict(
                    template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
                    type='xtuner.dataset.map_fns.template_map_fn_factory'),
                type='xtuner.dataset.CambrianDataset'),
            dict(
                dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
                image_folder='/data/wenhao/projects/xtuner/data/ALLaVA-4V',
                image_processor=dict(
                    crop_size=378,
                    pretrained_model_name_or_path=
                    'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                    size=378,
                    trust_remote_code=True,
                    type='transformers.CLIPImageProcessor.from_pretrained'),
                max_length=4096,
                offline_processed_text_folder=
                '/data/wenhao/projects/xtuner/data/ALLaVA-4V/pre_token_iv_llama31',
                pad_image_to_square=True,
                template_map_fn=dict(
                    template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
                    type='xtuner.dataset.map_fns.template_map_fn_factory'),
                type='xtuner.dataset.CambrianDataset'),
            dict(
                dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
                image_folder=
                '/data/wenhao/projects/xtuner/data/LLaVA-Instruct-150K/images',
                image_processor=dict(
                    crop_size=378,
                    pretrained_model_name_or_path=
                    'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                    size=378,
                    trust_remote_code=True,
                    type='transformers.CLIPImageProcessor.from_pretrained'),
                max_length=4096,
                offline_processed_text_folder=
                '/data/wenhao/projects/xtuner/data/LLaVA-Instruct-150K/pre_token_llama31',
                pad_image_to_square=True,
                template_map_fn=dict(
                    template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
                    type='xtuner.dataset.map_fns.template_map_fn_factory'),
                type='xtuner.dataset.CambrianDataset'),
            dict(
                dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
                image_folder=
                '/data/wenhao/projects/xtuner/data/ALLaVA-4V/allava_text/images',
                image_processor=dict(
                    crop_size=378,
                    pretrained_model_name_or_path=
                    'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                    size=378,
                    trust_remote_code=True,
                    type='transformers.CLIPImageProcessor.from_pretrained'),
                max_length=4096,
                offline_processed_text_folder=
                '/data/wenhao/projects/xtuner/data/ALLaVA-4V/pre_token_evol_llama31',
                pad_image_to_square=True,
                template_map_fn=dict(
                    template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
                    type='xtuner.dataset.map_fns.template_map_fn_factory'),
                type='xtuner.dataset.CambrianDataset'),
            dict(
                dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
                image_folder='/data/wenhao/projects/xtuner/data',
                image_processor=dict(
                    crop_size=378,
                    pretrained_model_name_or_path=
                    'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                    size=378,
                    trust_remote_code=True,
                    type='transformers.CLIPImageProcessor.from_pretrained'),
                max_length=4096,
                offline_processed_text_folder=
                '/data/wenhao/projects/xtuner/data/ShareGPT4V/pre_token_sharegpt4v_llama31',
                pad_image_to_square=True,
                template_map_fn=dict(
                    template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
                    type='xtuner.dataset.map_fns.template_map_fn_factory'),
                type='xtuner.dataset.CambrianDataset'),
            dict(
                dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
                image_folder=
                '/data/wenhao/projects/xtuner/data/FaceCaption-15M/full_data',
                image_processor=dict(
                    crop_size=378,
                    pretrained_model_name_or_path=
                    'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                    size=378,
                    trust_remote_code=True,
                    type='transformers.CLIPImageProcessor.from_pretrained'),
                max_length=4096,
                offline_processed_text_folder=
                '/data/wenhao/projects/xtuner/data/FaceCaption-15M/pre_token_llama3',
                pad_image_to_square=True,
                template_map_fn=dict(
                    template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
                    type='xtuner.dataset.map_fns.template_map_fn_factory'),
                type='xtuner.dataset.CambrianDataset'),
        ],
        type='xtuner.dataset.ConcatDataset'),
    num_workers=0,
    sampler=dict(shuffle=True, type='mmengine.dataset.DefaultSampler'))
train_dataset = dict(
    datasets=[
        dict(
            dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
            image_folder='/data/wenhao/projects/xtuner/data/M4-Instruct-Data/',
            image_processor=dict(
                crop_size=378,
                pretrained_model_name_or_path=
                'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                size=378,
                trust_remote_code=True,
                type='transformers.CLIPImageProcessor.from_pretrained'),
            max_length=4096,
            offline_processed_text_folder=
            '/data/wenhao/projects/xtuner/data/M4-Instruct-Data/pre_token_llama31',
            pad_image_to_square=True,
            template_map_fn=dict(
                template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
                type='xtuner.dataset.map_fns.template_map_fn_factory'),
            type='xtuner.dataset.CambrianDataset'),
        dict(
            dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
            image_folder=
            '/data/wenhao/projects/xtuner/data/LLaVA-NeXT-Data/images',
            image_processor=dict(
                crop_size=378,
                pretrained_model_name_or_path=
                'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                size=378,
                trust_remote_code=True,
                type='transformers.CLIPImageProcessor.from_pretrained'),
            max_length=4096,
            offline_processed_text_folder=
            '/data/wenhao/projects/xtuner/data/LLaVA-NeXT-Data/pre_token_llama31',
            pad_image_to_square=True,
            template_map_fn=dict(
                template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
                type='xtuner.dataset.map_fns.template_map_fn_factory'),
            type='xtuner.dataset.CambrianDataset'),
        dict(
            dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
            image_folder='/data/wenhao/projects/xtuner/data/ALLaVA-4V',
            image_processor=dict(
                crop_size=378,
                pretrained_model_name_or_path=
                'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                size=378,
                trust_remote_code=True,
                type='transformers.CLIPImageProcessor.from_pretrained'),
            max_length=4096,
            offline_processed_text_folder=
            '/data/wenhao/projects/xtuner/data/ALLaVA-4V/pre_token_cl_llama31',
            pad_image_to_square=True,
            template_map_fn=dict(
                template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
                type='xtuner.dataset.map_fns.template_map_fn_factory'),
            type='xtuner.dataset.CambrianDataset'),
        dict(
            dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
            image_folder='/data/wenhao/projects/xtuner/data/ALLaVA-4V',
            image_processor=dict(
                crop_size=378,
                pretrained_model_name_or_path=
                'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                size=378,
                trust_remote_code=True,
                type='transformers.CLIPImageProcessor.from_pretrained'),
            max_length=4096,
            offline_processed_text_folder=
            '/data/wenhao/projects/xtuner/data/ALLaVA-4V/pre_token_cv_llama31',
            pad_image_to_square=True,
            template_map_fn=dict(
                template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
                type='xtuner.dataset.map_fns.template_map_fn_factory'),
            type='xtuner.dataset.CambrianDataset'),
        dict(
            dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
            image_folder='/data/wenhao/projects/xtuner/data/ALLaVA-4V',
            image_processor=dict(
                crop_size=378,
                pretrained_model_name_or_path=
                'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                size=378,
                trust_remote_code=True,
                type='transformers.CLIPImageProcessor.from_pretrained'),
            max_length=4096,
            offline_processed_text_folder=
            '/data/wenhao/projects/xtuner/data/ALLaVA-4V/pre_token_il_llama31',
            pad_image_to_square=True,
            template_map_fn=dict(
                template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
                type='xtuner.dataset.map_fns.template_map_fn_factory'),
            type='xtuner.dataset.CambrianDataset'),
        dict(
            dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
            image_folder='/data/wenhao/projects/xtuner/data/ALLaVA-4V',
            image_processor=dict(
                crop_size=378,
                pretrained_model_name_or_path=
                'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                size=378,
                trust_remote_code=True,
                type='transformers.CLIPImageProcessor.from_pretrained'),
            max_length=4096,
            offline_processed_text_folder=
            '/data/wenhao/projects/xtuner/data/ALLaVA-4V/pre_token_iv_llama31',
            pad_image_to_square=True,
            template_map_fn=dict(
                template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
                type='xtuner.dataset.map_fns.template_map_fn_factory'),
            type='xtuner.dataset.CambrianDataset'),
        dict(
            dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
            image_folder=
            '/data/wenhao/projects/xtuner/data/LLaVA-Instruct-150K/images',
            image_processor=dict(
                crop_size=378,
                pretrained_model_name_or_path=
                'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                size=378,
                trust_remote_code=True,
                type='transformers.CLIPImageProcessor.from_pretrained'),
            max_length=4096,
            offline_processed_text_folder=
            '/data/wenhao/projects/xtuner/data/LLaVA-Instruct-150K/pre_token_llama31',
            pad_image_to_square=True,
            template_map_fn=dict(
                template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
                type='xtuner.dataset.map_fns.template_map_fn_factory'),
            type='xtuner.dataset.CambrianDataset'),
        dict(
            dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
            image_folder=
            '/data/wenhao/projects/xtuner/data/ALLaVA-4V/allava_text/images',
            image_processor=dict(
                crop_size=378,
                pretrained_model_name_or_path=
                'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                size=378,
                trust_remote_code=True,
                type='transformers.CLIPImageProcessor.from_pretrained'),
            max_length=4096,
            offline_processed_text_folder=
            '/data/wenhao/projects/xtuner/data/ALLaVA-4V/pre_token_evol_llama31',
            pad_image_to_square=True,
            template_map_fn=dict(
                template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
                type='xtuner.dataset.map_fns.template_map_fn_factory'),
            type='xtuner.dataset.CambrianDataset'),
        dict(
            dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
            image_folder='/data/wenhao/projects/xtuner/data',
            image_processor=dict(
                crop_size=378,
                pretrained_model_name_or_path=
                'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                size=378,
                trust_remote_code=True,
                type='transformers.CLIPImageProcessor.from_pretrained'),
            max_length=4096,
            offline_processed_text_folder=
            '/data/wenhao/projects/xtuner/data/ShareGPT4V/pre_token_sharegpt4v_llama31',
            pad_image_to_square=True,
            template_map_fn=dict(
                template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
                type='xtuner.dataset.map_fns.template_map_fn_factory'),
            type='xtuner.dataset.CambrianDataset'),
        dict(
            dataset_map_fn='xtuner.dataset.map_fns.cambrian_map_fn',
            image_folder=
            '/data/wenhao/projects/xtuner/data/FaceCaption-15M/full_data',
            image_processor=dict(
                crop_size=378,
                pretrained_model_name_or_path=
                'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                size=378,
                trust_remote_code=True,
                type='transformers.CLIPImageProcessor.from_pretrained'),
            max_length=4096,
            offline_processed_text_folder=
            '/data/wenhao/projects/xtuner/data/FaceCaption-15M/pre_token_llama3',
            pad_image_to_square=True,
            template_map_fn=dict(
                template='xtuner.utils.PROMPT_TEMPLATE.llama3_chat',
                type='xtuner.dataset.map_fns.template_map_fn_factory'),
            type='xtuner.dataset.CambrianDataset'),
    ],
    type='xtuner.dataset.ConcatDataset')
visual_encoder_name_or_path = '/data/wenhao/projects/xtuner/work_dirs/final_new_v/visual_encoder'
visual_token_merge_ratio = 0.1
visualizer = None
warmup_ratio = 0.03
weight_decay = 0
work_dir = 'work_dirs/new_image'