File size: 36,892 Bytes
1247a15
 
02162cc
 
 
 
78c0f10
 
 
 
 
81ae1df
9ca90e4
 
4af7ce0
07ccef2
 
 
 
f1d73bf
02162cc
 
 
 
 
 
 
78c0f10
 
 
02162cc
1247a15
 
feb23b6
139296d
feb23b6
4af7ce0
feb23b6
1247a15
feb23b6
 
 
 
 
 
 
1247a15
feb23b6
1247a15
feb23b6
d159d67
feb23b6
d159d67
feb23b6
 
 
 
 
 
 
 
 
402ed7d
feb23b6
44d9a0b
feb23b6
44d9a0b
feb23b6
 
 
44d9a0b
feb23b6
 
 
44d9a0b
feb23b6
 
 
44d9a0b
feb23b6
 
 
44d9a0b
feb23b6
 
 
44d9a0b
feb23b6
44d9a0b
feb23b6
44d9a0b
57da752
feb23b6
 
44d9a0b
feb23b6
75d2037
feb23b6
e204b87
cc56b1b
feb23b6
 
 
 
 
 
 
adb2018
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
---
license: apache-2.0
datasets:
- HuggingFaceFW/fineweb
- PleIAs/YouTube-Commons
- allenai/WildChat-1M
- Salesforce/xlam-function-calling-60k
- ShareGPT4Video/ShareGPT4Video
- OpenGVLab/ShareGPT-4o
- TempoFunk/webvid-10M
- MBZUAI/VideoInstruct-100K
- Isaak-Carter/j.o.s.i.e.v4.0.1o
- NousResearch/dolma-v1_7-c4
- NousResearch/dolma-v1_7-cc_en_head
- nyu-visionx/Cambrian-10M
- LargeWorldModel/ultrachat_qa_mix_1M
- LargeWorldModel/ultrachat_qa_mix_512K
- LargeWorldModel/ultrachat_qa_mix_256K
- LargeWorldModel/ultrachat_qa_mix_128K
- nkp37/OpenVid-1M
language:
- de
- en
library_name: mlx
tags:
- moe
- multimodal
- vision
- audio
- endtoend
- j.o.s.i.e.
---

# J.O.S.I.E. (Just a Smart and Intelligent Entity)

Welcome to the J.O.S.I.E. project repository! J.O.S.I.E. is a cutting-edge, super intelligent AI assistant designed to revolutionize the way we interact with smart home systems and general AI capabilities. This document provides an overview of J.O.S.I.E.'s features, capabilities, and development roadmap.

## Table of Contents

1. [Introduction](#introduction)
2. [Features](#features)
3. [Training Stages](#training-stages)
4. [Current Progress](#current-progress)
5. [Usage](#usage)
6. [Contributing](#contributing)
7. [License](#license)

## Introduction

J.O.S.I.E. stands for "Just a Smart and Intelligent Entity." It is not just a conversational AI assistant but a fully multimodal AI designed to understand and process images, videos, thermal images, depth, and audio in real-time. J.O.S.I.E. is built to autonomously manage smart homes and provide general-purpose assistance, with advanced capabilities accessible only to the main user.

## Features

- **Real-Time Processing:** J.O.S.I.E. operates in real-time, ensuring quick and efficient responses.
- **Tool Calling:** Capable of calling various tools to perform tasks (only for the main user).
- **Short/Long-Term Memory:** Remembers past interactions and uses this data to provide a more personalized experience.
- **Secure Information Access:** Accesses top-secret information upon receiving a special password from the main user.
- **Contextual Greetings:** Greets users based on contextual data such as time of day, birthdays, and more.
- **Voice Interaction:** Will support real-time voice responses with a response time under 0.3 ms.
- **Advanced Multimodal Capabilities:** Initially uses Meta's image binding model, transitioning to a self-implemented encoder.
- **Uncensored Interaction:** Full, uncensored interaction capabilities are reserved for the main user.
- **Autonomous Smart Home Management:** Manages smart home devices and systems autonomously.

## Training Stages

J.O.S.I.E.'s development is structured into several meticulously planned stages, each focusing on different aspects of its capabilities:

### Stage 1: **Genesis**
- **Objective:** Fine-tune the Large Language Model (LLM) with a custom dataset and prompt format. The LLM used is Qwen2 7B and 0.5B.
- **Outcome:** A robust foundation for text-based interactions.

### Stage 2: **Fusion**
- **Objective:** Train encoders separately using transfer learning to align input embeddings with text embeddings.
- **Outcome:** Harmonized multimodal input processing.

### Stage 3: **Synergy**
- **Objective:** Fine-tune the LLM for multimodal reasoning using a custom dataset.
- **Outcome:** Enhanced reasoning capabilities across text and other modalities.

### Stage 4: **Vocalize**
- **Objective:** Fine-tune the decoder for audio output, giving J.O.S.I.E. a voice.
- **Outcome:** Synchronized text and audio responses.

### Stage 5: **Convergence**
- **Objective:** Perform full model fine-tuning for seamless integration of all components.
- **Outcome:** A fully multimodal, real-time interactive AI assistant.

## Current Progress

J.O.S.I.E. is currently in its beta stage, specifically in Stage 1. The model is being actively developed, and the current version is focused on fine-tuning the LLM with custom datasets.

### Latest Beta Version 4 of Stage 1:
- **Model:** [Isaak-Carter/josiev4o-7b-stage1-v0.1](https://huggingface.co/Isaak-Carter/J.O.S.I.E.v4o-7b-stage1-v0.1-gguf)
- **Quants:** [Isaak-Carter/J.O.S.I.E.v4o-7b-stage1-v0.1-gguf](https://huggingface.co/Isaak-Carter/J.O.S.I.E.v4o-7b-stage1-v0.1-gguf)

For a sneak peek at the current progress, visit the [GitHub Repo](https://github.com/Goekdeniz-Guelmez/J.O.S.I.E.-v4o.git).

## Source Code

To se the latest updates on J.O.S.I.E.v4o you can see my <a href="https://github.com/Goekdeniz-Guelmez/J.O.S.I.E.-v4o.git">Github Repo</a>
   
## Contributing

I welcome contributions from the you! To contribute to J.O.S.I.E., please fork the repository and create a pull request with your changes. Ensure that your code adheres to my coding standards and includes appropriate tests and comments.

## License

J.O.S.I.E. is licensed under the Apache2 License. See the [LICENSE](LICENSE) file for more details.





# Big Updates!

I have finaly trained the Vision and Audio encoder part, big thangs to FaceBook Research for the ImageBind model, wich is what I have build it on top of.

What I did was, I copied the weights from the original ImageBind model into a second 'downcycled' ImageBindVisionAudioHuge model.
After that I have continued to trained the model on a custom Vision and Audio dataset using the contrastive learning Algorythm introduced by Google with Pali Gemma with the text embeddings from the origional ImageBind model.

After mergind the encoder with the test reasoner (Qwen2-0.5B-Instruct), I got succesfull inference on both video, image and audio.
I will slowly start writing the training scrypt, creating the new dataset, and optimizing the model and inference code a litle bit more, and lastly train the model.

Here are the actual model layers:

```txt
ImageBindModelAudioVision(
  (modality_preprocessors): ModuleDict(
    (vision): RGBDTPreprocessor(
      (cls_token): tensor((1, 1, 1280), requires_grad=True)
      
      (rgbt_stem): PatchEmbedGeneric(
        (proj): Sequential(
          (0): PadIm2Video()
          (1): Conv3d(3, 1280, kernel_size=(2, 14, 14), stride=(2, 14, 14), bias=False)
        )
      )
      (pos_embedding_helper): SpatioTemporalPosEmbeddingHelper(
        (pos_embed): tensor((1, 257, 1280), requires_grad=True)
        
      )
    )
    (audio): AudioPreprocessor(
      (cls_token): tensor((1, 1, 768), requires_grad=True)
      
      (rgbt_stem): PatchEmbedGeneric(
        (proj): Conv2d(1, 768, kernel_size=(16, 16), stride=(10, 10), bias=False)
        (norm_layer): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
      )
      (pos_embedding_helper): SpatioTemporalPosEmbeddingHelper(
        (pos_embed): tensor((1, 229, 768), requires_grad=True)
        
      )
    )
  )
  (modality_trunks): ModuleDict(
    (vision): SimpleTransformer(
      (pre_transformer_layer): Sequential(
        (0): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        (1): EinOpsRearrange()
      )
      (blocks): Sequential(
        (0): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (1): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (2): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (3): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (4): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (5): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (6): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (7): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (8): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (9): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (10): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (11): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (12): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (13): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (14): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (15): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (16): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (17): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (18): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (19): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (20): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (21): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (22): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (23): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (24): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (25): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (26): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (27): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (28): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (29): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (30): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
        (31): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=1280, out_features=1280, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=1280, out_features=5120, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=5120, out_features=1280, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
        )
      )
      (post_transformer_layer): EinOpsRearrange()
    )
    (audio): SimpleTransformer(
      (pre_transformer_layer): Sequential(
        (0): Identity()
        (1): EinOpsRearrange()
      )
      (blocks): Sequential(
        (0): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
          )
          (drop_path): Identity()
          (norm_1): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=768, out_features=3072, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=3072, out_features=768, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
        )
        (1): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.009)
          (norm_1): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=768, out_features=3072, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=3072, out_features=768, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
        )
        (2): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.018)
          (norm_1): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=768, out_features=3072, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=3072, out_features=768, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
        )
        (3): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.027)
          (norm_1): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=768, out_features=3072, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=3072, out_features=768, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
        )
        (4): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.036)
          (norm_1): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=768, out_features=3072, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=3072, out_features=768, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
        )
        (5): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.045)
          (norm_1): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=768, out_features=3072, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=3072, out_features=768, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
        )
        (6): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.055)
          (norm_1): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=768, out_features=3072, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=3072, out_features=768, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
        )
        (7): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.064)
          (norm_1): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=768, out_features=3072, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=3072, out_features=768, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
        )
        (8): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.073)
          (norm_1): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=768, out_features=3072, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=3072, out_features=768, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
        )
        (9): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.082)
          (norm_1): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=768, out_features=3072, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=3072, out_features=768, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
        )
        (10): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.091)
          (norm_1): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=768, out_features=3072, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=3072, out_features=768, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
        )
        (11): BlockWithMasking(
          (attn): MultiheadAttention(
            (out_proj): NonDynamicallyQuantizableLinear(in_features=768, out_features=768, bias=True)
          )
          (drop_path): DropPath(drop_prob=0.100)
          (norm_1): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
          (mlp): Mlp(
            (fc1): Linear(in_features=768, out_features=3072, bias=True)
            (act): GELU(approximate='none')
            (fc2): Linear(in_features=3072, out_features=768, bias=True)
            (drop): Dropout(p=0.0, inplace=False)
          )
          (norm_2): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
        )
      )
      (post_transformer_layer): EinOpsRearrange()
    )
  )
  (modality_heads): ModuleDict(
    (vision): Sequential(
      (0): LayerNorm((1280,), eps=1e-06, elementwise_affine=True)
      (1): SelectElement()
      (2): Linear(in_features=1280, out_features=1024, bias=False)
    )
    (audio): Sequential(
      (0): LayerNorm((768,), eps=1e-06, elementwise_affine=True)
      (1): SelectElement()
      (2): Linear(in_features=768, out_features=1024, bias=False)
    )
  )
  (modality_postprocessors): ModuleDict(
    (vision): Normalize()
    (audio): Sequential(
      (0): Normalize()
      (1): LearnableLogitScaling(logit_scale_init=20.0,learnable=False, max_logit_scale=100)
    )
  )
)
```