kaiw7 commited on
Commit
552c598
·
verified ·
1 Parent(s): e490e7e

Add files using upload-large-folder tool

Browse files
Files changed (39) hide show
  1. audio-only/000-Wan2_1_T2V_1_3B/config.txt +153 -0
  2. audio-only/000-Wan2_1_T2V_1_3B/epoch048-global_step52000/ema.pt +3 -0
  3. audio-only/000-Wan2_1_T2V_1_3B/epoch048-global_step52000/lr_scheduler +0 -0
  4. audio-only/000-Wan2_1_T2V_1_3B/epoch048-global_step52000/model/pytorch_model-00001.bin +3 -0
  5. audio-only/000-Wan2_1_T2V_1_3B/epoch048-global_step52000/model/pytorch_model-00002.bin +3 -0
  6. audio-only/000-Wan2_1_T2V_1_3B/epoch048-global_step52000/model/pytorch_model-00003.bin +3 -0
  7. audio-only/000-Wan2_1_T2V_1_3B/epoch048-global_step52000/model/pytorch_model.bin.index.json +864 -0
  8. audio-only/000-Wan2_1_T2V_1_3B/epoch048-global_step52000/optimizer/pytorch_optim-00001.bin +3 -0
  9. audio-only/000-Wan2_1_T2V_1_3B/epoch048-global_step52000/optimizer/pytorch_optim-00002.bin +3 -0
  10. audio-only/000-Wan2_1_T2V_1_3B/epoch048-global_step52000/optimizer/pytorch_optim.bin.index.json +165 -0
  11. audio-only/000-Wan2_1_T2V_1_3B/epoch048-global_step52000/optimizer/pytorch_optim_group.bin +3 -0
  12. audio-only/000-Wan2_1_T2V_1_3B/epoch048-global_step52000/running_states.json +6 -0
  13. audio-only/000-Wan2_1_T2V_1_3B/epoch048-global_step52000/sampler +0 -0
  14. audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53000/ema.pt +3 -0
  15. audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53000/lr_scheduler +0 -0
  16. audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53000/model/pytorch_model-00001.bin +3 -0
  17. audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53000/model/pytorch_model-00002.bin +3 -0
  18. audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53000/model/pytorch_model-00003.bin +3 -0
  19. audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53000/model/pytorch_model.bin.index.json +864 -0
  20. audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53000/optimizer/pytorch_optim-00001.bin +3 -0
  21. audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53000/optimizer/pytorch_optim-00002.bin +3 -0
  22. audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53000/optimizer/pytorch_optim.bin.index.json +165 -0
  23. audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53000/optimizer/pytorch_optim_group.bin +3 -0
  24. audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53000/running_states.json +6 -0
  25. audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53000/sampler +0 -0
  26. audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53650/ema.pt +3 -0
  27. audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53650/lr_scheduler +0 -0
  28. audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53650/model/pytorch_model-00001.bin +3 -0
  29. audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53650/model/pytorch_model-00002.bin +3 -0
  30. audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53650/model/pytorch_model-00003.bin +3 -0
  31. audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53650/model/pytorch_model.bin.index.json +864 -0
  32. audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53650/optimizer/pytorch_optim-00001.bin +3 -0
  33. audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53650/optimizer/pytorch_optim-00002.bin +3 -0
  34. audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53650/optimizer/pytorch_optim.bin.index.json +165 -0
  35. audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53650/optimizer/pytorch_optim_group.bin +3 -0
  36. audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53650/running_states.json +6 -0
  37. audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53650/sampler +0 -0
  38. audio-only/000-Wan2_1_T2V_1_3B/log.txt +0 -0
  39. audio-only/000-Wan2_1_T2V_1_3B/tensorboard/events.out.tfevents.1760758333.c0f6c83c-35.cloud.together.ai.2607279.0 +3 -0
audio-only/000-Wan2_1_T2V_1_3B/config.txt ADDED
@@ -0,0 +1,153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio_only": true,
3
+ "dataset": {
4
+ "type": "VariableVideoAudioTextDataset",
5
+ "transform_name": "resize_crop",
6
+ "audio_transform_name": "mel_spec_audioldm2",
7
+ "audio_only": true,
8
+ "default_video_fps": 24,
9
+ "data_path": "/data/yikai/mocha/pr/audio/alan/datasets/JAV-Audio-Data/JavisDiT_train_audio_v1.csv"
10
+ },
11
+ "bucket_config": {
12
+ "144p": {
13
+ "33": [
14
+ 1.0,
15
+ 128
16
+ ],
17
+ "65": [
18
+ [
19
+ 1.0,
20
+ 0.5
21
+ ],
22
+ 96
23
+ ],
24
+ "97": [
25
+ [
26
+ 1.0,
27
+ 0.3
28
+ ],
29
+ 80
30
+ ],
31
+ "129": [
32
+ [
33
+ 1.0,
34
+ 0.2
35
+ ],
36
+ 64
37
+ ]
38
+ }
39
+ },
40
+ "grad_checkpoint": true,
41
+ "num_workers": 16,
42
+ "num_bucket_build_workers": 8,
43
+ "dtype": "bf16",
44
+ "plugin": "zero2",
45
+ "weight_root": "/data/yikai/mocha/pr/audio/alan/projects/pretrained_weights",
46
+ "model": {
47
+ "type": "Wan2_1_T2V_1_3B",
48
+ "weight_init_from": "/data/yikai/mocha/pr/audio/alan/projects/pretrained_weights/Wan2.1-T2V-1.3B/diffusion_pytorch_model.safetensors",
49
+ "model_type": "t2a",
50
+ "patch_size": [
51
+ 1,
52
+ 2,
53
+ 2
54
+ ],
55
+ "dim": 1536,
56
+ "ffn_dim": 8960,
57
+ "freq_dim": 256,
58
+ "num_heads": 12,
59
+ "num_layers": 30,
60
+ "window_size": [
61
+ -1,
62
+ -1
63
+ ],
64
+ "qk_norm": true,
65
+ "cross_attn_norm": true,
66
+ "audio_patch_size": [
67
+ 2,
68
+ 2
69
+ ],
70
+ "audio_in_dim": 8,
71
+ "audio_out_dim": 8,
72
+ "audio_special_token": false,
73
+ "train_audio_specific_blocks": true,
74
+ "dual_ffn": true,
75
+ "init_from_video_branch": true,
76
+ "class_drop_prob": 0.1,
77
+ "audio_pe_type": "interleave_window_offset",
78
+ "audio_patch_type": "patch_2d"
79
+ },
80
+ "vae": {
81
+ "type": "Wan2_1_T2V_1_3B_VAE",
82
+ "from_pretrained": "/data/yikai/mocha/pr/audio/alan/projects/pretrained_weights/Wan2.1-T2V-1.3B",
83
+ "vae_checkpoint": "Wan2.1_VAE.pth",
84
+ "vae_stride": [
85
+ 4,
86
+ 8,
87
+ 8
88
+ ]
89
+ },
90
+ "audio_vae": {
91
+ "type": "AudioLDM2",
92
+ "from_pretrained": "/data/yikai/mocha/pr/audio/alan/projects/pretrained_weights/audioldm2"
93
+ },
94
+ "text_encoder": {
95
+ "type": "Wan2_1_T2V_1_3B_t5_umt5",
96
+ "from_pretrained": "/data/yikai/mocha/pr/audio/alan/projects/pretrained_weights/Wan2.1-T2V-1.3B",
97
+ "t5_checkpoint": "models_t5_umt5-xxl-enc-bf16.pth",
98
+ "t5_tokenizer": "google/umt5-xxl",
99
+ "text_len": 512
100
+ },
101
+ "scheduler": {
102
+ "type": "rflow",
103
+ "use_timestep_transform": true,
104
+ "sample_method": "logit-normal",
105
+ "num_sampling_steps": 50,
106
+ "transform_scale": 5.0
107
+ },
108
+ "aes": null,
109
+ "flow": null,
110
+ "neg_prompt": "\u8272\u8c03\u8273\u4e3d\uff0c\u8fc7\u66dd\uff0c\u9759\u6001\uff0c\u7ec6\u8282\u6a21\u7cca\u4e0d\u6e05\uff0c\u5b57\u5e55\uff0c\u98ce\u683c\uff0c\u4f5c\u54c1\uff0c\u753b\u4f5c\uff0c\u753b\u9762\uff0c\u9759\u6b62\uff0c\u6574\u4f53\u53d1\u7070\uff0c\u6700\u5dee\u8d28\u91cf\uff0c\u4f4e\u8d28\u91cf\uff0cJPEG\u538b\u7f29\u6b8b\u7559\uff0c\u4e11\u964b\u7684\uff0c\u6b8b\u7f3a\u7684\uff0c\u591a\u4f59\u7684\u624b\u6307\uff0c\u753b\u5f97\u4e0d\u597d\u7684\u624b\u90e8\uff0c\u753b\u5f97\u4e0d\u597d\u7684\u8138\u90e8\uff0c\u7578\u5f62\u7684\uff0c\u6bc1\u5bb9\u7684\uff0c\u5f62\u6001\u7578\u5f62\u7684\u80a2\u4f53\uff0c\u624b\u6307\u878d\u5408\uff0c\u9759\u6b62\u4e0d\u52a8\u7684\u753b\u9762\uff0c\u6742\u4e71\u7684\u80cc\u666f\uff0c\u4e09\u6761\u817f\uff0c\u80cc\u666f\u4eba\u5f88\u591a\uff0c\u5012\u7740\u8d70\uff0c\u4f4e\u97f3\u8d28\uff0c\u5dee\u97f3\u8d28\uff0c\u6700\u5dee\u97f3\u8d28\uff0c\u566a\u97f3\uff0c\u5931\u771f\u7684\uff0c\u7834\u97f3\uff0c\u524a\u6ce2\u5931\u771f\uff0c\u6570\u5b57\u7455\u75b5\uff0c\u58f0\u97f3\u6545\u969c\uff0c\u4e0d\u81ea\u7136\u7684\uff0c\u523a\u8033\u7684\uff0c\u5c16\u9510\u7684\uff0c\u5e95\u566a\uff0c\u8fc7\u591a\u6df7\u54cd\uff0c\u8fc7\u591a\u56de\u58f0\uff0c\u7a81\u5140\u7684\u526a\u8f91\uff0c\u4e0d\u81ea\u7136\u7684\u6de1\u51fa\uff0c\u5f55\u97f3\u8d28\u91cf\u5dee\uff0c\u4e1a\u4f59\u5f55\u97f3",
111
+ "lora_enabled": false,
112
+ "seed": 42,
113
+ "outputs": "outputs/audio-only",
114
+ "wandb": false,
115
+ "epochs": 50,
116
+ "log_every": 10,
117
+ "ckpt_every": 1000,
118
+ "save_total_limit": 2,
119
+ "load": null,
120
+ "grad_clip": 1.0,
121
+ "lr": 0.0001,
122
+ "ema_decay": 0.99,
123
+ "adam_eps": 1e-15,
124
+ "warmup_steps": 1000,
125
+ "sampling_rate": 16000,
126
+ "mel_bins": 64,
127
+ "audio_cfg": {
128
+ "preprocessing": {
129
+ "audio": {
130
+ "sampling_rate": 16000,
131
+ "max_wav_value": 32768.0,
132
+ "duration": 10.24,
133
+ "scale_factor": 8
134
+ },
135
+ "stft": {
136
+ "filter_length": 1024,
137
+ "hop_length": 160,
138
+ "win_length": 1024
139
+ },
140
+ "mel": {
141
+ "n_mel_channels": 64,
142
+ "mel_fmin": 0,
143
+ "mel_fmax": 8000
144
+ }
145
+ },
146
+ "augmentation": {
147
+ "mixup": 0.0
148
+ }
149
+ },
150
+ "config": "configs/wan2.1/train/stage1_audio.py",
151
+ "lora_dir": "lora",
152
+ "port": 29500
153
+ }
audio-only/000-Wan2_1_T2V_1_3B/epoch048-global_step52000/ema.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27e7e8efc3feb0d5a37b7ca80bd50e767432f19b6b6fac11467a9a7a88604bdf
3
+ size 5704739068
audio-only/000-Wan2_1_T2V_1_3B/epoch048-global_step52000/lr_scheduler ADDED
Binary file (1.01 kB). View file
 
audio-only/000-Wan2_1_T2V_1_3B/epoch048-global_step52000/model/pytorch_model-00001.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cafc0ed6f38219dceba38ff466caf945e4d0a2bda65c6e5ef9f9eabc0cbc8375
3
+ size 1059881014
audio-only/000-Wan2_1_T2V_1_3B/epoch048-global_step52000/model/pytorch_model-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd2a01fd41a7cf0faf79824104bcee54d47d0e7f1ab4dbf10858b44d40f1db56
3
+ size 1073076766
audio-only/000-Wan2_1_T2V_1_3B/epoch048-global_step52000/model/pytorch_model-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d3cb636158d485ef7ca185b1a4a2fef928e92a4dc10f543db761fe6ce5b56a8
3
+ size 719552332
audio-only/000-Wan2_1_T2V_1_3B/epoch048-global_step52000/model/pytorch_model.bin.index.json ADDED
@@ -0,0 +1,864 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 2720.1065063476562
4
+ },
5
+ "weight_map": {
6
+ "audio_patch_embedding.weight": "pytorch_model-00001.bin",
7
+ "audio_patch_embedding.bias": "pytorch_model-00001.bin",
8
+ "audio_head.modulation": "pytorch_model-00001.bin",
9
+ "audio_head.head.weight": "pytorch_model-00001.bin",
10
+ "audio_head.head.bias": "pytorch_model-00001.bin",
11
+ "text_embedding.0.weight": "pytorch_model-00001.bin",
12
+ "text_embedding.0.bias": "pytorch_model-00001.bin",
13
+ "text_embedding.2.weight": "pytorch_model-00001.bin",
14
+ "text_embedding.2.bias": "pytorch_model-00001.bin",
15
+ "time_embedding.0.weight": "pytorch_model-00001.bin",
16
+ "time_embedding.0.bias": "pytorch_model-00001.bin",
17
+ "time_embedding.2.weight": "pytorch_model-00001.bin",
18
+ "time_embedding.2.bias": "pytorch_model-00001.bin",
19
+ "time_projection.1.weight": "pytorch_model-00001.bin",
20
+ "time_projection.1.bias": "pytorch_model-00001.bin",
21
+ "audio_time_projection.1.weight": "pytorch_model-00001.bin",
22
+ "audio_time_projection.1.bias": "pytorch_model-00001.bin",
23
+ "blocks.0.modulation": "pytorch_model-00001.bin",
24
+ "blocks.0.self_attn.q.weight": "pytorch_model-00001.bin",
25
+ "blocks.0.self_attn.q.bias": "pytorch_model-00001.bin",
26
+ "blocks.0.self_attn.k.weight": "pytorch_model-00001.bin",
27
+ "blocks.0.self_attn.k.bias": "pytorch_model-00001.bin",
28
+ "blocks.0.self_attn.v.weight": "pytorch_model-00001.bin",
29
+ "blocks.0.self_attn.v.bias": "pytorch_model-00001.bin",
30
+ "blocks.0.self_attn.o.weight": "pytorch_model-00001.bin",
31
+ "blocks.0.self_attn.o.bias": "pytorch_model-00001.bin",
32
+ "blocks.0.self_attn.norm_q.weight": "pytorch_model-00001.bin",
33
+ "blocks.0.self_attn.norm_k.weight": "pytorch_model-00001.bin",
34
+ "blocks.0.norm3.weight": "pytorch_model-00001.bin",
35
+ "blocks.0.norm3.bias": "pytorch_model-00001.bin",
36
+ "blocks.0.cross_attn.q.weight": "pytorch_model-00001.bin",
37
+ "blocks.0.cross_attn.q.bias": "pytorch_model-00001.bin",
38
+ "blocks.0.cross_attn.k.weight": "pytorch_model-00001.bin",
39
+ "blocks.0.cross_attn.k.bias": "pytorch_model-00001.bin",
40
+ "blocks.0.cross_attn.v.weight": "pytorch_model-00001.bin",
41
+ "blocks.0.cross_attn.v.bias": "pytorch_model-00001.bin",
42
+ "blocks.0.cross_attn.o.weight": "pytorch_model-00001.bin",
43
+ "blocks.0.cross_attn.o.bias": "pytorch_model-00001.bin",
44
+ "blocks.0.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
45
+ "blocks.0.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
46
+ "blocks.0.audio_ffn.0.weight": "pytorch_model-00001.bin",
47
+ "blocks.0.audio_ffn.0.bias": "pytorch_model-00001.bin",
48
+ "blocks.0.audio_ffn.2.weight": "pytorch_model-00001.bin",
49
+ "blocks.0.audio_ffn.2.bias": "pytorch_model-00001.bin",
50
+ "blocks.0.audio_modulation.param": "pytorch_model-00001.bin",
51
+ "blocks.1.modulation": "pytorch_model-00001.bin",
52
+ "blocks.1.self_attn.q.weight": "pytorch_model-00001.bin",
53
+ "blocks.1.self_attn.q.bias": "pytorch_model-00001.bin",
54
+ "blocks.1.self_attn.k.weight": "pytorch_model-00001.bin",
55
+ "blocks.1.self_attn.k.bias": "pytorch_model-00001.bin",
56
+ "blocks.1.self_attn.v.weight": "pytorch_model-00001.bin",
57
+ "blocks.1.self_attn.v.bias": "pytorch_model-00001.bin",
58
+ "blocks.1.self_attn.o.weight": "pytorch_model-00001.bin",
59
+ "blocks.1.self_attn.o.bias": "pytorch_model-00001.bin",
60
+ "blocks.1.self_attn.norm_q.weight": "pytorch_model-00001.bin",
61
+ "blocks.1.self_attn.norm_k.weight": "pytorch_model-00001.bin",
62
+ "blocks.1.norm3.weight": "pytorch_model-00001.bin",
63
+ "blocks.1.norm3.bias": "pytorch_model-00001.bin",
64
+ "blocks.1.cross_attn.q.weight": "pytorch_model-00001.bin",
65
+ "blocks.1.cross_attn.q.bias": "pytorch_model-00001.bin",
66
+ "blocks.1.cross_attn.k.weight": "pytorch_model-00001.bin",
67
+ "blocks.1.cross_attn.k.bias": "pytorch_model-00001.bin",
68
+ "blocks.1.cross_attn.v.weight": "pytorch_model-00001.bin",
69
+ "blocks.1.cross_attn.v.bias": "pytorch_model-00001.bin",
70
+ "blocks.1.cross_attn.o.weight": "pytorch_model-00001.bin",
71
+ "blocks.1.cross_attn.o.bias": "pytorch_model-00001.bin",
72
+ "blocks.1.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
73
+ "blocks.1.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
74
+ "blocks.1.audio_ffn.0.weight": "pytorch_model-00001.bin",
75
+ "blocks.1.audio_ffn.0.bias": "pytorch_model-00001.bin",
76
+ "blocks.1.audio_ffn.2.weight": "pytorch_model-00001.bin",
77
+ "blocks.1.audio_ffn.2.bias": "pytorch_model-00001.bin",
78
+ "blocks.1.audio_modulation.param": "pytorch_model-00001.bin",
79
+ "blocks.2.modulation": "pytorch_model-00001.bin",
80
+ "blocks.2.self_attn.q.weight": "pytorch_model-00001.bin",
81
+ "blocks.2.self_attn.q.bias": "pytorch_model-00001.bin",
82
+ "blocks.2.self_attn.k.weight": "pytorch_model-00001.bin",
83
+ "blocks.2.self_attn.k.bias": "pytorch_model-00001.bin",
84
+ "blocks.2.self_attn.v.weight": "pytorch_model-00001.bin",
85
+ "blocks.2.self_attn.v.bias": "pytorch_model-00001.bin",
86
+ "blocks.2.self_attn.o.weight": "pytorch_model-00001.bin",
87
+ "blocks.2.self_attn.o.bias": "pytorch_model-00001.bin",
88
+ "blocks.2.self_attn.norm_q.weight": "pytorch_model-00001.bin",
89
+ "blocks.2.self_attn.norm_k.weight": "pytorch_model-00001.bin",
90
+ "blocks.2.norm3.weight": "pytorch_model-00001.bin",
91
+ "blocks.2.norm3.bias": "pytorch_model-00001.bin",
92
+ "blocks.2.cross_attn.q.weight": "pytorch_model-00001.bin",
93
+ "blocks.2.cross_attn.q.bias": "pytorch_model-00001.bin",
94
+ "blocks.2.cross_attn.k.weight": "pytorch_model-00001.bin",
95
+ "blocks.2.cross_attn.k.bias": "pytorch_model-00001.bin",
96
+ "blocks.2.cross_attn.v.weight": "pytorch_model-00001.bin",
97
+ "blocks.2.cross_attn.v.bias": "pytorch_model-00001.bin",
98
+ "blocks.2.cross_attn.o.weight": "pytorch_model-00001.bin",
99
+ "blocks.2.cross_attn.o.bias": "pytorch_model-00001.bin",
100
+ "blocks.2.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
101
+ "blocks.2.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
102
+ "blocks.2.audio_ffn.0.weight": "pytorch_model-00001.bin",
103
+ "blocks.2.audio_ffn.0.bias": "pytorch_model-00001.bin",
104
+ "blocks.2.audio_ffn.2.weight": "pytorch_model-00001.bin",
105
+ "blocks.2.audio_ffn.2.bias": "pytorch_model-00001.bin",
106
+ "blocks.2.audio_modulation.param": "pytorch_model-00001.bin",
107
+ "blocks.3.modulation": "pytorch_model-00001.bin",
108
+ "blocks.3.self_attn.q.weight": "pytorch_model-00001.bin",
109
+ "blocks.3.self_attn.q.bias": "pytorch_model-00001.bin",
110
+ "blocks.3.self_attn.k.weight": "pytorch_model-00001.bin",
111
+ "blocks.3.self_attn.k.bias": "pytorch_model-00001.bin",
112
+ "blocks.3.self_attn.v.weight": "pytorch_model-00001.bin",
113
+ "blocks.3.self_attn.v.bias": "pytorch_model-00001.bin",
114
+ "blocks.3.self_attn.o.weight": "pytorch_model-00001.bin",
115
+ "blocks.3.self_attn.o.bias": "pytorch_model-00001.bin",
116
+ "blocks.3.self_attn.norm_q.weight": "pytorch_model-00001.bin",
117
+ "blocks.3.self_attn.norm_k.weight": "pytorch_model-00001.bin",
118
+ "blocks.3.norm3.weight": "pytorch_model-00001.bin",
119
+ "blocks.3.norm3.bias": "pytorch_model-00001.bin",
120
+ "blocks.3.cross_attn.q.weight": "pytorch_model-00001.bin",
121
+ "blocks.3.cross_attn.q.bias": "pytorch_model-00001.bin",
122
+ "blocks.3.cross_attn.k.weight": "pytorch_model-00001.bin",
123
+ "blocks.3.cross_attn.k.bias": "pytorch_model-00001.bin",
124
+ "blocks.3.cross_attn.v.weight": "pytorch_model-00001.bin",
125
+ "blocks.3.cross_attn.v.bias": "pytorch_model-00001.bin",
126
+ "blocks.3.cross_attn.o.weight": "pytorch_model-00001.bin",
127
+ "blocks.3.cross_attn.o.bias": "pytorch_model-00001.bin",
128
+ "blocks.3.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
129
+ "blocks.3.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
130
+ "blocks.3.audio_ffn.0.weight": "pytorch_model-00001.bin",
131
+ "blocks.3.audio_ffn.0.bias": "pytorch_model-00001.bin",
132
+ "blocks.3.audio_ffn.2.weight": "pytorch_model-00001.bin",
133
+ "blocks.3.audio_ffn.2.bias": "pytorch_model-00001.bin",
134
+ "blocks.3.audio_modulation.param": "pytorch_model-00001.bin",
135
+ "blocks.4.modulation": "pytorch_model-00001.bin",
136
+ "blocks.4.self_attn.q.weight": "pytorch_model-00001.bin",
137
+ "blocks.4.self_attn.q.bias": "pytorch_model-00001.bin",
138
+ "blocks.4.self_attn.k.weight": "pytorch_model-00001.bin",
139
+ "blocks.4.self_attn.k.bias": "pytorch_model-00001.bin",
140
+ "blocks.4.self_attn.v.weight": "pytorch_model-00001.bin",
141
+ "blocks.4.self_attn.v.bias": "pytorch_model-00001.bin",
142
+ "blocks.4.self_attn.o.weight": "pytorch_model-00001.bin",
143
+ "blocks.4.self_attn.o.bias": "pytorch_model-00001.bin",
144
+ "blocks.4.self_attn.norm_q.weight": "pytorch_model-00001.bin",
145
+ "blocks.4.self_attn.norm_k.weight": "pytorch_model-00001.bin",
146
+ "blocks.4.norm3.weight": "pytorch_model-00001.bin",
147
+ "blocks.4.norm3.bias": "pytorch_model-00001.bin",
148
+ "blocks.4.cross_attn.q.weight": "pytorch_model-00001.bin",
149
+ "blocks.4.cross_attn.q.bias": "pytorch_model-00001.bin",
150
+ "blocks.4.cross_attn.k.weight": "pytorch_model-00001.bin",
151
+ "blocks.4.cross_attn.k.bias": "pytorch_model-00001.bin",
152
+ "blocks.4.cross_attn.v.weight": "pytorch_model-00001.bin",
153
+ "blocks.4.cross_attn.v.bias": "pytorch_model-00001.bin",
154
+ "blocks.4.cross_attn.o.weight": "pytorch_model-00001.bin",
155
+ "blocks.4.cross_attn.o.bias": "pytorch_model-00001.bin",
156
+ "blocks.4.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
157
+ "blocks.4.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
158
+ "blocks.4.audio_ffn.0.weight": "pytorch_model-00001.bin",
159
+ "blocks.4.audio_ffn.0.bias": "pytorch_model-00001.bin",
160
+ "blocks.4.audio_ffn.2.weight": "pytorch_model-00001.bin",
161
+ "blocks.4.audio_ffn.2.bias": "pytorch_model-00001.bin",
162
+ "blocks.4.audio_modulation.param": "pytorch_model-00001.bin",
163
+ "blocks.5.modulation": "pytorch_model-00001.bin",
164
+ "blocks.5.self_attn.q.weight": "pytorch_model-00001.bin",
165
+ "blocks.5.self_attn.q.bias": "pytorch_model-00001.bin",
166
+ "blocks.5.self_attn.k.weight": "pytorch_model-00001.bin",
167
+ "blocks.5.self_attn.k.bias": "pytorch_model-00001.bin",
168
+ "blocks.5.self_attn.v.weight": "pytorch_model-00001.bin",
169
+ "blocks.5.self_attn.v.bias": "pytorch_model-00001.bin",
170
+ "blocks.5.self_attn.o.weight": "pytorch_model-00001.bin",
171
+ "blocks.5.self_attn.o.bias": "pytorch_model-00001.bin",
172
+ "blocks.5.self_attn.norm_q.weight": "pytorch_model-00001.bin",
173
+ "blocks.5.self_attn.norm_k.weight": "pytorch_model-00001.bin",
174
+ "blocks.5.norm3.weight": "pytorch_model-00001.bin",
175
+ "blocks.5.norm3.bias": "pytorch_model-00001.bin",
176
+ "blocks.5.cross_attn.q.weight": "pytorch_model-00001.bin",
177
+ "blocks.5.cross_attn.q.bias": "pytorch_model-00001.bin",
178
+ "blocks.5.cross_attn.k.weight": "pytorch_model-00001.bin",
179
+ "blocks.5.cross_attn.k.bias": "pytorch_model-00001.bin",
180
+ "blocks.5.cross_attn.v.weight": "pytorch_model-00001.bin",
181
+ "blocks.5.cross_attn.v.bias": "pytorch_model-00001.bin",
182
+ "blocks.5.cross_attn.o.weight": "pytorch_model-00001.bin",
183
+ "blocks.5.cross_attn.o.bias": "pytorch_model-00001.bin",
184
+ "blocks.5.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
185
+ "blocks.5.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
186
+ "blocks.5.audio_ffn.0.weight": "pytorch_model-00001.bin",
187
+ "blocks.5.audio_ffn.0.bias": "pytorch_model-00001.bin",
188
+ "blocks.5.audio_ffn.2.weight": "pytorch_model-00001.bin",
189
+ "blocks.5.audio_ffn.2.bias": "pytorch_model-00001.bin",
190
+ "blocks.5.audio_modulation.param": "pytorch_model-00001.bin",
191
+ "blocks.6.modulation": "pytorch_model-00001.bin",
192
+ "blocks.6.self_attn.q.weight": "pytorch_model-00001.bin",
193
+ "blocks.6.self_attn.q.bias": "pytorch_model-00001.bin",
194
+ "blocks.6.self_attn.k.weight": "pytorch_model-00001.bin",
195
+ "blocks.6.self_attn.k.bias": "pytorch_model-00001.bin",
196
+ "blocks.6.self_attn.v.weight": "pytorch_model-00001.bin",
197
+ "blocks.6.self_attn.v.bias": "pytorch_model-00001.bin",
198
+ "blocks.6.self_attn.o.weight": "pytorch_model-00001.bin",
199
+ "blocks.6.self_attn.o.bias": "pytorch_model-00001.bin",
200
+ "blocks.6.self_attn.norm_q.weight": "pytorch_model-00001.bin",
201
+ "blocks.6.self_attn.norm_k.weight": "pytorch_model-00001.bin",
202
+ "blocks.6.norm3.weight": "pytorch_model-00001.bin",
203
+ "blocks.6.norm3.bias": "pytorch_model-00001.bin",
204
+ "blocks.6.cross_attn.q.weight": "pytorch_model-00001.bin",
205
+ "blocks.6.cross_attn.q.bias": "pytorch_model-00001.bin",
206
+ "blocks.6.cross_attn.k.weight": "pytorch_model-00001.bin",
207
+ "blocks.6.cross_attn.k.bias": "pytorch_model-00001.bin",
208
+ "blocks.6.cross_attn.v.weight": "pytorch_model-00001.bin",
209
+ "blocks.6.cross_attn.v.bias": "pytorch_model-00001.bin",
210
+ "blocks.6.cross_attn.o.weight": "pytorch_model-00001.bin",
211
+ "blocks.6.cross_attn.o.bias": "pytorch_model-00001.bin",
212
+ "blocks.6.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
213
+ "blocks.6.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
214
+ "blocks.6.audio_ffn.0.weight": "pytorch_model-00001.bin",
215
+ "blocks.6.audio_ffn.0.bias": "pytorch_model-00001.bin",
216
+ "blocks.6.audio_ffn.2.weight": "pytorch_model-00001.bin",
217
+ "blocks.6.audio_ffn.2.bias": "pytorch_model-00001.bin",
218
+ "blocks.6.audio_modulation.param": "pytorch_model-00001.bin",
219
+ "blocks.7.modulation": "pytorch_model-00001.bin",
220
+ "blocks.7.self_attn.q.weight": "pytorch_model-00001.bin",
221
+ "blocks.7.self_attn.q.bias": "pytorch_model-00001.bin",
222
+ "blocks.7.self_attn.k.weight": "pytorch_model-00001.bin",
223
+ "blocks.7.self_attn.k.bias": "pytorch_model-00001.bin",
224
+ "blocks.7.self_attn.v.weight": "pytorch_model-00001.bin",
225
+ "blocks.7.self_attn.v.bias": "pytorch_model-00001.bin",
226
+ "blocks.7.self_attn.o.weight": "pytorch_model-00001.bin",
227
+ "blocks.7.self_attn.o.bias": "pytorch_model-00001.bin",
228
+ "blocks.7.self_attn.norm_q.weight": "pytorch_model-00001.bin",
229
+ "blocks.7.self_attn.norm_k.weight": "pytorch_model-00001.bin",
230
+ "blocks.7.norm3.weight": "pytorch_model-00001.bin",
231
+ "blocks.7.norm3.bias": "pytorch_model-00001.bin",
232
+ "blocks.7.cross_attn.q.weight": "pytorch_model-00001.bin",
233
+ "blocks.7.cross_attn.q.bias": "pytorch_model-00001.bin",
234
+ "blocks.7.cross_attn.k.weight": "pytorch_model-00001.bin",
235
+ "blocks.7.cross_attn.k.bias": "pytorch_model-00001.bin",
236
+ "blocks.7.cross_attn.v.weight": "pytorch_model-00001.bin",
237
+ "blocks.7.cross_attn.v.bias": "pytorch_model-00001.bin",
238
+ "blocks.7.cross_attn.o.weight": "pytorch_model-00001.bin",
239
+ "blocks.7.cross_attn.o.bias": "pytorch_model-00001.bin",
240
+ "blocks.7.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
241
+ "blocks.7.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
242
+ "blocks.7.audio_ffn.0.weight": "pytorch_model-00001.bin",
243
+ "blocks.7.audio_ffn.0.bias": "pytorch_model-00001.bin",
244
+ "blocks.7.audio_ffn.2.weight": "pytorch_model-00001.bin",
245
+ "blocks.7.audio_ffn.2.bias": "pytorch_model-00001.bin",
246
+ "blocks.7.audio_modulation.param": "pytorch_model-00001.bin",
247
+ "blocks.8.modulation": "pytorch_model-00001.bin",
248
+ "blocks.8.self_attn.q.weight": "pytorch_model-00001.bin",
249
+ "blocks.8.self_attn.q.bias": "pytorch_model-00001.bin",
250
+ "blocks.8.self_attn.k.weight": "pytorch_model-00001.bin",
251
+ "blocks.8.self_attn.k.bias": "pytorch_model-00001.bin",
252
+ "blocks.8.self_attn.v.weight": "pytorch_model-00001.bin",
253
+ "blocks.8.self_attn.v.bias": "pytorch_model-00001.bin",
254
+ "blocks.8.self_attn.o.weight": "pytorch_model-00001.bin",
255
+ "blocks.8.self_attn.o.bias": "pytorch_model-00001.bin",
256
+ "blocks.8.self_attn.norm_q.weight": "pytorch_model-00001.bin",
257
+ "blocks.8.self_attn.norm_k.weight": "pytorch_model-00001.bin",
258
+ "blocks.8.norm3.weight": "pytorch_model-00001.bin",
259
+ "blocks.8.norm3.bias": "pytorch_model-00001.bin",
260
+ "blocks.8.cross_attn.q.weight": "pytorch_model-00001.bin",
261
+ "blocks.8.cross_attn.q.bias": "pytorch_model-00001.bin",
262
+ "blocks.8.cross_attn.k.weight": "pytorch_model-00001.bin",
263
+ "blocks.8.cross_attn.k.bias": "pytorch_model-00001.bin",
264
+ "blocks.8.cross_attn.v.weight": "pytorch_model-00001.bin",
265
+ "blocks.8.cross_attn.v.bias": "pytorch_model-00001.bin",
266
+ "blocks.8.cross_attn.o.weight": "pytorch_model-00001.bin",
267
+ "blocks.8.cross_attn.o.bias": "pytorch_model-00001.bin",
268
+ "blocks.8.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
269
+ "blocks.8.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
270
+ "blocks.8.audio_ffn.0.weight": "pytorch_model-00001.bin",
271
+ "blocks.8.audio_ffn.0.bias": "pytorch_model-00001.bin",
272
+ "blocks.8.audio_ffn.2.weight": "pytorch_model-00001.bin",
273
+ "blocks.8.audio_ffn.2.bias": "pytorch_model-00001.bin",
274
+ "blocks.8.audio_modulation.param": "pytorch_model-00001.bin",
275
+ "blocks.9.modulation": "pytorch_model-00001.bin",
276
+ "blocks.9.self_attn.q.weight": "pytorch_model-00001.bin",
277
+ "blocks.9.self_attn.q.bias": "pytorch_model-00001.bin",
278
+ "blocks.9.self_attn.k.weight": "pytorch_model-00001.bin",
279
+ "blocks.9.self_attn.k.bias": "pytorch_model-00001.bin",
280
+ "blocks.9.self_attn.v.weight": "pytorch_model-00001.bin",
281
+ "blocks.9.self_attn.v.bias": "pytorch_model-00001.bin",
282
+ "blocks.9.self_attn.o.weight": "pytorch_model-00001.bin",
283
+ "blocks.9.self_attn.o.bias": "pytorch_model-00001.bin",
284
+ "blocks.9.self_attn.norm_q.weight": "pytorch_model-00001.bin",
285
+ "blocks.9.self_attn.norm_k.weight": "pytorch_model-00001.bin",
286
+ "blocks.9.norm3.weight": "pytorch_model-00001.bin",
287
+ "blocks.9.norm3.bias": "pytorch_model-00001.bin",
288
+ "blocks.9.cross_attn.q.weight": "pytorch_model-00001.bin",
289
+ "blocks.9.cross_attn.q.bias": "pytorch_model-00001.bin",
290
+ "blocks.9.cross_attn.k.weight": "pytorch_model-00001.bin",
291
+ "blocks.9.cross_attn.k.bias": "pytorch_model-00001.bin",
292
+ "blocks.9.cross_attn.v.weight": "pytorch_model-00001.bin",
293
+ "blocks.9.cross_attn.v.bias": "pytorch_model-00001.bin",
294
+ "blocks.9.cross_attn.o.weight": "pytorch_model-00001.bin",
295
+ "blocks.9.cross_attn.o.bias": "pytorch_model-00001.bin",
296
+ "blocks.9.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
297
+ "blocks.9.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
298
+ "blocks.9.audio_ffn.0.weight": "pytorch_model-00001.bin",
299
+ "blocks.9.audio_ffn.0.bias": "pytorch_model-00001.bin",
300
+ "blocks.9.audio_ffn.2.weight": "pytorch_model-00001.bin",
301
+ "blocks.9.audio_ffn.2.bias": "pytorch_model-00001.bin",
302
+ "blocks.9.audio_modulation.param": "pytorch_model-00001.bin",
303
+ "blocks.10.modulation": "pytorch_model-00001.bin",
304
+ "blocks.10.self_attn.q.weight": "pytorch_model-00001.bin",
305
+ "blocks.10.self_attn.q.bias": "pytorch_model-00001.bin",
306
+ "blocks.10.self_attn.k.weight": "pytorch_model-00001.bin",
307
+ "blocks.10.self_attn.k.bias": "pytorch_model-00001.bin",
308
+ "blocks.10.self_attn.v.weight": "pytorch_model-00001.bin",
309
+ "blocks.10.self_attn.v.bias": "pytorch_model-00001.bin",
310
+ "blocks.10.self_attn.o.weight": "pytorch_model-00001.bin",
311
+ "blocks.10.self_attn.o.bias": "pytorch_model-00001.bin",
312
+ "blocks.10.self_attn.norm_q.weight": "pytorch_model-00001.bin",
313
+ "blocks.10.self_attn.norm_k.weight": "pytorch_model-00001.bin",
314
+ "blocks.10.norm3.weight": "pytorch_model-00001.bin",
315
+ "blocks.10.norm3.bias": "pytorch_model-00001.bin",
316
+ "blocks.10.cross_attn.q.weight": "pytorch_model-00001.bin",
317
+ "blocks.10.cross_attn.q.bias": "pytorch_model-00001.bin",
318
+ "blocks.10.cross_attn.k.weight": "pytorch_model-00001.bin",
319
+ "blocks.10.cross_attn.k.bias": "pytorch_model-00001.bin",
320
+ "blocks.10.cross_attn.v.weight": "pytorch_model-00001.bin",
321
+ "blocks.10.cross_attn.v.bias": "pytorch_model-00001.bin",
322
+ "blocks.10.cross_attn.o.weight": "pytorch_model-00001.bin",
323
+ "blocks.10.cross_attn.o.bias": "pytorch_model-00001.bin",
324
+ "blocks.10.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
325
+ "blocks.10.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
326
+ "blocks.10.audio_ffn.0.weight": "pytorch_model-00001.bin",
327
+ "blocks.10.audio_ffn.0.bias": "pytorch_model-00001.bin",
328
+ "blocks.10.audio_ffn.2.weight": "pytorch_model-00002.bin",
329
+ "blocks.10.audio_ffn.2.bias": "pytorch_model-00002.bin",
330
+ "blocks.10.audio_modulation.param": "pytorch_model-00002.bin",
331
+ "blocks.11.modulation": "pytorch_model-00002.bin",
332
+ "blocks.11.self_attn.q.weight": "pytorch_model-00002.bin",
333
+ "blocks.11.self_attn.q.bias": "pytorch_model-00002.bin",
334
+ "blocks.11.self_attn.k.weight": "pytorch_model-00002.bin",
335
+ "blocks.11.self_attn.k.bias": "pytorch_model-00002.bin",
336
+ "blocks.11.self_attn.v.weight": "pytorch_model-00002.bin",
337
+ "blocks.11.self_attn.v.bias": "pytorch_model-00002.bin",
338
+ "blocks.11.self_attn.o.weight": "pytorch_model-00002.bin",
339
+ "blocks.11.self_attn.o.bias": "pytorch_model-00002.bin",
340
+ "blocks.11.self_attn.norm_q.weight": "pytorch_model-00002.bin",
341
+ "blocks.11.self_attn.norm_k.weight": "pytorch_model-00002.bin",
342
+ "blocks.11.norm3.weight": "pytorch_model-00002.bin",
343
+ "blocks.11.norm3.bias": "pytorch_model-00002.bin",
344
+ "blocks.11.cross_attn.q.weight": "pytorch_model-00002.bin",
345
+ "blocks.11.cross_attn.q.bias": "pytorch_model-00002.bin",
346
+ "blocks.11.cross_attn.k.weight": "pytorch_model-00002.bin",
347
+ "blocks.11.cross_attn.k.bias": "pytorch_model-00002.bin",
348
+ "blocks.11.cross_attn.v.weight": "pytorch_model-00002.bin",
349
+ "blocks.11.cross_attn.v.bias": "pytorch_model-00002.bin",
350
+ "blocks.11.cross_attn.o.weight": "pytorch_model-00002.bin",
351
+ "blocks.11.cross_attn.o.bias": "pytorch_model-00002.bin",
352
+ "blocks.11.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
353
+ "blocks.11.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
354
+ "blocks.11.audio_ffn.0.weight": "pytorch_model-00002.bin",
355
+ "blocks.11.audio_ffn.0.bias": "pytorch_model-00002.bin",
356
+ "blocks.11.audio_ffn.2.weight": "pytorch_model-00002.bin",
357
+ "blocks.11.audio_ffn.2.bias": "pytorch_model-00002.bin",
358
+ "blocks.11.audio_modulation.param": "pytorch_model-00002.bin",
359
+ "blocks.12.modulation": "pytorch_model-00002.bin",
360
+ "blocks.12.self_attn.q.weight": "pytorch_model-00002.bin",
361
+ "blocks.12.self_attn.q.bias": "pytorch_model-00002.bin",
362
+ "blocks.12.self_attn.k.weight": "pytorch_model-00002.bin",
363
+ "blocks.12.self_attn.k.bias": "pytorch_model-00002.bin",
364
+ "blocks.12.self_attn.v.weight": "pytorch_model-00002.bin",
365
+ "blocks.12.self_attn.v.bias": "pytorch_model-00002.bin",
366
+ "blocks.12.self_attn.o.weight": "pytorch_model-00002.bin",
367
+ "blocks.12.self_attn.o.bias": "pytorch_model-00002.bin",
368
+ "blocks.12.self_attn.norm_q.weight": "pytorch_model-00002.bin",
369
+ "blocks.12.self_attn.norm_k.weight": "pytorch_model-00002.bin",
370
+ "blocks.12.norm3.weight": "pytorch_model-00002.bin",
371
+ "blocks.12.norm3.bias": "pytorch_model-00002.bin",
372
+ "blocks.12.cross_attn.q.weight": "pytorch_model-00002.bin",
373
+ "blocks.12.cross_attn.q.bias": "pytorch_model-00002.bin",
374
+ "blocks.12.cross_attn.k.weight": "pytorch_model-00002.bin",
375
+ "blocks.12.cross_attn.k.bias": "pytorch_model-00002.bin",
376
+ "blocks.12.cross_attn.v.weight": "pytorch_model-00002.bin",
377
+ "blocks.12.cross_attn.v.bias": "pytorch_model-00002.bin",
378
+ "blocks.12.cross_attn.o.weight": "pytorch_model-00002.bin",
379
+ "blocks.12.cross_attn.o.bias": "pytorch_model-00002.bin",
380
+ "blocks.12.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
381
+ "blocks.12.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
382
+ "blocks.12.audio_ffn.0.weight": "pytorch_model-00002.bin",
383
+ "blocks.12.audio_ffn.0.bias": "pytorch_model-00002.bin",
384
+ "blocks.12.audio_ffn.2.weight": "pytorch_model-00002.bin",
385
+ "blocks.12.audio_ffn.2.bias": "pytorch_model-00002.bin",
386
+ "blocks.12.audio_modulation.param": "pytorch_model-00002.bin",
387
+ "blocks.13.modulation": "pytorch_model-00002.bin",
388
+ "blocks.13.self_attn.q.weight": "pytorch_model-00002.bin",
389
+ "blocks.13.self_attn.q.bias": "pytorch_model-00002.bin",
390
+ "blocks.13.self_attn.k.weight": "pytorch_model-00002.bin",
391
+ "blocks.13.self_attn.k.bias": "pytorch_model-00002.bin",
392
+ "blocks.13.self_attn.v.weight": "pytorch_model-00002.bin",
393
+ "blocks.13.self_attn.v.bias": "pytorch_model-00002.bin",
394
+ "blocks.13.self_attn.o.weight": "pytorch_model-00002.bin",
395
+ "blocks.13.self_attn.o.bias": "pytorch_model-00002.bin",
396
+ "blocks.13.self_attn.norm_q.weight": "pytorch_model-00002.bin",
397
+ "blocks.13.self_attn.norm_k.weight": "pytorch_model-00002.bin",
398
+ "blocks.13.norm3.weight": "pytorch_model-00002.bin",
399
+ "blocks.13.norm3.bias": "pytorch_model-00002.bin",
400
+ "blocks.13.cross_attn.q.weight": "pytorch_model-00002.bin",
401
+ "blocks.13.cross_attn.q.bias": "pytorch_model-00002.bin",
402
+ "blocks.13.cross_attn.k.weight": "pytorch_model-00002.bin",
403
+ "blocks.13.cross_attn.k.bias": "pytorch_model-00002.bin",
404
+ "blocks.13.cross_attn.v.weight": "pytorch_model-00002.bin",
405
+ "blocks.13.cross_attn.v.bias": "pytorch_model-00002.bin",
406
+ "blocks.13.cross_attn.o.weight": "pytorch_model-00002.bin",
407
+ "blocks.13.cross_attn.o.bias": "pytorch_model-00002.bin",
408
+ "blocks.13.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
409
+ "blocks.13.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
410
+ "blocks.13.audio_ffn.0.weight": "pytorch_model-00002.bin",
411
+ "blocks.13.audio_ffn.0.bias": "pytorch_model-00002.bin",
412
+ "blocks.13.audio_ffn.2.weight": "pytorch_model-00002.bin",
413
+ "blocks.13.audio_ffn.2.bias": "pytorch_model-00002.bin",
414
+ "blocks.13.audio_modulation.param": "pytorch_model-00002.bin",
415
+ "blocks.14.modulation": "pytorch_model-00002.bin",
416
+ "blocks.14.self_attn.q.weight": "pytorch_model-00002.bin",
417
+ "blocks.14.self_attn.q.bias": "pytorch_model-00002.bin",
418
+ "blocks.14.self_attn.k.weight": "pytorch_model-00002.bin",
419
+ "blocks.14.self_attn.k.bias": "pytorch_model-00002.bin",
420
+ "blocks.14.self_attn.v.weight": "pytorch_model-00002.bin",
421
+ "blocks.14.self_attn.v.bias": "pytorch_model-00002.bin",
422
+ "blocks.14.self_attn.o.weight": "pytorch_model-00002.bin",
423
+ "blocks.14.self_attn.o.bias": "pytorch_model-00002.bin",
424
+ "blocks.14.self_attn.norm_q.weight": "pytorch_model-00002.bin",
425
+ "blocks.14.self_attn.norm_k.weight": "pytorch_model-00002.bin",
426
+ "blocks.14.norm3.weight": "pytorch_model-00002.bin",
427
+ "blocks.14.norm3.bias": "pytorch_model-00002.bin",
428
+ "blocks.14.cross_attn.q.weight": "pytorch_model-00002.bin",
429
+ "blocks.14.cross_attn.q.bias": "pytorch_model-00002.bin",
430
+ "blocks.14.cross_attn.k.weight": "pytorch_model-00002.bin",
431
+ "blocks.14.cross_attn.k.bias": "pytorch_model-00002.bin",
432
+ "blocks.14.cross_attn.v.weight": "pytorch_model-00002.bin",
433
+ "blocks.14.cross_attn.v.bias": "pytorch_model-00002.bin",
434
+ "blocks.14.cross_attn.o.weight": "pytorch_model-00002.bin",
435
+ "blocks.14.cross_attn.o.bias": "pytorch_model-00002.bin",
436
+ "blocks.14.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
437
+ "blocks.14.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
438
+ "blocks.14.audio_ffn.0.weight": "pytorch_model-00002.bin",
439
+ "blocks.14.audio_ffn.0.bias": "pytorch_model-00002.bin",
440
+ "blocks.14.audio_ffn.2.weight": "pytorch_model-00002.bin",
441
+ "blocks.14.audio_ffn.2.bias": "pytorch_model-00002.bin",
442
+ "blocks.14.audio_modulation.param": "pytorch_model-00002.bin",
443
+ "blocks.15.modulation": "pytorch_model-00002.bin",
444
+ "blocks.15.self_attn.q.weight": "pytorch_model-00002.bin",
445
+ "blocks.15.self_attn.q.bias": "pytorch_model-00002.bin",
446
+ "blocks.15.self_attn.k.weight": "pytorch_model-00002.bin",
447
+ "blocks.15.self_attn.k.bias": "pytorch_model-00002.bin",
448
+ "blocks.15.self_attn.v.weight": "pytorch_model-00002.bin",
449
+ "blocks.15.self_attn.v.bias": "pytorch_model-00002.bin",
450
+ "blocks.15.self_attn.o.weight": "pytorch_model-00002.bin",
451
+ "blocks.15.self_attn.o.bias": "pytorch_model-00002.bin",
452
+ "blocks.15.self_attn.norm_q.weight": "pytorch_model-00002.bin",
453
+ "blocks.15.self_attn.norm_k.weight": "pytorch_model-00002.bin",
454
+ "blocks.15.norm3.weight": "pytorch_model-00002.bin",
455
+ "blocks.15.norm3.bias": "pytorch_model-00002.bin",
456
+ "blocks.15.cross_attn.q.weight": "pytorch_model-00002.bin",
457
+ "blocks.15.cross_attn.q.bias": "pytorch_model-00002.bin",
458
+ "blocks.15.cross_attn.k.weight": "pytorch_model-00002.bin",
459
+ "blocks.15.cross_attn.k.bias": "pytorch_model-00002.bin",
460
+ "blocks.15.cross_attn.v.weight": "pytorch_model-00002.bin",
461
+ "blocks.15.cross_attn.v.bias": "pytorch_model-00002.bin",
462
+ "blocks.15.cross_attn.o.weight": "pytorch_model-00002.bin",
463
+ "blocks.15.cross_attn.o.bias": "pytorch_model-00002.bin",
464
+ "blocks.15.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
465
+ "blocks.15.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
466
+ "blocks.15.audio_ffn.0.weight": "pytorch_model-00002.bin",
467
+ "blocks.15.audio_ffn.0.bias": "pytorch_model-00002.bin",
468
+ "blocks.15.audio_ffn.2.weight": "pytorch_model-00002.bin",
469
+ "blocks.15.audio_ffn.2.bias": "pytorch_model-00002.bin",
470
+ "blocks.15.audio_modulation.param": "pytorch_model-00002.bin",
471
+ "blocks.16.modulation": "pytorch_model-00002.bin",
472
+ "blocks.16.self_attn.q.weight": "pytorch_model-00002.bin",
473
+ "blocks.16.self_attn.q.bias": "pytorch_model-00002.bin",
474
+ "blocks.16.self_attn.k.weight": "pytorch_model-00002.bin",
475
+ "blocks.16.self_attn.k.bias": "pytorch_model-00002.bin",
476
+ "blocks.16.self_attn.v.weight": "pytorch_model-00002.bin",
477
+ "blocks.16.self_attn.v.bias": "pytorch_model-00002.bin",
478
+ "blocks.16.self_attn.o.weight": "pytorch_model-00002.bin",
479
+ "blocks.16.self_attn.o.bias": "pytorch_model-00002.bin",
480
+ "blocks.16.self_attn.norm_q.weight": "pytorch_model-00002.bin",
481
+ "blocks.16.self_attn.norm_k.weight": "pytorch_model-00002.bin",
482
+ "blocks.16.norm3.weight": "pytorch_model-00002.bin",
483
+ "blocks.16.norm3.bias": "pytorch_model-00002.bin",
484
+ "blocks.16.cross_attn.q.weight": "pytorch_model-00002.bin",
485
+ "blocks.16.cross_attn.q.bias": "pytorch_model-00002.bin",
486
+ "blocks.16.cross_attn.k.weight": "pytorch_model-00002.bin",
487
+ "blocks.16.cross_attn.k.bias": "pytorch_model-00002.bin",
488
+ "blocks.16.cross_attn.v.weight": "pytorch_model-00002.bin",
489
+ "blocks.16.cross_attn.v.bias": "pytorch_model-00002.bin",
490
+ "blocks.16.cross_attn.o.weight": "pytorch_model-00002.bin",
491
+ "blocks.16.cross_attn.o.bias": "pytorch_model-00002.bin",
492
+ "blocks.16.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
493
+ "blocks.16.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
494
+ "blocks.16.audio_ffn.0.weight": "pytorch_model-00002.bin",
495
+ "blocks.16.audio_ffn.0.bias": "pytorch_model-00002.bin",
496
+ "blocks.16.audio_ffn.2.weight": "pytorch_model-00002.bin",
497
+ "blocks.16.audio_ffn.2.bias": "pytorch_model-00002.bin",
498
+ "blocks.16.audio_modulation.param": "pytorch_model-00002.bin",
499
+ "blocks.17.modulation": "pytorch_model-00002.bin",
500
+ "blocks.17.self_attn.q.weight": "pytorch_model-00002.bin",
501
+ "blocks.17.self_attn.q.bias": "pytorch_model-00002.bin",
502
+ "blocks.17.self_attn.k.weight": "pytorch_model-00002.bin",
503
+ "blocks.17.self_attn.k.bias": "pytorch_model-00002.bin",
504
+ "blocks.17.self_attn.v.weight": "pytorch_model-00002.bin",
505
+ "blocks.17.self_attn.v.bias": "pytorch_model-00002.bin",
506
+ "blocks.17.self_attn.o.weight": "pytorch_model-00002.bin",
507
+ "blocks.17.self_attn.o.bias": "pytorch_model-00002.bin",
508
+ "blocks.17.self_attn.norm_q.weight": "pytorch_model-00002.bin",
509
+ "blocks.17.self_attn.norm_k.weight": "pytorch_model-00002.bin",
510
+ "blocks.17.norm3.weight": "pytorch_model-00002.bin",
511
+ "blocks.17.norm3.bias": "pytorch_model-00002.bin",
512
+ "blocks.17.cross_attn.q.weight": "pytorch_model-00002.bin",
513
+ "blocks.17.cross_attn.q.bias": "pytorch_model-00002.bin",
514
+ "blocks.17.cross_attn.k.weight": "pytorch_model-00002.bin",
515
+ "blocks.17.cross_attn.k.bias": "pytorch_model-00002.bin",
516
+ "blocks.17.cross_attn.v.weight": "pytorch_model-00002.bin",
517
+ "blocks.17.cross_attn.v.bias": "pytorch_model-00002.bin",
518
+ "blocks.17.cross_attn.o.weight": "pytorch_model-00002.bin",
519
+ "blocks.17.cross_attn.o.bias": "pytorch_model-00002.bin",
520
+ "blocks.17.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
521
+ "blocks.17.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
522
+ "blocks.17.audio_ffn.0.weight": "pytorch_model-00002.bin",
523
+ "blocks.17.audio_ffn.0.bias": "pytorch_model-00002.bin",
524
+ "blocks.17.audio_ffn.2.weight": "pytorch_model-00002.bin",
525
+ "blocks.17.audio_ffn.2.bias": "pytorch_model-00002.bin",
526
+ "blocks.17.audio_modulation.param": "pytorch_model-00002.bin",
527
+ "blocks.18.modulation": "pytorch_model-00002.bin",
528
+ "blocks.18.self_attn.q.weight": "pytorch_model-00002.bin",
529
+ "blocks.18.self_attn.q.bias": "pytorch_model-00002.bin",
530
+ "blocks.18.self_attn.k.weight": "pytorch_model-00002.bin",
531
+ "blocks.18.self_attn.k.bias": "pytorch_model-00002.bin",
532
+ "blocks.18.self_attn.v.weight": "pytorch_model-00002.bin",
533
+ "blocks.18.self_attn.v.bias": "pytorch_model-00002.bin",
534
+ "blocks.18.self_attn.o.weight": "pytorch_model-00002.bin",
535
+ "blocks.18.self_attn.o.bias": "pytorch_model-00002.bin",
536
+ "blocks.18.self_attn.norm_q.weight": "pytorch_model-00002.bin",
537
+ "blocks.18.self_attn.norm_k.weight": "pytorch_model-00002.bin",
538
+ "blocks.18.norm3.weight": "pytorch_model-00002.bin",
539
+ "blocks.18.norm3.bias": "pytorch_model-00002.bin",
540
+ "blocks.18.cross_attn.q.weight": "pytorch_model-00002.bin",
541
+ "blocks.18.cross_attn.q.bias": "pytorch_model-00002.bin",
542
+ "blocks.18.cross_attn.k.weight": "pytorch_model-00002.bin",
543
+ "blocks.18.cross_attn.k.bias": "pytorch_model-00002.bin",
544
+ "blocks.18.cross_attn.v.weight": "pytorch_model-00002.bin",
545
+ "blocks.18.cross_attn.v.bias": "pytorch_model-00002.bin",
546
+ "blocks.18.cross_attn.o.weight": "pytorch_model-00002.bin",
547
+ "blocks.18.cross_attn.o.bias": "pytorch_model-00002.bin",
548
+ "blocks.18.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
549
+ "blocks.18.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
550
+ "blocks.18.audio_ffn.0.weight": "pytorch_model-00002.bin",
551
+ "blocks.18.audio_ffn.0.bias": "pytorch_model-00002.bin",
552
+ "blocks.18.audio_ffn.2.weight": "pytorch_model-00002.bin",
553
+ "blocks.18.audio_ffn.2.bias": "pytorch_model-00002.bin",
554
+ "blocks.18.audio_modulation.param": "pytorch_model-00002.bin",
555
+ "blocks.19.modulation": "pytorch_model-00002.bin",
556
+ "blocks.19.self_attn.q.weight": "pytorch_model-00002.bin",
557
+ "blocks.19.self_attn.q.bias": "pytorch_model-00002.bin",
558
+ "blocks.19.self_attn.k.weight": "pytorch_model-00002.bin",
559
+ "blocks.19.self_attn.k.bias": "pytorch_model-00002.bin",
560
+ "blocks.19.self_attn.v.weight": "pytorch_model-00002.bin",
561
+ "blocks.19.self_attn.v.bias": "pytorch_model-00002.bin",
562
+ "blocks.19.self_attn.o.weight": "pytorch_model-00002.bin",
563
+ "blocks.19.self_attn.o.bias": "pytorch_model-00002.bin",
564
+ "blocks.19.self_attn.norm_q.weight": "pytorch_model-00002.bin",
565
+ "blocks.19.self_attn.norm_k.weight": "pytorch_model-00002.bin",
566
+ "blocks.19.norm3.weight": "pytorch_model-00002.bin",
567
+ "blocks.19.norm3.bias": "pytorch_model-00002.bin",
568
+ "blocks.19.cross_attn.q.weight": "pytorch_model-00002.bin",
569
+ "blocks.19.cross_attn.q.bias": "pytorch_model-00002.bin",
570
+ "blocks.19.cross_attn.k.weight": "pytorch_model-00002.bin",
571
+ "blocks.19.cross_attn.k.bias": "pytorch_model-00002.bin",
572
+ "blocks.19.cross_attn.v.weight": "pytorch_model-00002.bin",
573
+ "blocks.19.cross_attn.v.bias": "pytorch_model-00002.bin",
574
+ "blocks.19.cross_attn.o.weight": "pytorch_model-00002.bin",
575
+ "blocks.19.cross_attn.o.bias": "pytorch_model-00002.bin",
576
+ "blocks.19.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
577
+ "blocks.19.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
578
+ "blocks.19.audio_ffn.0.weight": "pytorch_model-00002.bin",
579
+ "blocks.19.audio_ffn.0.bias": "pytorch_model-00002.bin",
580
+ "blocks.19.audio_ffn.2.weight": "pytorch_model-00002.bin",
581
+ "blocks.19.audio_ffn.2.bias": "pytorch_model-00002.bin",
582
+ "blocks.19.audio_modulation.param": "pytorch_model-00002.bin",
583
+ "blocks.20.modulation": "pytorch_model-00002.bin",
584
+ "blocks.20.self_attn.q.weight": "pytorch_model-00002.bin",
585
+ "blocks.20.self_attn.q.bias": "pytorch_model-00002.bin",
586
+ "blocks.20.self_attn.k.weight": "pytorch_model-00002.bin",
587
+ "blocks.20.self_attn.k.bias": "pytorch_model-00002.bin",
588
+ "blocks.20.self_attn.v.weight": "pytorch_model-00002.bin",
589
+ "blocks.20.self_attn.v.bias": "pytorch_model-00002.bin",
590
+ "blocks.20.self_attn.o.weight": "pytorch_model-00002.bin",
591
+ "blocks.20.self_attn.o.bias": "pytorch_model-00002.bin",
592
+ "blocks.20.self_attn.norm_q.weight": "pytorch_model-00002.bin",
593
+ "blocks.20.self_attn.norm_k.weight": "pytorch_model-00002.bin",
594
+ "blocks.20.norm3.weight": "pytorch_model-00002.bin",
595
+ "blocks.20.norm3.bias": "pytorch_model-00002.bin",
596
+ "blocks.20.cross_attn.q.weight": "pytorch_model-00002.bin",
597
+ "blocks.20.cross_attn.q.bias": "pytorch_model-00002.bin",
598
+ "blocks.20.cross_attn.k.weight": "pytorch_model-00002.bin",
599
+ "blocks.20.cross_attn.k.bias": "pytorch_model-00002.bin",
600
+ "blocks.20.cross_attn.v.weight": "pytorch_model-00002.bin",
601
+ "blocks.20.cross_attn.v.bias": "pytorch_model-00002.bin",
602
+ "blocks.20.cross_attn.o.weight": "pytorch_model-00002.bin",
603
+ "blocks.20.cross_attn.o.bias": "pytorch_model-00002.bin",
604
+ "blocks.20.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
605
+ "blocks.20.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
606
+ "blocks.20.audio_ffn.0.weight": "pytorch_model-00002.bin",
607
+ "blocks.20.audio_ffn.0.bias": "pytorch_model-00002.bin",
608
+ "blocks.20.audio_ffn.2.weight": "pytorch_model-00002.bin",
609
+ "blocks.20.audio_ffn.2.bias": "pytorch_model-00002.bin",
610
+ "blocks.20.audio_modulation.param": "pytorch_model-00002.bin",
611
+ "blocks.21.modulation": "pytorch_model-00002.bin",
612
+ "blocks.21.self_attn.q.weight": "pytorch_model-00002.bin",
613
+ "blocks.21.self_attn.q.bias": "pytorch_model-00002.bin",
614
+ "blocks.21.self_attn.k.weight": "pytorch_model-00002.bin",
615
+ "blocks.21.self_attn.k.bias": "pytorch_model-00002.bin",
616
+ "blocks.21.self_attn.v.weight": "pytorch_model-00002.bin",
617
+ "blocks.21.self_attn.v.bias": "pytorch_model-00002.bin",
618
+ "blocks.21.self_attn.o.weight": "pytorch_model-00002.bin",
619
+ "blocks.21.self_attn.o.bias": "pytorch_model-00002.bin",
620
+ "blocks.21.self_attn.norm_q.weight": "pytorch_model-00002.bin",
621
+ "blocks.21.self_attn.norm_k.weight": "pytorch_model-00002.bin",
622
+ "blocks.21.norm3.weight": "pytorch_model-00002.bin",
623
+ "blocks.21.norm3.bias": "pytorch_model-00002.bin",
624
+ "blocks.21.cross_attn.q.weight": "pytorch_model-00002.bin",
625
+ "blocks.21.cross_attn.q.bias": "pytorch_model-00002.bin",
626
+ "blocks.21.cross_attn.k.weight": "pytorch_model-00002.bin",
627
+ "blocks.21.cross_attn.k.bias": "pytorch_model-00002.bin",
628
+ "blocks.21.cross_attn.v.weight": "pytorch_model-00002.bin",
629
+ "blocks.21.cross_attn.v.bias": "pytorch_model-00002.bin",
630
+ "blocks.21.cross_attn.o.weight": "pytorch_model-00002.bin",
631
+ "blocks.21.cross_attn.o.bias": "pytorch_model-00002.bin",
632
+ "blocks.21.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
633
+ "blocks.21.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
634
+ "blocks.21.audio_ffn.0.weight": "pytorch_model-00002.bin",
635
+ "blocks.21.audio_ffn.0.bias": "pytorch_model-00002.bin",
636
+ "blocks.21.audio_ffn.2.weight": "pytorch_model-00002.bin",
637
+ "blocks.21.audio_ffn.2.bias": "pytorch_model-00002.bin",
638
+ "blocks.21.audio_modulation.param": "pytorch_model-00002.bin",
639
+ "blocks.22.modulation": "pytorch_model-00002.bin",
640
+ "blocks.22.self_attn.q.weight": "pytorch_model-00002.bin",
641
+ "blocks.22.self_attn.q.bias": "pytorch_model-00002.bin",
642
+ "blocks.22.self_attn.k.weight": "pytorch_model-00002.bin",
643
+ "blocks.22.self_attn.k.bias": "pytorch_model-00002.bin",
644
+ "blocks.22.self_attn.v.weight": "pytorch_model-00002.bin",
645
+ "blocks.22.self_attn.v.bias": "pytorch_model-00002.bin",
646
+ "blocks.22.self_attn.o.weight": "pytorch_model-00002.bin",
647
+ "blocks.22.self_attn.o.bias": "pytorch_model-00002.bin",
648
+ "blocks.22.self_attn.norm_q.weight": "pytorch_model-00002.bin",
649
+ "blocks.22.self_attn.norm_k.weight": "pytorch_model-00002.bin",
650
+ "blocks.22.norm3.weight": "pytorch_model-00002.bin",
651
+ "blocks.22.norm3.bias": "pytorch_model-00002.bin",
652
+ "blocks.22.cross_attn.q.weight": "pytorch_model-00002.bin",
653
+ "blocks.22.cross_attn.q.bias": "pytorch_model-00002.bin",
654
+ "blocks.22.cross_attn.k.weight": "pytorch_model-00003.bin",
655
+ "blocks.22.cross_attn.k.bias": "pytorch_model-00003.bin",
656
+ "blocks.22.cross_attn.v.weight": "pytorch_model-00003.bin",
657
+ "blocks.22.cross_attn.v.bias": "pytorch_model-00003.bin",
658
+ "blocks.22.cross_attn.o.weight": "pytorch_model-00003.bin",
659
+ "blocks.22.cross_attn.o.bias": "pytorch_model-00003.bin",
660
+ "blocks.22.cross_attn.norm_q.weight": "pytorch_model-00003.bin",
661
+ "blocks.22.cross_attn.norm_k.weight": "pytorch_model-00003.bin",
662
+ "blocks.22.audio_ffn.0.weight": "pytorch_model-00003.bin",
663
+ "blocks.22.audio_ffn.0.bias": "pytorch_model-00003.bin",
664
+ "blocks.22.audio_ffn.2.weight": "pytorch_model-00003.bin",
665
+ "blocks.22.audio_ffn.2.bias": "pytorch_model-00003.bin",
666
+ "blocks.22.audio_modulation.param": "pytorch_model-00003.bin",
667
+ "blocks.23.modulation": "pytorch_model-00003.bin",
668
+ "blocks.23.self_attn.q.weight": "pytorch_model-00003.bin",
669
+ "blocks.23.self_attn.q.bias": "pytorch_model-00003.bin",
670
+ "blocks.23.self_attn.k.weight": "pytorch_model-00003.bin",
671
+ "blocks.23.self_attn.k.bias": "pytorch_model-00003.bin",
672
+ "blocks.23.self_attn.v.weight": "pytorch_model-00003.bin",
673
+ "blocks.23.self_attn.v.bias": "pytorch_model-00003.bin",
674
+ "blocks.23.self_attn.o.weight": "pytorch_model-00003.bin",
675
+ "blocks.23.self_attn.o.bias": "pytorch_model-00003.bin",
676
+ "blocks.23.self_attn.norm_q.weight": "pytorch_model-00003.bin",
677
+ "blocks.23.self_attn.norm_k.weight": "pytorch_model-00003.bin",
678
+ "blocks.23.norm3.weight": "pytorch_model-00003.bin",
679
+ "blocks.23.norm3.bias": "pytorch_model-00003.bin",
680
+ "blocks.23.cross_attn.q.weight": "pytorch_model-00003.bin",
681
+ "blocks.23.cross_attn.q.bias": "pytorch_model-00003.bin",
682
+ "blocks.23.cross_attn.k.weight": "pytorch_model-00003.bin",
683
+ "blocks.23.cross_attn.k.bias": "pytorch_model-00003.bin",
684
+ "blocks.23.cross_attn.v.weight": "pytorch_model-00003.bin",
685
+ "blocks.23.cross_attn.v.bias": "pytorch_model-00003.bin",
686
+ "blocks.23.cross_attn.o.weight": "pytorch_model-00003.bin",
687
+ "blocks.23.cross_attn.o.bias": "pytorch_model-00003.bin",
688
+ "blocks.23.cross_attn.norm_q.weight": "pytorch_model-00003.bin",
689
+ "blocks.23.cross_attn.norm_k.weight": "pytorch_model-00003.bin",
690
+ "blocks.23.audio_ffn.0.weight": "pytorch_model-00003.bin",
691
+ "blocks.23.audio_ffn.0.bias": "pytorch_model-00003.bin",
692
+ "blocks.23.audio_ffn.2.weight": "pytorch_model-00003.bin",
693
+ "blocks.23.audio_ffn.2.bias": "pytorch_model-00003.bin",
694
+ "blocks.23.audio_modulation.param": "pytorch_model-00003.bin",
695
+ "blocks.24.modulation": "pytorch_model-00003.bin",
696
+ "blocks.24.self_attn.q.weight": "pytorch_model-00003.bin",
697
+ "blocks.24.self_attn.q.bias": "pytorch_model-00003.bin",
698
+ "blocks.24.self_attn.k.weight": "pytorch_model-00003.bin",
699
+ "blocks.24.self_attn.k.bias": "pytorch_model-00003.bin",
700
+ "blocks.24.self_attn.v.weight": "pytorch_model-00003.bin",
701
+ "blocks.24.self_attn.v.bias": "pytorch_model-00003.bin",
702
+ "blocks.24.self_attn.o.weight": "pytorch_model-00003.bin",
703
+ "blocks.24.self_attn.o.bias": "pytorch_model-00003.bin",
704
+ "blocks.24.self_attn.norm_q.weight": "pytorch_model-00003.bin",
705
+ "blocks.24.self_attn.norm_k.weight": "pytorch_model-00003.bin",
706
+ "blocks.24.norm3.weight": "pytorch_model-00003.bin",
707
+ "blocks.24.norm3.bias": "pytorch_model-00003.bin",
708
+ "blocks.24.cross_attn.q.weight": "pytorch_model-00003.bin",
709
+ "blocks.24.cross_attn.q.bias": "pytorch_model-00003.bin",
710
+ "blocks.24.cross_attn.k.weight": "pytorch_model-00003.bin",
711
+ "blocks.24.cross_attn.k.bias": "pytorch_model-00003.bin",
712
+ "blocks.24.cross_attn.v.weight": "pytorch_model-00003.bin",
713
+ "blocks.24.cross_attn.v.bias": "pytorch_model-00003.bin",
714
+ "blocks.24.cross_attn.o.weight": "pytorch_model-00003.bin",
715
+ "blocks.24.cross_attn.o.bias": "pytorch_model-00003.bin",
716
+ "blocks.24.cross_attn.norm_q.weight": "pytorch_model-00003.bin",
717
+ "blocks.24.cross_attn.norm_k.weight": "pytorch_model-00003.bin",
718
+ "blocks.24.audio_ffn.0.weight": "pytorch_model-00003.bin",
719
+ "blocks.24.audio_ffn.0.bias": "pytorch_model-00003.bin",
720
+ "blocks.24.audio_ffn.2.weight": "pytorch_model-00003.bin",
721
+ "blocks.24.audio_ffn.2.bias": "pytorch_model-00003.bin",
722
+ "blocks.24.audio_modulation.param": "pytorch_model-00003.bin",
723
+ "blocks.25.modulation": "pytorch_model-00003.bin",
724
+ "blocks.25.self_attn.q.weight": "pytorch_model-00003.bin",
725
+ "blocks.25.self_attn.q.bias": "pytorch_model-00003.bin",
726
+ "blocks.25.self_attn.k.weight": "pytorch_model-00003.bin",
727
+ "blocks.25.self_attn.k.bias": "pytorch_model-00003.bin",
728
+ "blocks.25.self_attn.v.weight": "pytorch_model-00003.bin",
729
+ "blocks.25.self_attn.v.bias": "pytorch_model-00003.bin",
730
+ "blocks.25.self_attn.o.weight": "pytorch_model-00003.bin",
731
+ "blocks.25.self_attn.o.bias": "pytorch_model-00003.bin",
732
+ "blocks.25.self_attn.norm_q.weight": "pytorch_model-00003.bin",
733
+ "blocks.25.self_attn.norm_k.weight": "pytorch_model-00003.bin",
734
+ "blocks.25.norm3.weight": "pytorch_model-00003.bin",
735
+ "blocks.25.norm3.bias": "pytorch_model-00003.bin",
736
+ "blocks.25.cross_attn.q.weight": "pytorch_model-00003.bin",
737
+ "blocks.25.cross_attn.q.bias": "pytorch_model-00003.bin",
738
+ "blocks.25.cross_attn.k.weight": "pytorch_model-00003.bin",
739
+ "blocks.25.cross_attn.k.bias": "pytorch_model-00003.bin",
740
+ "blocks.25.cross_attn.v.weight": "pytorch_model-00003.bin",
741
+ "blocks.25.cross_attn.v.bias": "pytorch_model-00003.bin",
742
+ "blocks.25.cross_attn.o.weight": "pytorch_model-00003.bin",
743
+ "blocks.25.cross_attn.o.bias": "pytorch_model-00003.bin",
744
+ "blocks.25.cross_attn.norm_q.weight": "pytorch_model-00003.bin",
745
+ "blocks.25.cross_attn.norm_k.weight": "pytorch_model-00003.bin",
746
+ "blocks.25.audio_ffn.0.weight": "pytorch_model-00003.bin",
747
+ "blocks.25.audio_ffn.0.bias": "pytorch_model-00003.bin",
748
+ "blocks.25.audio_ffn.2.weight": "pytorch_model-00003.bin",
749
+ "blocks.25.audio_ffn.2.bias": "pytorch_model-00003.bin",
750
+ "blocks.25.audio_modulation.param": "pytorch_model-00003.bin",
751
+ "blocks.26.modulation": "pytorch_model-00003.bin",
752
+ "blocks.26.self_attn.q.weight": "pytorch_model-00003.bin",
753
+ "blocks.26.self_attn.q.bias": "pytorch_model-00003.bin",
754
+ "blocks.26.self_attn.k.weight": "pytorch_model-00003.bin",
755
+ "blocks.26.self_attn.k.bias": "pytorch_model-00003.bin",
756
+ "blocks.26.self_attn.v.weight": "pytorch_model-00003.bin",
757
+ "blocks.26.self_attn.v.bias": "pytorch_model-00003.bin",
758
+ "blocks.26.self_attn.o.weight": "pytorch_model-00003.bin",
759
+ "blocks.26.self_attn.o.bias": "pytorch_model-00003.bin",
760
+ "blocks.26.self_attn.norm_q.weight": "pytorch_model-00003.bin",
761
+ "blocks.26.self_attn.norm_k.weight": "pytorch_model-00003.bin",
762
+ "blocks.26.norm3.weight": "pytorch_model-00003.bin",
763
+ "blocks.26.norm3.bias": "pytorch_model-00003.bin",
764
+ "blocks.26.cross_attn.q.weight": "pytorch_model-00003.bin",
765
+ "blocks.26.cross_attn.q.bias": "pytorch_model-00003.bin",
766
+ "blocks.26.cross_attn.k.weight": "pytorch_model-00003.bin",
767
+ "blocks.26.cross_attn.k.bias": "pytorch_model-00003.bin",
768
+ "blocks.26.cross_attn.v.weight": "pytorch_model-00003.bin",
769
+ "blocks.26.cross_attn.v.bias": "pytorch_model-00003.bin",
770
+ "blocks.26.cross_attn.o.weight": "pytorch_model-00003.bin",
771
+ "blocks.26.cross_attn.o.bias": "pytorch_model-00003.bin",
772
+ "blocks.26.cross_attn.norm_q.weight": "pytorch_model-00003.bin",
773
+ "blocks.26.cross_attn.norm_k.weight": "pytorch_model-00003.bin",
774
+ "blocks.26.audio_ffn.0.weight": "pytorch_model-00003.bin",
775
+ "blocks.26.audio_ffn.0.bias": "pytorch_model-00003.bin",
776
+ "blocks.26.audio_ffn.2.weight": "pytorch_model-00003.bin",
777
+ "blocks.26.audio_ffn.2.bias": "pytorch_model-00003.bin",
778
+ "blocks.26.audio_modulation.param": "pytorch_model-00003.bin",
779
+ "blocks.27.modulation": "pytorch_model-00003.bin",
780
+ "blocks.27.self_attn.q.weight": "pytorch_model-00003.bin",
781
+ "blocks.27.self_attn.q.bias": "pytorch_model-00003.bin",
782
+ "blocks.27.self_attn.k.weight": "pytorch_model-00003.bin",
783
+ "blocks.27.self_attn.k.bias": "pytorch_model-00003.bin",
784
+ "blocks.27.self_attn.v.weight": "pytorch_model-00003.bin",
785
+ "blocks.27.self_attn.v.bias": "pytorch_model-00003.bin",
786
+ "blocks.27.self_attn.o.weight": "pytorch_model-00003.bin",
787
+ "blocks.27.self_attn.o.bias": "pytorch_model-00003.bin",
788
+ "blocks.27.self_attn.norm_q.weight": "pytorch_model-00003.bin",
789
+ "blocks.27.self_attn.norm_k.weight": "pytorch_model-00003.bin",
790
+ "blocks.27.norm3.weight": "pytorch_model-00003.bin",
791
+ "blocks.27.norm3.bias": "pytorch_model-00003.bin",
792
+ "blocks.27.cross_attn.q.weight": "pytorch_model-00003.bin",
793
+ "blocks.27.cross_attn.q.bias": "pytorch_model-00003.bin",
794
+ "blocks.27.cross_attn.k.weight": "pytorch_model-00003.bin",
795
+ "blocks.27.cross_attn.k.bias": "pytorch_model-00003.bin",
796
+ "blocks.27.cross_attn.v.weight": "pytorch_model-00003.bin",
797
+ "blocks.27.cross_attn.v.bias": "pytorch_model-00003.bin",
798
+ "blocks.27.cross_attn.o.weight": "pytorch_model-00003.bin",
799
+ "blocks.27.cross_attn.o.bias": "pytorch_model-00003.bin",
800
+ "blocks.27.cross_attn.norm_q.weight": "pytorch_model-00003.bin",
801
+ "blocks.27.cross_attn.norm_k.weight": "pytorch_model-00003.bin",
802
+ "blocks.27.audio_ffn.0.weight": "pytorch_model-00003.bin",
803
+ "blocks.27.audio_ffn.0.bias": "pytorch_model-00003.bin",
804
+ "blocks.27.audio_ffn.2.weight": "pytorch_model-00003.bin",
805
+ "blocks.27.audio_ffn.2.bias": "pytorch_model-00003.bin",
806
+ "blocks.27.audio_modulation.param": "pytorch_model-00003.bin",
807
+ "blocks.28.modulation": "pytorch_model-00003.bin",
808
+ "blocks.28.self_attn.q.weight": "pytorch_model-00003.bin",
809
+ "blocks.28.self_attn.q.bias": "pytorch_model-00003.bin",
810
+ "blocks.28.self_attn.k.weight": "pytorch_model-00003.bin",
811
+ "blocks.28.self_attn.k.bias": "pytorch_model-00003.bin",
812
+ "blocks.28.self_attn.v.weight": "pytorch_model-00003.bin",
813
+ "blocks.28.self_attn.v.bias": "pytorch_model-00003.bin",
814
+ "blocks.28.self_attn.o.weight": "pytorch_model-00003.bin",
815
+ "blocks.28.self_attn.o.bias": "pytorch_model-00003.bin",
816
+ "blocks.28.self_attn.norm_q.weight": "pytorch_model-00003.bin",
817
+ "blocks.28.self_attn.norm_k.weight": "pytorch_model-00003.bin",
818
+ "blocks.28.norm3.weight": "pytorch_model-00003.bin",
819
+ "blocks.28.norm3.bias": "pytorch_model-00003.bin",
820
+ "blocks.28.cross_attn.q.weight": "pytorch_model-00003.bin",
821
+ "blocks.28.cross_attn.q.bias": "pytorch_model-00003.bin",
822
+ "blocks.28.cross_attn.k.weight": "pytorch_model-00003.bin",
823
+ "blocks.28.cross_attn.k.bias": "pytorch_model-00003.bin",
824
+ "blocks.28.cross_attn.v.weight": "pytorch_model-00003.bin",
825
+ "blocks.28.cross_attn.v.bias": "pytorch_model-00003.bin",
826
+ "blocks.28.cross_attn.o.weight": "pytorch_model-00003.bin",
827
+ "blocks.28.cross_attn.o.bias": "pytorch_model-00003.bin",
828
+ "blocks.28.cross_attn.norm_q.weight": "pytorch_model-00003.bin",
829
+ "blocks.28.cross_attn.norm_k.weight": "pytorch_model-00003.bin",
830
+ "blocks.28.audio_ffn.0.weight": "pytorch_model-00003.bin",
831
+ "blocks.28.audio_ffn.0.bias": "pytorch_model-00003.bin",
832
+ "blocks.28.audio_ffn.2.weight": "pytorch_model-00003.bin",
833
+ "blocks.28.audio_ffn.2.bias": "pytorch_model-00003.bin",
834
+ "blocks.28.audio_modulation.param": "pytorch_model-00003.bin",
835
+ "blocks.29.modulation": "pytorch_model-00003.bin",
836
+ "blocks.29.self_attn.q.weight": "pytorch_model-00003.bin",
837
+ "blocks.29.self_attn.q.bias": "pytorch_model-00003.bin",
838
+ "blocks.29.self_attn.k.weight": "pytorch_model-00003.bin",
839
+ "blocks.29.self_attn.k.bias": "pytorch_model-00003.bin",
840
+ "blocks.29.self_attn.v.weight": "pytorch_model-00003.bin",
841
+ "blocks.29.self_attn.v.bias": "pytorch_model-00003.bin",
842
+ "blocks.29.self_attn.o.weight": "pytorch_model-00003.bin",
843
+ "blocks.29.self_attn.o.bias": "pytorch_model-00003.bin",
844
+ "blocks.29.self_attn.norm_q.weight": "pytorch_model-00003.bin",
845
+ "blocks.29.self_attn.norm_k.weight": "pytorch_model-00003.bin",
846
+ "blocks.29.norm3.weight": "pytorch_model-00003.bin",
847
+ "blocks.29.norm3.bias": "pytorch_model-00003.bin",
848
+ "blocks.29.cross_attn.q.weight": "pytorch_model-00003.bin",
849
+ "blocks.29.cross_attn.q.bias": "pytorch_model-00003.bin",
850
+ "blocks.29.cross_attn.k.weight": "pytorch_model-00003.bin",
851
+ "blocks.29.cross_attn.k.bias": "pytorch_model-00003.bin",
852
+ "blocks.29.cross_attn.v.weight": "pytorch_model-00003.bin",
853
+ "blocks.29.cross_attn.v.bias": "pytorch_model-00003.bin",
854
+ "blocks.29.cross_attn.o.weight": "pytorch_model-00003.bin",
855
+ "blocks.29.cross_attn.o.bias": "pytorch_model-00003.bin",
856
+ "blocks.29.cross_attn.norm_q.weight": "pytorch_model-00003.bin",
857
+ "blocks.29.cross_attn.norm_k.weight": "pytorch_model-00003.bin",
858
+ "blocks.29.audio_ffn.0.weight": "pytorch_model-00003.bin",
859
+ "blocks.29.audio_ffn.0.bias": "pytorch_model-00003.bin",
860
+ "blocks.29.audio_ffn.2.weight": "pytorch_model-00003.bin",
861
+ "blocks.29.audio_ffn.2.bias": "pytorch_model-00003.bin",
862
+ "blocks.29.audio_modulation.param": "pytorch_model-00003.bin"
863
+ }
864
+ }
audio-only/000-Wan2_1_T2V_1_3B/epoch048-global_step52000/optimizer/pytorch_optim-00001.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de07ff4727b96991e2e5a2173c6bf1e90ba1b052455cc26b113cf97dcb0fa165
3
+ size 4243656922
audio-only/000-Wan2_1_T2V_1_3B/epoch048-global_step52000/optimizer/pytorch_optim-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e2458b0e3eec3e4185f6c5dccbacf23634286f7be176e2b69c46a5c40f5a392
3
+ size 2423571758
audio-only/000-Wan2_1_T2V_1_3B/epoch048-global_step52000/optimizer/pytorch_optim.bin.index.json ADDED
@@ -0,0 +1,165 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "param_groups": "pytorch_optim_group.bin",
4
+ "total_size": 6358.277587890625
5
+ },
6
+ "weight_map": {
7
+ "0": "pytorch_optim-00001.bin",
8
+ "1": "pytorch_optim-00001.bin",
9
+ "2": "pytorch_optim-00001.bin",
10
+ "3": "pytorch_optim-00001.bin",
11
+ "4": "pytorch_optim-00001.bin",
12
+ "5": "pytorch_optim-00001.bin",
13
+ "6": "pytorch_optim-00001.bin",
14
+ "7": "pytorch_optim-00001.bin",
15
+ "8": "pytorch_optim-00001.bin",
16
+ "9": "pytorch_optim-00001.bin",
17
+ "10": "pytorch_optim-00001.bin",
18
+ "11": "pytorch_optim-00001.bin",
19
+ "12": "pytorch_optim-00001.bin",
20
+ "13": "pytorch_optim-00001.bin",
21
+ "14": "pytorch_optim-00001.bin",
22
+ "15": "pytorch_optim-00001.bin",
23
+ "16": "pytorch_optim-00001.bin",
24
+ "17": "pytorch_optim-00001.bin",
25
+ "18": "pytorch_optim-00001.bin",
26
+ "19": "pytorch_optim-00001.bin",
27
+ "20": "pytorch_optim-00001.bin",
28
+ "21": "pytorch_optim-00001.bin",
29
+ "22": "pytorch_optim-00001.bin",
30
+ "23": "pytorch_optim-00001.bin",
31
+ "24": "pytorch_optim-00001.bin",
32
+ "25": "pytorch_optim-00001.bin",
33
+ "26": "pytorch_optim-00001.bin",
34
+ "27": "pytorch_optim-00001.bin",
35
+ "28": "pytorch_optim-00001.bin",
36
+ "29": "pytorch_optim-00001.bin",
37
+ "30": "pytorch_optim-00001.bin",
38
+ "31": "pytorch_optim-00001.bin",
39
+ "32": "pytorch_optim-00001.bin",
40
+ "33": "pytorch_optim-00001.bin",
41
+ "34": "pytorch_optim-00001.bin",
42
+ "35": "pytorch_optim-00001.bin",
43
+ "36": "pytorch_optim-00001.bin",
44
+ "37": "pytorch_optim-00001.bin",
45
+ "38": "pytorch_optim-00001.bin",
46
+ "39": "pytorch_optim-00001.bin",
47
+ "40": "pytorch_optim-00001.bin",
48
+ "41": "pytorch_optim-00001.bin",
49
+ "42": "pytorch_optim-00001.bin",
50
+ "43": "pytorch_optim-00001.bin",
51
+ "44": "pytorch_optim-00001.bin",
52
+ "45": "pytorch_optim-00001.bin",
53
+ "46": "pytorch_optim-00001.bin",
54
+ "47": "pytorch_optim-00001.bin",
55
+ "48": "pytorch_optim-00001.bin",
56
+ "49": "pytorch_optim-00001.bin",
57
+ "50": "pytorch_optim-00001.bin",
58
+ "51": "pytorch_optim-00001.bin",
59
+ "52": "pytorch_optim-00001.bin",
60
+ "53": "pytorch_optim-00001.bin",
61
+ "54": "pytorch_optim-00001.bin",
62
+ "55": "pytorch_optim-00001.bin",
63
+ "56": "pytorch_optim-00001.bin",
64
+ "57": "pytorch_optim-00001.bin",
65
+ "58": "pytorch_optim-00001.bin",
66
+ "59": "pytorch_optim-00001.bin",
67
+ "60": "pytorch_optim-00001.bin",
68
+ "61": "pytorch_optim-00001.bin",
69
+ "62": "pytorch_optim-00001.bin",
70
+ "63": "pytorch_optim-00001.bin",
71
+ "64": "pytorch_optim-00001.bin",
72
+ "65": "pytorch_optim-00001.bin",
73
+ "66": "pytorch_optim-00001.bin",
74
+ "67": "pytorch_optim-00001.bin",
75
+ "68": "pytorch_optim-00001.bin",
76
+ "69": "pytorch_optim-00001.bin",
77
+ "70": "pytorch_optim-00001.bin",
78
+ "71": "pytorch_optim-00001.bin",
79
+ "72": "pytorch_optim-00001.bin",
80
+ "73": "pytorch_optim-00001.bin",
81
+ "74": "pytorch_optim-00001.bin",
82
+ "75": "pytorch_optim-00001.bin",
83
+ "76": "pytorch_optim-00001.bin",
84
+ "77": "pytorch_optim-00001.bin",
85
+ "78": "pytorch_optim-00001.bin",
86
+ "79": "pytorch_optim-00001.bin",
87
+ "80": "pytorch_optim-00001.bin",
88
+ "81": "pytorch_optim-00001.bin",
89
+ "82": "pytorch_optim-00001.bin",
90
+ "83": "pytorch_optim-00001.bin",
91
+ "84": "pytorch_optim-00001.bin",
92
+ "85": "pytorch_optim-00001.bin",
93
+ "86": "pytorch_optim-00001.bin",
94
+ "87": "pytorch_optim-00001.bin",
95
+ "88": "pytorch_optim-00001.bin",
96
+ "89": "pytorch_optim-00001.bin",
97
+ "90": "pytorch_optim-00001.bin",
98
+ "91": "pytorch_optim-00001.bin",
99
+ "92": "pytorch_optim-00001.bin",
100
+ "93": "pytorch_optim-00001.bin",
101
+ "94": "pytorch_optim-00001.bin",
102
+ "95": "pytorch_optim-00001.bin",
103
+ "96": "pytorch_optim-00001.bin",
104
+ "97": "pytorch_optim-00001.bin",
105
+ "98": "pytorch_optim-00001.bin",
106
+ "99": "pytorch_optim-00001.bin",
107
+ "100": "pytorch_optim-00001.bin",
108
+ "101": "pytorch_optim-00001.bin",
109
+ "102": "pytorch_optim-00002.bin",
110
+ "103": "pytorch_optim-00002.bin",
111
+ "104": "pytorch_optim-00002.bin",
112
+ "105": "pytorch_optim-00002.bin",
113
+ "106": "pytorch_optim-00002.bin",
114
+ "107": "pytorch_optim-00002.bin",
115
+ "108": "pytorch_optim-00002.bin",
116
+ "109": "pytorch_optim-00002.bin",
117
+ "110": "pytorch_optim-00002.bin",
118
+ "111": "pytorch_optim-00002.bin",
119
+ "112": "pytorch_optim-00002.bin",
120
+ "113": "pytorch_optim-00002.bin",
121
+ "114": "pytorch_optim-00002.bin",
122
+ "115": "pytorch_optim-00002.bin",
123
+ "116": "pytorch_optim-00002.bin",
124
+ "117": "pytorch_optim-00002.bin",
125
+ "118": "pytorch_optim-00002.bin",
126
+ "119": "pytorch_optim-00002.bin",
127
+ "120": "pytorch_optim-00002.bin",
128
+ "121": "pytorch_optim-00002.bin",
129
+ "122": "pytorch_optim-00002.bin",
130
+ "123": "pytorch_optim-00002.bin",
131
+ "124": "pytorch_optim-00002.bin",
132
+ "125": "pytorch_optim-00002.bin",
133
+ "126": "pytorch_optim-00002.bin",
134
+ "127": "pytorch_optim-00002.bin",
135
+ "128": "pytorch_optim-00002.bin",
136
+ "129": "pytorch_optim-00002.bin",
137
+ "130": "pytorch_optim-00002.bin",
138
+ "131": "pytorch_optim-00002.bin",
139
+ "132": "pytorch_optim-00002.bin",
140
+ "133": "pytorch_optim-00002.bin",
141
+ "134": "pytorch_optim-00002.bin",
142
+ "135": "pytorch_optim-00002.bin",
143
+ "136": "pytorch_optim-00002.bin",
144
+ "137": "pytorch_optim-00002.bin",
145
+ "138": "pytorch_optim-00002.bin",
146
+ "139": "pytorch_optim-00002.bin",
147
+ "140": "pytorch_optim-00002.bin",
148
+ "141": "pytorch_optim-00002.bin",
149
+ "142": "pytorch_optim-00002.bin",
150
+ "143": "pytorch_optim-00002.bin",
151
+ "144": "pytorch_optim-00002.bin",
152
+ "145": "pytorch_optim-00002.bin",
153
+ "146": "pytorch_optim-00002.bin",
154
+ "147": "pytorch_optim-00002.bin",
155
+ "148": "pytorch_optim-00002.bin",
156
+ "149": "pytorch_optim-00002.bin",
157
+ "150": "pytorch_optim-00002.bin",
158
+ "151": "pytorch_optim-00002.bin",
159
+ "152": "pytorch_optim-00002.bin",
160
+ "153": "pytorch_optim-00002.bin",
161
+ "154": "pytorch_optim-00002.bin",
162
+ "155": "pytorch_optim-00002.bin",
163
+ "156": "pytorch_optim-00002.bin"
164
+ }
165
+ }
audio-only/000-Wan2_1_T2V_1_3B/epoch048-global_step52000/optimizer/pytorch_optim_group.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:821c8504135947a0f7bc707c16e2865d3740fd6a307b8b5232645e4f886c0ebf
3
+ size 1360
audio-only/000-Wan2_1_T2V_1_3B/epoch048-global_step52000/running_states.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 48,
3
+ "step": 496,
4
+ "global_step": 52000,
5
+ "batch_size": null
6
+ }
audio-only/000-Wan2_1_T2V_1_3B/epoch048-global_step52000/sampler ADDED
Binary file (928 Bytes). View file
 
audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53000/ema.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f90eec8edbd4685f70149bdff6f94478f71650f5b478847d025a033d4e843a0
3
+ size 5704739068
audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53000/lr_scheduler ADDED
Binary file (1.01 kB). View file
 
audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53000/model/pytorch_model-00001.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14e972842bc3b2e1e5374d312269befb44fcce793c7e7e99b82d3fc38cfd8655
3
+ size 1059881014
audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53000/model/pytorch_model-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef27467046c64e1977d304d7fd934337ddb6116517d7b007a1e41a2a48d6ae55
3
+ size 1073076766
audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53000/model/pytorch_model-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85542e8f8d223c6f13491a2045f921ddfba7dbe842dbd75d21b3f6eecf5fb1b4
3
+ size 719552332
audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53000/model/pytorch_model.bin.index.json ADDED
@@ -0,0 +1,864 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 2720.1065063476562
4
+ },
5
+ "weight_map": {
6
+ "audio_patch_embedding.weight": "pytorch_model-00001.bin",
7
+ "audio_patch_embedding.bias": "pytorch_model-00001.bin",
8
+ "audio_head.modulation": "pytorch_model-00001.bin",
9
+ "audio_head.head.weight": "pytorch_model-00001.bin",
10
+ "audio_head.head.bias": "pytorch_model-00001.bin",
11
+ "text_embedding.0.weight": "pytorch_model-00001.bin",
12
+ "text_embedding.0.bias": "pytorch_model-00001.bin",
13
+ "text_embedding.2.weight": "pytorch_model-00001.bin",
14
+ "text_embedding.2.bias": "pytorch_model-00001.bin",
15
+ "time_embedding.0.weight": "pytorch_model-00001.bin",
16
+ "time_embedding.0.bias": "pytorch_model-00001.bin",
17
+ "time_embedding.2.weight": "pytorch_model-00001.bin",
18
+ "time_embedding.2.bias": "pytorch_model-00001.bin",
19
+ "time_projection.1.weight": "pytorch_model-00001.bin",
20
+ "time_projection.1.bias": "pytorch_model-00001.bin",
21
+ "audio_time_projection.1.weight": "pytorch_model-00001.bin",
22
+ "audio_time_projection.1.bias": "pytorch_model-00001.bin",
23
+ "blocks.0.modulation": "pytorch_model-00001.bin",
24
+ "blocks.0.self_attn.q.weight": "pytorch_model-00001.bin",
25
+ "blocks.0.self_attn.q.bias": "pytorch_model-00001.bin",
26
+ "blocks.0.self_attn.k.weight": "pytorch_model-00001.bin",
27
+ "blocks.0.self_attn.k.bias": "pytorch_model-00001.bin",
28
+ "blocks.0.self_attn.v.weight": "pytorch_model-00001.bin",
29
+ "blocks.0.self_attn.v.bias": "pytorch_model-00001.bin",
30
+ "blocks.0.self_attn.o.weight": "pytorch_model-00001.bin",
31
+ "blocks.0.self_attn.o.bias": "pytorch_model-00001.bin",
32
+ "blocks.0.self_attn.norm_q.weight": "pytorch_model-00001.bin",
33
+ "blocks.0.self_attn.norm_k.weight": "pytorch_model-00001.bin",
34
+ "blocks.0.norm3.weight": "pytorch_model-00001.bin",
35
+ "blocks.0.norm3.bias": "pytorch_model-00001.bin",
36
+ "blocks.0.cross_attn.q.weight": "pytorch_model-00001.bin",
37
+ "blocks.0.cross_attn.q.bias": "pytorch_model-00001.bin",
38
+ "blocks.0.cross_attn.k.weight": "pytorch_model-00001.bin",
39
+ "blocks.0.cross_attn.k.bias": "pytorch_model-00001.bin",
40
+ "blocks.0.cross_attn.v.weight": "pytorch_model-00001.bin",
41
+ "blocks.0.cross_attn.v.bias": "pytorch_model-00001.bin",
42
+ "blocks.0.cross_attn.o.weight": "pytorch_model-00001.bin",
43
+ "blocks.0.cross_attn.o.bias": "pytorch_model-00001.bin",
44
+ "blocks.0.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
45
+ "blocks.0.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
46
+ "blocks.0.audio_ffn.0.weight": "pytorch_model-00001.bin",
47
+ "blocks.0.audio_ffn.0.bias": "pytorch_model-00001.bin",
48
+ "blocks.0.audio_ffn.2.weight": "pytorch_model-00001.bin",
49
+ "blocks.0.audio_ffn.2.bias": "pytorch_model-00001.bin",
50
+ "blocks.0.audio_modulation.param": "pytorch_model-00001.bin",
51
+ "blocks.1.modulation": "pytorch_model-00001.bin",
52
+ "blocks.1.self_attn.q.weight": "pytorch_model-00001.bin",
53
+ "blocks.1.self_attn.q.bias": "pytorch_model-00001.bin",
54
+ "blocks.1.self_attn.k.weight": "pytorch_model-00001.bin",
55
+ "blocks.1.self_attn.k.bias": "pytorch_model-00001.bin",
56
+ "blocks.1.self_attn.v.weight": "pytorch_model-00001.bin",
57
+ "blocks.1.self_attn.v.bias": "pytorch_model-00001.bin",
58
+ "blocks.1.self_attn.o.weight": "pytorch_model-00001.bin",
59
+ "blocks.1.self_attn.o.bias": "pytorch_model-00001.bin",
60
+ "blocks.1.self_attn.norm_q.weight": "pytorch_model-00001.bin",
61
+ "blocks.1.self_attn.norm_k.weight": "pytorch_model-00001.bin",
62
+ "blocks.1.norm3.weight": "pytorch_model-00001.bin",
63
+ "blocks.1.norm3.bias": "pytorch_model-00001.bin",
64
+ "blocks.1.cross_attn.q.weight": "pytorch_model-00001.bin",
65
+ "blocks.1.cross_attn.q.bias": "pytorch_model-00001.bin",
66
+ "blocks.1.cross_attn.k.weight": "pytorch_model-00001.bin",
67
+ "blocks.1.cross_attn.k.bias": "pytorch_model-00001.bin",
68
+ "blocks.1.cross_attn.v.weight": "pytorch_model-00001.bin",
69
+ "blocks.1.cross_attn.v.bias": "pytorch_model-00001.bin",
70
+ "blocks.1.cross_attn.o.weight": "pytorch_model-00001.bin",
71
+ "blocks.1.cross_attn.o.bias": "pytorch_model-00001.bin",
72
+ "blocks.1.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
73
+ "blocks.1.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
74
+ "blocks.1.audio_ffn.0.weight": "pytorch_model-00001.bin",
75
+ "blocks.1.audio_ffn.0.bias": "pytorch_model-00001.bin",
76
+ "blocks.1.audio_ffn.2.weight": "pytorch_model-00001.bin",
77
+ "blocks.1.audio_ffn.2.bias": "pytorch_model-00001.bin",
78
+ "blocks.1.audio_modulation.param": "pytorch_model-00001.bin",
79
+ "blocks.2.modulation": "pytorch_model-00001.bin",
80
+ "blocks.2.self_attn.q.weight": "pytorch_model-00001.bin",
81
+ "blocks.2.self_attn.q.bias": "pytorch_model-00001.bin",
82
+ "blocks.2.self_attn.k.weight": "pytorch_model-00001.bin",
83
+ "blocks.2.self_attn.k.bias": "pytorch_model-00001.bin",
84
+ "blocks.2.self_attn.v.weight": "pytorch_model-00001.bin",
85
+ "blocks.2.self_attn.v.bias": "pytorch_model-00001.bin",
86
+ "blocks.2.self_attn.o.weight": "pytorch_model-00001.bin",
87
+ "blocks.2.self_attn.o.bias": "pytorch_model-00001.bin",
88
+ "blocks.2.self_attn.norm_q.weight": "pytorch_model-00001.bin",
89
+ "blocks.2.self_attn.norm_k.weight": "pytorch_model-00001.bin",
90
+ "blocks.2.norm3.weight": "pytorch_model-00001.bin",
91
+ "blocks.2.norm3.bias": "pytorch_model-00001.bin",
92
+ "blocks.2.cross_attn.q.weight": "pytorch_model-00001.bin",
93
+ "blocks.2.cross_attn.q.bias": "pytorch_model-00001.bin",
94
+ "blocks.2.cross_attn.k.weight": "pytorch_model-00001.bin",
95
+ "blocks.2.cross_attn.k.bias": "pytorch_model-00001.bin",
96
+ "blocks.2.cross_attn.v.weight": "pytorch_model-00001.bin",
97
+ "blocks.2.cross_attn.v.bias": "pytorch_model-00001.bin",
98
+ "blocks.2.cross_attn.o.weight": "pytorch_model-00001.bin",
99
+ "blocks.2.cross_attn.o.bias": "pytorch_model-00001.bin",
100
+ "blocks.2.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
101
+ "blocks.2.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
102
+ "blocks.2.audio_ffn.0.weight": "pytorch_model-00001.bin",
103
+ "blocks.2.audio_ffn.0.bias": "pytorch_model-00001.bin",
104
+ "blocks.2.audio_ffn.2.weight": "pytorch_model-00001.bin",
105
+ "blocks.2.audio_ffn.2.bias": "pytorch_model-00001.bin",
106
+ "blocks.2.audio_modulation.param": "pytorch_model-00001.bin",
107
+ "blocks.3.modulation": "pytorch_model-00001.bin",
108
+ "blocks.3.self_attn.q.weight": "pytorch_model-00001.bin",
109
+ "blocks.3.self_attn.q.bias": "pytorch_model-00001.bin",
110
+ "blocks.3.self_attn.k.weight": "pytorch_model-00001.bin",
111
+ "blocks.3.self_attn.k.bias": "pytorch_model-00001.bin",
112
+ "blocks.3.self_attn.v.weight": "pytorch_model-00001.bin",
113
+ "blocks.3.self_attn.v.bias": "pytorch_model-00001.bin",
114
+ "blocks.3.self_attn.o.weight": "pytorch_model-00001.bin",
115
+ "blocks.3.self_attn.o.bias": "pytorch_model-00001.bin",
116
+ "blocks.3.self_attn.norm_q.weight": "pytorch_model-00001.bin",
117
+ "blocks.3.self_attn.norm_k.weight": "pytorch_model-00001.bin",
118
+ "blocks.3.norm3.weight": "pytorch_model-00001.bin",
119
+ "blocks.3.norm3.bias": "pytorch_model-00001.bin",
120
+ "blocks.3.cross_attn.q.weight": "pytorch_model-00001.bin",
121
+ "blocks.3.cross_attn.q.bias": "pytorch_model-00001.bin",
122
+ "blocks.3.cross_attn.k.weight": "pytorch_model-00001.bin",
123
+ "blocks.3.cross_attn.k.bias": "pytorch_model-00001.bin",
124
+ "blocks.3.cross_attn.v.weight": "pytorch_model-00001.bin",
125
+ "blocks.3.cross_attn.v.bias": "pytorch_model-00001.bin",
126
+ "blocks.3.cross_attn.o.weight": "pytorch_model-00001.bin",
127
+ "blocks.3.cross_attn.o.bias": "pytorch_model-00001.bin",
128
+ "blocks.3.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
129
+ "blocks.3.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
130
+ "blocks.3.audio_ffn.0.weight": "pytorch_model-00001.bin",
131
+ "blocks.3.audio_ffn.0.bias": "pytorch_model-00001.bin",
132
+ "blocks.3.audio_ffn.2.weight": "pytorch_model-00001.bin",
133
+ "blocks.3.audio_ffn.2.bias": "pytorch_model-00001.bin",
134
+ "blocks.3.audio_modulation.param": "pytorch_model-00001.bin",
135
+ "blocks.4.modulation": "pytorch_model-00001.bin",
136
+ "blocks.4.self_attn.q.weight": "pytorch_model-00001.bin",
137
+ "blocks.4.self_attn.q.bias": "pytorch_model-00001.bin",
138
+ "blocks.4.self_attn.k.weight": "pytorch_model-00001.bin",
139
+ "blocks.4.self_attn.k.bias": "pytorch_model-00001.bin",
140
+ "blocks.4.self_attn.v.weight": "pytorch_model-00001.bin",
141
+ "blocks.4.self_attn.v.bias": "pytorch_model-00001.bin",
142
+ "blocks.4.self_attn.o.weight": "pytorch_model-00001.bin",
143
+ "blocks.4.self_attn.o.bias": "pytorch_model-00001.bin",
144
+ "blocks.4.self_attn.norm_q.weight": "pytorch_model-00001.bin",
145
+ "blocks.4.self_attn.norm_k.weight": "pytorch_model-00001.bin",
146
+ "blocks.4.norm3.weight": "pytorch_model-00001.bin",
147
+ "blocks.4.norm3.bias": "pytorch_model-00001.bin",
148
+ "blocks.4.cross_attn.q.weight": "pytorch_model-00001.bin",
149
+ "blocks.4.cross_attn.q.bias": "pytorch_model-00001.bin",
150
+ "blocks.4.cross_attn.k.weight": "pytorch_model-00001.bin",
151
+ "blocks.4.cross_attn.k.bias": "pytorch_model-00001.bin",
152
+ "blocks.4.cross_attn.v.weight": "pytorch_model-00001.bin",
153
+ "blocks.4.cross_attn.v.bias": "pytorch_model-00001.bin",
154
+ "blocks.4.cross_attn.o.weight": "pytorch_model-00001.bin",
155
+ "blocks.4.cross_attn.o.bias": "pytorch_model-00001.bin",
156
+ "blocks.4.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
157
+ "blocks.4.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
158
+ "blocks.4.audio_ffn.0.weight": "pytorch_model-00001.bin",
159
+ "blocks.4.audio_ffn.0.bias": "pytorch_model-00001.bin",
160
+ "blocks.4.audio_ffn.2.weight": "pytorch_model-00001.bin",
161
+ "blocks.4.audio_ffn.2.bias": "pytorch_model-00001.bin",
162
+ "blocks.4.audio_modulation.param": "pytorch_model-00001.bin",
163
+ "blocks.5.modulation": "pytorch_model-00001.bin",
164
+ "blocks.5.self_attn.q.weight": "pytorch_model-00001.bin",
165
+ "blocks.5.self_attn.q.bias": "pytorch_model-00001.bin",
166
+ "blocks.5.self_attn.k.weight": "pytorch_model-00001.bin",
167
+ "blocks.5.self_attn.k.bias": "pytorch_model-00001.bin",
168
+ "blocks.5.self_attn.v.weight": "pytorch_model-00001.bin",
169
+ "blocks.5.self_attn.v.bias": "pytorch_model-00001.bin",
170
+ "blocks.5.self_attn.o.weight": "pytorch_model-00001.bin",
171
+ "blocks.5.self_attn.o.bias": "pytorch_model-00001.bin",
172
+ "blocks.5.self_attn.norm_q.weight": "pytorch_model-00001.bin",
173
+ "blocks.5.self_attn.norm_k.weight": "pytorch_model-00001.bin",
174
+ "blocks.5.norm3.weight": "pytorch_model-00001.bin",
175
+ "blocks.5.norm3.bias": "pytorch_model-00001.bin",
176
+ "blocks.5.cross_attn.q.weight": "pytorch_model-00001.bin",
177
+ "blocks.5.cross_attn.q.bias": "pytorch_model-00001.bin",
178
+ "blocks.5.cross_attn.k.weight": "pytorch_model-00001.bin",
179
+ "blocks.5.cross_attn.k.bias": "pytorch_model-00001.bin",
180
+ "blocks.5.cross_attn.v.weight": "pytorch_model-00001.bin",
181
+ "blocks.5.cross_attn.v.bias": "pytorch_model-00001.bin",
182
+ "blocks.5.cross_attn.o.weight": "pytorch_model-00001.bin",
183
+ "blocks.5.cross_attn.o.bias": "pytorch_model-00001.bin",
184
+ "blocks.5.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
185
+ "blocks.5.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
186
+ "blocks.5.audio_ffn.0.weight": "pytorch_model-00001.bin",
187
+ "blocks.5.audio_ffn.0.bias": "pytorch_model-00001.bin",
188
+ "blocks.5.audio_ffn.2.weight": "pytorch_model-00001.bin",
189
+ "blocks.5.audio_ffn.2.bias": "pytorch_model-00001.bin",
190
+ "blocks.5.audio_modulation.param": "pytorch_model-00001.bin",
191
+ "blocks.6.modulation": "pytorch_model-00001.bin",
192
+ "blocks.6.self_attn.q.weight": "pytorch_model-00001.bin",
193
+ "blocks.6.self_attn.q.bias": "pytorch_model-00001.bin",
194
+ "blocks.6.self_attn.k.weight": "pytorch_model-00001.bin",
195
+ "blocks.6.self_attn.k.bias": "pytorch_model-00001.bin",
196
+ "blocks.6.self_attn.v.weight": "pytorch_model-00001.bin",
197
+ "blocks.6.self_attn.v.bias": "pytorch_model-00001.bin",
198
+ "blocks.6.self_attn.o.weight": "pytorch_model-00001.bin",
199
+ "blocks.6.self_attn.o.bias": "pytorch_model-00001.bin",
200
+ "blocks.6.self_attn.norm_q.weight": "pytorch_model-00001.bin",
201
+ "blocks.6.self_attn.norm_k.weight": "pytorch_model-00001.bin",
202
+ "blocks.6.norm3.weight": "pytorch_model-00001.bin",
203
+ "blocks.6.norm3.bias": "pytorch_model-00001.bin",
204
+ "blocks.6.cross_attn.q.weight": "pytorch_model-00001.bin",
205
+ "blocks.6.cross_attn.q.bias": "pytorch_model-00001.bin",
206
+ "blocks.6.cross_attn.k.weight": "pytorch_model-00001.bin",
207
+ "blocks.6.cross_attn.k.bias": "pytorch_model-00001.bin",
208
+ "blocks.6.cross_attn.v.weight": "pytorch_model-00001.bin",
209
+ "blocks.6.cross_attn.v.bias": "pytorch_model-00001.bin",
210
+ "blocks.6.cross_attn.o.weight": "pytorch_model-00001.bin",
211
+ "blocks.6.cross_attn.o.bias": "pytorch_model-00001.bin",
212
+ "blocks.6.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
213
+ "blocks.6.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
214
+ "blocks.6.audio_ffn.0.weight": "pytorch_model-00001.bin",
215
+ "blocks.6.audio_ffn.0.bias": "pytorch_model-00001.bin",
216
+ "blocks.6.audio_ffn.2.weight": "pytorch_model-00001.bin",
217
+ "blocks.6.audio_ffn.2.bias": "pytorch_model-00001.bin",
218
+ "blocks.6.audio_modulation.param": "pytorch_model-00001.bin",
219
+ "blocks.7.modulation": "pytorch_model-00001.bin",
220
+ "blocks.7.self_attn.q.weight": "pytorch_model-00001.bin",
221
+ "blocks.7.self_attn.q.bias": "pytorch_model-00001.bin",
222
+ "blocks.7.self_attn.k.weight": "pytorch_model-00001.bin",
223
+ "blocks.7.self_attn.k.bias": "pytorch_model-00001.bin",
224
+ "blocks.7.self_attn.v.weight": "pytorch_model-00001.bin",
225
+ "blocks.7.self_attn.v.bias": "pytorch_model-00001.bin",
226
+ "blocks.7.self_attn.o.weight": "pytorch_model-00001.bin",
227
+ "blocks.7.self_attn.o.bias": "pytorch_model-00001.bin",
228
+ "blocks.7.self_attn.norm_q.weight": "pytorch_model-00001.bin",
229
+ "blocks.7.self_attn.norm_k.weight": "pytorch_model-00001.bin",
230
+ "blocks.7.norm3.weight": "pytorch_model-00001.bin",
231
+ "blocks.7.norm3.bias": "pytorch_model-00001.bin",
232
+ "blocks.7.cross_attn.q.weight": "pytorch_model-00001.bin",
233
+ "blocks.7.cross_attn.q.bias": "pytorch_model-00001.bin",
234
+ "blocks.7.cross_attn.k.weight": "pytorch_model-00001.bin",
235
+ "blocks.7.cross_attn.k.bias": "pytorch_model-00001.bin",
236
+ "blocks.7.cross_attn.v.weight": "pytorch_model-00001.bin",
237
+ "blocks.7.cross_attn.v.bias": "pytorch_model-00001.bin",
238
+ "blocks.7.cross_attn.o.weight": "pytorch_model-00001.bin",
239
+ "blocks.7.cross_attn.o.bias": "pytorch_model-00001.bin",
240
+ "blocks.7.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
241
+ "blocks.7.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
242
+ "blocks.7.audio_ffn.0.weight": "pytorch_model-00001.bin",
243
+ "blocks.7.audio_ffn.0.bias": "pytorch_model-00001.bin",
244
+ "blocks.7.audio_ffn.2.weight": "pytorch_model-00001.bin",
245
+ "blocks.7.audio_ffn.2.bias": "pytorch_model-00001.bin",
246
+ "blocks.7.audio_modulation.param": "pytorch_model-00001.bin",
247
+ "blocks.8.modulation": "pytorch_model-00001.bin",
248
+ "blocks.8.self_attn.q.weight": "pytorch_model-00001.bin",
249
+ "blocks.8.self_attn.q.bias": "pytorch_model-00001.bin",
250
+ "blocks.8.self_attn.k.weight": "pytorch_model-00001.bin",
251
+ "blocks.8.self_attn.k.bias": "pytorch_model-00001.bin",
252
+ "blocks.8.self_attn.v.weight": "pytorch_model-00001.bin",
253
+ "blocks.8.self_attn.v.bias": "pytorch_model-00001.bin",
254
+ "blocks.8.self_attn.o.weight": "pytorch_model-00001.bin",
255
+ "blocks.8.self_attn.o.bias": "pytorch_model-00001.bin",
256
+ "blocks.8.self_attn.norm_q.weight": "pytorch_model-00001.bin",
257
+ "blocks.8.self_attn.norm_k.weight": "pytorch_model-00001.bin",
258
+ "blocks.8.norm3.weight": "pytorch_model-00001.bin",
259
+ "blocks.8.norm3.bias": "pytorch_model-00001.bin",
260
+ "blocks.8.cross_attn.q.weight": "pytorch_model-00001.bin",
261
+ "blocks.8.cross_attn.q.bias": "pytorch_model-00001.bin",
262
+ "blocks.8.cross_attn.k.weight": "pytorch_model-00001.bin",
263
+ "blocks.8.cross_attn.k.bias": "pytorch_model-00001.bin",
264
+ "blocks.8.cross_attn.v.weight": "pytorch_model-00001.bin",
265
+ "blocks.8.cross_attn.v.bias": "pytorch_model-00001.bin",
266
+ "blocks.8.cross_attn.o.weight": "pytorch_model-00001.bin",
267
+ "blocks.8.cross_attn.o.bias": "pytorch_model-00001.bin",
268
+ "blocks.8.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
269
+ "blocks.8.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
270
+ "blocks.8.audio_ffn.0.weight": "pytorch_model-00001.bin",
271
+ "blocks.8.audio_ffn.0.bias": "pytorch_model-00001.bin",
272
+ "blocks.8.audio_ffn.2.weight": "pytorch_model-00001.bin",
273
+ "blocks.8.audio_ffn.2.bias": "pytorch_model-00001.bin",
274
+ "blocks.8.audio_modulation.param": "pytorch_model-00001.bin",
275
+ "blocks.9.modulation": "pytorch_model-00001.bin",
276
+ "blocks.9.self_attn.q.weight": "pytorch_model-00001.bin",
277
+ "blocks.9.self_attn.q.bias": "pytorch_model-00001.bin",
278
+ "blocks.9.self_attn.k.weight": "pytorch_model-00001.bin",
279
+ "blocks.9.self_attn.k.bias": "pytorch_model-00001.bin",
280
+ "blocks.9.self_attn.v.weight": "pytorch_model-00001.bin",
281
+ "blocks.9.self_attn.v.bias": "pytorch_model-00001.bin",
282
+ "blocks.9.self_attn.o.weight": "pytorch_model-00001.bin",
283
+ "blocks.9.self_attn.o.bias": "pytorch_model-00001.bin",
284
+ "blocks.9.self_attn.norm_q.weight": "pytorch_model-00001.bin",
285
+ "blocks.9.self_attn.norm_k.weight": "pytorch_model-00001.bin",
286
+ "blocks.9.norm3.weight": "pytorch_model-00001.bin",
287
+ "blocks.9.norm3.bias": "pytorch_model-00001.bin",
288
+ "blocks.9.cross_attn.q.weight": "pytorch_model-00001.bin",
289
+ "blocks.9.cross_attn.q.bias": "pytorch_model-00001.bin",
290
+ "blocks.9.cross_attn.k.weight": "pytorch_model-00001.bin",
291
+ "blocks.9.cross_attn.k.bias": "pytorch_model-00001.bin",
292
+ "blocks.9.cross_attn.v.weight": "pytorch_model-00001.bin",
293
+ "blocks.9.cross_attn.v.bias": "pytorch_model-00001.bin",
294
+ "blocks.9.cross_attn.o.weight": "pytorch_model-00001.bin",
295
+ "blocks.9.cross_attn.o.bias": "pytorch_model-00001.bin",
296
+ "blocks.9.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
297
+ "blocks.9.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
298
+ "blocks.9.audio_ffn.0.weight": "pytorch_model-00001.bin",
299
+ "blocks.9.audio_ffn.0.bias": "pytorch_model-00001.bin",
300
+ "blocks.9.audio_ffn.2.weight": "pytorch_model-00001.bin",
301
+ "blocks.9.audio_ffn.2.bias": "pytorch_model-00001.bin",
302
+ "blocks.9.audio_modulation.param": "pytorch_model-00001.bin",
303
+ "blocks.10.modulation": "pytorch_model-00001.bin",
304
+ "blocks.10.self_attn.q.weight": "pytorch_model-00001.bin",
305
+ "blocks.10.self_attn.q.bias": "pytorch_model-00001.bin",
306
+ "blocks.10.self_attn.k.weight": "pytorch_model-00001.bin",
307
+ "blocks.10.self_attn.k.bias": "pytorch_model-00001.bin",
308
+ "blocks.10.self_attn.v.weight": "pytorch_model-00001.bin",
309
+ "blocks.10.self_attn.v.bias": "pytorch_model-00001.bin",
310
+ "blocks.10.self_attn.o.weight": "pytorch_model-00001.bin",
311
+ "blocks.10.self_attn.o.bias": "pytorch_model-00001.bin",
312
+ "blocks.10.self_attn.norm_q.weight": "pytorch_model-00001.bin",
313
+ "blocks.10.self_attn.norm_k.weight": "pytorch_model-00001.bin",
314
+ "blocks.10.norm3.weight": "pytorch_model-00001.bin",
315
+ "blocks.10.norm3.bias": "pytorch_model-00001.bin",
316
+ "blocks.10.cross_attn.q.weight": "pytorch_model-00001.bin",
317
+ "blocks.10.cross_attn.q.bias": "pytorch_model-00001.bin",
318
+ "blocks.10.cross_attn.k.weight": "pytorch_model-00001.bin",
319
+ "blocks.10.cross_attn.k.bias": "pytorch_model-00001.bin",
320
+ "blocks.10.cross_attn.v.weight": "pytorch_model-00001.bin",
321
+ "blocks.10.cross_attn.v.bias": "pytorch_model-00001.bin",
322
+ "blocks.10.cross_attn.o.weight": "pytorch_model-00001.bin",
323
+ "blocks.10.cross_attn.o.bias": "pytorch_model-00001.bin",
324
+ "blocks.10.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
325
+ "blocks.10.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
326
+ "blocks.10.audio_ffn.0.weight": "pytorch_model-00001.bin",
327
+ "blocks.10.audio_ffn.0.bias": "pytorch_model-00001.bin",
328
+ "blocks.10.audio_ffn.2.weight": "pytorch_model-00002.bin",
329
+ "blocks.10.audio_ffn.2.bias": "pytorch_model-00002.bin",
330
+ "blocks.10.audio_modulation.param": "pytorch_model-00002.bin",
331
+ "blocks.11.modulation": "pytorch_model-00002.bin",
332
+ "blocks.11.self_attn.q.weight": "pytorch_model-00002.bin",
333
+ "blocks.11.self_attn.q.bias": "pytorch_model-00002.bin",
334
+ "blocks.11.self_attn.k.weight": "pytorch_model-00002.bin",
335
+ "blocks.11.self_attn.k.bias": "pytorch_model-00002.bin",
336
+ "blocks.11.self_attn.v.weight": "pytorch_model-00002.bin",
337
+ "blocks.11.self_attn.v.bias": "pytorch_model-00002.bin",
338
+ "blocks.11.self_attn.o.weight": "pytorch_model-00002.bin",
339
+ "blocks.11.self_attn.o.bias": "pytorch_model-00002.bin",
340
+ "blocks.11.self_attn.norm_q.weight": "pytorch_model-00002.bin",
341
+ "blocks.11.self_attn.norm_k.weight": "pytorch_model-00002.bin",
342
+ "blocks.11.norm3.weight": "pytorch_model-00002.bin",
343
+ "blocks.11.norm3.bias": "pytorch_model-00002.bin",
344
+ "blocks.11.cross_attn.q.weight": "pytorch_model-00002.bin",
345
+ "blocks.11.cross_attn.q.bias": "pytorch_model-00002.bin",
346
+ "blocks.11.cross_attn.k.weight": "pytorch_model-00002.bin",
347
+ "blocks.11.cross_attn.k.bias": "pytorch_model-00002.bin",
348
+ "blocks.11.cross_attn.v.weight": "pytorch_model-00002.bin",
349
+ "blocks.11.cross_attn.v.bias": "pytorch_model-00002.bin",
350
+ "blocks.11.cross_attn.o.weight": "pytorch_model-00002.bin",
351
+ "blocks.11.cross_attn.o.bias": "pytorch_model-00002.bin",
352
+ "blocks.11.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
353
+ "blocks.11.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
354
+ "blocks.11.audio_ffn.0.weight": "pytorch_model-00002.bin",
355
+ "blocks.11.audio_ffn.0.bias": "pytorch_model-00002.bin",
356
+ "blocks.11.audio_ffn.2.weight": "pytorch_model-00002.bin",
357
+ "blocks.11.audio_ffn.2.bias": "pytorch_model-00002.bin",
358
+ "blocks.11.audio_modulation.param": "pytorch_model-00002.bin",
359
+ "blocks.12.modulation": "pytorch_model-00002.bin",
360
+ "blocks.12.self_attn.q.weight": "pytorch_model-00002.bin",
361
+ "blocks.12.self_attn.q.bias": "pytorch_model-00002.bin",
362
+ "blocks.12.self_attn.k.weight": "pytorch_model-00002.bin",
363
+ "blocks.12.self_attn.k.bias": "pytorch_model-00002.bin",
364
+ "blocks.12.self_attn.v.weight": "pytorch_model-00002.bin",
365
+ "blocks.12.self_attn.v.bias": "pytorch_model-00002.bin",
366
+ "blocks.12.self_attn.o.weight": "pytorch_model-00002.bin",
367
+ "blocks.12.self_attn.o.bias": "pytorch_model-00002.bin",
368
+ "blocks.12.self_attn.norm_q.weight": "pytorch_model-00002.bin",
369
+ "blocks.12.self_attn.norm_k.weight": "pytorch_model-00002.bin",
370
+ "blocks.12.norm3.weight": "pytorch_model-00002.bin",
371
+ "blocks.12.norm3.bias": "pytorch_model-00002.bin",
372
+ "blocks.12.cross_attn.q.weight": "pytorch_model-00002.bin",
373
+ "blocks.12.cross_attn.q.bias": "pytorch_model-00002.bin",
374
+ "blocks.12.cross_attn.k.weight": "pytorch_model-00002.bin",
375
+ "blocks.12.cross_attn.k.bias": "pytorch_model-00002.bin",
376
+ "blocks.12.cross_attn.v.weight": "pytorch_model-00002.bin",
377
+ "blocks.12.cross_attn.v.bias": "pytorch_model-00002.bin",
378
+ "blocks.12.cross_attn.o.weight": "pytorch_model-00002.bin",
379
+ "blocks.12.cross_attn.o.bias": "pytorch_model-00002.bin",
380
+ "blocks.12.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
381
+ "blocks.12.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
382
+ "blocks.12.audio_ffn.0.weight": "pytorch_model-00002.bin",
383
+ "blocks.12.audio_ffn.0.bias": "pytorch_model-00002.bin",
384
+ "blocks.12.audio_ffn.2.weight": "pytorch_model-00002.bin",
385
+ "blocks.12.audio_ffn.2.bias": "pytorch_model-00002.bin",
386
+ "blocks.12.audio_modulation.param": "pytorch_model-00002.bin",
387
+ "blocks.13.modulation": "pytorch_model-00002.bin",
388
+ "blocks.13.self_attn.q.weight": "pytorch_model-00002.bin",
389
+ "blocks.13.self_attn.q.bias": "pytorch_model-00002.bin",
390
+ "blocks.13.self_attn.k.weight": "pytorch_model-00002.bin",
391
+ "blocks.13.self_attn.k.bias": "pytorch_model-00002.bin",
392
+ "blocks.13.self_attn.v.weight": "pytorch_model-00002.bin",
393
+ "blocks.13.self_attn.v.bias": "pytorch_model-00002.bin",
394
+ "blocks.13.self_attn.o.weight": "pytorch_model-00002.bin",
395
+ "blocks.13.self_attn.o.bias": "pytorch_model-00002.bin",
396
+ "blocks.13.self_attn.norm_q.weight": "pytorch_model-00002.bin",
397
+ "blocks.13.self_attn.norm_k.weight": "pytorch_model-00002.bin",
398
+ "blocks.13.norm3.weight": "pytorch_model-00002.bin",
399
+ "blocks.13.norm3.bias": "pytorch_model-00002.bin",
400
+ "blocks.13.cross_attn.q.weight": "pytorch_model-00002.bin",
401
+ "blocks.13.cross_attn.q.bias": "pytorch_model-00002.bin",
402
+ "blocks.13.cross_attn.k.weight": "pytorch_model-00002.bin",
403
+ "blocks.13.cross_attn.k.bias": "pytorch_model-00002.bin",
404
+ "blocks.13.cross_attn.v.weight": "pytorch_model-00002.bin",
405
+ "blocks.13.cross_attn.v.bias": "pytorch_model-00002.bin",
406
+ "blocks.13.cross_attn.o.weight": "pytorch_model-00002.bin",
407
+ "blocks.13.cross_attn.o.bias": "pytorch_model-00002.bin",
408
+ "blocks.13.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
409
+ "blocks.13.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
410
+ "blocks.13.audio_ffn.0.weight": "pytorch_model-00002.bin",
411
+ "blocks.13.audio_ffn.0.bias": "pytorch_model-00002.bin",
412
+ "blocks.13.audio_ffn.2.weight": "pytorch_model-00002.bin",
413
+ "blocks.13.audio_ffn.2.bias": "pytorch_model-00002.bin",
414
+ "blocks.13.audio_modulation.param": "pytorch_model-00002.bin",
415
+ "blocks.14.modulation": "pytorch_model-00002.bin",
416
+ "blocks.14.self_attn.q.weight": "pytorch_model-00002.bin",
417
+ "blocks.14.self_attn.q.bias": "pytorch_model-00002.bin",
418
+ "blocks.14.self_attn.k.weight": "pytorch_model-00002.bin",
419
+ "blocks.14.self_attn.k.bias": "pytorch_model-00002.bin",
420
+ "blocks.14.self_attn.v.weight": "pytorch_model-00002.bin",
421
+ "blocks.14.self_attn.v.bias": "pytorch_model-00002.bin",
422
+ "blocks.14.self_attn.o.weight": "pytorch_model-00002.bin",
423
+ "blocks.14.self_attn.o.bias": "pytorch_model-00002.bin",
424
+ "blocks.14.self_attn.norm_q.weight": "pytorch_model-00002.bin",
425
+ "blocks.14.self_attn.norm_k.weight": "pytorch_model-00002.bin",
426
+ "blocks.14.norm3.weight": "pytorch_model-00002.bin",
427
+ "blocks.14.norm3.bias": "pytorch_model-00002.bin",
428
+ "blocks.14.cross_attn.q.weight": "pytorch_model-00002.bin",
429
+ "blocks.14.cross_attn.q.bias": "pytorch_model-00002.bin",
430
+ "blocks.14.cross_attn.k.weight": "pytorch_model-00002.bin",
431
+ "blocks.14.cross_attn.k.bias": "pytorch_model-00002.bin",
432
+ "blocks.14.cross_attn.v.weight": "pytorch_model-00002.bin",
433
+ "blocks.14.cross_attn.v.bias": "pytorch_model-00002.bin",
434
+ "blocks.14.cross_attn.o.weight": "pytorch_model-00002.bin",
435
+ "blocks.14.cross_attn.o.bias": "pytorch_model-00002.bin",
436
+ "blocks.14.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
437
+ "blocks.14.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
438
+ "blocks.14.audio_ffn.0.weight": "pytorch_model-00002.bin",
439
+ "blocks.14.audio_ffn.0.bias": "pytorch_model-00002.bin",
440
+ "blocks.14.audio_ffn.2.weight": "pytorch_model-00002.bin",
441
+ "blocks.14.audio_ffn.2.bias": "pytorch_model-00002.bin",
442
+ "blocks.14.audio_modulation.param": "pytorch_model-00002.bin",
443
+ "blocks.15.modulation": "pytorch_model-00002.bin",
444
+ "blocks.15.self_attn.q.weight": "pytorch_model-00002.bin",
445
+ "blocks.15.self_attn.q.bias": "pytorch_model-00002.bin",
446
+ "blocks.15.self_attn.k.weight": "pytorch_model-00002.bin",
447
+ "blocks.15.self_attn.k.bias": "pytorch_model-00002.bin",
448
+ "blocks.15.self_attn.v.weight": "pytorch_model-00002.bin",
449
+ "blocks.15.self_attn.v.bias": "pytorch_model-00002.bin",
450
+ "blocks.15.self_attn.o.weight": "pytorch_model-00002.bin",
451
+ "blocks.15.self_attn.o.bias": "pytorch_model-00002.bin",
452
+ "blocks.15.self_attn.norm_q.weight": "pytorch_model-00002.bin",
453
+ "blocks.15.self_attn.norm_k.weight": "pytorch_model-00002.bin",
454
+ "blocks.15.norm3.weight": "pytorch_model-00002.bin",
455
+ "blocks.15.norm3.bias": "pytorch_model-00002.bin",
456
+ "blocks.15.cross_attn.q.weight": "pytorch_model-00002.bin",
457
+ "blocks.15.cross_attn.q.bias": "pytorch_model-00002.bin",
458
+ "blocks.15.cross_attn.k.weight": "pytorch_model-00002.bin",
459
+ "blocks.15.cross_attn.k.bias": "pytorch_model-00002.bin",
460
+ "blocks.15.cross_attn.v.weight": "pytorch_model-00002.bin",
461
+ "blocks.15.cross_attn.v.bias": "pytorch_model-00002.bin",
462
+ "blocks.15.cross_attn.o.weight": "pytorch_model-00002.bin",
463
+ "blocks.15.cross_attn.o.bias": "pytorch_model-00002.bin",
464
+ "blocks.15.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
465
+ "blocks.15.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
466
+ "blocks.15.audio_ffn.0.weight": "pytorch_model-00002.bin",
467
+ "blocks.15.audio_ffn.0.bias": "pytorch_model-00002.bin",
468
+ "blocks.15.audio_ffn.2.weight": "pytorch_model-00002.bin",
469
+ "blocks.15.audio_ffn.2.bias": "pytorch_model-00002.bin",
470
+ "blocks.15.audio_modulation.param": "pytorch_model-00002.bin",
471
+ "blocks.16.modulation": "pytorch_model-00002.bin",
472
+ "blocks.16.self_attn.q.weight": "pytorch_model-00002.bin",
473
+ "blocks.16.self_attn.q.bias": "pytorch_model-00002.bin",
474
+ "blocks.16.self_attn.k.weight": "pytorch_model-00002.bin",
475
+ "blocks.16.self_attn.k.bias": "pytorch_model-00002.bin",
476
+ "blocks.16.self_attn.v.weight": "pytorch_model-00002.bin",
477
+ "blocks.16.self_attn.v.bias": "pytorch_model-00002.bin",
478
+ "blocks.16.self_attn.o.weight": "pytorch_model-00002.bin",
479
+ "blocks.16.self_attn.o.bias": "pytorch_model-00002.bin",
480
+ "blocks.16.self_attn.norm_q.weight": "pytorch_model-00002.bin",
481
+ "blocks.16.self_attn.norm_k.weight": "pytorch_model-00002.bin",
482
+ "blocks.16.norm3.weight": "pytorch_model-00002.bin",
483
+ "blocks.16.norm3.bias": "pytorch_model-00002.bin",
484
+ "blocks.16.cross_attn.q.weight": "pytorch_model-00002.bin",
485
+ "blocks.16.cross_attn.q.bias": "pytorch_model-00002.bin",
486
+ "blocks.16.cross_attn.k.weight": "pytorch_model-00002.bin",
487
+ "blocks.16.cross_attn.k.bias": "pytorch_model-00002.bin",
488
+ "blocks.16.cross_attn.v.weight": "pytorch_model-00002.bin",
489
+ "blocks.16.cross_attn.v.bias": "pytorch_model-00002.bin",
490
+ "blocks.16.cross_attn.o.weight": "pytorch_model-00002.bin",
491
+ "blocks.16.cross_attn.o.bias": "pytorch_model-00002.bin",
492
+ "blocks.16.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
493
+ "blocks.16.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
494
+ "blocks.16.audio_ffn.0.weight": "pytorch_model-00002.bin",
495
+ "blocks.16.audio_ffn.0.bias": "pytorch_model-00002.bin",
496
+ "blocks.16.audio_ffn.2.weight": "pytorch_model-00002.bin",
497
+ "blocks.16.audio_ffn.2.bias": "pytorch_model-00002.bin",
498
+ "blocks.16.audio_modulation.param": "pytorch_model-00002.bin",
499
+ "blocks.17.modulation": "pytorch_model-00002.bin",
500
+ "blocks.17.self_attn.q.weight": "pytorch_model-00002.bin",
501
+ "blocks.17.self_attn.q.bias": "pytorch_model-00002.bin",
502
+ "blocks.17.self_attn.k.weight": "pytorch_model-00002.bin",
503
+ "blocks.17.self_attn.k.bias": "pytorch_model-00002.bin",
504
+ "blocks.17.self_attn.v.weight": "pytorch_model-00002.bin",
505
+ "blocks.17.self_attn.v.bias": "pytorch_model-00002.bin",
506
+ "blocks.17.self_attn.o.weight": "pytorch_model-00002.bin",
507
+ "blocks.17.self_attn.o.bias": "pytorch_model-00002.bin",
508
+ "blocks.17.self_attn.norm_q.weight": "pytorch_model-00002.bin",
509
+ "blocks.17.self_attn.norm_k.weight": "pytorch_model-00002.bin",
510
+ "blocks.17.norm3.weight": "pytorch_model-00002.bin",
511
+ "blocks.17.norm3.bias": "pytorch_model-00002.bin",
512
+ "blocks.17.cross_attn.q.weight": "pytorch_model-00002.bin",
513
+ "blocks.17.cross_attn.q.bias": "pytorch_model-00002.bin",
514
+ "blocks.17.cross_attn.k.weight": "pytorch_model-00002.bin",
515
+ "blocks.17.cross_attn.k.bias": "pytorch_model-00002.bin",
516
+ "blocks.17.cross_attn.v.weight": "pytorch_model-00002.bin",
517
+ "blocks.17.cross_attn.v.bias": "pytorch_model-00002.bin",
518
+ "blocks.17.cross_attn.o.weight": "pytorch_model-00002.bin",
519
+ "blocks.17.cross_attn.o.bias": "pytorch_model-00002.bin",
520
+ "blocks.17.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
521
+ "blocks.17.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
522
+ "blocks.17.audio_ffn.0.weight": "pytorch_model-00002.bin",
523
+ "blocks.17.audio_ffn.0.bias": "pytorch_model-00002.bin",
524
+ "blocks.17.audio_ffn.2.weight": "pytorch_model-00002.bin",
525
+ "blocks.17.audio_ffn.2.bias": "pytorch_model-00002.bin",
526
+ "blocks.17.audio_modulation.param": "pytorch_model-00002.bin",
527
+ "blocks.18.modulation": "pytorch_model-00002.bin",
528
+ "blocks.18.self_attn.q.weight": "pytorch_model-00002.bin",
529
+ "blocks.18.self_attn.q.bias": "pytorch_model-00002.bin",
530
+ "blocks.18.self_attn.k.weight": "pytorch_model-00002.bin",
531
+ "blocks.18.self_attn.k.bias": "pytorch_model-00002.bin",
532
+ "blocks.18.self_attn.v.weight": "pytorch_model-00002.bin",
533
+ "blocks.18.self_attn.v.bias": "pytorch_model-00002.bin",
534
+ "blocks.18.self_attn.o.weight": "pytorch_model-00002.bin",
535
+ "blocks.18.self_attn.o.bias": "pytorch_model-00002.bin",
536
+ "blocks.18.self_attn.norm_q.weight": "pytorch_model-00002.bin",
537
+ "blocks.18.self_attn.norm_k.weight": "pytorch_model-00002.bin",
538
+ "blocks.18.norm3.weight": "pytorch_model-00002.bin",
539
+ "blocks.18.norm3.bias": "pytorch_model-00002.bin",
540
+ "blocks.18.cross_attn.q.weight": "pytorch_model-00002.bin",
541
+ "blocks.18.cross_attn.q.bias": "pytorch_model-00002.bin",
542
+ "blocks.18.cross_attn.k.weight": "pytorch_model-00002.bin",
543
+ "blocks.18.cross_attn.k.bias": "pytorch_model-00002.bin",
544
+ "blocks.18.cross_attn.v.weight": "pytorch_model-00002.bin",
545
+ "blocks.18.cross_attn.v.bias": "pytorch_model-00002.bin",
546
+ "blocks.18.cross_attn.o.weight": "pytorch_model-00002.bin",
547
+ "blocks.18.cross_attn.o.bias": "pytorch_model-00002.bin",
548
+ "blocks.18.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
549
+ "blocks.18.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
550
+ "blocks.18.audio_ffn.0.weight": "pytorch_model-00002.bin",
551
+ "blocks.18.audio_ffn.0.bias": "pytorch_model-00002.bin",
552
+ "blocks.18.audio_ffn.2.weight": "pytorch_model-00002.bin",
553
+ "blocks.18.audio_ffn.2.bias": "pytorch_model-00002.bin",
554
+ "blocks.18.audio_modulation.param": "pytorch_model-00002.bin",
555
+ "blocks.19.modulation": "pytorch_model-00002.bin",
556
+ "blocks.19.self_attn.q.weight": "pytorch_model-00002.bin",
557
+ "blocks.19.self_attn.q.bias": "pytorch_model-00002.bin",
558
+ "blocks.19.self_attn.k.weight": "pytorch_model-00002.bin",
559
+ "blocks.19.self_attn.k.bias": "pytorch_model-00002.bin",
560
+ "blocks.19.self_attn.v.weight": "pytorch_model-00002.bin",
561
+ "blocks.19.self_attn.v.bias": "pytorch_model-00002.bin",
562
+ "blocks.19.self_attn.o.weight": "pytorch_model-00002.bin",
563
+ "blocks.19.self_attn.o.bias": "pytorch_model-00002.bin",
564
+ "blocks.19.self_attn.norm_q.weight": "pytorch_model-00002.bin",
565
+ "blocks.19.self_attn.norm_k.weight": "pytorch_model-00002.bin",
566
+ "blocks.19.norm3.weight": "pytorch_model-00002.bin",
567
+ "blocks.19.norm3.bias": "pytorch_model-00002.bin",
568
+ "blocks.19.cross_attn.q.weight": "pytorch_model-00002.bin",
569
+ "blocks.19.cross_attn.q.bias": "pytorch_model-00002.bin",
570
+ "blocks.19.cross_attn.k.weight": "pytorch_model-00002.bin",
571
+ "blocks.19.cross_attn.k.bias": "pytorch_model-00002.bin",
572
+ "blocks.19.cross_attn.v.weight": "pytorch_model-00002.bin",
573
+ "blocks.19.cross_attn.v.bias": "pytorch_model-00002.bin",
574
+ "blocks.19.cross_attn.o.weight": "pytorch_model-00002.bin",
575
+ "blocks.19.cross_attn.o.bias": "pytorch_model-00002.bin",
576
+ "blocks.19.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
577
+ "blocks.19.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
578
+ "blocks.19.audio_ffn.0.weight": "pytorch_model-00002.bin",
579
+ "blocks.19.audio_ffn.0.bias": "pytorch_model-00002.bin",
580
+ "blocks.19.audio_ffn.2.weight": "pytorch_model-00002.bin",
581
+ "blocks.19.audio_ffn.2.bias": "pytorch_model-00002.bin",
582
+ "blocks.19.audio_modulation.param": "pytorch_model-00002.bin",
583
+ "blocks.20.modulation": "pytorch_model-00002.bin",
584
+ "blocks.20.self_attn.q.weight": "pytorch_model-00002.bin",
585
+ "blocks.20.self_attn.q.bias": "pytorch_model-00002.bin",
586
+ "blocks.20.self_attn.k.weight": "pytorch_model-00002.bin",
587
+ "blocks.20.self_attn.k.bias": "pytorch_model-00002.bin",
588
+ "blocks.20.self_attn.v.weight": "pytorch_model-00002.bin",
589
+ "blocks.20.self_attn.v.bias": "pytorch_model-00002.bin",
590
+ "blocks.20.self_attn.o.weight": "pytorch_model-00002.bin",
591
+ "blocks.20.self_attn.o.bias": "pytorch_model-00002.bin",
592
+ "blocks.20.self_attn.norm_q.weight": "pytorch_model-00002.bin",
593
+ "blocks.20.self_attn.norm_k.weight": "pytorch_model-00002.bin",
594
+ "blocks.20.norm3.weight": "pytorch_model-00002.bin",
595
+ "blocks.20.norm3.bias": "pytorch_model-00002.bin",
596
+ "blocks.20.cross_attn.q.weight": "pytorch_model-00002.bin",
597
+ "blocks.20.cross_attn.q.bias": "pytorch_model-00002.bin",
598
+ "blocks.20.cross_attn.k.weight": "pytorch_model-00002.bin",
599
+ "blocks.20.cross_attn.k.bias": "pytorch_model-00002.bin",
600
+ "blocks.20.cross_attn.v.weight": "pytorch_model-00002.bin",
601
+ "blocks.20.cross_attn.v.bias": "pytorch_model-00002.bin",
602
+ "blocks.20.cross_attn.o.weight": "pytorch_model-00002.bin",
603
+ "blocks.20.cross_attn.o.bias": "pytorch_model-00002.bin",
604
+ "blocks.20.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
605
+ "blocks.20.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
606
+ "blocks.20.audio_ffn.0.weight": "pytorch_model-00002.bin",
607
+ "blocks.20.audio_ffn.0.bias": "pytorch_model-00002.bin",
608
+ "blocks.20.audio_ffn.2.weight": "pytorch_model-00002.bin",
609
+ "blocks.20.audio_ffn.2.bias": "pytorch_model-00002.bin",
610
+ "blocks.20.audio_modulation.param": "pytorch_model-00002.bin",
611
+ "blocks.21.modulation": "pytorch_model-00002.bin",
612
+ "blocks.21.self_attn.q.weight": "pytorch_model-00002.bin",
613
+ "blocks.21.self_attn.q.bias": "pytorch_model-00002.bin",
614
+ "blocks.21.self_attn.k.weight": "pytorch_model-00002.bin",
615
+ "blocks.21.self_attn.k.bias": "pytorch_model-00002.bin",
616
+ "blocks.21.self_attn.v.weight": "pytorch_model-00002.bin",
617
+ "blocks.21.self_attn.v.bias": "pytorch_model-00002.bin",
618
+ "blocks.21.self_attn.o.weight": "pytorch_model-00002.bin",
619
+ "blocks.21.self_attn.o.bias": "pytorch_model-00002.bin",
620
+ "blocks.21.self_attn.norm_q.weight": "pytorch_model-00002.bin",
621
+ "blocks.21.self_attn.norm_k.weight": "pytorch_model-00002.bin",
622
+ "blocks.21.norm3.weight": "pytorch_model-00002.bin",
623
+ "blocks.21.norm3.bias": "pytorch_model-00002.bin",
624
+ "blocks.21.cross_attn.q.weight": "pytorch_model-00002.bin",
625
+ "blocks.21.cross_attn.q.bias": "pytorch_model-00002.bin",
626
+ "blocks.21.cross_attn.k.weight": "pytorch_model-00002.bin",
627
+ "blocks.21.cross_attn.k.bias": "pytorch_model-00002.bin",
628
+ "blocks.21.cross_attn.v.weight": "pytorch_model-00002.bin",
629
+ "blocks.21.cross_attn.v.bias": "pytorch_model-00002.bin",
630
+ "blocks.21.cross_attn.o.weight": "pytorch_model-00002.bin",
631
+ "blocks.21.cross_attn.o.bias": "pytorch_model-00002.bin",
632
+ "blocks.21.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
633
+ "blocks.21.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
634
+ "blocks.21.audio_ffn.0.weight": "pytorch_model-00002.bin",
635
+ "blocks.21.audio_ffn.0.bias": "pytorch_model-00002.bin",
636
+ "blocks.21.audio_ffn.2.weight": "pytorch_model-00002.bin",
637
+ "blocks.21.audio_ffn.2.bias": "pytorch_model-00002.bin",
638
+ "blocks.21.audio_modulation.param": "pytorch_model-00002.bin",
639
+ "blocks.22.modulation": "pytorch_model-00002.bin",
640
+ "blocks.22.self_attn.q.weight": "pytorch_model-00002.bin",
641
+ "blocks.22.self_attn.q.bias": "pytorch_model-00002.bin",
642
+ "blocks.22.self_attn.k.weight": "pytorch_model-00002.bin",
643
+ "blocks.22.self_attn.k.bias": "pytorch_model-00002.bin",
644
+ "blocks.22.self_attn.v.weight": "pytorch_model-00002.bin",
645
+ "blocks.22.self_attn.v.bias": "pytorch_model-00002.bin",
646
+ "blocks.22.self_attn.o.weight": "pytorch_model-00002.bin",
647
+ "blocks.22.self_attn.o.bias": "pytorch_model-00002.bin",
648
+ "blocks.22.self_attn.norm_q.weight": "pytorch_model-00002.bin",
649
+ "blocks.22.self_attn.norm_k.weight": "pytorch_model-00002.bin",
650
+ "blocks.22.norm3.weight": "pytorch_model-00002.bin",
651
+ "blocks.22.norm3.bias": "pytorch_model-00002.bin",
652
+ "blocks.22.cross_attn.q.weight": "pytorch_model-00002.bin",
653
+ "blocks.22.cross_attn.q.bias": "pytorch_model-00002.bin",
654
+ "blocks.22.cross_attn.k.weight": "pytorch_model-00003.bin",
655
+ "blocks.22.cross_attn.k.bias": "pytorch_model-00003.bin",
656
+ "blocks.22.cross_attn.v.weight": "pytorch_model-00003.bin",
657
+ "blocks.22.cross_attn.v.bias": "pytorch_model-00003.bin",
658
+ "blocks.22.cross_attn.o.weight": "pytorch_model-00003.bin",
659
+ "blocks.22.cross_attn.o.bias": "pytorch_model-00003.bin",
660
+ "blocks.22.cross_attn.norm_q.weight": "pytorch_model-00003.bin",
661
+ "blocks.22.cross_attn.norm_k.weight": "pytorch_model-00003.bin",
662
+ "blocks.22.audio_ffn.0.weight": "pytorch_model-00003.bin",
663
+ "blocks.22.audio_ffn.0.bias": "pytorch_model-00003.bin",
664
+ "blocks.22.audio_ffn.2.weight": "pytorch_model-00003.bin",
665
+ "blocks.22.audio_ffn.2.bias": "pytorch_model-00003.bin",
666
+ "blocks.22.audio_modulation.param": "pytorch_model-00003.bin",
667
+ "blocks.23.modulation": "pytorch_model-00003.bin",
668
+ "blocks.23.self_attn.q.weight": "pytorch_model-00003.bin",
669
+ "blocks.23.self_attn.q.bias": "pytorch_model-00003.bin",
670
+ "blocks.23.self_attn.k.weight": "pytorch_model-00003.bin",
671
+ "blocks.23.self_attn.k.bias": "pytorch_model-00003.bin",
672
+ "blocks.23.self_attn.v.weight": "pytorch_model-00003.bin",
673
+ "blocks.23.self_attn.v.bias": "pytorch_model-00003.bin",
674
+ "blocks.23.self_attn.o.weight": "pytorch_model-00003.bin",
675
+ "blocks.23.self_attn.o.bias": "pytorch_model-00003.bin",
676
+ "blocks.23.self_attn.norm_q.weight": "pytorch_model-00003.bin",
677
+ "blocks.23.self_attn.norm_k.weight": "pytorch_model-00003.bin",
678
+ "blocks.23.norm3.weight": "pytorch_model-00003.bin",
679
+ "blocks.23.norm3.bias": "pytorch_model-00003.bin",
680
+ "blocks.23.cross_attn.q.weight": "pytorch_model-00003.bin",
681
+ "blocks.23.cross_attn.q.bias": "pytorch_model-00003.bin",
682
+ "blocks.23.cross_attn.k.weight": "pytorch_model-00003.bin",
683
+ "blocks.23.cross_attn.k.bias": "pytorch_model-00003.bin",
684
+ "blocks.23.cross_attn.v.weight": "pytorch_model-00003.bin",
685
+ "blocks.23.cross_attn.v.bias": "pytorch_model-00003.bin",
686
+ "blocks.23.cross_attn.o.weight": "pytorch_model-00003.bin",
687
+ "blocks.23.cross_attn.o.bias": "pytorch_model-00003.bin",
688
+ "blocks.23.cross_attn.norm_q.weight": "pytorch_model-00003.bin",
689
+ "blocks.23.cross_attn.norm_k.weight": "pytorch_model-00003.bin",
690
+ "blocks.23.audio_ffn.0.weight": "pytorch_model-00003.bin",
691
+ "blocks.23.audio_ffn.0.bias": "pytorch_model-00003.bin",
692
+ "blocks.23.audio_ffn.2.weight": "pytorch_model-00003.bin",
693
+ "blocks.23.audio_ffn.2.bias": "pytorch_model-00003.bin",
694
+ "blocks.23.audio_modulation.param": "pytorch_model-00003.bin",
695
+ "blocks.24.modulation": "pytorch_model-00003.bin",
696
+ "blocks.24.self_attn.q.weight": "pytorch_model-00003.bin",
697
+ "blocks.24.self_attn.q.bias": "pytorch_model-00003.bin",
698
+ "blocks.24.self_attn.k.weight": "pytorch_model-00003.bin",
699
+ "blocks.24.self_attn.k.bias": "pytorch_model-00003.bin",
700
+ "blocks.24.self_attn.v.weight": "pytorch_model-00003.bin",
701
+ "blocks.24.self_attn.v.bias": "pytorch_model-00003.bin",
702
+ "blocks.24.self_attn.o.weight": "pytorch_model-00003.bin",
703
+ "blocks.24.self_attn.o.bias": "pytorch_model-00003.bin",
704
+ "blocks.24.self_attn.norm_q.weight": "pytorch_model-00003.bin",
705
+ "blocks.24.self_attn.norm_k.weight": "pytorch_model-00003.bin",
706
+ "blocks.24.norm3.weight": "pytorch_model-00003.bin",
707
+ "blocks.24.norm3.bias": "pytorch_model-00003.bin",
708
+ "blocks.24.cross_attn.q.weight": "pytorch_model-00003.bin",
709
+ "blocks.24.cross_attn.q.bias": "pytorch_model-00003.bin",
710
+ "blocks.24.cross_attn.k.weight": "pytorch_model-00003.bin",
711
+ "blocks.24.cross_attn.k.bias": "pytorch_model-00003.bin",
712
+ "blocks.24.cross_attn.v.weight": "pytorch_model-00003.bin",
713
+ "blocks.24.cross_attn.v.bias": "pytorch_model-00003.bin",
714
+ "blocks.24.cross_attn.o.weight": "pytorch_model-00003.bin",
715
+ "blocks.24.cross_attn.o.bias": "pytorch_model-00003.bin",
716
+ "blocks.24.cross_attn.norm_q.weight": "pytorch_model-00003.bin",
717
+ "blocks.24.cross_attn.norm_k.weight": "pytorch_model-00003.bin",
718
+ "blocks.24.audio_ffn.0.weight": "pytorch_model-00003.bin",
719
+ "blocks.24.audio_ffn.0.bias": "pytorch_model-00003.bin",
720
+ "blocks.24.audio_ffn.2.weight": "pytorch_model-00003.bin",
721
+ "blocks.24.audio_ffn.2.bias": "pytorch_model-00003.bin",
722
+ "blocks.24.audio_modulation.param": "pytorch_model-00003.bin",
723
+ "blocks.25.modulation": "pytorch_model-00003.bin",
724
+ "blocks.25.self_attn.q.weight": "pytorch_model-00003.bin",
725
+ "blocks.25.self_attn.q.bias": "pytorch_model-00003.bin",
726
+ "blocks.25.self_attn.k.weight": "pytorch_model-00003.bin",
727
+ "blocks.25.self_attn.k.bias": "pytorch_model-00003.bin",
728
+ "blocks.25.self_attn.v.weight": "pytorch_model-00003.bin",
729
+ "blocks.25.self_attn.v.bias": "pytorch_model-00003.bin",
730
+ "blocks.25.self_attn.o.weight": "pytorch_model-00003.bin",
731
+ "blocks.25.self_attn.o.bias": "pytorch_model-00003.bin",
732
+ "blocks.25.self_attn.norm_q.weight": "pytorch_model-00003.bin",
733
+ "blocks.25.self_attn.norm_k.weight": "pytorch_model-00003.bin",
734
+ "blocks.25.norm3.weight": "pytorch_model-00003.bin",
735
+ "blocks.25.norm3.bias": "pytorch_model-00003.bin",
736
+ "blocks.25.cross_attn.q.weight": "pytorch_model-00003.bin",
737
+ "blocks.25.cross_attn.q.bias": "pytorch_model-00003.bin",
738
+ "blocks.25.cross_attn.k.weight": "pytorch_model-00003.bin",
739
+ "blocks.25.cross_attn.k.bias": "pytorch_model-00003.bin",
740
+ "blocks.25.cross_attn.v.weight": "pytorch_model-00003.bin",
741
+ "blocks.25.cross_attn.v.bias": "pytorch_model-00003.bin",
742
+ "blocks.25.cross_attn.o.weight": "pytorch_model-00003.bin",
743
+ "blocks.25.cross_attn.o.bias": "pytorch_model-00003.bin",
744
+ "blocks.25.cross_attn.norm_q.weight": "pytorch_model-00003.bin",
745
+ "blocks.25.cross_attn.norm_k.weight": "pytorch_model-00003.bin",
746
+ "blocks.25.audio_ffn.0.weight": "pytorch_model-00003.bin",
747
+ "blocks.25.audio_ffn.0.bias": "pytorch_model-00003.bin",
748
+ "blocks.25.audio_ffn.2.weight": "pytorch_model-00003.bin",
749
+ "blocks.25.audio_ffn.2.bias": "pytorch_model-00003.bin",
750
+ "blocks.25.audio_modulation.param": "pytorch_model-00003.bin",
751
+ "blocks.26.modulation": "pytorch_model-00003.bin",
752
+ "blocks.26.self_attn.q.weight": "pytorch_model-00003.bin",
753
+ "blocks.26.self_attn.q.bias": "pytorch_model-00003.bin",
754
+ "blocks.26.self_attn.k.weight": "pytorch_model-00003.bin",
755
+ "blocks.26.self_attn.k.bias": "pytorch_model-00003.bin",
756
+ "blocks.26.self_attn.v.weight": "pytorch_model-00003.bin",
757
+ "blocks.26.self_attn.v.bias": "pytorch_model-00003.bin",
758
+ "blocks.26.self_attn.o.weight": "pytorch_model-00003.bin",
759
+ "blocks.26.self_attn.o.bias": "pytorch_model-00003.bin",
760
+ "blocks.26.self_attn.norm_q.weight": "pytorch_model-00003.bin",
761
+ "blocks.26.self_attn.norm_k.weight": "pytorch_model-00003.bin",
762
+ "blocks.26.norm3.weight": "pytorch_model-00003.bin",
763
+ "blocks.26.norm3.bias": "pytorch_model-00003.bin",
764
+ "blocks.26.cross_attn.q.weight": "pytorch_model-00003.bin",
765
+ "blocks.26.cross_attn.q.bias": "pytorch_model-00003.bin",
766
+ "blocks.26.cross_attn.k.weight": "pytorch_model-00003.bin",
767
+ "blocks.26.cross_attn.k.bias": "pytorch_model-00003.bin",
768
+ "blocks.26.cross_attn.v.weight": "pytorch_model-00003.bin",
769
+ "blocks.26.cross_attn.v.bias": "pytorch_model-00003.bin",
770
+ "blocks.26.cross_attn.o.weight": "pytorch_model-00003.bin",
771
+ "blocks.26.cross_attn.o.bias": "pytorch_model-00003.bin",
772
+ "blocks.26.cross_attn.norm_q.weight": "pytorch_model-00003.bin",
773
+ "blocks.26.cross_attn.norm_k.weight": "pytorch_model-00003.bin",
774
+ "blocks.26.audio_ffn.0.weight": "pytorch_model-00003.bin",
775
+ "blocks.26.audio_ffn.0.bias": "pytorch_model-00003.bin",
776
+ "blocks.26.audio_ffn.2.weight": "pytorch_model-00003.bin",
777
+ "blocks.26.audio_ffn.2.bias": "pytorch_model-00003.bin",
778
+ "blocks.26.audio_modulation.param": "pytorch_model-00003.bin",
779
+ "blocks.27.modulation": "pytorch_model-00003.bin",
780
+ "blocks.27.self_attn.q.weight": "pytorch_model-00003.bin",
781
+ "blocks.27.self_attn.q.bias": "pytorch_model-00003.bin",
782
+ "blocks.27.self_attn.k.weight": "pytorch_model-00003.bin",
783
+ "blocks.27.self_attn.k.bias": "pytorch_model-00003.bin",
784
+ "blocks.27.self_attn.v.weight": "pytorch_model-00003.bin",
785
+ "blocks.27.self_attn.v.bias": "pytorch_model-00003.bin",
786
+ "blocks.27.self_attn.o.weight": "pytorch_model-00003.bin",
787
+ "blocks.27.self_attn.o.bias": "pytorch_model-00003.bin",
788
+ "blocks.27.self_attn.norm_q.weight": "pytorch_model-00003.bin",
789
+ "blocks.27.self_attn.norm_k.weight": "pytorch_model-00003.bin",
790
+ "blocks.27.norm3.weight": "pytorch_model-00003.bin",
791
+ "blocks.27.norm3.bias": "pytorch_model-00003.bin",
792
+ "blocks.27.cross_attn.q.weight": "pytorch_model-00003.bin",
793
+ "blocks.27.cross_attn.q.bias": "pytorch_model-00003.bin",
794
+ "blocks.27.cross_attn.k.weight": "pytorch_model-00003.bin",
795
+ "blocks.27.cross_attn.k.bias": "pytorch_model-00003.bin",
796
+ "blocks.27.cross_attn.v.weight": "pytorch_model-00003.bin",
797
+ "blocks.27.cross_attn.v.bias": "pytorch_model-00003.bin",
798
+ "blocks.27.cross_attn.o.weight": "pytorch_model-00003.bin",
799
+ "blocks.27.cross_attn.o.bias": "pytorch_model-00003.bin",
800
+ "blocks.27.cross_attn.norm_q.weight": "pytorch_model-00003.bin",
801
+ "blocks.27.cross_attn.norm_k.weight": "pytorch_model-00003.bin",
802
+ "blocks.27.audio_ffn.0.weight": "pytorch_model-00003.bin",
803
+ "blocks.27.audio_ffn.0.bias": "pytorch_model-00003.bin",
804
+ "blocks.27.audio_ffn.2.weight": "pytorch_model-00003.bin",
805
+ "blocks.27.audio_ffn.2.bias": "pytorch_model-00003.bin",
806
+ "blocks.27.audio_modulation.param": "pytorch_model-00003.bin",
807
+ "blocks.28.modulation": "pytorch_model-00003.bin",
808
+ "blocks.28.self_attn.q.weight": "pytorch_model-00003.bin",
809
+ "blocks.28.self_attn.q.bias": "pytorch_model-00003.bin",
810
+ "blocks.28.self_attn.k.weight": "pytorch_model-00003.bin",
811
+ "blocks.28.self_attn.k.bias": "pytorch_model-00003.bin",
812
+ "blocks.28.self_attn.v.weight": "pytorch_model-00003.bin",
813
+ "blocks.28.self_attn.v.bias": "pytorch_model-00003.bin",
814
+ "blocks.28.self_attn.o.weight": "pytorch_model-00003.bin",
815
+ "blocks.28.self_attn.o.bias": "pytorch_model-00003.bin",
816
+ "blocks.28.self_attn.norm_q.weight": "pytorch_model-00003.bin",
817
+ "blocks.28.self_attn.norm_k.weight": "pytorch_model-00003.bin",
818
+ "blocks.28.norm3.weight": "pytorch_model-00003.bin",
819
+ "blocks.28.norm3.bias": "pytorch_model-00003.bin",
820
+ "blocks.28.cross_attn.q.weight": "pytorch_model-00003.bin",
821
+ "blocks.28.cross_attn.q.bias": "pytorch_model-00003.bin",
822
+ "blocks.28.cross_attn.k.weight": "pytorch_model-00003.bin",
823
+ "blocks.28.cross_attn.k.bias": "pytorch_model-00003.bin",
824
+ "blocks.28.cross_attn.v.weight": "pytorch_model-00003.bin",
825
+ "blocks.28.cross_attn.v.bias": "pytorch_model-00003.bin",
826
+ "blocks.28.cross_attn.o.weight": "pytorch_model-00003.bin",
827
+ "blocks.28.cross_attn.o.bias": "pytorch_model-00003.bin",
828
+ "blocks.28.cross_attn.norm_q.weight": "pytorch_model-00003.bin",
829
+ "blocks.28.cross_attn.norm_k.weight": "pytorch_model-00003.bin",
830
+ "blocks.28.audio_ffn.0.weight": "pytorch_model-00003.bin",
831
+ "blocks.28.audio_ffn.0.bias": "pytorch_model-00003.bin",
832
+ "blocks.28.audio_ffn.2.weight": "pytorch_model-00003.bin",
833
+ "blocks.28.audio_ffn.2.bias": "pytorch_model-00003.bin",
834
+ "blocks.28.audio_modulation.param": "pytorch_model-00003.bin",
835
+ "blocks.29.modulation": "pytorch_model-00003.bin",
836
+ "blocks.29.self_attn.q.weight": "pytorch_model-00003.bin",
837
+ "blocks.29.self_attn.q.bias": "pytorch_model-00003.bin",
838
+ "blocks.29.self_attn.k.weight": "pytorch_model-00003.bin",
839
+ "blocks.29.self_attn.k.bias": "pytorch_model-00003.bin",
840
+ "blocks.29.self_attn.v.weight": "pytorch_model-00003.bin",
841
+ "blocks.29.self_attn.v.bias": "pytorch_model-00003.bin",
842
+ "blocks.29.self_attn.o.weight": "pytorch_model-00003.bin",
843
+ "blocks.29.self_attn.o.bias": "pytorch_model-00003.bin",
844
+ "blocks.29.self_attn.norm_q.weight": "pytorch_model-00003.bin",
845
+ "blocks.29.self_attn.norm_k.weight": "pytorch_model-00003.bin",
846
+ "blocks.29.norm3.weight": "pytorch_model-00003.bin",
847
+ "blocks.29.norm3.bias": "pytorch_model-00003.bin",
848
+ "blocks.29.cross_attn.q.weight": "pytorch_model-00003.bin",
849
+ "blocks.29.cross_attn.q.bias": "pytorch_model-00003.bin",
850
+ "blocks.29.cross_attn.k.weight": "pytorch_model-00003.bin",
851
+ "blocks.29.cross_attn.k.bias": "pytorch_model-00003.bin",
852
+ "blocks.29.cross_attn.v.weight": "pytorch_model-00003.bin",
853
+ "blocks.29.cross_attn.v.bias": "pytorch_model-00003.bin",
854
+ "blocks.29.cross_attn.o.weight": "pytorch_model-00003.bin",
855
+ "blocks.29.cross_attn.o.bias": "pytorch_model-00003.bin",
856
+ "blocks.29.cross_attn.norm_q.weight": "pytorch_model-00003.bin",
857
+ "blocks.29.cross_attn.norm_k.weight": "pytorch_model-00003.bin",
858
+ "blocks.29.audio_ffn.0.weight": "pytorch_model-00003.bin",
859
+ "blocks.29.audio_ffn.0.bias": "pytorch_model-00003.bin",
860
+ "blocks.29.audio_ffn.2.weight": "pytorch_model-00003.bin",
861
+ "blocks.29.audio_ffn.2.bias": "pytorch_model-00003.bin",
862
+ "blocks.29.audio_modulation.param": "pytorch_model-00003.bin"
863
+ }
864
+ }
audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53000/optimizer/pytorch_optim-00001.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2222778b21283d3453b829e5ff0e42c6d8cb326434b5890e19cc03a53ec5b51c
3
+ size 4243656922
audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53000/optimizer/pytorch_optim-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6abdac7f4143454de7c8b46778738a9f6e3c5449ca9c2b3bc8cc1a6a879ff0fa
3
+ size 2423571758
audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53000/optimizer/pytorch_optim.bin.index.json ADDED
@@ -0,0 +1,165 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "param_groups": "pytorch_optim_group.bin",
4
+ "total_size": 6358.277587890625
5
+ },
6
+ "weight_map": {
7
+ "0": "pytorch_optim-00001.bin",
8
+ "1": "pytorch_optim-00001.bin",
9
+ "2": "pytorch_optim-00001.bin",
10
+ "3": "pytorch_optim-00001.bin",
11
+ "4": "pytorch_optim-00001.bin",
12
+ "5": "pytorch_optim-00001.bin",
13
+ "6": "pytorch_optim-00001.bin",
14
+ "7": "pytorch_optim-00001.bin",
15
+ "8": "pytorch_optim-00001.bin",
16
+ "9": "pytorch_optim-00001.bin",
17
+ "10": "pytorch_optim-00001.bin",
18
+ "11": "pytorch_optim-00001.bin",
19
+ "12": "pytorch_optim-00001.bin",
20
+ "13": "pytorch_optim-00001.bin",
21
+ "14": "pytorch_optim-00001.bin",
22
+ "15": "pytorch_optim-00001.bin",
23
+ "16": "pytorch_optim-00001.bin",
24
+ "17": "pytorch_optim-00001.bin",
25
+ "18": "pytorch_optim-00001.bin",
26
+ "19": "pytorch_optim-00001.bin",
27
+ "20": "pytorch_optim-00001.bin",
28
+ "21": "pytorch_optim-00001.bin",
29
+ "22": "pytorch_optim-00001.bin",
30
+ "23": "pytorch_optim-00001.bin",
31
+ "24": "pytorch_optim-00001.bin",
32
+ "25": "pytorch_optim-00001.bin",
33
+ "26": "pytorch_optim-00001.bin",
34
+ "27": "pytorch_optim-00001.bin",
35
+ "28": "pytorch_optim-00001.bin",
36
+ "29": "pytorch_optim-00001.bin",
37
+ "30": "pytorch_optim-00001.bin",
38
+ "31": "pytorch_optim-00001.bin",
39
+ "32": "pytorch_optim-00001.bin",
40
+ "33": "pytorch_optim-00001.bin",
41
+ "34": "pytorch_optim-00001.bin",
42
+ "35": "pytorch_optim-00001.bin",
43
+ "36": "pytorch_optim-00001.bin",
44
+ "37": "pytorch_optim-00001.bin",
45
+ "38": "pytorch_optim-00001.bin",
46
+ "39": "pytorch_optim-00001.bin",
47
+ "40": "pytorch_optim-00001.bin",
48
+ "41": "pytorch_optim-00001.bin",
49
+ "42": "pytorch_optim-00001.bin",
50
+ "43": "pytorch_optim-00001.bin",
51
+ "44": "pytorch_optim-00001.bin",
52
+ "45": "pytorch_optim-00001.bin",
53
+ "46": "pytorch_optim-00001.bin",
54
+ "47": "pytorch_optim-00001.bin",
55
+ "48": "pytorch_optim-00001.bin",
56
+ "49": "pytorch_optim-00001.bin",
57
+ "50": "pytorch_optim-00001.bin",
58
+ "51": "pytorch_optim-00001.bin",
59
+ "52": "pytorch_optim-00001.bin",
60
+ "53": "pytorch_optim-00001.bin",
61
+ "54": "pytorch_optim-00001.bin",
62
+ "55": "pytorch_optim-00001.bin",
63
+ "56": "pytorch_optim-00001.bin",
64
+ "57": "pytorch_optim-00001.bin",
65
+ "58": "pytorch_optim-00001.bin",
66
+ "59": "pytorch_optim-00001.bin",
67
+ "60": "pytorch_optim-00001.bin",
68
+ "61": "pytorch_optim-00001.bin",
69
+ "62": "pytorch_optim-00001.bin",
70
+ "63": "pytorch_optim-00001.bin",
71
+ "64": "pytorch_optim-00001.bin",
72
+ "65": "pytorch_optim-00001.bin",
73
+ "66": "pytorch_optim-00001.bin",
74
+ "67": "pytorch_optim-00001.bin",
75
+ "68": "pytorch_optim-00001.bin",
76
+ "69": "pytorch_optim-00001.bin",
77
+ "70": "pytorch_optim-00001.bin",
78
+ "71": "pytorch_optim-00001.bin",
79
+ "72": "pytorch_optim-00001.bin",
80
+ "73": "pytorch_optim-00001.bin",
81
+ "74": "pytorch_optim-00001.bin",
82
+ "75": "pytorch_optim-00001.bin",
83
+ "76": "pytorch_optim-00001.bin",
84
+ "77": "pytorch_optim-00001.bin",
85
+ "78": "pytorch_optim-00001.bin",
86
+ "79": "pytorch_optim-00001.bin",
87
+ "80": "pytorch_optim-00001.bin",
88
+ "81": "pytorch_optim-00001.bin",
89
+ "82": "pytorch_optim-00001.bin",
90
+ "83": "pytorch_optim-00001.bin",
91
+ "84": "pytorch_optim-00001.bin",
92
+ "85": "pytorch_optim-00001.bin",
93
+ "86": "pytorch_optim-00001.bin",
94
+ "87": "pytorch_optim-00001.bin",
95
+ "88": "pytorch_optim-00001.bin",
96
+ "89": "pytorch_optim-00001.bin",
97
+ "90": "pytorch_optim-00001.bin",
98
+ "91": "pytorch_optim-00001.bin",
99
+ "92": "pytorch_optim-00001.bin",
100
+ "93": "pytorch_optim-00001.bin",
101
+ "94": "pytorch_optim-00001.bin",
102
+ "95": "pytorch_optim-00001.bin",
103
+ "96": "pytorch_optim-00001.bin",
104
+ "97": "pytorch_optim-00001.bin",
105
+ "98": "pytorch_optim-00001.bin",
106
+ "99": "pytorch_optim-00001.bin",
107
+ "100": "pytorch_optim-00001.bin",
108
+ "101": "pytorch_optim-00001.bin",
109
+ "102": "pytorch_optim-00002.bin",
110
+ "103": "pytorch_optim-00002.bin",
111
+ "104": "pytorch_optim-00002.bin",
112
+ "105": "pytorch_optim-00002.bin",
113
+ "106": "pytorch_optim-00002.bin",
114
+ "107": "pytorch_optim-00002.bin",
115
+ "108": "pytorch_optim-00002.bin",
116
+ "109": "pytorch_optim-00002.bin",
117
+ "110": "pytorch_optim-00002.bin",
118
+ "111": "pytorch_optim-00002.bin",
119
+ "112": "pytorch_optim-00002.bin",
120
+ "113": "pytorch_optim-00002.bin",
121
+ "114": "pytorch_optim-00002.bin",
122
+ "115": "pytorch_optim-00002.bin",
123
+ "116": "pytorch_optim-00002.bin",
124
+ "117": "pytorch_optim-00002.bin",
125
+ "118": "pytorch_optim-00002.bin",
126
+ "119": "pytorch_optim-00002.bin",
127
+ "120": "pytorch_optim-00002.bin",
128
+ "121": "pytorch_optim-00002.bin",
129
+ "122": "pytorch_optim-00002.bin",
130
+ "123": "pytorch_optim-00002.bin",
131
+ "124": "pytorch_optim-00002.bin",
132
+ "125": "pytorch_optim-00002.bin",
133
+ "126": "pytorch_optim-00002.bin",
134
+ "127": "pytorch_optim-00002.bin",
135
+ "128": "pytorch_optim-00002.bin",
136
+ "129": "pytorch_optim-00002.bin",
137
+ "130": "pytorch_optim-00002.bin",
138
+ "131": "pytorch_optim-00002.bin",
139
+ "132": "pytorch_optim-00002.bin",
140
+ "133": "pytorch_optim-00002.bin",
141
+ "134": "pytorch_optim-00002.bin",
142
+ "135": "pytorch_optim-00002.bin",
143
+ "136": "pytorch_optim-00002.bin",
144
+ "137": "pytorch_optim-00002.bin",
145
+ "138": "pytorch_optim-00002.bin",
146
+ "139": "pytorch_optim-00002.bin",
147
+ "140": "pytorch_optim-00002.bin",
148
+ "141": "pytorch_optim-00002.bin",
149
+ "142": "pytorch_optim-00002.bin",
150
+ "143": "pytorch_optim-00002.bin",
151
+ "144": "pytorch_optim-00002.bin",
152
+ "145": "pytorch_optim-00002.bin",
153
+ "146": "pytorch_optim-00002.bin",
154
+ "147": "pytorch_optim-00002.bin",
155
+ "148": "pytorch_optim-00002.bin",
156
+ "149": "pytorch_optim-00002.bin",
157
+ "150": "pytorch_optim-00002.bin",
158
+ "151": "pytorch_optim-00002.bin",
159
+ "152": "pytorch_optim-00002.bin",
160
+ "153": "pytorch_optim-00002.bin",
161
+ "154": "pytorch_optim-00002.bin",
162
+ "155": "pytorch_optim-00002.bin",
163
+ "156": "pytorch_optim-00002.bin"
164
+ }
165
+ }
audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53000/optimizer/pytorch_optim_group.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:821c8504135947a0f7bc707c16e2865d3740fd6a307b8b5232645e4f886c0ebf
3
+ size 1360
audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53000/running_states.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 49,
3
+ "step": 423,
4
+ "global_step": 53000,
5
+ "batch_size": null
6
+ }
audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53000/sampler ADDED
Binary file (928 Bytes). View file
 
audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53650/ema.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f490c4f53e9268fb0c5e6d16239fab6494192316d180a4f61b259e26932e666
3
+ size 5704739068
audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53650/lr_scheduler ADDED
Binary file (1.01 kB). View file
 
audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53650/model/pytorch_model-00001.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38ab1ed9f54f7f35c0d0235889be036c2bf7b6cc7a296c3c122ed8f44bdff680
3
+ size 1059881014
audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53650/model/pytorch_model-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f913d62f03801714dba76d5a68073c9d2dc2bc803ecc11f9aa53d9a441b63ab3
3
+ size 1073076766
audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53650/model/pytorch_model-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3551c4ea5490a1a730024249749e33ecac48dc2ac0c3a17af3ae4ec0eb7153f8
3
+ size 719552332
audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53650/model/pytorch_model.bin.index.json ADDED
@@ -0,0 +1,864 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 2720.1065063476562
4
+ },
5
+ "weight_map": {
6
+ "audio_patch_embedding.weight": "pytorch_model-00001.bin",
7
+ "audio_patch_embedding.bias": "pytorch_model-00001.bin",
8
+ "audio_head.modulation": "pytorch_model-00001.bin",
9
+ "audio_head.head.weight": "pytorch_model-00001.bin",
10
+ "audio_head.head.bias": "pytorch_model-00001.bin",
11
+ "text_embedding.0.weight": "pytorch_model-00001.bin",
12
+ "text_embedding.0.bias": "pytorch_model-00001.bin",
13
+ "text_embedding.2.weight": "pytorch_model-00001.bin",
14
+ "text_embedding.2.bias": "pytorch_model-00001.bin",
15
+ "time_embedding.0.weight": "pytorch_model-00001.bin",
16
+ "time_embedding.0.bias": "pytorch_model-00001.bin",
17
+ "time_embedding.2.weight": "pytorch_model-00001.bin",
18
+ "time_embedding.2.bias": "pytorch_model-00001.bin",
19
+ "time_projection.1.weight": "pytorch_model-00001.bin",
20
+ "time_projection.1.bias": "pytorch_model-00001.bin",
21
+ "audio_time_projection.1.weight": "pytorch_model-00001.bin",
22
+ "audio_time_projection.1.bias": "pytorch_model-00001.bin",
23
+ "blocks.0.modulation": "pytorch_model-00001.bin",
24
+ "blocks.0.self_attn.q.weight": "pytorch_model-00001.bin",
25
+ "blocks.0.self_attn.q.bias": "pytorch_model-00001.bin",
26
+ "blocks.0.self_attn.k.weight": "pytorch_model-00001.bin",
27
+ "blocks.0.self_attn.k.bias": "pytorch_model-00001.bin",
28
+ "blocks.0.self_attn.v.weight": "pytorch_model-00001.bin",
29
+ "blocks.0.self_attn.v.bias": "pytorch_model-00001.bin",
30
+ "blocks.0.self_attn.o.weight": "pytorch_model-00001.bin",
31
+ "blocks.0.self_attn.o.bias": "pytorch_model-00001.bin",
32
+ "blocks.0.self_attn.norm_q.weight": "pytorch_model-00001.bin",
33
+ "blocks.0.self_attn.norm_k.weight": "pytorch_model-00001.bin",
34
+ "blocks.0.norm3.weight": "pytorch_model-00001.bin",
35
+ "blocks.0.norm3.bias": "pytorch_model-00001.bin",
36
+ "blocks.0.cross_attn.q.weight": "pytorch_model-00001.bin",
37
+ "blocks.0.cross_attn.q.bias": "pytorch_model-00001.bin",
38
+ "blocks.0.cross_attn.k.weight": "pytorch_model-00001.bin",
39
+ "blocks.0.cross_attn.k.bias": "pytorch_model-00001.bin",
40
+ "blocks.0.cross_attn.v.weight": "pytorch_model-00001.bin",
41
+ "blocks.0.cross_attn.v.bias": "pytorch_model-00001.bin",
42
+ "blocks.0.cross_attn.o.weight": "pytorch_model-00001.bin",
43
+ "blocks.0.cross_attn.o.bias": "pytorch_model-00001.bin",
44
+ "blocks.0.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
45
+ "blocks.0.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
46
+ "blocks.0.audio_ffn.0.weight": "pytorch_model-00001.bin",
47
+ "blocks.0.audio_ffn.0.bias": "pytorch_model-00001.bin",
48
+ "blocks.0.audio_ffn.2.weight": "pytorch_model-00001.bin",
49
+ "blocks.0.audio_ffn.2.bias": "pytorch_model-00001.bin",
50
+ "blocks.0.audio_modulation.param": "pytorch_model-00001.bin",
51
+ "blocks.1.modulation": "pytorch_model-00001.bin",
52
+ "blocks.1.self_attn.q.weight": "pytorch_model-00001.bin",
53
+ "blocks.1.self_attn.q.bias": "pytorch_model-00001.bin",
54
+ "blocks.1.self_attn.k.weight": "pytorch_model-00001.bin",
55
+ "blocks.1.self_attn.k.bias": "pytorch_model-00001.bin",
56
+ "blocks.1.self_attn.v.weight": "pytorch_model-00001.bin",
57
+ "blocks.1.self_attn.v.bias": "pytorch_model-00001.bin",
58
+ "blocks.1.self_attn.o.weight": "pytorch_model-00001.bin",
59
+ "blocks.1.self_attn.o.bias": "pytorch_model-00001.bin",
60
+ "blocks.1.self_attn.norm_q.weight": "pytorch_model-00001.bin",
61
+ "blocks.1.self_attn.norm_k.weight": "pytorch_model-00001.bin",
62
+ "blocks.1.norm3.weight": "pytorch_model-00001.bin",
63
+ "blocks.1.norm3.bias": "pytorch_model-00001.bin",
64
+ "blocks.1.cross_attn.q.weight": "pytorch_model-00001.bin",
65
+ "blocks.1.cross_attn.q.bias": "pytorch_model-00001.bin",
66
+ "blocks.1.cross_attn.k.weight": "pytorch_model-00001.bin",
67
+ "blocks.1.cross_attn.k.bias": "pytorch_model-00001.bin",
68
+ "blocks.1.cross_attn.v.weight": "pytorch_model-00001.bin",
69
+ "blocks.1.cross_attn.v.bias": "pytorch_model-00001.bin",
70
+ "blocks.1.cross_attn.o.weight": "pytorch_model-00001.bin",
71
+ "blocks.1.cross_attn.o.bias": "pytorch_model-00001.bin",
72
+ "blocks.1.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
73
+ "blocks.1.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
74
+ "blocks.1.audio_ffn.0.weight": "pytorch_model-00001.bin",
75
+ "blocks.1.audio_ffn.0.bias": "pytorch_model-00001.bin",
76
+ "blocks.1.audio_ffn.2.weight": "pytorch_model-00001.bin",
77
+ "blocks.1.audio_ffn.2.bias": "pytorch_model-00001.bin",
78
+ "blocks.1.audio_modulation.param": "pytorch_model-00001.bin",
79
+ "blocks.2.modulation": "pytorch_model-00001.bin",
80
+ "blocks.2.self_attn.q.weight": "pytorch_model-00001.bin",
81
+ "blocks.2.self_attn.q.bias": "pytorch_model-00001.bin",
82
+ "blocks.2.self_attn.k.weight": "pytorch_model-00001.bin",
83
+ "blocks.2.self_attn.k.bias": "pytorch_model-00001.bin",
84
+ "blocks.2.self_attn.v.weight": "pytorch_model-00001.bin",
85
+ "blocks.2.self_attn.v.bias": "pytorch_model-00001.bin",
86
+ "blocks.2.self_attn.o.weight": "pytorch_model-00001.bin",
87
+ "blocks.2.self_attn.o.bias": "pytorch_model-00001.bin",
88
+ "blocks.2.self_attn.norm_q.weight": "pytorch_model-00001.bin",
89
+ "blocks.2.self_attn.norm_k.weight": "pytorch_model-00001.bin",
90
+ "blocks.2.norm3.weight": "pytorch_model-00001.bin",
91
+ "blocks.2.norm3.bias": "pytorch_model-00001.bin",
92
+ "blocks.2.cross_attn.q.weight": "pytorch_model-00001.bin",
93
+ "blocks.2.cross_attn.q.bias": "pytorch_model-00001.bin",
94
+ "blocks.2.cross_attn.k.weight": "pytorch_model-00001.bin",
95
+ "blocks.2.cross_attn.k.bias": "pytorch_model-00001.bin",
96
+ "blocks.2.cross_attn.v.weight": "pytorch_model-00001.bin",
97
+ "blocks.2.cross_attn.v.bias": "pytorch_model-00001.bin",
98
+ "blocks.2.cross_attn.o.weight": "pytorch_model-00001.bin",
99
+ "blocks.2.cross_attn.o.bias": "pytorch_model-00001.bin",
100
+ "blocks.2.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
101
+ "blocks.2.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
102
+ "blocks.2.audio_ffn.0.weight": "pytorch_model-00001.bin",
103
+ "blocks.2.audio_ffn.0.bias": "pytorch_model-00001.bin",
104
+ "blocks.2.audio_ffn.2.weight": "pytorch_model-00001.bin",
105
+ "blocks.2.audio_ffn.2.bias": "pytorch_model-00001.bin",
106
+ "blocks.2.audio_modulation.param": "pytorch_model-00001.bin",
107
+ "blocks.3.modulation": "pytorch_model-00001.bin",
108
+ "blocks.3.self_attn.q.weight": "pytorch_model-00001.bin",
109
+ "blocks.3.self_attn.q.bias": "pytorch_model-00001.bin",
110
+ "blocks.3.self_attn.k.weight": "pytorch_model-00001.bin",
111
+ "blocks.3.self_attn.k.bias": "pytorch_model-00001.bin",
112
+ "blocks.3.self_attn.v.weight": "pytorch_model-00001.bin",
113
+ "blocks.3.self_attn.v.bias": "pytorch_model-00001.bin",
114
+ "blocks.3.self_attn.o.weight": "pytorch_model-00001.bin",
115
+ "blocks.3.self_attn.o.bias": "pytorch_model-00001.bin",
116
+ "blocks.3.self_attn.norm_q.weight": "pytorch_model-00001.bin",
117
+ "blocks.3.self_attn.norm_k.weight": "pytorch_model-00001.bin",
118
+ "blocks.3.norm3.weight": "pytorch_model-00001.bin",
119
+ "blocks.3.norm3.bias": "pytorch_model-00001.bin",
120
+ "blocks.3.cross_attn.q.weight": "pytorch_model-00001.bin",
121
+ "blocks.3.cross_attn.q.bias": "pytorch_model-00001.bin",
122
+ "blocks.3.cross_attn.k.weight": "pytorch_model-00001.bin",
123
+ "blocks.3.cross_attn.k.bias": "pytorch_model-00001.bin",
124
+ "blocks.3.cross_attn.v.weight": "pytorch_model-00001.bin",
125
+ "blocks.3.cross_attn.v.bias": "pytorch_model-00001.bin",
126
+ "blocks.3.cross_attn.o.weight": "pytorch_model-00001.bin",
127
+ "blocks.3.cross_attn.o.bias": "pytorch_model-00001.bin",
128
+ "blocks.3.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
129
+ "blocks.3.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
130
+ "blocks.3.audio_ffn.0.weight": "pytorch_model-00001.bin",
131
+ "blocks.3.audio_ffn.0.bias": "pytorch_model-00001.bin",
132
+ "blocks.3.audio_ffn.2.weight": "pytorch_model-00001.bin",
133
+ "blocks.3.audio_ffn.2.bias": "pytorch_model-00001.bin",
134
+ "blocks.3.audio_modulation.param": "pytorch_model-00001.bin",
135
+ "blocks.4.modulation": "pytorch_model-00001.bin",
136
+ "blocks.4.self_attn.q.weight": "pytorch_model-00001.bin",
137
+ "blocks.4.self_attn.q.bias": "pytorch_model-00001.bin",
138
+ "blocks.4.self_attn.k.weight": "pytorch_model-00001.bin",
139
+ "blocks.4.self_attn.k.bias": "pytorch_model-00001.bin",
140
+ "blocks.4.self_attn.v.weight": "pytorch_model-00001.bin",
141
+ "blocks.4.self_attn.v.bias": "pytorch_model-00001.bin",
142
+ "blocks.4.self_attn.o.weight": "pytorch_model-00001.bin",
143
+ "blocks.4.self_attn.o.bias": "pytorch_model-00001.bin",
144
+ "blocks.4.self_attn.norm_q.weight": "pytorch_model-00001.bin",
145
+ "blocks.4.self_attn.norm_k.weight": "pytorch_model-00001.bin",
146
+ "blocks.4.norm3.weight": "pytorch_model-00001.bin",
147
+ "blocks.4.norm3.bias": "pytorch_model-00001.bin",
148
+ "blocks.4.cross_attn.q.weight": "pytorch_model-00001.bin",
149
+ "blocks.4.cross_attn.q.bias": "pytorch_model-00001.bin",
150
+ "blocks.4.cross_attn.k.weight": "pytorch_model-00001.bin",
151
+ "blocks.4.cross_attn.k.bias": "pytorch_model-00001.bin",
152
+ "blocks.4.cross_attn.v.weight": "pytorch_model-00001.bin",
153
+ "blocks.4.cross_attn.v.bias": "pytorch_model-00001.bin",
154
+ "blocks.4.cross_attn.o.weight": "pytorch_model-00001.bin",
155
+ "blocks.4.cross_attn.o.bias": "pytorch_model-00001.bin",
156
+ "blocks.4.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
157
+ "blocks.4.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
158
+ "blocks.4.audio_ffn.0.weight": "pytorch_model-00001.bin",
159
+ "blocks.4.audio_ffn.0.bias": "pytorch_model-00001.bin",
160
+ "blocks.4.audio_ffn.2.weight": "pytorch_model-00001.bin",
161
+ "blocks.4.audio_ffn.2.bias": "pytorch_model-00001.bin",
162
+ "blocks.4.audio_modulation.param": "pytorch_model-00001.bin",
163
+ "blocks.5.modulation": "pytorch_model-00001.bin",
164
+ "blocks.5.self_attn.q.weight": "pytorch_model-00001.bin",
165
+ "blocks.5.self_attn.q.bias": "pytorch_model-00001.bin",
166
+ "blocks.5.self_attn.k.weight": "pytorch_model-00001.bin",
167
+ "blocks.5.self_attn.k.bias": "pytorch_model-00001.bin",
168
+ "blocks.5.self_attn.v.weight": "pytorch_model-00001.bin",
169
+ "blocks.5.self_attn.v.bias": "pytorch_model-00001.bin",
170
+ "blocks.5.self_attn.o.weight": "pytorch_model-00001.bin",
171
+ "blocks.5.self_attn.o.bias": "pytorch_model-00001.bin",
172
+ "blocks.5.self_attn.norm_q.weight": "pytorch_model-00001.bin",
173
+ "blocks.5.self_attn.norm_k.weight": "pytorch_model-00001.bin",
174
+ "blocks.5.norm3.weight": "pytorch_model-00001.bin",
175
+ "blocks.5.norm3.bias": "pytorch_model-00001.bin",
176
+ "blocks.5.cross_attn.q.weight": "pytorch_model-00001.bin",
177
+ "blocks.5.cross_attn.q.bias": "pytorch_model-00001.bin",
178
+ "blocks.5.cross_attn.k.weight": "pytorch_model-00001.bin",
179
+ "blocks.5.cross_attn.k.bias": "pytorch_model-00001.bin",
180
+ "blocks.5.cross_attn.v.weight": "pytorch_model-00001.bin",
181
+ "blocks.5.cross_attn.v.bias": "pytorch_model-00001.bin",
182
+ "blocks.5.cross_attn.o.weight": "pytorch_model-00001.bin",
183
+ "blocks.5.cross_attn.o.bias": "pytorch_model-00001.bin",
184
+ "blocks.5.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
185
+ "blocks.5.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
186
+ "blocks.5.audio_ffn.0.weight": "pytorch_model-00001.bin",
187
+ "blocks.5.audio_ffn.0.bias": "pytorch_model-00001.bin",
188
+ "blocks.5.audio_ffn.2.weight": "pytorch_model-00001.bin",
189
+ "blocks.5.audio_ffn.2.bias": "pytorch_model-00001.bin",
190
+ "blocks.5.audio_modulation.param": "pytorch_model-00001.bin",
191
+ "blocks.6.modulation": "pytorch_model-00001.bin",
192
+ "blocks.6.self_attn.q.weight": "pytorch_model-00001.bin",
193
+ "blocks.6.self_attn.q.bias": "pytorch_model-00001.bin",
194
+ "blocks.6.self_attn.k.weight": "pytorch_model-00001.bin",
195
+ "blocks.6.self_attn.k.bias": "pytorch_model-00001.bin",
196
+ "blocks.6.self_attn.v.weight": "pytorch_model-00001.bin",
197
+ "blocks.6.self_attn.v.bias": "pytorch_model-00001.bin",
198
+ "blocks.6.self_attn.o.weight": "pytorch_model-00001.bin",
199
+ "blocks.6.self_attn.o.bias": "pytorch_model-00001.bin",
200
+ "blocks.6.self_attn.norm_q.weight": "pytorch_model-00001.bin",
201
+ "blocks.6.self_attn.norm_k.weight": "pytorch_model-00001.bin",
202
+ "blocks.6.norm3.weight": "pytorch_model-00001.bin",
203
+ "blocks.6.norm3.bias": "pytorch_model-00001.bin",
204
+ "blocks.6.cross_attn.q.weight": "pytorch_model-00001.bin",
205
+ "blocks.6.cross_attn.q.bias": "pytorch_model-00001.bin",
206
+ "blocks.6.cross_attn.k.weight": "pytorch_model-00001.bin",
207
+ "blocks.6.cross_attn.k.bias": "pytorch_model-00001.bin",
208
+ "blocks.6.cross_attn.v.weight": "pytorch_model-00001.bin",
209
+ "blocks.6.cross_attn.v.bias": "pytorch_model-00001.bin",
210
+ "blocks.6.cross_attn.o.weight": "pytorch_model-00001.bin",
211
+ "blocks.6.cross_attn.o.bias": "pytorch_model-00001.bin",
212
+ "blocks.6.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
213
+ "blocks.6.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
214
+ "blocks.6.audio_ffn.0.weight": "pytorch_model-00001.bin",
215
+ "blocks.6.audio_ffn.0.bias": "pytorch_model-00001.bin",
216
+ "blocks.6.audio_ffn.2.weight": "pytorch_model-00001.bin",
217
+ "blocks.6.audio_ffn.2.bias": "pytorch_model-00001.bin",
218
+ "blocks.6.audio_modulation.param": "pytorch_model-00001.bin",
219
+ "blocks.7.modulation": "pytorch_model-00001.bin",
220
+ "blocks.7.self_attn.q.weight": "pytorch_model-00001.bin",
221
+ "blocks.7.self_attn.q.bias": "pytorch_model-00001.bin",
222
+ "blocks.7.self_attn.k.weight": "pytorch_model-00001.bin",
223
+ "blocks.7.self_attn.k.bias": "pytorch_model-00001.bin",
224
+ "blocks.7.self_attn.v.weight": "pytorch_model-00001.bin",
225
+ "blocks.7.self_attn.v.bias": "pytorch_model-00001.bin",
226
+ "blocks.7.self_attn.o.weight": "pytorch_model-00001.bin",
227
+ "blocks.7.self_attn.o.bias": "pytorch_model-00001.bin",
228
+ "blocks.7.self_attn.norm_q.weight": "pytorch_model-00001.bin",
229
+ "blocks.7.self_attn.norm_k.weight": "pytorch_model-00001.bin",
230
+ "blocks.7.norm3.weight": "pytorch_model-00001.bin",
231
+ "blocks.7.norm3.bias": "pytorch_model-00001.bin",
232
+ "blocks.7.cross_attn.q.weight": "pytorch_model-00001.bin",
233
+ "blocks.7.cross_attn.q.bias": "pytorch_model-00001.bin",
234
+ "blocks.7.cross_attn.k.weight": "pytorch_model-00001.bin",
235
+ "blocks.7.cross_attn.k.bias": "pytorch_model-00001.bin",
236
+ "blocks.7.cross_attn.v.weight": "pytorch_model-00001.bin",
237
+ "blocks.7.cross_attn.v.bias": "pytorch_model-00001.bin",
238
+ "blocks.7.cross_attn.o.weight": "pytorch_model-00001.bin",
239
+ "blocks.7.cross_attn.o.bias": "pytorch_model-00001.bin",
240
+ "blocks.7.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
241
+ "blocks.7.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
242
+ "blocks.7.audio_ffn.0.weight": "pytorch_model-00001.bin",
243
+ "blocks.7.audio_ffn.0.bias": "pytorch_model-00001.bin",
244
+ "blocks.7.audio_ffn.2.weight": "pytorch_model-00001.bin",
245
+ "blocks.7.audio_ffn.2.bias": "pytorch_model-00001.bin",
246
+ "blocks.7.audio_modulation.param": "pytorch_model-00001.bin",
247
+ "blocks.8.modulation": "pytorch_model-00001.bin",
248
+ "blocks.8.self_attn.q.weight": "pytorch_model-00001.bin",
249
+ "blocks.8.self_attn.q.bias": "pytorch_model-00001.bin",
250
+ "blocks.8.self_attn.k.weight": "pytorch_model-00001.bin",
251
+ "blocks.8.self_attn.k.bias": "pytorch_model-00001.bin",
252
+ "blocks.8.self_attn.v.weight": "pytorch_model-00001.bin",
253
+ "blocks.8.self_attn.v.bias": "pytorch_model-00001.bin",
254
+ "blocks.8.self_attn.o.weight": "pytorch_model-00001.bin",
255
+ "blocks.8.self_attn.o.bias": "pytorch_model-00001.bin",
256
+ "blocks.8.self_attn.norm_q.weight": "pytorch_model-00001.bin",
257
+ "blocks.8.self_attn.norm_k.weight": "pytorch_model-00001.bin",
258
+ "blocks.8.norm3.weight": "pytorch_model-00001.bin",
259
+ "blocks.8.norm3.bias": "pytorch_model-00001.bin",
260
+ "blocks.8.cross_attn.q.weight": "pytorch_model-00001.bin",
261
+ "blocks.8.cross_attn.q.bias": "pytorch_model-00001.bin",
262
+ "blocks.8.cross_attn.k.weight": "pytorch_model-00001.bin",
263
+ "blocks.8.cross_attn.k.bias": "pytorch_model-00001.bin",
264
+ "blocks.8.cross_attn.v.weight": "pytorch_model-00001.bin",
265
+ "blocks.8.cross_attn.v.bias": "pytorch_model-00001.bin",
266
+ "blocks.8.cross_attn.o.weight": "pytorch_model-00001.bin",
267
+ "blocks.8.cross_attn.o.bias": "pytorch_model-00001.bin",
268
+ "blocks.8.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
269
+ "blocks.8.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
270
+ "blocks.8.audio_ffn.0.weight": "pytorch_model-00001.bin",
271
+ "blocks.8.audio_ffn.0.bias": "pytorch_model-00001.bin",
272
+ "blocks.8.audio_ffn.2.weight": "pytorch_model-00001.bin",
273
+ "blocks.8.audio_ffn.2.bias": "pytorch_model-00001.bin",
274
+ "blocks.8.audio_modulation.param": "pytorch_model-00001.bin",
275
+ "blocks.9.modulation": "pytorch_model-00001.bin",
276
+ "blocks.9.self_attn.q.weight": "pytorch_model-00001.bin",
277
+ "blocks.9.self_attn.q.bias": "pytorch_model-00001.bin",
278
+ "blocks.9.self_attn.k.weight": "pytorch_model-00001.bin",
279
+ "blocks.9.self_attn.k.bias": "pytorch_model-00001.bin",
280
+ "blocks.9.self_attn.v.weight": "pytorch_model-00001.bin",
281
+ "blocks.9.self_attn.v.bias": "pytorch_model-00001.bin",
282
+ "blocks.9.self_attn.o.weight": "pytorch_model-00001.bin",
283
+ "blocks.9.self_attn.o.bias": "pytorch_model-00001.bin",
284
+ "blocks.9.self_attn.norm_q.weight": "pytorch_model-00001.bin",
285
+ "blocks.9.self_attn.norm_k.weight": "pytorch_model-00001.bin",
286
+ "blocks.9.norm3.weight": "pytorch_model-00001.bin",
287
+ "blocks.9.norm3.bias": "pytorch_model-00001.bin",
288
+ "blocks.9.cross_attn.q.weight": "pytorch_model-00001.bin",
289
+ "blocks.9.cross_attn.q.bias": "pytorch_model-00001.bin",
290
+ "blocks.9.cross_attn.k.weight": "pytorch_model-00001.bin",
291
+ "blocks.9.cross_attn.k.bias": "pytorch_model-00001.bin",
292
+ "blocks.9.cross_attn.v.weight": "pytorch_model-00001.bin",
293
+ "blocks.9.cross_attn.v.bias": "pytorch_model-00001.bin",
294
+ "blocks.9.cross_attn.o.weight": "pytorch_model-00001.bin",
295
+ "blocks.9.cross_attn.o.bias": "pytorch_model-00001.bin",
296
+ "blocks.9.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
297
+ "blocks.9.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
298
+ "blocks.9.audio_ffn.0.weight": "pytorch_model-00001.bin",
299
+ "blocks.9.audio_ffn.0.bias": "pytorch_model-00001.bin",
300
+ "blocks.9.audio_ffn.2.weight": "pytorch_model-00001.bin",
301
+ "blocks.9.audio_ffn.2.bias": "pytorch_model-00001.bin",
302
+ "blocks.9.audio_modulation.param": "pytorch_model-00001.bin",
303
+ "blocks.10.modulation": "pytorch_model-00001.bin",
304
+ "blocks.10.self_attn.q.weight": "pytorch_model-00001.bin",
305
+ "blocks.10.self_attn.q.bias": "pytorch_model-00001.bin",
306
+ "blocks.10.self_attn.k.weight": "pytorch_model-00001.bin",
307
+ "blocks.10.self_attn.k.bias": "pytorch_model-00001.bin",
308
+ "blocks.10.self_attn.v.weight": "pytorch_model-00001.bin",
309
+ "blocks.10.self_attn.v.bias": "pytorch_model-00001.bin",
310
+ "blocks.10.self_attn.o.weight": "pytorch_model-00001.bin",
311
+ "blocks.10.self_attn.o.bias": "pytorch_model-00001.bin",
312
+ "blocks.10.self_attn.norm_q.weight": "pytorch_model-00001.bin",
313
+ "blocks.10.self_attn.norm_k.weight": "pytorch_model-00001.bin",
314
+ "blocks.10.norm3.weight": "pytorch_model-00001.bin",
315
+ "blocks.10.norm3.bias": "pytorch_model-00001.bin",
316
+ "blocks.10.cross_attn.q.weight": "pytorch_model-00001.bin",
317
+ "blocks.10.cross_attn.q.bias": "pytorch_model-00001.bin",
318
+ "blocks.10.cross_attn.k.weight": "pytorch_model-00001.bin",
319
+ "blocks.10.cross_attn.k.bias": "pytorch_model-00001.bin",
320
+ "blocks.10.cross_attn.v.weight": "pytorch_model-00001.bin",
321
+ "blocks.10.cross_attn.v.bias": "pytorch_model-00001.bin",
322
+ "blocks.10.cross_attn.o.weight": "pytorch_model-00001.bin",
323
+ "blocks.10.cross_attn.o.bias": "pytorch_model-00001.bin",
324
+ "blocks.10.cross_attn.norm_q.weight": "pytorch_model-00001.bin",
325
+ "blocks.10.cross_attn.norm_k.weight": "pytorch_model-00001.bin",
326
+ "blocks.10.audio_ffn.0.weight": "pytorch_model-00001.bin",
327
+ "blocks.10.audio_ffn.0.bias": "pytorch_model-00001.bin",
328
+ "blocks.10.audio_ffn.2.weight": "pytorch_model-00002.bin",
329
+ "blocks.10.audio_ffn.2.bias": "pytorch_model-00002.bin",
330
+ "blocks.10.audio_modulation.param": "pytorch_model-00002.bin",
331
+ "blocks.11.modulation": "pytorch_model-00002.bin",
332
+ "blocks.11.self_attn.q.weight": "pytorch_model-00002.bin",
333
+ "blocks.11.self_attn.q.bias": "pytorch_model-00002.bin",
334
+ "blocks.11.self_attn.k.weight": "pytorch_model-00002.bin",
335
+ "blocks.11.self_attn.k.bias": "pytorch_model-00002.bin",
336
+ "blocks.11.self_attn.v.weight": "pytorch_model-00002.bin",
337
+ "blocks.11.self_attn.v.bias": "pytorch_model-00002.bin",
338
+ "blocks.11.self_attn.o.weight": "pytorch_model-00002.bin",
339
+ "blocks.11.self_attn.o.bias": "pytorch_model-00002.bin",
340
+ "blocks.11.self_attn.norm_q.weight": "pytorch_model-00002.bin",
341
+ "blocks.11.self_attn.norm_k.weight": "pytorch_model-00002.bin",
342
+ "blocks.11.norm3.weight": "pytorch_model-00002.bin",
343
+ "blocks.11.norm3.bias": "pytorch_model-00002.bin",
344
+ "blocks.11.cross_attn.q.weight": "pytorch_model-00002.bin",
345
+ "blocks.11.cross_attn.q.bias": "pytorch_model-00002.bin",
346
+ "blocks.11.cross_attn.k.weight": "pytorch_model-00002.bin",
347
+ "blocks.11.cross_attn.k.bias": "pytorch_model-00002.bin",
348
+ "blocks.11.cross_attn.v.weight": "pytorch_model-00002.bin",
349
+ "blocks.11.cross_attn.v.bias": "pytorch_model-00002.bin",
350
+ "blocks.11.cross_attn.o.weight": "pytorch_model-00002.bin",
351
+ "blocks.11.cross_attn.o.bias": "pytorch_model-00002.bin",
352
+ "blocks.11.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
353
+ "blocks.11.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
354
+ "blocks.11.audio_ffn.0.weight": "pytorch_model-00002.bin",
355
+ "blocks.11.audio_ffn.0.bias": "pytorch_model-00002.bin",
356
+ "blocks.11.audio_ffn.2.weight": "pytorch_model-00002.bin",
357
+ "blocks.11.audio_ffn.2.bias": "pytorch_model-00002.bin",
358
+ "blocks.11.audio_modulation.param": "pytorch_model-00002.bin",
359
+ "blocks.12.modulation": "pytorch_model-00002.bin",
360
+ "blocks.12.self_attn.q.weight": "pytorch_model-00002.bin",
361
+ "blocks.12.self_attn.q.bias": "pytorch_model-00002.bin",
362
+ "blocks.12.self_attn.k.weight": "pytorch_model-00002.bin",
363
+ "blocks.12.self_attn.k.bias": "pytorch_model-00002.bin",
364
+ "blocks.12.self_attn.v.weight": "pytorch_model-00002.bin",
365
+ "blocks.12.self_attn.v.bias": "pytorch_model-00002.bin",
366
+ "blocks.12.self_attn.o.weight": "pytorch_model-00002.bin",
367
+ "blocks.12.self_attn.o.bias": "pytorch_model-00002.bin",
368
+ "blocks.12.self_attn.norm_q.weight": "pytorch_model-00002.bin",
369
+ "blocks.12.self_attn.norm_k.weight": "pytorch_model-00002.bin",
370
+ "blocks.12.norm3.weight": "pytorch_model-00002.bin",
371
+ "blocks.12.norm3.bias": "pytorch_model-00002.bin",
372
+ "blocks.12.cross_attn.q.weight": "pytorch_model-00002.bin",
373
+ "blocks.12.cross_attn.q.bias": "pytorch_model-00002.bin",
374
+ "blocks.12.cross_attn.k.weight": "pytorch_model-00002.bin",
375
+ "blocks.12.cross_attn.k.bias": "pytorch_model-00002.bin",
376
+ "blocks.12.cross_attn.v.weight": "pytorch_model-00002.bin",
377
+ "blocks.12.cross_attn.v.bias": "pytorch_model-00002.bin",
378
+ "blocks.12.cross_attn.o.weight": "pytorch_model-00002.bin",
379
+ "blocks.12.cross_attn.o.bias": "pytorch_model-00002.bin",
380
+ "blocks.12.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
381
+ "blocks.12.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
382
+ "blocks.12.audio_ffn.0.weight": "pytorch_model-00002.bin",
383
+ "blocks.12.audio_ffn.0.bias": "pytorch_model-00002.bin",
384
+ "blocks.12.audio_ffn.2.weight": "pytorch_model-00002.bin",
385
+ "blocks.12.audio_ffn.2.bias": "pytorch_model-00002.bin",
386
+ "blocks.12.audio_modulation.param": "pytorch_model-00002.bin",
387
+ "blocks.13.modulation": "pytorch_model-00002.bin",
388
+ "blocks.13.self_attn.q.weight": "pytorch_model-00002.bin",
389
+ "blocks.13.self_attn.q.bias": "pytorch_model-00002.bin",
390
+ "blocks.13.self_attn.k.weight": "pytorch_model-00002.bin",
391
+ "blocks.13.self_attn.k.bias": "pytorch_model-00002.bin",
392
+ "blocks.13.self_attn.v.weight": "pytorch_model-00002.bin",
393
+ "blocks.13.self_attn.v.bias": "pytorch_model-00002.bin",
394
+ "blocks.13.self_attn.o.weight": "pytorch_model-00002.bin",
395
+ "blocks.13.self_attn.o.bias": "pytorch_model-00002.bin",
396
+ "blocks.13.self_attn.norm_q.weight": "pytorch_model-00002.bin",
397
+ "blocks.13.self_attn.norm_k.weight": "pytorch_model-00002.bin",
398
+ "blocks.13.norm3.weight": "pytorch_model-00002.bin",
399
+ "blocks.13.norm3.bias": "pytorch_model-00002.bin",
400
+ "blocks.13.cross_attn.q.weight": "pytorch_model-00002.bin",
401
+ "blocks.13.cross_attn.q.bias": "pytorch_model-00002.bin",
402
+ "blocks.13.cross_attn.k.weight": "pytorch_model-00002.bin",
403
+ "blocks.13.cross_attn.k.bias": "pytorch_model-00002.bin",
404
+ "blocks.13.cross_attn.v.weight": "pytorch_model-00002.bin",
405
+ "blocks.13.cross_attn.v.bias": "pytorch_model-00002.bin",
406
+ "blocks.13.cross_attn.o.weight": "pytorch_model-00002.bin",
407
+ "blocks.13.cross_attn.o.bias": "pytorch_model-00002.bin",
408
+ "blocks.13.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
409
+ "blocks.13.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
410
+ "blocks.13.audio_ffn.0.weight": "pytorch_model-00002.bin",
411
+ "blocks.13.audio_ffn.0.bias": "pytorch_model-00002.bin",
412
+ "blocks.13.audio_ffn.2.weight": "pytorch_model-00002.bin",
413
+ "blocks.13.audio_ffn.2.bias": "pytorch_model-00002.bin",
414
+ "blocks.13.audio_modulation.param": "pytorch_model-00002.bin",
415
+ "blocks.14.modulation": "pytorch_model-00002.bin",
416
+ "blocks.14.self_attn.q.weight": "pytorch_model-00002.bin",
417
+ "blocks.14.self_attn.q.bias": "pytorch_model-00002.bin",
418
+ "blocks.14.self_attn.k.weight": "pytorch_model-00002.bin",
419
+ "blocks.14.self_attn.k.bias": "pytorch_model-00002.bin",
420
+ "blocks.14.self_attn.v.weight": "pytorch_model-00002.bin",
421
+ "blocks.14.self_attn.v.bias": "pytorch_model-00002.bin",
422
+ "blocks.14.self_attn.o.weight": "pytorch_model-00002.bin",
423
+ "blocks.14.self_attn.o.bias": "pytorch_model-00002.bin",
424
+ "blocks.14.self_attn.norm_q.weight": "pytorch_model-00002.bin",
425
+ "blocks.14.self_attn.norm_k.weight": "pytorch_model-00002.bin",
426
+ "blocks.14.norm3.weight": "pytorch_model-00002.bin",
427
+ "blocks.14.norm3.bias": "pytorch_model-00002.bin",
428
+ "blocks.14.cross_attn.q.weight": "pytorch_model-00002.bin",
429
+ "blocks.14.cross_attn.q.bias": "pytorch_model-00002.bin",
430
+ "blocks.14.cross_attn.k.weight": "pytorch_model-00002.bin",
431
+ "blocks.14.cross_attn.k.bias": "pytorch_model-00002.bin",
432
+ "blocks.14.cross_attn.v.weight": "pytorch_model-00002.bin",
433
+ "blocks.14.cross_attn.v.bias": "pytorch_model-00002.bin",
434
+ "blocks.14.cross_attn.o.weight": "pytorch_model-00002.bin",
435
+ "blocks.14.cross_attn.o.bias": "pytorch_model-00002.bin",
436
+ "blocks.14.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
437
+ "blocks.14.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
438
+ "blocks.14.audio_ffn.0.weight": "pytorch_model-00002.bin",
439
+ "blocks.14.audio_ffn.0.bias": "pytorch_model-00002.bin",
440
+ "blocks.14.audio_ffn.2.weight": "pytorch_model-00002.bin",
441
+ "blocks.14.audio_ffn.2.bias": "pytorch_model-00002.bin",
442
+ "blocks.14.audio_modulation.param": "pytorch_model-00002.bin",
443
+ "blocks.15.modulation": "pytorch_model-00002.bin",
444
+ "blocks.15.self_attn.q.weight": "pytorch_model-00002.bin",
445
+ "blocks.15.self_attn.q.bias": "pytorch_model-00002.bin",
446
+ "blocks.15.self_attn.k.weight": "pytorch_model-00002.bin",
447
+ "blocks.15.self_attn.k.bias": "pytorch_model-00002.bin",
448
+ "blocks.15.self_attn.v.weight": "pytorch_model-00002.bin",
449
+ "blocks.15.self_attn.v.bias": "pytorch_model-00002.bin",
450
+ "blocks.15.self_attn.o.weight": "pytorch_model-00002.bin",
451
+ "blocks.15.self_attn.o.bias": "pytorch_model-00002.bin",
452
+ "blocks.15.self_attn.norm_q.weight": "pytorch_model-00002.bin",
453
+ "blocks.15.self_attn.norm_k.weight": "pytorch_model-00002.bin",
454
+ "blocks.15.norm3.weight": "pytorch_model-00002.bin",
455
+ "blocks.15.norm3.bias": "pytorch_model-00002.bin",
456
+ "blocks.15.cross_attn.q.weight": "pytorch_model-00002.bin",
457
+ "blocks.15.cross_attn.q.bias": "pytorch_model-00002.bin",
458
+ "blocks.15.cross_attn.k.weight": "pytorch_model-00002.bin",
459
+ "blocks.15.cross_attn.k.bias": "pytorch_model-00002.bin",
460
+ "blocks.15.cross_attn.v.weight": "pytorch_model-00002.bin",
461
+ "blocks.15.cross_attn.v.bias": "pytorch_model-00002.bin",
462
+ "blocks.15.cross_attn.o.weight": "pytorch_model-00002.bin",
463
+ "blocks.15.cross_attn.o.bias": "pytorch_model-00002.bin",
464
+ "blocks.15.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
465
+ "blocks.15.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
466
+ "blocks.15.audio_ffn.0.weight": "pytorch_model-00002.bin",
467
+ "blocks.15.audio_ffn.0.bias": "pytorch_model-00002.bin",
468
+ "blocks.15.audio_ffn.2.weight": "pytorch_model-00002.bin",
469
+ "blocks.15.audio_ffn.2.bias": "pytorch_model-00002.bin",
470
+ "blocks.15.audio_modulation.param": "pytorch_model-00002.bin",
471
+ "blocks.16.modulation": "pytorch_model-00002.bin",
472
+ "blocks.16.self_attn.q.weight": "pytorch_model-00002.bin",
473
+ "blocks.16.self_attn.q.bias": "pytorch_model-00002.bin",
474
+ "blocks.16.self_attn.k.weight": "pytorch_model-00002.bin",
475
+ "blocks.16.self_attn.k.bias": "pytorch_model-00002.bin",
476
+ "blocks.16.self_attn.v.weight": "pytorch_model-00002.bin",
477
+ "blocks.16.self_attn.v.bias": "pytorch_model-00002.bin",
478
+ "blocks.16.self_attn.o.weight": "pytorch_model-00002.bin",
479
+ "blocks.16.self_attn.o.bias": "pytorch_model-00002.bin",
480
+ "blocks.16.self_attn.norm_q.weight": "pytorch_model-00002.bin",
481
+ "blocks.16.self_attn.norm_k.weight": "pytorch_model-00002.bin",
482
+ "blocks.16.norm3.weight": "pytorch_model-00002.bin",
483
+ "blocks.16.norm3.bias": "pytorch_model-00002.bin",
484
+ "blocks.16.cross_attn.q.weight": "pytorch_model-00002.bin",
485
+ "blocks.16.cross_attn.q.bias": "pytorch_model-00002.bin",
486
+ "blocks.16.cross_attn.k.weight": "pytorch_model-00002.bin",
487
+ "blocks.16.cross_attn.k.bias": "pytorch_model-00002.bin",
488
+ "blocks.16.cross_attn.v.weight": "pytorch_model-00002.bin",
489
+ "blocks.16.cross_attn.v.bias": "pytorch_model-00002.bin",
490
+ "blocks.16.cross_attn.o.weight": "pytorch_model-00002.bin",
491
+ "blocks.16.cross_attn.o.bias": "pytorch_model-00002.bin",
492
+ "blocks.16.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
493
+ "blocks.16.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
494
+ "blocks.16.audio_ffn.0.weight": "pytorch_model-00002.bin",
495
+ "blocks.16.audio_ffn.0.bias": "pytorch_model-00002.bin",
496
+ "blocks.16.audio_ffn.2.weight": "pytorch_model-00002.bin",
497
+ "blocks.16.audio_ffn.2.bias": "pytorch_model-00002.bin",
498
+ "blocks.16.audio_modulation.param": "pytorch_model-00002.bin",
499
+ "blocks.17.modulation": "pytorch_model-00002.bin",
500
+ "blocks.17.self_attn.q.weight": "pytorch_model-00002.bin",
501
+ "blocks.17.self_attn.q.bias": "pytorch_model-00002.bin",
502
+ "blocks.17.self_attn.k.weight": "pytorch_model-00002.bin",
503
+ "blocks.17.self_attn.k.bias": "pytorch_model-00002.bin",
504
+ "blocks.17.self_attn.v.weight": "pytorch_model-00002.bin",
505
+ "blocks.17.self_attn.v.bias": "pytorch_model-00002.bin",
506
+ "blocks.17.self_attn.o.weight": "pytorch_model-00002.bin",
507
+ "blocks.17.self_attn.o.bias": "pytorch_model-00002.bin",
508
+ "blocks.17.self_attn.norm_q.weight": "pytorch_model-00002.bin",
509
+ "blocks.17.self_attn.norm_k.weight": "pytorch_model-00002.bin",
510
+ "blocks.17.norm3.weight": "pytorch_model-00002.bin",
511
+ "blocks.17.norm3.bias": "pytorch_model-00002.bin",
512
+ "blocks.17.cross_attn.q.weight": "pytorch_model-00002.bin",
513
+ "blocks.17.cross_attn.q.bias": "pytorch_model-00002.bin",
514
+ "blocks.17.cross_attn.k.weight": "pytorch_model-00002.bin",
515
+ "blocks.17.cross_attn.k.bias": "pytorch_model-00002.bin",
516
+ "blocks.17.cross_attn.v.weight": "pytorch_model-00002.bin",
517
+ "blocks.17.cross_attn.v.bias": "pytorch_model-00002.bin",
518
+ "blocks.17.cross_attn.o.weight": "pytorch_model-00002.bin",
519
+ "blocks.17.cross_attn.o.bias": "pytorch_model-00002.bin",
520
+ "blocks.17.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
521
+ "blocks.17.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
522
+ "blocks.17.audio_ffn.0.weight": "pytorch_model-00002.bin",
523
+ "blocks.17.audio_ffn.0.bias": "pytorch_model-00002.bin",
524
+ "blocks.17.audio_ffn.2.weight": "pytorch_model-00002.bin",
525
+ "blocks.17.audio_ffn.2.bias": "pytorch_model-00002.bin",
526
+ "blocks.17.audio_modulation.param": "pytorch_model-00002.bin",
527
+ "blocks.18.modulation": "pytorch_model-00002.bin",
528
+ "blocks.18.self_attn.q.weight": "pytorch_model-00002.bin",
529
+ "blocks.18.self_attn.q.bias": "pytorch_model-00002.bin",
530
+ "blocks.18.self_attn.k.weight": "pytorch_model-00002.bin",
531
+ "blocks.18.self_attn.k.bias": "pytorch_model-00002.bin",
532
+ "blocks.18.self_attn.v.weight": "pytorch_model-00002.bin",
533
+ "blocks.18.self_attn.v.bias": "pytorch_model-00002.bin",
534
+ "blocks.18.self_attn.o.weight": "pytorch_model-00002.bin",
535
+ "blocks.18.self_attn.o.bias": "pytorch_model-00002.bin",
536
+ "blocks.18.self_attn.norm_q.weight": "pytorch_model-00002.bin",
537
+ "blocks.18.self_attn.norm_k.weight": "pytorch_model-00002.bin",
538
+ "blocks.18.norm3.weight": "pytorch_model-00002.bin",
539
+ "blocks.18.norm3.bias": "pytorch_model-00002.bin",
540
+ "blocks.18.cross_attn.q.weight": "pytorch_model-00002.bin",
541
+ "blocks.18.cross_attn.q.bias": "pytorch_model-00002.bin",
542
+ "blocks.18.cross_attn.k.weight": "pytorch_model-00002.bin",
543
+ "blocks.18.cross_attn.k.bias": "pytorch_model-00002.bin",
544
+ "blocks.18.cross_attn.v.weight": "pytorch_model-00002.bin",
545
+ "blocks.18.cross_attn.v.bias": "pytorch_model-00002.bin",
546
+ "blocks.18.cross_attn.o.weight": "pytorch_model-00002.bin",
547
+ "blocks.18.cross_attn.o.bias": "pytorch_model-00002.bin",
548
+ "blocks.18.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
549
+ "blocks.18.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
550
+ "blocks.18.audio_ffn.0.weight": "pytorch_model-00002.bin",
551
+ "blocks.18.audio_ffn.0.bias": "pytorch_model-00002.bin",
552
+ "blocks.18.audio_ffn.2.weight": "pytorch_model-00002.bin",
553
+ "blocks.18.audio_ffn.2.bias": "pytorch_model-00002.bin",
554
+ "blocks.18.audio_modulation.param": "pytorch_model-00002.bin",
555
+ "blocks.19.modulation": "pytorch_model-00002.bin",
556
+ "blocks.19.self_attn.q.weight": "pytorch_model-00002.bin",
557
+ "blocks.19.self_attn.q.bias": "pytorch_model-00002.bin",
558
+ "blocks.19.self_attn.k.weight": "pytorch_model-00002.bin",
559
+ "blocks.19.self_attn.k.bias": "pytorch_model-00002.bin",
560
+ "blocks.19.self_attn.v.weight": "pytorch_model-00002.bin",
561
+ "blocks.19.self_attn.v.bias": "pytorch_model-00002.bin",
562
+ "blocks.19.self_attn.o.weight": "pytorch_model-00002.bin",
563
+ "blocks.19.self_attn.o.bias": "pytorch_model-00002.bin",
564
+ "blocks.19.self_attn.norm_q.weight": "pytorch_model-00002.bin",
565
+ "blocks.19.self_attn.norm_k.weight": "pytorch_model-00002.bin",
566
+ "blocks.19.norm3.weight": "pytorch_model-00002.bin",
567
+ "blocks.19.norm3.bias": "pytorch_model-00002.bin",
568
+ "blocks.19.cross_attn.q.weight": "pytorch_model-00002.bin",
569
+ "blocks.19.cross_attn.q.bias": "pytorch_model-00002.bin",
570
+ "blocks.19.cross_attn.k.weight": "pytorch_model-00002.bin",
571
+ "blocks.19.cross_attn.k.bias": "pytorch_model-00002.bin",
572
+ "blocks.19.cross_attn.v.weight": "pytorch_model-00002.bin",
573
+ "blocks.19.cross_attn.v.bias": "pytorch_model-00002.bin",
574
+ "blocks.19.cross_attn.o.weight": "pytorch_model-00002.bin",
575
+ "blocks.19.cross_attn.o.bias": "pytorch_model-00002.bin",
576
+ "blocks.19.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
577
+ "blocks.19.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
578
+ "blocks.19.audio_ffn.0.weight": "pytorch_model-00002.bin",
579
+ "blocks.19.audio_ffn.0.bias": "pytorch_model-00002.bin",
580
+ "blocks.19.audio_ffn.2.weight": "pytorch_model-00002.bin",
581
+ "blocks.19.audio_ffn.2.bias": "pytorch_model-00002.bin",
582
+ "blocks.19.audio_modulation.param": "pytorch_model-00002.bin",
583
+ "blocks.20.modulation": "pytorch_model-00002.bin",
584
+ "blocks.20.self_attn.q.weight": "pytorch_model-00002.bin",
585
+ "blocks.20.self_attn.q.bias": "pytorch_model-00002.bin",
586
+ "blocks.20.self_attn.k.weight": "pytorch_model-00002.bin",
587
+ "blocks.20.self_attn.k.bias": "pytorch_model-00002.bin",
588
+ "blocks.20.self_attn.v.weight": "pytorch_model-00002.bin",
589
+ "blocks.20.self_attn.v.bias": "pytorch_model-00002.bin",
590
+ "blocks.20.self_attn.o.weight": "pytorch_model-00002.bin",
591
+ "blocks.20.self_attn.o.bias": "pytorch_model-00002.bin",
592
+ "blocks.20.self_attn.norm_q.weight": "pytorch_model-00002.bin",
593
+ "blocks.20.self_attn.norm_k.weight": "pytorch_model-00002.bin",
594
+ "blocks.20.norm3.weight": "pytorch_model-00002.bin",
595
+ "blocks.20.norm3.bias": "pytorch_model-00002.bin",
596
+ "blocks.20.cross_attn.q.weight": "pytorch_model-00002.bin",
597
+ "blocks.20.cross_attn.q.bias": "pytorch_model-00002.bin",
598
+ "blocks.20.cross_attn.k.weight": "pytorch_model-00002.bin",
599
+ "blocks.20.cross_attn.k.bias": "pytorch_model-00002.bin",
600
+ "blocks.20.cross_attn.v.weight": "pytorch_model-00002.bin",
601
+ "blocks.20.cross_attn.v.bias": "pytorch_model-00002.bin",
602
+ "blocks.20.cross_attn.o.weight": "pytorch_model-00002.bin",
603
+ "blocks.20.cross_attn.o.bias": "pytorch_model-00002.bin",
604
+ "blocks.20.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
605
+ "blocks.20.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
606
+ "blocks.20.audio_ffn.0.weight": "pytorch_model-00002.bin",
607
+ "blocks.20.audio_ffn.0.bias": "pytorch_model-00002.bin",
608
+ "blocks.20.audio_ffn.2.weight": "pytorch_model-00002.bin",
609
+ "blocks.20.audio_ffn.2.bias": "pytorch_model-00002.bin",
610
+ "blocks.20.audio_modulation.param": "pytorch_model-00002.bin",
611
+ "blocks.21.modulation": "pytorch_model-00002.bin",
612
+ "blocks.21.self_attn.q.weight": "pytorch_model-00002.bin",
613
+ "blocks.21.self_attn.q.bias": "pytorch_model-00002.bin",
614
+ "blocks.21.self_attn.k.weight": "pytorch_model-00002.bin",
615
+ "blocks.21.self_attn.k.bias": "pytorch_model-00002.bin",
616
+ "blocks.21.self_attn.v.weight": "pytorch_model-00002.bin",
617
+ "blocks.21.self_attn.v.bias": "pytorch_model-00002.bin",
618
+ "blocks.21.self_attn.o.weight": "pytorch_model-00002.bin",
619
+ "blocks.21.self_attn.o.bias": "pytorch_model-00002.bin",
620
+ "blocks.21.self_attn.norm_q.weight": "pytorch_model-00002.bin",
621
+ "blocks.21.self_attn.norm_k.weight": "pytorch_model-00002.bin",
622
+ "blocks.21.norm3.weight": "pytorch_model-00002.bin",
623
+ "blocks.21.norm3.bias": "pytorch_model-00002.bin",
624
+ "blocks.21.cross_attn.q.weight": "pytorch_model-00002.bin",
625
+ "blocks.21.cross_attn.q.bias": "pytorch_model-00002.bin",
626
+ "blocks.21.cross_attn.k.weight": "pytorch_model-00002.bin",
627
+ "blocks.21.cross_attn.k.bias": "pytorch_model-00002.bin",
628
+ "blocks.21.cross_attn.v.weight": "pytorch_model-00002.bin",
629
+ "blocks.21.cross_attn.v.bias": "pytorch_model-00002.bin",
630
+ "blocks.21.cross_attn.o.weight": "pytorch_model-00002.bin",
631
+ "blocks.21.cross_attn.o.bias": "pytorch_model-00002.bin",
632
+ "blocks.21.cross_attn.norm_q.weight": "pytorch_model-00002.bin",
633
+ "blocks.21.cross_attn.norm_k.weight": "pytorch_model-00002.bin",
634
+ "blocks.21.audio_ffn.0.weight": "pytorch_model-00002.bin",
635
+ "blocks.21.audio_ffn.0.bias": "pytorch_model-00002.bin",
636
+ "blocks.21.audio_ffn.2.weight": "pytorch_model-00002.bin",
637
+ "blocks.21.audio_ffn.2.bias": "pytorch_model-00002.bin",
638
+ "blocks.21.audio_modulation.param": "pytorch_model-00002.bin",
639
+ "blocks.22.modulation": "pytorch_model-00002.bin",
640
+ "blocks.22.self_attn.q.weight": "pytorch_model-00002.bin",
641
+ "blocks.22.self_attn.q.bias": "pytorch_model-00002.bin",
642
+ "blocks.22.self_attn.k.weight": "pytorch_model-00002.bin",
643
+ "blocks.22.self_attn.k.bias": "pytorch_model-00002.bin",
644
+ "blocks.22.self_attn.v.weight": "pytorch_model-00002.bin",
645
+ "blocks.22.self_attn.v.bias": "pytorch_model-00002.bin",
646
+ "blocks.22.self_attn.o.weight": "pytorch_model-00002.bin",
647
+ "blocks.22.self_attn.o.bias": "pytorch_model-00002.bin",
648
+ "blocks.22.self_attn.norm_q.weight": "pytorch_model-00002.bin",
649
+ "blocks.22.self_attn.norm_k.weight": "pytorch_model-00002.bin",
650
+ "blocks.22.norm3.weight": "pytorch_model-00002.bin",
651
+ "blocks.22.norm3.bias": "pytorch_model-00002.bin",
652
+ "blocks.22.cross_attn.q.weight": "pytorch_model-00002.bin",
653
+ "blocks.22.cross_attn.q.bias": "pytorch_model-00002.bin",
654
+ "blocks.22.cross_attn.k.weight": "pytorch_model-00003.bin",
655
+ "blocks.22.cross_attn.k.bias": "pytorch_model-00003.bin",
656
+ "blocks.22.cross_attn.v.weight": "pytorch_model-00003.bin",
657
+ "blocks.22.cross_attn.v.bias": "pytorch_model-00003.bin",
658
+ "blocks.22.cross_attn.o.weight": "pytorch_model-00003.bin",
659
+ "blocks.22.cross_attn.o.bias": "pytorch_model-00003.bin",
660
+ "blocks.22.cross_attn.norm_q.weight": "pytorch_model-00003.bin",
661
+ "blocks.22.cross_attn.norm_k.weight": "pytorch_model-00003.bin",
662
+ "blocks.22.audio_ffn.0.weight": "pytorch_model-00003.bin",
663
+ "blocks.22.audio_ffn.0.bias": "pytorch_model-00003.bin",
664
+ "blocks.22.audio_ffn.2.weight": "pytorch_model-00003.bin",
665
+ "blocks.22.audio_ffn.2.bias": "pytorch_model-00003.bin",
666
+ "blocks.22.audio_modulation.param": "pytorch_model-00003.bin",
667
+ "blocks.23.modulation": "pytorch_model-00003.bin",
668
+ "blocks.23.self_attn.q.weight": "pytorch_model-00003.bin",
669
+ "blocks.23.self_attn.q.bias": "pytorch_model-00003.bin",
670
+ "blocks.23.self_attn.k.weight": "pytorch_model-00003.bin",
671
+ "blocks.23.self_attn.k.bias": "pytorch_model-00003.bin",
672
+ "blocks.23.self_attn.v.weight": "pytorch_model-00003.bin",
673
+ "blocks.23.self_attn.v.bias": "pytorch_model-00003.bin",
674
+ "blocks.23.self_attn.o.weight": "pytorch_model-00003.bin",
675
+ "blocks.23.self_attn.o.bias": "pytorch_model-00003.bin",
676
+ "blocks.23.self_attn.norm_q.weight": "pytorch_model-00003.bin",
677
+ "blocks.23.self_attn.norm_k.weight": "pytorch_model-00003.bin",
678
+ "blocks.23.norm3.weight": "pytorch_model-00003.bin",
679
+ "blocks.23.norm3.bias": "pytorch_model-00003.bin",
680
+ "blocks.23.cross_attn.q.weight": "pytorch_model-00003.bin",
681
+ "blocks.23.cross_attn.q.bias": "pytorch_model-00003.bin",
682
+ "blocks.23.cross_attn.k.weight": "pytorch_model-00003.bin",
683
+ "blocks.23.cross_attn.k.bias": "pytorch_model-00003.bin",
684
+ "blocks.23.cross_attn.v.weight": "pytorch_model-00003.bin",
685
+ "blocks.23.cross_attn.v.bias": "pytorch_model-00003.bin",
686
+ "blocks.23.cross_attn.o.weight": "pytorch_model-00003.bin",
687
+ "blocks.23.cross_attn.o.bias": "pytorch_model-00003.bin",
688
+ "blocks.23.cross_attn.norm_q.weight": "pytorch_model-00003.bin",
689
+ "blocks.23.cross_attn.norm_k.weight": "pytorch_model-00003.bin",
690
+ "blocks.23.audio_ffn.0.weight": "pytorch_model-00003.bin",
691
+ "blocks.23.audio_ffn.0.bias": "pytorch_model-00003.bin",
692
+ "blocks.23.audio_ffn.2.weight": "pytorch_model-00003.bin",
693
+ "blocks.23.audio_ffn.2.bias": "pytorch_model-00003.bin",
694
+ "blocks.23.audio_modulation.param": "pytorch_model-00003.bin",
695
+ "blocks.24.modulation": "pytorch_model-00003.bin",
696
+ "blocks.24.self_attn.q.weight": "pytorch_model-00003.bin",
697
+ "blocks.24.self_attn.q.bias": "pytorch_model-00003.bin",
698
+ "blocks.24.self_attn.k.weight": "pytorch_model-00003.bin",
699
+ "blocks.24.self_attn.k.bias": "pytorch_model-00003.bin",
700
+ "blocks.24.self_attn.v.weight": "pytorch_model-00003.bin",
701
+ "blocks.24.self_attn.v.bias": "pytorch_model-00003.bin",
702
+ "blocks.24.self_attn.o.weight": "pytorch_model-00003.bin",
703
+ "blocks.24.self_attn.o.bias": "pytorch_model-00003.bin",
704
+ "blocks.24.self_attn.norm_q.weight": "pytorch_model-00003.bin",
705
+ "blocks.24.self_attn.norm_k.weight": "pytorch_model-00003.bin",
706
+ "blocks.24.norm3.weight": "pytorch_model-00003.bin",
707
+ "blocks.24.norm3.bias": "pytorch_model-00003.bin",
708
+ "blocks.24.cross_attn.q.weight": "pytorch_model-00003.bin",
709
+ "blocks.24.cross_attn.q.bias": "pytorch_model-00003.bin",
710
+ "blocks.24.cross_attn.k.weight": "pytorch_model-00003.bin",
711
+ "blocks.24.cross_attn.k.bias": "pytorch_model-00003.bin",
712
+ "blocks.24.cross_attn.v.weight": "pytorch_model-00003.bin",
713
+ "blocks.24.cross_attn.v.bias": "pytorch_model-00003.bin",
714
+ "blocks.24.cross_attn.o.weight": "pytorch_model-00003.bin",
715
+ "blocks.24.cross_attn.o.bias": "pytorch_model-00003.bin",
716
+ "blocks.24.cross_attn.norm_q.weight": "pytorch_model-00003.bin",
717
+ "blocks.24.cross_attn.norm_k.weight": "pytorch_model-00003.bin",
718
+ "blocks.24.audio_ffn.0.weight": "pytorch_model-00003.bin",
719
+ "blocks.24.audio_ffn.0.bias": "pytorch_model-00003.bin",
720
+ "blocks.24.audio_ffn.2.weight": "pytorch_model-00003.bin",
721
+ "blocks.24.audio_ffn.2.bias": "pytorch_model-00003.bin",
722
+ "blocks.24.audio_modulation.param": "pytorch_model-00003.bin",
723
+ "blocks.25.modulation": "pytorch_model-00003.bin",
724
+ "blocks.25.self_attn.q.weight": "pytorch_model-00003.bin",
725
+ "blocks.25.self_attn.q.bias": "pytorch_model-00003.bin",
726
+ "blocks.25.self_attn.k.weight": "pytorch_model-00003.bin",
727
+ "blocks.25.self_attn.k.bias": "pytorch_model-00003.bin",
728
+ "blocks.25.self_attn.v.weight": "pytorch_model-00003.bin",
729
+ "blocks.25.self_attn.v.bias": "pytorch_model-00003.bin",
730
+ "blocks.25.self_attn.o.weight": "pytorch_model-00003.bin",
731
+ "blocks.25.self_attn.o.bias": "pytorch_model-00003.bin",
732
+ "blocks.25.self_attn.norm_q.weight": "pytorch_model-00003.bin",
733
+ "blocks.25.self_attn.norm_k.weight": "pytorch_model-00003.bin",
734
+ "blocks.25.norm3.weight": "pytorch_model-00003.bin",
735
+ "blocks.25.norm3.bias": "pytorch_model-00003.bin",
736
+ "blocks.25.cross_attn.q.weight": "pytorch_model-00003.bin",
737
+ "blocks.25.cross_attn.q.bias": "pytorch_model-00003.bin",
738
+ "blocks.25.cross_attn.k.weight": "pytorch_model-00003.bin",
739
+ "blocks.25.cross_attn.k.bias": "pytorch_model-00003.bin",
740
+ "blocks.25.cross_attn.v.weight": "pytorch_model-00003.bin",
741
+ "blocks.25.cross_attn.v.bias": "pytorch_model-00003.bin",
742
+ "blocks.25.cross_attn.o.weight": "pytorch_model-00003.bin",
743
+ "blocks.25.cross_attn.o.bias": "pytorch_model-00003.bin",
744
+ "blocks.25.cross_attn.norm_q.weight": "pytorch_model-00003.bin",
745
+ "blocks.25.cross_attn.norm_k.weight": "pytorch_model-00003.bin",
746
+ "blocks.25.audio_ffn.0.weight": "pytorch_model-00003.bin",
747
+ "blocks.25.audio_ffn.0.bias": "pytorch_model-00003.bin",
748
+ "blocks.25.audio_ffn.2.weight": "pytorch_model-00003.bin",
749
+ "blocks.25.audio_ffn.2.bias": "pytorch_model-00003.bin",
750
+ "blocks.25.audio_modulation.param": "pytorch_model-00003.bin",
751
+ "blocks.26.modulation": "pytorch_model-00003.bin",
752
+ "blocks.26.self_attn.q.weight": "pytorch_model-00003.bin",
753
+ "blocks.26.self_attn.q.bias": "pytorch_model-00003.bin",
754
+ "blocks.26.self_attn.k.weight": "pytorch_model-00003.bin",
755
+ "blocks.26.self_attn.k.bias": "pytorch_model-00003.bin",
756
+ "blocks.26.self_attn.v.weight": "pytorch_model-00003.bin",
757
+ "blocks.26.self_attn.v.bias": "pytorch_model-00003.bin",
758
+ "blocks.26.self_attn.o.weight": "pytorch_model-00003.bin",
759
+ "blocks.26.self_attn.o.bias": "pytorch_model-00003.bin",
760
+ "blocks.26.self_attn.norm_q.weight": "pytorch_model-00003.bin",
761
+ "blocks.26.self_attn.norm_k.weight": "pytorch_model-00003.bin",
762
+ "blocks.26.norm3.weight": "pytorch_model-00003.bin",
763
+ "blocks.26.norm3.bias": "pytorch_model-00003.bin",
764
+ "blocks.26.cross_attn.q.weight": "pytorch_model-00003.bin",
765
+ "blocks.26.cross_attn.q.bias": "pytorch_model-00003.bin",
766
+ "blocks.26.cross_attn.k.weight": "pytorch_model-00003.bin",
767
+ "blocks.26.cross_attn.k.bias": "pytorch_model-00003.bin",
768
+ "blocks.26.cross_attn.v.weight": "pytorch_model-00003.bin",
769
+ "blocks.26.cross_attn.v.bias": "pytorch_model-00003.bin",
770
+ "blocks.26.cross_attn.o.weight": "pytorch_model-00003.bin",
771
+ "blocks.26.cross_attn.o.bias": "pytorch_model-00003.bin",
772
+ "blocks.26.cross_attn.norm_q.weight": "pytorch_model-00003.bin",
773
+ "blocks.26.cross_attn.norm_k.weight": "pytorch_model-00003.bin",
774
+ "blocks.26.audio_ffn.0.weight": "pytorch_model-00003.bin",
775
+ "blocks.26.audio_ffn.0.bias": "pytorch_model-00003.bin",
776
+ "blocks.26.audio_ffn.2.weight": "pytorch_model-00003.bin",
777
+ "blocks.26.audio_ffn.2.bias": "pytorch_model-00003.bin",
778
+ "blocks.26.audio_modulation.param": "pytorch_model-00003.bin",
779
+ "blocks.27.modulation": "pytorch_model-00003.bin",
780
+ "blocks.27.self_attn.q.weight": "pytorch_model-00003.bin",
781
+ "blocks.27.self_attn.q.bias": "pytorch_model-00003.bin",
782
+ "blocks.27.self_attn.k.weight": "pytorch_model-00003.bin",
783
+ "blocks.27.self_attn.k.bias": "pytorch_model-00003.bin",
784
+ "blocks.27.self_attn.v.weight": "pytorch_model-00003.bin",
785
+ "blocks.27.self_attn.v.bias": "pytorch_model-00003.bin",
786
+ "blocks.27.self_attn.o.weight": "pytorch_model-00003.bin",
787
+ "blocks.27.self_attn.o.bias": "pytorch_model-00003.bin",
788
+ "blocks.27.self_attn.norm_q.weight": "pytorch_model-00003.bin",
789
+ "blocks.27.self_attn.norm_k.weight": "pytorch_model-00003.bin",
790
+ "blocks.27.norm3.weight": "pytorch_model-00003.bin",
791
+ "blocks.27.norm3.bias": "pytorch_model-00003.bin",
792
+ "blocks.27.cross_attn.q.weight": "pytorch_model-00003.bin",
793
+ "blocks.27.cross_attn.q.bias": "pytorch_model-00003.bin",
794
+ "blocks.27.cross_attn.k.weight": "pytorch_model-00003.bin",
795
+ "blocks.27.cross_attn.k.bias": "pytorch_model-00003.bin",
796
+ "blocks.27.cross_attn.v.weight": "pytorch_model-00003.bin",
797
+ "blocks.27.cross_attn.v.bias": "pytorch_model-00003.bin",
798
+ "blocks.27.cross_attn.o.weight": "pytorch_model-00003.bin",
799
+ "blocks.27.cross_attn.o.bias": "pytorch_model-00003.bin",
800
+ "blocks.27.cross_attn.norm_q.weight": "pytorch_model-00003.bin",
801
+ "blocks.27.cross_attn.norm_k.weight": "pytorch_model-00003.bin",
802
+ "blocks.27.audio_ffn.0.weight": "pytorch_model-00003.bin",
803
+ "blocks.27.audio_ffn.0.bias": "pytorch_model-00003.bin",
804
+ "blocks.27.audio_ffn.2.weight": "pytorch_model-00003.bin",
805
+ "blocks.27.audio_ffn.2.bias": "pytorch_model-00003.bin",
806
+ "blocks.27.audio_modulation.param": "pytorch_model-00003.bin",
807
+ "blocks.28.modulation": "pytorch_model-00003.bin",
808
+ "blocks.28.self_attn.q.weight": "pytorch_model-00003.bin",
809
+ "blocks.28.self_attn.q.bias": "pytorch_model-00003.bin",
810
+ "blocks.28.self_attn.k.weight": "pytorch_model-00003.bin",
811
+ "blocks.28.self_attn.k.bias": "pytorch_model-00003.bin",
812
+ "blocks.28.self_attn.v.weight": "pytorch_model-00003.bin",
813
+ "blocks.28.self_attn.v.bias": "pytorch_model-00003.bin",
814
+ "blocks.28.self_attn.o.weight": "pytorch_model-00003.bin",
815
+ "blocks.28.self_attn.o.bias": "pytorch_model-00003.bin",
816
+ "blocks.28.self_attn.norm_q.weight": "pytorch_model-00003.bin",
817
+ "blocks.28.self_attn.norm_k.weight": "pytorch_model-00003.bin",
818
+ "blocks.28.norm3.weight": "pytorch_model-00003.bin",
819
+ "blocks.28.norm3.bias": "pytorch_model-00003.bin",
820
+ "blocks.28.cross_attn.q.weight": "pytorch_model-00003.bin",
821
+ "blocks.28.cross_attn.q.bias": "pytorch_model-00003.bin",
822
+ "blocks.28.cross_attn.k.weight": "pytorch_model-00003.bin",
823
+ "blocks.28.cross_attn.k.bias": "pytorch_model-00003.bin",
824
+ "blocks.28.cross_attn.v.weight": "pytorch_model-00003.bin",
825
+ "blocks.28.cross_attn.v.bias": "pytorch_model-00003.bin",
826
+ "blocks.28.cross_attn.o.weight": "pytorch_model-00003.bin",
827
+ "blocks.28.cross_attn.o.bias": "pytorch_model-00003.bin",
828
+ "blocks.28.cross_attn.norm_q.weight": "pytorch_model-00003.bin",
829
+ "blocks.28.cross_attn.norm_k.weight": "pytorch_model-00003.bin",
830
+ "blocks.28.audio_ffn.0.weight": "pytorch_model-00003.bin",
831
+ "blocks.28.audio_ffn.0.bias": "pytorch_model-00003.bin",
832
+ "blocks.28.audio_ffn.2.weight": "pytorch_model-00003.bin",
833
+ "blocks.28.audio_ffn.2.bias": "pytorch_model-00003.bin",
834
+ "blocks.28.audio_modulation.param": "pytorch_model-00003.bin",
835
+ "blocks.29.modulation": "pytorch_model-00003.bin",
836
+ "blocks.29.self_attn.q.weight": "pytorch_model-00003.bin",
837
+ "blocks.29.self_attn.q.bias": "pytorch_model-00003.bin",
838
+ "blocks.29.self_attn.k.weight": "pytorch_model-00003.bin",
839
+ "blocks.29.self_attn.k.bias": "pytorch_model-00003.bin",
840
+ "blocks.29.self_attn.v.weight": "pytorch_model-00003.bin",
841
+ "blocks.29.self_attn.v.bias": "pytorch_model-00003.bin",
842
+ "blocks.29.self_attn.o.weight": "pytorch_model-00003.bin",
843
+ "blocks.29.self_attn.o.bias": "pytorch_model-00003.bin",
844
+ "blocks.29.self_attn.norm_q.weight": "pytorch_model-00003.bin",
845
+ "blocks.29.self_attn.norm_k.weight": "pytorch_model-00003.bin",
846
+ "blocks.29.norm3.weight": "pytorch_model-00003.bin",
847
+ "blocks.29.norm3.bias": "pytorch_model-00003.bin",
848
+ "blocks.29.cross_attn.q.weight": "pytorch_model-00003.bin",
849
+ "blocks.29.cross_attn.q.bias": "pytorch_model-00003.bin",
850
+ "blocks.29.cross_attn.k.weight": "pytorch_model-00003.bin",
851
+ "blocks.29.cross_attn.k.bias": "pytorch_model-00003.bin",
852
+ "blocks.29.cross_attn.v.weight": "pytorch_model-00003.bin",
853
+ "blocks.29.cross_attn.v.bias": "pytorch_model-00003.bin",
854
+ "blocks.29.cross_attn.o.weight": "pytorch_model-00003.bin",
855
+ "blocks.29.cross_attn.o.bias": "pytorch_model-00003.bin",
856
+ "blocks.29.cross_attn.norm_q.weight": "pytorch_model-00003.bin",
857
+ "blocks.29.cross_attn.norm_k.weight": "pytorch_model-00003.bin",
858
+ "blocks.29.audio_ffn.0.weight": "pytorch_model-00003.bin",
859
+ "blocks.29.audio_ffn.0.bias": "pytorch_model-00003.bin",
860
+ "blocks.29.audio_ffn.2.weight": "pytorch_model-00003.bin",
861
+ "blocks.29.audio_ffn.2.bias": "pytorch_model-00003.bin",
862
+ "blocks.29.audio_modulation.param": "pytorch_model-00003.bin"
863
+ }
864
+ }
audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53650/optimizer/pytorch_optim-00001.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6db987ceabeaf4e6386d1ebb892312987fe3a4cfe6bbc40fa7170ac0aac4830
3
+ size 4243656922
audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53650/optimizer/pytorch_optim-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09c527400625a77edd23133303ef923d0172124a83974cf4db420481b59479c5
3
+ size 2423571758
audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53650/optimizer/pytorch_optim.bin.index.json ADDED
@@ -0,0 +1,165 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "param_groups": "pytorch_optim_group.bin",
4
+ "total_size": 6358.277587890625
5
+ },
6
+ "weight_map": {
7
+ "0": "pytorch_optim-00001.bin",
8
+ "1": "pytorch_optim-00001.bin",
9
+ "2": "pytorch_optim-00001.bin",
10
+ "3": "pytorch_optim-00001.bin",
11
+ "4": "pytorch_optim-00001.bin",
12
+ "5": "pytorch_optim-00001.bin",
13
+ "6": "pytorch_optim-00001.bin",
14
+ "7": "pytorch_optim-00001.bin",
15
+ "8": "pytorch_optim-00001.bin",
16
+ "9": "pytorch_optim-00001.bin",
17
+ "10": "pytorch_optim-00001.bin",
18
+ "11": "pytorch_optim-00001.bin",
19
+ "12": "pytorch_optim-00001.bin",
20
+ "13": "pytorch_optim-00001.bin",
21
+ "14": "pytorch_optim-00001.bin",
22
+ "15": "pytorch_optim-00001.bin",
23
+ "16": "pytorch_optim-00001.bin",
24
+ "17": "pytorch_optim-00001.bin",
25
+ "18": "pytorch_optim-00001.bin",
26
+ "19": "pytorch_optim-00001.bin",
27
+ "20": "pytorch_optim-00001.bin",
28
+ "21": "pytorch_optim-00001.bin",
29
+ "22": "pytorch_optim-00001.bin",
30
+ "23": "pytorch_optim-00001.bin",
31
+ "24": "pytorch_optim-00001.bin",
32
+ "25": "pytorch_optim-00001.bin",
33
+ "26": "pytorch_optim-00001.bin",
34
+ "27": "pytorch_optim-00001.bin",
35
+ "28": "pytorch_optim-00001.bin",
36
+ "29": "pytorch_optim-00001.bin",
37
+ "30": "pytorch_optim-00001.bin",
38
+ "31": "pytorch_optim-00001.bin",
39
+ "32": "pytorch_optim-00001.bin",
40
+ "33": "pytorch_optim-00001.bin",
41
+ "34": "pytorch_optim-00001.bin",
42
+ "35": "pytorch_optim-00001.bin",
43
+ "36": "pytorch_optim-00001.bin",
44
+ "37": "pytorch_optim-00001.bin",
45
+ "38": "pytorch_optim-00001.bin",
46
+ "39": "pytorch_optim-00001.bin",
47
+ "40": "pytorch_optim-00001.bin",
48
+ "41": "pytorch_optim-00001.bin",
49
+ "42": "pytorch_optim-00001.bin",
50
+ "43": "pytorch_optim-00001.bin",
51
+ "44": "pytorch_optim-00001.bin",
52
+ "45": "pytorch_optim-00001.bin",
53
+ "46": "pytorch_optim-00001.bin",
54
+ "47": "pytorch_optim-00001.bin",
55
+ "48": "pytorch_optim-00001.bin",
56
+ "49": "pytorch_optim-00001.bin",
57
+ "50": "pytorch_optim-00001.bin",
58
+ "51": "pytorch_optim-00001.bin",
59
+ "52": "pytorch_optim-00001.bin",
60
+ "53": "pytorch_optim-00001.bin",
61
+ "54": "pytorch_optim-00001.bin",
62
+ "55": "pytorch_optim-00001.bin",
63
+ "56": "pytorch_optim-00001.bin",
64
+ "57": "pytorch_optim-00001.bin",
65
+ "58": "pytorch_optim-00001.bin",
66
+ "59": "pytorch_optim-00001.bin",
67
+ "60": "pytorch_optim-00001.bin",
68
+ "61": "pytorch_optim-00001.bin",
69
+ "62": "pytorch_optim-00001.bin",
70
+ "63": "pytorch_optim-00001.bin",
71
+ "64": "pytorch_optim-00001.bin",
72
+ "65": "pytorch_optim-00001.bin",
73
+ "66": "pytorch_optim-00001.bin",
74
+ "67": "pytorch_optim-00001.bin",
75
+ "68": "pytorch_optim-00001.bin",
76
+ "69": "pytorch_optim-00001.bin",
77
+ "70": "pytorch_optim-00001.bin",
78
+ "71": "pytorch_optim-00001.bin",
79
+ "72": "pytorch_optim-00001.bin",
80
+ "73": "pytorch_optim-00001.bin",
81
+ "74": "pytorch_optim-00001.bin",
82
+ "75": "pytorch_optim-00001.bin",
83
+ "76": "pytorch_optim-00001.bin",
84
+ "77": "pytorch_optim-00001.bin",
85
+ "78": "pytorch_optim-00001.bin",
86
+ "79": "pytorch_optim-00001.bin",
87
+ "80": "pytorch_optim-00001.bin",
88
+ "81": "pytorch_optim-00001.bin",
89
+ "82": "pytorch_optim-00001.bin",
90
+ "83": "pytorch_optim-00001.bin",
91
+ "84": "pytorch_optim-00001.bin",
92
+ "85": "pytorch_optim-00001.bin",
93
+ "86": "pytorch_optim-00001.bin",
94
+ "87": "pytorch_optim-00001.bin",
95
+ "88": "pytorch_optim-00001.bin",
96
+ "89": "pytorch_optim-00001.bin",
97
+ "90": "pytorch_optim-00001.bin",
98
+ "91": "pytorch_optim-00001.bin",
99
+ "92": "pytorch_optim-00001.bin",
100
+ "93": "pytorch_optim-00001.bin",
101
+ "94": "pytorch_optim-00001.bin",
102
+ "95": "pytorch_optim-00001.bin",
103
+ "96": "pytorch_optim-00001.bin",
104
+ "97": "pytorch_optim-00001.bin",
105
+ "98": "pytorch_optim-00001.bin",
106
+ "99": "pytorch_optim-00001.bin",
107
+ "100": "pytorch_optim-00001.bin",
108
+ "101": "pytorch_optim-00001.bin",
109
+ "102": "pytorch_optim-00002.bin",
110
+ "103": "pytorch_optim-00002.bin",
111
+ "104": "pytorch_optim-00002.bin",
112
+ "105": "pytorch_optim-00002.bin",
113
+ "106": "pytorch_optim-00002.bin",
114
+ "107": "pytorch_optim-00002.bin",
115
+ "108": "pytorch_optim-00002.bin",
116
+ "109": "pytorch_optim-00002.bin",
117
+ "110": "pytorch_optim-00002.bin",
118
+ "111": "pytorch_optim-00002.bin",
119
+ "112": "pytorch_optim-00002.bin",
120
+ "113": "pytorch_optim-00002.bin",
121
+ "114": "pytorch_optim-00002.bin",
122
+ "115": "pytorch_optim-00002.bin",
123
+ "116": "pytorch_optim-00002.bin",
124
+ "117": "pytorch_optim-00002.bin",
125
+ "118": "pytorch_optim-00002.bin",
126
+ "119": "pytorch_optim-00002.bin",
127
+ "120": "pytorch_optim-00002.bin",
128
+ "121": "pytorch_optim-00002.bin",
129
+ "122": "pytorch_optim-00002.bin",
130
+ "123": "pytorch_optim-00002.bin",
131
+ "124": "pytorch_optim-00002.bin",
132
+ "125": "pytorch_optim-00002.bin",
133
+ "126": "pytorch_optim-00002.bin",
134
+ "127": "pytorch_optim-00002.bin",
135
+ "128": "pytorch_optim-00002.bin",
136
+ "129": "pytorch_optim-00002.bin",
137
+ "130": "pytorch_optim-00002.bin",
138
+ "131": "pytorch_optim-00002.bin",
139
+ "132": "pytorch_optim-00002.bin",
140
+ "133": "pytorch_optim-00002.bin",
141
+ "134": "pytorch_optim-00002.bin",
142
+ "135": "pytorch_optim-00002.bin",
143
+ "136": "pytorch_optim-00002.bin",
144
+ "137": "pytorch_optim-00002.bin",
145
+ "138": "pytorch_optim-00002.bin",
146
+ "139": "pytorch_optim-00002.bin",
147
+ "140": "pytorch_optim-00002.bin",
148
+ "141": "pytorch_optim-00002.bin",
149
+ "142": "pytorch_optim-00002.bin",
150
+ "143": "pytorch_optim-00002.bin",
151
+ "144": "pytorch_optim-00002.bin",
152
+ "145": "pytorch_optim-00002.bin",
153
+ "146": "pytorch_optim-00002.bin",
154
+ "147": "pytorch_optim-00002.bin",
155
+ "148": "pytorch_optim-00002.bin",
156
+ "149": "pytorch_optim-00002.bin",
157
+ "150": "pytorch_optim-00002.bin",
158
+ "151": "pytorch_optim-00002.bin",
159
+ "152": "pytorch_optim-00002.bin",
160
+ "153": "pytorch_optim-00002.bin",
161
+ "154": "pytorch_optim-00002.bin",
162
+ "155": "pytorch_optim-00002.bin",
163
+ "156": "pytorch_optim-00002.bin"
164
+ }
165
+ }
audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53650/optimizer/pytorch_optim_group.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:821c8504135947a0f7bc707c16e2865d3740fd6a307b8b5232645e4f886c0ebf
3
+ size 1360
audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53650/running_states.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 49,
3
+ "step": 1073,
4
+ "global_step": 53650,
5
+ "batch_size": null
6
+ }
audio-only/000-Wan2_1_T2V_1_3B/epoch049-global_step53650/sampler ADDED
Binary file (928 Bytes). View file
 
audio-only/000-Wan2_1_T2V_1_3B/log.txt ADDED
The diff for this file is too large to render. See raw diff
 
audio-only/000-Wan2_1_T2V_1_3B/tensorboard/events.out.tfevents.1760758333.c0f6c83c-35.cloud.together.ai.2607279.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af42cec851a2eaac5afd3a5ab5563b13ce0589c7e998a945ba52a28e73c2adbc
3
+ size 501190