Hugging Face's logo

HumeAI
/
tada-3b-ml

Text-to-Speech
Safetensors
llama
tts
speech-language-model
Model card Files
xet
Community
2
trungd-hume commited on
Commit
3c9c19e
·
verified ·
1 Parent(s): b0922de

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. README.md +0 -3
  2. config.json +53 -0
  3. generation_config.json +10 -0
  4. model-00001-of-00002.safetensors +3 -0
  5. model-00002-of-00002.safetensors +3 -0
  6. model.safetensors.index.json +510 -0
README.md DELETED
@@ -1,3 +0,0 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "acoustic_dim": 512,
3
+ "acoustic_from_nth_hidden_state": -1,
4
+ "acoustic_mean": 0.0,
5
+ "acoustic_std": 1.5,
6
+ "add_semantic_to_condition": 0.0,
7
+ "architectures": [
8
+ "TadaForCausalLM"
9
+ ],
10
+ "attention_bias": false,
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 128000,
13
+ "bottleneck_dim": null,
14
+ "context_window": 8,
15
+ "diffusion_head_type": "vibevoice",
16
+ "dist_type": "fixed",
17
+ "dtype": "bfloat16",
18
+ "eos_token_id": [
19
+ 128001,
20
+ 128008,
21
+ 128009
22
+ ],
23
+ "head_dim": 128,
24
+ "head_ffn_ratio": 4.0,
25
+ "head_layers": 6,
26
+ "hidden_act": "silu",
27
+ "hidden_size": 3072,
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 8192,
30
+ "latent_dropout": 0.0,
31
+ "max_position_embeddings": 131072,
32
+ "mlp_bias": false,
33
+ "model_type": "llama",
34
+ "num_attention_heads": 24,
35
+ "num_hidden_layers": 28,
36
+ "num_key_value_heads": 8,
37
+ "num_time_classes": 256,
38
+ "pretraining_tp": 1,
39
+ "rms_norm_eps": 1e-05,
40
+ "rope_scaling": {
41
+ "factor": 32.0,
42
+ "high_freq_factor": 4.0,
43
+ "low_freq_factor": 1.0,
44
+ "original_max_position_embeddings": 8192,
45
+ "rope_type": "llama3"
46
+ },
47
+ "rope_theta": 500000.0,
48
+ "shift_acoustic": 5,
49
+ "tie_word_embeddings": true,
50
+ "transformers_version": "4.57.3",
51
+ "use_cache": true,
52
+ "vocab_size": 128256
53
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "transformers_version": "4.57.3"
10
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b772727c263f9c49411b8fafe738c2a41598d89256e4d786364ce39959628ea
3
+ size 4965799096
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae4108a1cb178a3ccf82caf6dabfaa1fe7646cd4a6126b8a32535aa489de1193
3
+ size 3901011596
model.safetensors.index.json ADDED
@@ -0,0 +1,510 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 4225756258,
4
+ "total_size": 8866748612
5
+ },
6
+ "weight_map": {
7
+ "_decoder.decoder_proj.bias": "model-00002-of-00002.safetensors",
8
+ "_decoder.decoder_proj.weight": "model-00002-of-00002.safetensors",
9
+ "_decoder.local_attention_decoder.final_norm.bias": "model-00002-of-00002.safetensors",
10
+ "_decoder.local_attention_decoder.final_norm.weight": "model-00002-of-00002.safetensors",
11
+ "_decoder.local_attention_decoder.layers.0.ffn.0.bias": "model-00002-of-00002.safetensors",
12
+ "_decoder.local_attention_decoder.layers.0.ffn.0.weight": "model-00002-of-00002.safetensors",
13
+ "_decoder.local_attention_decoder.layers.0.ffn.3.bias": "model-00002-of-00002.safetensors",
14
+ "_decoder.local_attention_decoder.layers.0.ffn.3.weight": "model-00002-of-00002.safetensors",
15
+ "_decoder.local_attention_decoder.layers.0.norm.bias": "model-00002-of-00002.safetensors",
16
+ "_decoder.local_attention_decoder.layers.0.norm.weight": "model-00002-of-00002.safetensors",
17
+ "_decoder.local_attention_decoder.layers.0.self_attn._precomputed_mask": "model-00002-of-00002.safetensors",
18
+ "_decoder.local_attention_decoder.layers.0.self_attn.layer_norm.bias": "model-00002-of-00002.safetensors",
19
+ "_decoder.local_attention_decoder.layers.0.self_attn.layer_norm.weight": "model-00002-of-00002.safetensors",
20
+ "_decoder.local_attention_decoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
21
+ "_decoder.local_attention_decoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
22
+ "_decoder.local_attention_decoder.layers.0.self_attn.qkv.bias": "model-00002-of-00002.safetensors",
23
+ "_decoder.local_attention_decoder.layers.0.self_attn.qkv.weight": "model-00002-of-00002.safetensors",
24
+ "_decoder.local_attention_decoder.layers.0.self_attn.rope_freqs": "model-00002-of-00002.safetensors",
25
+ "_decoder.local_attention_decoder.layers.1.ffn.0.bias": "model-00002-of-00002.safetensors",
26
+ "_decoder.local_attention_decoder.layers.1.ffn.0.weight": "model-00002-of-00002.safetensors",
27
+ "_decoder.local_attention_decoder.layers.1.ffn.3.bias": "model-00002-of-00002.safetensors",
28
+ "_decoder.local_attention_decoder.layers.1.ffn.3.weight": "model-00002-of-00002.safetensors",
29
+ "_decoder.local_attention_decoder.layers.1.norm.bias": "model-00002-of-00002.safetensors",
30
+ "_decoder.local_attention_decoder.layers.1.norm.weight": "model-00002-of-00002.safetensors",
31
+ "_decoder.local_attention_decoder.layers.1.self_attn._precomputed_mask": "model-00002-of-00002.safetensors",
32
+ "_decoder.local_attention_decoder.layers.1.self_attn.layer_norm.bias": "model-00002-of-00002.safetensors",
33
+ "_decoder.local_attention_decoder.layers.1.self_attn.layer_norm.weight": "model-00002-of-00002.safetensors",
34
+ "_decoder.local_attention_decoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
35
+ "_decoder.local_attention_decoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
36
+ "_decoder.local_attention_decoder.layers.1.self_attn.qkv.bias": "model-00002-of-00002.safetensors",
37
+ "_decoder.local_attention_decoder.layers.1.self_attn.qkv.weight": "model-00002-of-00002.safetensors",
38
+ "_decoder.local_attention_decoder.layers.1.self_attn.rope_freqs": "model-00002-of-00002.safetensors",
39
+ "_decoder.local_attention_decoder.layers.2.ffn.0.bias": "model-00002-of-00002.safetensors",
40
+ "_decoder.local_attention_decoder.layers.2.ffn.0.weight": "model-00002-of-00002.safetensors",
41
+ "_decoder.local_attention_decoder.layers.2.ffn.3.bias": "model-00002-of-00002.safetensors",
42
+ "_decoder.local_attention_decoder.layers.2.ffn.3.weight": "model-00002-of-00002.safetensors",
43
+ "_decoder.local_attention_decoder.layers.2.norm.bias": "model-00002-of-00002.safetensors",
44
+ "_decoder.local_attention_decoder.layers.2.norm.weight": "model-00002-of-00002.safetensors",
45
+ "_decoder.local_attention_decoder.layers.2.self_attn._precomputed_mask": "model-00002-of-00002.safetensors",
46
+ "_decoder.local_attention_decoder.layers.2.self_attn.layer_norm.bias": "model-00002-of-00002.safetensors",
47
+ "_decoder.local_attention_decoder.layers.2.self_attn.layer_norm.weight": "model-00002-of-00002.safetensors",
48
+ "_decoder.local_attention_decoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
49
+ "_decoder.local_attention_decoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
50
+ "_decoder.local_attention_decoder.layers.2.self_attn.qkv.bias": "model-00002-of-00002.safetensors",
51
+ "_decoder.local_attention_decoder.layers.2.self_attn.qkv.weight": "model-00002-of-00002.safetensors",
52
+ "_decoder.local_attention_decoder.layers.2.self_attn.rope_freqs": "model-00002-of-00002.safetensors",
53
+ "_decoder.local_attention_decoder.layers.3.ffn.0.bias": "model-00002-of-00002.safetensors",
54
+ "_decoder.local_attention_decoder.layers.3.ffn.0.weight": "model-00002-of-00002.safetensors",
55
+ "_decoder.local_attention_decoder.layers.3.ffn.3.bias": "model-00002-of-00002.safetensors",
56
+ "_decoder.local_attention_decoder.layers.3.ffn.3.weight": "model-00002-of-00002.safetensors",
57
+ "_decoder.local_attention_decoder.layers.3.norm.bias": "model-00002-of-00002.safetensors",
58
+ "_decoder.local_attention_decoder.layers.3.norm.weight": "model-00002-of-00002.safetensors",
59
+ "_decoder.local_attention_decoder.layers.3.self_attn._precomputed_mask": "model-00002-of-00002.safetensors",
60
+ "_decoder.local_attention_decoder.layers.3.self_attn.layer_norm.bias": "model-00002-of-00002.safetensors",
61
+ "_decoder.local_attention_decoder.layers.3.self_attn.layer_norm.weight": "model-00002-of-00002.safetensors",
62
+ "_decoder.local_attention_decoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
63
+ "_decoder.local_attention_decoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
64
+ "_decoder.local_attention_decoder.layers.3.self_attn.qkv.bias": "model-00002-of-00002.safetensors",
65
+ "_decoder.local_attention_decoder.layers.3.self_attn.qkv.weight": "model-00002-of-00002.safetensors",
66
+ "_decoder.local_attention_decoder.layers.3.self_attn.rope_freqs": "model-00002-of-00002.safetensors",
67
+ "_decoder.local_attention_decoder.layers.4.ffn.0.bias": "model-00002-of-00002.safetensors",
68
+ "_decoder.local_attention_decoder.layers.4.ffn.0.weight": "model-00002-of-00002.safetensors",
69
+ "_decoder.local_attention_decoder.layers.4.ffn.3.bias": "model-00002-of-00002.safetensors",
70
+ "_decoder.local_attention_decoder.layers.4.ffn.3.weight": "model-00002-of-00002.safetensors",
71
+ "_decoder.local_attention_decoder.layers.4.norm.bias": "model-00002-of-00002.safetensors",
72
+ "_decoder.local_attention_decoder.layers.4.norm.weight": "model-00002-of-00002.safetensors",
73
+ "_decoder.local_attention_decoder.layers.4.self_attn._precomputed_mask": "model-00002-of-00002.safetensors",
74
+ "_decoder.local_attention_decoder.layers.4.self_attn.layer_norm.bias": "model-00002-of-00002.safetensors",
75
+ "_decoder.local_attention_decoder.layers.4.self_attn.layer_norm.weight": "model-00002-of-00002.safetensors",
76
+ "_decoder.local_attention_decoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
77
+ "_decoder.local_attention_decoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
78
+ "_decoder.local_attention_decoder.layers.4.self_attn.qkv.bias": "model-00002-of-00002.safetensors",
79
+ "_decoder.local_attention_decoder.layers.4.self_attn.qkv.weight": "model-00002-of-00002.safetensors",
80
+ "_decoder.local_attention_decoder.layers.4.self_attn.rope_freqs": "model-00002-of-00002.safetensors",
81
+ "_decoder.local_attention_decoder.layers.5.ffn.0.bias": "model-00002-of-00002.safetensors",
82
+ "_decoder.local_attention_decoder.layers.5.ffn.0.weight": "model-00002-of-00002.safetensors",
83
+ "_decoder.local_attention_decoder.layers.5.ffn.3.bias": "model-00002-of-00002.safetensors",
84
+ "_decoder.local_attention_decoder.layers.5.ffn.3.weight": "model-00002-of-00002.safetensors",
85
+ "_decoder.local_attention_decoder.layers.5.norm.bias": "model-00002-of-00002.safetensors",
86
+ "_decoder.local_attention_decoder.layers.5.norm.weight": "model-00002-of-00002.safetensors",
87
+ "_decoder.local_attention_decoder.layers.5.self_attn._precomputed_mask": "model-00002-of-00002.safetensors",
88
+ "_decoder.local_attention_decoder.layers.5.self_attn.layer_norm.bias": "model-00002-of-00002.safetensors",
89
+ "_decoder.local_attention_decoder.layers.5.self_attn.layer_norm.weight": "model-00002-of-00002.safetensors",
90
+ "_decoder.local_attention_decoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
91
+ "_decoder.local_attention_decoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
92
+ "_decoder.local_attention_decoder.layers.5.self_attn.qkv.bias": "model-00002-of-00002.safetensors",
93
+ "_decoder.local_attention_decoder.layers.5.self_attn.qkv.weight": "model-00002-of-00002.safetensors",
94
+ "_decoder.local_attention_decoder.layers.5.self_attn.rope_freqs": "model-00002-of-00002.safetensors",
95
+ "_decoder.wav_decoder.model.0.bias": "model-00002-of-00002.safetensors",
96
+ "_decoder.wav_decoder.model.0.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
97
+ "_decoder.wav_decoder.model.0.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
98
+ "_decoder.wav_decoder.model.1.block.0.alpha": "model-00002-of-00002.safetensors",
99
+ "_decoder.wav_decoder.model.1.block.1.bias": "model-00002-of-00002.safetensors",
100
+ "_decoder.wav_decoder.model.1.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
101
+ "_decoder.wav_decoder.model.1.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
102
+ "_decoder.wav_decoder.model.1.block.2.block.0.alpha": "model-00002-of-00002.safetensors",
103
+ "_decoder.wav_decoder.model.1.block.2.block.1.bias": "model-00002-of-00002.safetensors",
104
+ "_decoder.wav_decoder.model.1.block.2.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
105
+ "_decoder.wav_decoder.model.1.block.2.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
106
+ "_decoder.wav_decoder.model.1.block.2.block.2.alpha": "model-00002-of-00002.safetensors",
107
+ "_decoder.wav_decoder.model.1.block.2.block.3.bias": "model-00002-of-00002.safetensors",
108
+ "_decoder.wav_decoder.model.1.block.2.block.3.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
109
+ "_decoder.wav_decoder.model.1.block.2.block.3.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
110
+ "_decoder.wav_decoder.model.1.block.3.block.0.alpha": "model-00002-of-00002.safetensors",
111
+ "_decoder.wav_decoder.model.1.block.3.block.1.bias": "model-00002-of-00002.safetensors",
112
+ "_decoder.wav_decoder.model.1.block.3.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
113
+ "_decoder.wav_decoder.model.1.block.3.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
114
+ "_decoder.wav_decoder.model.1.block.3.block.2.alpha": "model-00002-of-00002.safetensors",
115
+ "_decoder.wav_decoder.model.1.block.3.block.3.bias": "model-00002-of-00002.safetensors",
116
+ "_decoder.wav_decoder.model.1.block.3.block.3.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
117
+ "_decoder.wav_decoder.model.1.block.3.block.3.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
118
+ "_decoder.wav_decoder.model.1.block.4.block.0.alpha": "model-00002-of-00002.safetensors",
119
+ "_decoder.wav_decoder.model.1.block.4.block.1.bias": "model-00002-of-00002.safetensors",
120
+ "_decoder.wav_decoder.model.1.block.4.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
121
+ "_decoder.wav_decoder.model.1.block.4.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
122
+ "_decoder.wav_decoder.model.1.block.4.block.2.alpha": "model-00002-of-00002.safetensors",
123
+ "_decoder.wav_decoder.model.1.block.4.block.3.bias": "model-00002-of-00002.safetensors",
124
+ "_decoder.wav_decoder.model.1.block.4.block.3.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
125
+ "_decoder.wav_decoder.model.1.block.4.block.3.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
126
+ "_decoder.wav_decoder.model.2.block.0.alpha": "model-00002-of-00002.safetensors",
127
+ "_decoder.wav_decoder.model.2.block.1.bias": "model-00002-of-00002.safetensors",
128
+ "_decoder.wav_decoder.model.2.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
129
+ "_decoder.wav_decoder.model.2.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
130
+ "_decoder.wav_decoder.model.2.block.2.block.0.alpha": "model-00002-of-00002.safetensors",
131
+ "_decoder.wav_decoder.model.2.block.2.block.1.bias": "model-00002-of-00002.safetensors",
132
+ "_decoder.wav_decoder.model.2.block.2.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
133
+ "_decoder.wav_decoder.model.2.block.2.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
134
+ "_decoder.wav_decoder.model.2.block.2.block.2.alpha": "model-00002-of-00002.safetensors",
135
+ "_decoder.wav_decoder.model.2.block.2.block.3.bias": "model-00002-of-00002.safetensors",
136
+ "_decoder.wav_decoder.model.2.block.2.block.3.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
137
+ "_decoder.wav_decoder.model.2.block.2.block.3.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
138
+ "_decoder.wav_decoder.model.2.block.3.block.0.alpha": "model-00002-of-00002.safetensors",
139
+ "_decoder.wav_decoder.model.2.block.3.block.1.bias": "model-00002-of-00002.safetensors",
140
+ "_decoder.wav_decoder.model.2.block.3.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
141
+ "_decoder.wav_decoder.model.2.block.3.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
142
+ "_decoder.wav_decoder.model.2.block.3.block.2.alpha": "model-00002-of-00002.safetensors",
143
+ "_decoder.wav_decoder.model.2.block.3.block.3.bias": "model-00002-of-00002.safetensors",
144
+ "_decoder.wav_decoder.model.2.block.3.block.3.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
145
+ "_decoder.wav_decoder.model.2.block.3.block.3.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
146
+ "_decoder.wav_decoder.model.2.block.4.block.0.alpha": "model-00002-of-00002.safetensors",
147
+ "_decoder.wav_decoder.model.2.block.4.block.1.bias": "model-00002-of-00002.safetensors",
148
+ "_decoder.wav_decoder.model.2.block.4.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
149
+ "_decoder.wav_decoder.model.2.block.4.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
150
+ "_decoder.wav_decoder.model.2.block.4.block.2.alpha": "model-00002-of-00002.safetensors",
151
+ "_decoder.wav_decoder.model.2.block.4.block.3.bias": "model-00002-of-00002.safetensors",
152
+ "_decoder.wav_decoder.model.2.block.4.block.3.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
153
+ "_decoder.wav_decoder.model.2.block.4.block.3.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
154
+ "_decoder.wav_decoder.model.3.block.0.alpha": "model-00002-of-00002.safetensors",
155
+ "_decoder.wav_decoder.model.3.block.1.bias": "model-00002-of-00002.safetensors",
156
+ "_decoder.wav_decoder.model.3.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
157
+ "_decoder.wav_decoder.model.3.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
158
+ "_decoder.wav_decoder.model.3.block.2.block.0.alpha": "model-00002-of-00002.safetensors",
159
+ "_decoder.wav_decoder.model.3.block.2.block.1.bias": "model-00002-of-00002.safetensors",
160
+ "_decoder.wav_decoder.model.3.block.2.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
161
+ "_decoder.wav_decoder.model.3.block.2.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
162
+ "_decoder.wav_decoder.model.3.block.2.block.2.alpha": "model-00002-of-00002.safetensors",
163
+ "_decoder.wav_decoder.model.3.block.2.block.3.bias": "model-00002-of-00002.safetensors",
164
+ "_decoder.wav_decoder.model.3.block.2.block.3.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
165
+ "_decoder.wav_decoder.model.3.block.2.block.3.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
166
+ "_decoder.wav_decoder.model.3.block.3.block.0.alpha": "model-00002-of-00002.safetensors",
167
+ "_decoder.wav_decoder.model.3.block.3.block.1.bias": "model-00002-of-00002.safetensors",
168
+ "_decoder.wav_decoder.model.3.block.3.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
169
+ "_decoder.wav_decoder.model.3.block.3.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
170
+ "_decoder.wav_decoder.model.3.block.3.block.2.alpha": "model-00002-of-00002.safetensors",
171
+ "_decoder.wav_decoder.model.3.block.3.block.3.bias": "model-00002-of-00002.safetensors",
172
+ "_decoder.wav_decoder.model.3.block.3.block.3.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
173
+ "_decoder.wav_decoder.model.3.block.3.block.3.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
174
+ "_decoder.wav_decoder.model.3.block.4.block.0.alpha": "model-00002-of-00002.safetensors",
175
+ "_decoder.wav_decoder.model.3.block.4.block.1.bias": "model-00002-of-00002.safetensors",
176
+ "_decoder.wav_decoder.model.3.block.4.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
177
+ "_decoder.wav_decoder.model.3.block.4.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
178
+ "_decoder.wav_decoder.model.3.block.4.block.2.alpha": "model-00002-of-00002.safetensors",
179
+ "_decoder.wav_decoder.model.3.block.4.block.3.bias": "model-00002-of-00002.safetensors",
180
+ "_decoder.wav_decoder.model.3.block.4.block.3.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
181
+ "_decoder.wav_decoder.model.3.block.4.block.3.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
182
+ "_decoder.wav_decoder.model.4.block.0.alpha": "model-00002-of-00002.safetensors",
183
+ "_decoder.wav_decoder.model.4.block.1.bias": "model-00002-of-00002.safetensors",
184
+ "_decoder.wav_decoder.model.4.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
185
+ "_decoder.wav_decoder.model.4.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
186
+ "_decoder.wav_decoder.model.4.block.2.block.0.alpha": "model-00002-of-00002.safetensors",
187
+ "_decoder.wav_decoder.model.4.block.2.block.1.bias": "model-00002-of-00002.safetensors",
188
+ "_decoder.wav_decoder.model.4.block.2.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
189
+ "_decoder.wav_decoder.model.4.block.2.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
190
+ "_decoder.wav_decoder.model.4.block.2.block.2.alpha": "model-00002-of-00002.safetensors",
191
+ "_decoder.wav_decoder.model.4.block.2.block.3.bias": "model-00002-of-00002.safetensors",
192
+ "_decoder.wav_decoder.model.4.block.2.block.3.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
193
+ "_decoder.wav_decoder.model.4.block.2.block.3.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
194
+ "_decoder.wav_decoder.model.4.block.3.block.0.alpha": "model-00002-of-00002.safetensors",
195
+ "_decoder.wav_decoder.model.4.block.3.block.1.bias": "model-00002-of-00002.safetensors",
196
+ "_decoder.wav_decoder.model.4.block.3.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
197
+ "_decoder.wav_decoder.model.4.block.3.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
198
+ "_decoder.wav_decoder.model.4.block.3.block.2.alpha": "model-00002-of-00002.safetensors",
199
+ "_decoder.wav_decoder.model.4.block.3.block.3.bias": "model-00002-of-00002.safetensors",
200
+ "_decoder.wav_decoder.model.4.block.3.block.3.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
201
+ "_decoder.wav_decoder.model.4.block.3.block.3.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
202
+ "_decoder.wav_decoder.model.4.block.4.block.0.alpha": "model-00002-of-00002.safetensors",
203
+ "_decoder.wav_decoder.model.4.block.4.block.1.bias": "model-00002-of-00002.safetensors",
204
+ "_decoder.wav_decoder.model.4.block.4.block.1.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
205
+ "_decoder.wav_decoder.model.4.block.4.block.1.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
206
+ "_decoder.wav_decoder.model.4.block.4.block.2.alpha": "model-00002-of-00002.safetensors",
207
+ "_decoder.wav_decoder.model.4.block.4.block.3.bias": "model-00002-of-00002.safetensors",
208
+ "_decoder.wav_decoder.model.4.block.4.block.3.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
209
+ "_decoder.wav_decoder.model.4.block.4.block.3.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
210
+ "_decoder.wav_decoder.model.5.alpha": "model-00002-of-00002.safetensors",
211
+ "_decoder.wav_decoder.model.6.bias": "model-00002-of-00002.safetensors",
212
+ "_decoder.wav_decoder.model.6.parametrizations.weight.original0": "model-00002-of-00002.safetensors",
213
+ "_decoder.wav_decoder.model.6.parametrizations.weight.original1": "model-00002-of-00002.safetensors",
214
+ "acoustic_mask_emb.weight": "model-00002-of-00002.safetensors",
215
+ "acoustic_proj.bias": "model-00002-of-00002.safetensors",
216
+ "acoustic_proj.weight": "model-00002-of-00002.safetensors",
217
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
234
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
236
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
238
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
262
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
266
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
268
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
272
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
274
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
276
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
278
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
279
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
280
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
282
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
284
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
294
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
296
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
297
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
298
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
299
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
300
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
301
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
302
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
303
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
304
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
305
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
306
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
307
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
308
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
309
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
310
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
311
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
312
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
313
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
314
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
315
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
316
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
317
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
318
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
319
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
320
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
321
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
322
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
323
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
324
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
325
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
326
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
327
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
328
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
329
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
330
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
331
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
332
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
333
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
334
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
335
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
336
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
337
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
338
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
339
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
340
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
341
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
342
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
343
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
344
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
345
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
346
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
347
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
348
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
349
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
350
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
351
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
352
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
353
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
354
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
355
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
356
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
357
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
358
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
359
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
360
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
361
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
362
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
363
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
364
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
365
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
366
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
367
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
368
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
369
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
370
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
371
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
372
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
373
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
374
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
375
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
376
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
377
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
378
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
379
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
380
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
381
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
382
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
383
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
384
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
385
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
386
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
387
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
388
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
389
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
390
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
391
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
392
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
393
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
394
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
395
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
396
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
397
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
398
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
399
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
400
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
401
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
402
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
403
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
404
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
405
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
406
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
407
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
408
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
409
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
410
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
411
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
412
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
413
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
414
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
415
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
416
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
417
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
418
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
419
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
420
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
421
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
422
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
423
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
424
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
425
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
426
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
427
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
428
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
429
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
430
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
431
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
432
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
433
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
434
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
435
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
436
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
437
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
438
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
439
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
440
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
441
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
442
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
443
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
444
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
445
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
446
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
447
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
448
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
449
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
450
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
451
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
452
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
453
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
454
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
455
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
456
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
457
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
458
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
459
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
460
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
461
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
462
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
463
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
464
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
465
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
466
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
467
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
468
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
469
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
470
+ "model.norm.weight": "model-00002-of-00002.safetensors",
471
+ "prediction_head.cond_proj.weight": "model-00002-of-00002.safetensors",
472
+ "prediction_head.final_layer.adaLN_modulation.1.weight": "model-00002-of-00002.safetensors",
473
+ "prediction_head.final_layer.linear.weight": "model-00002-of-00002.safetensors",
474
+ "prediction_head.layers.0.adaLN_modulation.1.weight": "model-00002-of-00002.safetensors",
475
+ "prediction_head.layers.0.ffn.down_proj.weight": "model-00002-of-00002.safetensors",
476
+ "prediction_head.layers.0.ffn.gate_proj.weight": "model-00002-of-00002.safetensors",
477
+ "prediction_head.layers.0.ffn.up_proj.weight": "model-00002-of-00002.safetensors",
478
+ "prediction_head.layers.0.norm.weight": "model-00002-of-00002.safetensors",
479
+ "prediction_head.layers.1.adaLN_modulation.1.weight": "model-00002-of-00002.safetensors",
480
+ "prediction_head.layers.1.ffn.down_proj.weight": "model-00002-of-00002.safetensors",
481
+ "prediction_head.layers.1.ffn.gate_proj.weight": "model-00002-of-00002.safetensors",
482
+ "prediction_head.layers.1.ffn.up_proj.weight": "model-00002-of-00002.safetensors",
483
+ "prediction_head.layers.1.norm.weight": "model-00002-of-00002.safetensors",
484
+ "prediction_head.layers.2.adaLN_modulation.1.weight": "model-00002-of-00002.safetensors",
485
+ "prediction_head.layers.2.ffn.down_proj.weight": "model-00002-of-00002.safetensors",
486
+ "prediction_head.layers.2.ffn.gate_proj.weight": "model-00002-of-00002.safetensors",
487
+ "prediction_head.layers.2.ffn.up_proj.weight": "model-00002-of-00002.safetensors",
488
+ "prediction_head.layers.2.norm.weight": "model-00002-of-00002.safetensors",
489
+ "prediction_head.layers.3.adaLN_modulation.1.weight": "model-00002-of-00002.safetensors",
490
+ "prediction_head.layers.3.ffn.down_proj.weight": "model-00002-of-00002.safetensors",
491
+ "prediction_head.layers.3.ffn.gate_proj.weight": "model-00002-of-00002.safetensors",
492
+ "prediction_head.layers.3.ffn.up_proj.weight": "model-00002-of-00002.safetensors",
493
+ "prediction_head.layers.3.norm.weight": "model-00002-of-00002.safetensors",
494
+ "prediction_head.layers.4.adaLN_modulation.1.weight": "model-00002-of-00002.safetensors",
495
+ "prediction_head.layers.4.ffn.down_proj.weight": "model-00002-of-00002.safetensors",
496
+ "prediction_head.layers.4.ffn.gate_proj.weight": "model-00002-of-00002.safetensors",
497
+ "prediction_head.layers.4.ffn.up_proj.weight": "model-00002-of-00002.safetensors",
498
+ "prediction_head.layers.4.norm.weight": "model-00002-of-00002.safetensors",
499
+ "prediction_head.layers.5.adaLN_modulation.1.weight": "model-00002-of-00002.safetensors",
500
+ "prediction_head.layers.5.ffn.down_proj.weight": "model-00002-of-00002.safetensors",
501
+ "prediction_head.layers.5.ffn.gate_proj.weight": "model-00002-of-00002.safetensors",
502
+ "prediction_head.layers.5.ffn.up_proj.weight": "model-00002-of-00002.safetensors",
503
+ "prediction_head.layers.5.norm.weight": "model-00002-of-00002.safetensors",
504
+ "prediction_head.noisy_images_proj.weight": "model-00002-of-00002.safetensors",
505
+ "prediction_head.t_embedder.mlp.0.weight": "model-00002-of-00002.safetensors",
506
+ "prediction_head.t_embedder.mlp.2.weight": "model-00002-of-00002.safetensors",
507
+ "time_end_embed.weight": "model-00002-of-00002.safetensors",
508
+ "time_start_embed.weight": "model-00002-of-00002.safetensors"
509
+ }
510
+ }