Hugging Face's logo

mlx-community
/
VoxCPM2-bf16

Text-to-Speech
Safetensors
MLX
mlx-audio
voxcpm2
tts
voice-cloning
voice-design
Model card Files
xet
 Community
acul3 commited on
Commit
b140808
·
verified ·
1 Parent(s): de517cb

Upload model.safetensors.index.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. model.safetensors.index.json +827 -0
model.safetensors.index.json ADDED
@@ -0,0 +1,827 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 4955158672
4
+ },
5
+ "weight_map": {
6
+ "audio_vae.decoder._sr_boundaries": "model-00001.safetensors",
7
+ "audio_vae.decoder.blocks.layers.0.conv_t.bias": "model-00001.safetensors",
8
+ "audio_vae.decoder.blocks.layers.0.conv_t.weight": "model-00001.safetensors",
9
+ "audio_vae.decoder.blocks.layers.0.res1.conv1.bias": "model-00001.safetensors",
10
+ "audio_vae.decoder.blocks.layers.0.res1.conv1.weight": "model-00001.safetensors",
11
+ "audio_vae.decoder.blocks.layers.0.res1.conv2.bias": "model-00001.safetensors",
12
+ "audio_vae.decoder.blocks.layers.0.res1.conv2.weight": "model-00001.safetensors",
13
+ "audio_vae.decoder.blocks.layers.0.res1.snake1.alpha": "model-00001.safetensors",
14
+ "audio_vae.decoder.blocks.layers.0.res1.snake2.alpha": "model-00001.safetensors",
15
+ "audio_vae.decoder.blocks.layers.0.res2.conv1.bias": "model-00001.safetensors",
16
+ "audio_vae.decoder.blocks.layers.0.res2.conv1.weight": "model-00001.safetensors",
17
+ "audio_vae.decoder.blocks.layers.0.res2.conv2.bias": "model-00001.safetensors",
18
+ "audio_vae.decoder.blocks.layers.0.res2.conv2.weight": "model-00001.safetensors",
19
+ "audio_vae.decoder.blocks.layers.0.res2.snake1.alpha": "model-00001.safetensors",
20
+ "audio_vae.decoder.blocks.layers.0.res2.snake2.alpha": "model-00001.safetensors",
21
+ "audio_vae.decoder.blocks.layers.0.res3.conv1.bias": "model-00001.safetensors",
22
+ "audio_vae.decoder.blocks.layers.0.res3.conv1.weight": "model-00001.safetensors",
23
+ "audio_vae.decoder.blocks.layers.0.res3.conv2.bias": "model-00001.safetensors",
24
+ "audio_vae.decoder.blocks.layers.0.res3.conv2.weight": "model-00001.safetensors",
25
+ "audio_vae.decoder.blocks.layers.0.res3.snake1.alpha": "model-00001.safetensors",
26
+ "audio_vae.decoder.blocks.layers.0.res3.snake2.alpha": "model-00001.safetensors",
27
+ "audio_vae.decoder.blocks.layers.0.snake.alpha": "model-00001.safetensors",
28
+ "audio_vae.decoder.blocks.layers.1.conv_t.bias": "model-00001.safetensors",
29
+ "audio_vae.decoder.blocks.layers.1.conv_t.weight": "model-00001.safetensors",
30
+ "audio_vae.decoder.blocks.layers.1.res1.conv1.bias": "model-00001.safetensors",
31
+ "audio_vae.decoder.blocks.layers.1.res1.conv1.weight": "model-00001.safetensors",
32
+ "audio_vae.decoder.blocks.layers.1.res1.conv2.bias": "model-00001.safetensors",
33
+ "audio_vae.decoder.blocks.layers.1.res1.conv2.weight": "model-00001.safetensors",
34
+ "audio_vae.decoder.blocks.layers.1.res1.snake1.alpha": "model-00001.safetensors",
35
+ "audio_vae.decoder.blocks.layers.1.res1.snake2.alpha": "model-00001.safetensors",
36
+ "audio_vae.decoder.blocks.layers.1.res2.conv1.bias": "model-00001.safetensors",
37
+ "audio_vae.decoder.blocks.layers.1.res2.conv1.weight": "model-00001.safetensors",
38
+ "audio_vae.decoder.blocks.layers.1.res2.conv2.bias": "model-00001.safetensors",
39
+ "audio_vae.decoder.blocks.layers.1.res2.conv2.weight": "model-00001.safetensors",
40
+ "audio_vae.decoder.blocks.layers.1.res2.snake1.alpha": "model-00001.safetensors",
41
+ "audio_vae.decoder.blocks.layers.1.res2.snake2.alpha": "model-00001.safetensors",
42
+ "audio_vae.decoder.blocks.layers.1.res3.conv1.bias": "model-00001.safetensors",
43
+ "audio_vae.decoder.blocks.layers.1.res3.conv1.weight": "model-00001.safetensors",
44
+ "audio_vae.decoder.blocks.layers.1.res3.conv2.bias": "model-00001.safetensors",
45
+ "audio_vae.decoder.blocks.layers.1.res3.conv2.weight": "model-00001.safetensors",
46
+ "audio_vae.decoder.blocks.layers.1.res3.snake1.alpha": "model-00001.safetensors",
47
+ "audio_vae.decoder.blocks.layers.1.res3.snake2.alpha": "model-00001.safetensors",
48
+ "audio_vae.decoder.blocks.layers.1.snake.alpha": "model-00001.safetensors",
49
+ "audio_vae.decoder.blocks.layers.2.conv_t.bias": "model-00001.safetensors",
50
+ "audio_vae.decoder.blocks.layers.2.conv_t.weight": "model-00001.safetensors",
51
+ "audio_vae.decoder.blocks.layers.2.res1.conv1.bias": "model-00001.safetensors",
52
+ "audio_vae.decoder.blocks.layers.2.res1.conv1.weight": "model-00001.safetensors",
53
+ "audio_vae.decoder.blocks.layers.2.res1.conv2.bias": "model-00001.safetensors",
54
+ "audio_vae.decoder.blocks.layers.2.res1.conv2.weight": "model-00001.safetensors",
55
+ "audio_vae.decoder.blocks.layers.2.res1.snake1.alpha": "model-00001.safetensors",
56
+ "audio_vae.decoder.blocks.layers.2.res1.snake2.alpha": "model-00001.safetensors",
57
+ "audio_vae.decoder.blocks.layers.2.res2.conv1.bias": "model-00001.safetensors",
58
+ "audio_vae.decoder.blocks.layers.2.res2.conv1.weight": "model-00001.safetensors",
59
+ "audio_vae.decoder.blocks.layers.2.res2.conv2.bias": "model-00001.safetensors",
60
+ "audio_vae.decoder.blocks.layers.2.res2.conv2.weight": "model-00001.safetensors",
61
+ "audio_vae.decoder.blocks.layers.2.res2.snake1.alpha": "model-00001.safetensors",
62
+ "audio_vae.decoder.blocks.layers.2.res2.snake2.alpha": "model-00001.safetensors",
63
+ "audio_vae.decoder.blocks.layers.2.res3.conv1.bias": "model-00001.safetensors",
64
+ "audio_vae.decoder.blocks.layers.2.res3.conv1.weight": "model-00001.safetensors",
65
+ "audio_vae.decoder.blocks.layers.2.res3.conv2.bias": "model-00001.safetensors",
66
+ "audio_vae.decoder.blocks.layers.2.res3.conv2.weight": "model-00001.safetensors",
67
+ "audio_vae.decoder.blocks.layers.2.res3.snake1.alpha": "model-00001.safetensors",
68
+ "audio_vae.decoder.blocks.layers.2.res3.snake2.alpha": "model-00001.safetensors",
69
+ "audio_vae.decoder.blocks.layers.2.snake.alpha": "model-00001.safetensors",
70
+ "audio_vae.decoder.blocks.layers.3.conv_t.bias": "model-00001.safetensors",
71
+ "audio_vae.decoder.blocks.layers.3.conv_t.weight": "model-00001.safetensors",
72
+ "audio_vae.decoder.blocks.layers.3.res1.conv1.bias": "model-00001.safetensors",
73
+ "audio_vae.decoder.blocks.layers.3.res1.conv1.weight": "model-00001.safetensors",
74
+ "audio_vae.decoder.blocks.layers.3.res1.conv2.bias": "model-00001.safetensors",
75
+ "audio_vae.decoder.blocks.layers.3.res1.conv2.weight": "model-00001.safetensors",
76
+ "audio_vae.decoder.blocks.layers.3.res1.snake1.alpha": "model-00001.safetensors",
77
+ "audio_vae.decoder.blocks.layers.3.res1.snake2.alpha": "model-00001.safetensors",
78
+ "audio_vae.decoder.blocks.layers.3.res2.conv1.bias": "model-00001.safetensors",
79
+ "audio_vae.decoder.blocks.layers.3.res2.conv1.weight": "model-00001.safetensors",
80
+ "audio_vae.decoder.blocks.layers.3.res2.conv2.bias": "model-00001.safetensors",
81
+ "audio_vae.decoder.blocks.layers.3.res2.conv2.weight": "model-00001.safetensors",
82
+ "audio_vae.decoder.blocks.layers.3.res2.snake1.alpha": "model-00001.safetensors",
83
+ "audio_vae.decoder.blocks.layers.3.res2.snake2.alpha": "model-00001.safetensors",
84
+ "audio_vae.decoder.blocks.layers.3.res3.conv1.bias": "model-00001.safetensors",
85
+ "audio_vae.decoder.blocks.layers.3.res3.conv1.weight": "model-00001.safetensors",
86
+ "audio_vae.decoder.blocks.layers.3.res3.conv2.bias": "model-00001.safetensors",
87
+ "audio_vae.decoder.blocks.layers.3.res3.conv2.weight": "model-00001.safetensors",
88
+ "audio_vae.decoder.blocks.layers.3.res3.snake1.alpha": "model-00001.safetensors",
89
+ "audio_vae.decoder.blocks.layers.3.res3.snake2.alpha": "model-00001.safetensors",
90
+ "audio_vae.decoder.blocks.layers.3.snake.alpha": "model-00001.safetensors",
91
+ "audio_vae.decoder.blocks.layers.4.conv_t.bias": "model-00001.safetensors",
92
+ "audio_vae.decoder.blocks.layers.4.conv_t.weight": "model-00001.safetensors",
93
+ "audio_vae.decoder.blocks.layers.4.res1.conv1.bias": "model-00001.safetensors",
94
+ "audio_vae.decoder.blocks.layers.4.res1.conv1.weight": "model-00001.safetensors",
95
+ "audio_vae.decoder.blocks.layers.4.res1.conv2.bias": "model-00001.safetensors",
96
+ "audio_vae.decoder.blocks.layers.4.res1.conv2.weight": "model-00001.safetensors",
97
+ "audio_vae.decoder.blocks.layers.4.res1.snake1.alpha": "model-00001.safetensors",
98
+ "audio_vae.decoder.blocks.layers.4.res1.snake2.alpha": "model-00001.safetensors",
99
+ "audio_vae.decoder.blocks.layers.4.res2.conv1.bias": "model-00001.safetensors",
100
+ "audio_vae.decoder.blocks.layers.4.res2.conv1.weight": "model-00001.safetensors",
101
+ "audio_vae.decoder.blocks.layers.4.res2.conv2.bias": "model-00001.safetensors",
102
+ "audio_vae.decoder.blocks.layers.4.res2.conv2.weight": "model-00001.safetensors",
103
+ "audio_vae.decoder.blocks.layers.4.res2.snake1.alpha": "model-00001.safetensors",
104
+ "audio_vae.decoder.blocks.layers.4.res2.snake2.alpha": "model-00001.safetensors",
105
+ "audio_vae.decoder.blocks.layers.4.res3.conv1.bias": "model-00001.safetensors",
106
+ "audio_vae.decoder.blocks.layers.4.res3.conv1.weight": "model-00001.safetensors",
107
+ "audio_vae.decoder.blocks.layers.4.res3.conv2.bias": "model-00001.safetensors",
108
+ "audio_vae.decoder.blocks.layers.4.res3.conv2.weight": "model-00001.safetensors",
109
+ "audio_vae.decoder.blocks.layers.4.res3.snake1.alpha": "model-00001.safetensors",
110
+ "audio_vae.decoder.blocks.layers.4.res3.snake2.alpha": "model-00001.safetensors",
111
+ "audio_vae.decoder.blocks.layers.4.snake.alpha": "model-00001.safetensors",
112
+ "audio_vae.decoder.blocks.layers.5.conv_t.bias": "model-00001.safetensors",
113
+ "audio_vae.decoder.blocks.layers.5.conv_t.weight": "model-00001.safetensors",
114
+ "audio_vae.decoder.blocks.layers.5.res1.conv1.bias": "model-00001.safetensors",
115
+ "audio_vae.decoder.blocks.layers.5.res1.conv1.weight": "model-00001.safetensors",
116
+ "audio_vae.decoder.blocks.layers.5.res1.conv2.bias": "model-00001.safetensors",
117
+ "audio_vae.decoder.blocks.layers.5.res1.conv2.weight": "model-00001.safetensors",
118
+ "audio_vae.decoder.blocks.layers.5.res1.snake1.alpha": "model-00001.safetensors",
119
+ "audio_vae.decoder.blocks.layers.5.res1.snake2.alpha": "model-00001.safetensors",
120
+ "audio_vae.decoder.blocks.layers.5.res2.conv1.bias": "model-00001.safetensors",
121
+ "audio_vae.decoder.blocks.layers.5.res2.conv1.weight": "model-00001.safetensors",
122
+ "audio_vae.decoder.blocks.layers.5.res2.conv2.bias": "model-00001.safetensors",
123
+ "audio_vae.decoder.blocks.layers.5.res2.conv2.weight": "model-00001.safetensors",
124
+ "audio_vae.decoder.blocks.layers.5.res2.snake1.alpha": "model-00001.safetensors",
125
+ "audio_vae.decoder.blocks.layers.5.res2.snake2.alpha": "model-00001.safetensors",
126
+ "audio_vae.decoder.blocks.layers.5.res3.conv1.bias": "model-00001.safetensors",
127
+ "audio_vae.decoder.blocks.layers.5.res3.conv1.weight": "model-00001.safetensors",
128
+ "audio_vae.decoder.blocks.layers.5.res3.conv2.bias": "model-00001.safetensors",
129
+ "audio_vae.decoder.blocks.layers.5.res3.conv2.weight": "model-00001.safetensors",
130
+ "audio_vae.decoder.blocks.layers.5.res3.snake1.alpha": "model-00001.safetensors",
131
+ "audio_vae.decoder.blocks.layers.5.res3.snake2.alpha": "model-00001.safetensors",
132
+ "audio_vae.decoder.blocks.layers.5.snake.alpha": "model-00001.safetensors",
133
+ "audio_vae.decoder.conv_in.layers.0.bias": "model-00001.safetensors",
134
+ "audio_vae.decoder.conv_in.layers.0.weight": "model-00001.safetensors",
135
+ "audio_vae.decoder.conv_in.layers.1.bias": "model-00001.safetensors",
136
+ "audio_vae.decoder.conv_in.layers.1.weight": "model-00001.safetensors",
137
+ "audio_vae.decoder.conv_out.bias": "model-00001.safetensors",
138
+ "audio_vae.decoder.conv_out.weight": "model-00001.safetensors",
139
+ "audio_vae.decoder.snake_out.alpha": "model-00001.safetensors",
140
+ "audio_vae.decoder.sr_cond_layers.0.bias_embed.weight": "model-00001.safetensors",
141
+ "audio_vae.decoder.sr_cond_layers.0.scale_embed.weight": "model-00001.safetensors",
142
+ "audio_vae.decoder.sr_cond_layers.1.bias_embed.weight": "model-00001.safetensors",
143
+ "audio_vae.decoder.sr_cond_layers.1.scale_embed.weight": "model-00001.safetensors",
144
+ "audio_vae.decoder.sr_cond_layers.2.bias_embed.weight": "model-00001.safetensors",
145
+ "audio_vae.decoder.sr_cond_layers.2.scale_embed.weight": "model-00001.safetensors",
146
+ "audio_vae.decoder.sr_cond_layers.3.bias_embed.weight": "model-00001.safetensors",
147
+ "audio_vae.decoder.sr_cond_layers.3.scale_embed.weight": "model-00001.safetensors",
148
+ "audio_vae.decoder.sr_cond_layers.4.bias_embed.weight": "model-00001.safetensors",
149
+ "audio_vae.decoder.sr_cond_layers.4.scale_embed.weight": "model-00001.safetensors",
150
+ "audio_vae.decoder.sr_cond_layers.5.bias_embed.weight": "model-00001.safetensors",
151
+ "audio_vae.decoder.sr_cond_layers.5.scale_embed.weight": "model-00001.safetensors",
152
+ "audio_vae.encoder.blocks.layers.0.conv.bias": "model-00001.safetensors",
153
+ "audio_vae.encoder.blocks.layers.0.conv.weight": "model-00001.safetensors",
154
+ "audio_vae.encoder.blocks.layers.0.res1.conv1.bias": "model-00001.safetensors",
155
+ "audio_vae.encoder.blocks.layers.0.res1.conv1.weight": "model-00001.safetensors",
156
+ "audio_vae.encoder.blocks.layers.0.res1.conv2.bias": "model-00001.safetensors",
157
+ "audio_vae.encoder.blocks.layers.0.res1.conv2.weight": "model-00001.safetensors",
158
+ "audio_vae.encoder.blocks.layers.0.res1.snake1.alpha": "model-00001.safetensors",
159
+ "audio_vae.encoder.blocks.layers.0.res1.snake2.alpha": "model-00001.safetensors",
160
+ "audio_vae.encoder.blocks.layers.0.res2.conv1.bias": "model-00001.safetensors",
161
+ "audio_vae.encoder.blocks.layers.0.res2.conv1.weight": "model-00001.safetensors",
162
+ "audio_vae.encoder.blocks.layers.0.res2.conv2.bias": "model-00001.safetensors",
163
+ "audio_vae.encoder.blocks.layers.0.res2.conv2.weight": "model-00001.safetensors",
164
+ "audio_vae.encoder.blocks.layers.0.res2.snake1.alpha": "model-00001.safetensors",
165
+ "audio_vae.encoder.blocks.layers.0.res2.snake2.alpha": "model-00001.safetensors",
166
+ "audio_vae.encoder.blocks.layers.0.res3.conv1.bias": "model-00001.safetensors",
167
+ "audio_vae.encoder.blocks.layers.0.res3.conv1.weight": "model-00001.safetensors",
168
+ "audio_vae.encoder.blocks.layers.0.res3.conv2.bias": "model-00001.safetensors",
169
+ "audio_vae.encoder.blocks.layers.0.res3.conv2.weight": "model-00001.safetensors",
170
+ "audio_vae.encoder.blocks.layers.0.res3.snake1.alpha": "model-00001.safetensors",
171
+ "audio_vae.encoder.blocks.layers.0.res3.snake2.alpha": "model-00001.safetensors",
172
+ "audio_vae.encoder.blocks.layers.0.snake.alpha": "model-00001.safetensors",
173
+ "audio_vae.encoder.blocks.layers.1.conv.bias": "model-00001.safetensors",
174
+ "audio_vae.encoder.blocks.layers.1.conv.weight": "model-00001.safetensors",
175
+ "audio_vae.encoder.blocks.layers.1.res1.conv1.bias": "model-00001.safetensors",
176
+ "audio_vae.encoder.blocks.layers.1.res1.conv1.weight": "model-00001.safetensors",
177
+ "audio_vae.encoder.blocks.layers.1.res1.conv2.bias": "model-00001.safetensors",
178
+ "audio_vae.encoder.blocks.layers.1.res1.conv2.weight": "model-00001.safetensors",
179
+ "audio_vae.encoder.blocks.layers.1.res1.snake1.alpha": "model-00001.safetensors",
180
+ "audio_vae.encoder.blocks.layers.1.res1.snake2.alpha": "model-00001.safetensors",
181
+ "audio_vae.encoder.blocks.layers.1.res2.conv1.bias": "model-00001.safetensors",
182
+ "audio_vae.encoder.blocks.layers.1.res2.conv1.weight": "model-00001.safetensors",
183
+ "audio_vae.encoder.blocks.layers.1.res2.conv2.bias": "model-00001.safetensors",
184
+ "audio_vae.encoder.blocks.layers.1.res2.conv2.weight": "model-00001.safetensors",
185
+ "audio_vae.encoder.blocks.layers.1.res2.snake1.alpha": "model-00001.safetensors",
186
+ "audio_vae.encoder.blocks.layers.1.res2.snake2.alpha": "model-00001.safetensors",
187
+ "audio_vae.encoder.blocks.layers.1.res3.conv1.bias": "model-00001.safetensors",
188
+ "audio_vae.encoder.blocks.layers.1.res3.conv1.weight": "model-00001.safetensors",
189
+ "audio_vae.encoder.blocks.layers.1.res3.conv2.bias": "model-00001.safetensors",
190
+ "audio_vae.encoder.blocks.layers.1.res3.conv2.weight": "model-00001.safetensors",
191
+ "audio_vae.encoder.blocks.layers.1.res3.snake1.alpha": "model-00001.safetensors",
192
+ "audio_vae.encoder.blocks.layers.1.res3.snake2.alpha": "model-00001.safetensors",
193
+ "audio_vae.encoder.blocks.layers.1.snake.alpha": "model-00001.safetensors",
194
+ "audio_vae.encoder.blocks.layers.2.conv.bias": "model-00001.safetensors",
195
+ "audio_vae.encoder.blocks.layers.2.conv.weight": "model-00001.safetensors",
196
+ "audio_vae.encoder.blocks.layers.2.res1.conv1.bias": "model-00001.safetensors",
197
+ "audio_vae.encoder.blocks.layers.2.res1.conv1.weight": "model-00001.safetensors",
198
+ "audio_vae.encoder.blocks.layers.2.res1.conv2.bias": "model-00001.safetensors",
199
+ "audio_vae.encoder.blocks.layers.2.res1.conv2.weight": "model-00001.safetensors",
200
+ "audio_vae.encoder.blocks.layers.2.res1.snake1.alpha": "model-00001.safetensors",
201
+ "audio_vae.encoder.blocks.layers.2.res1.snake2.alpha": "model-00001.safetensors",
202
+ "audio_vae.encoder.blocks.layers.2.res2.conv1.bias": "model-00001.safetensors",
203
+ "audio_vae.encoder.blocks.layers.2.res2.conv1.weight": "model-00001.safetensors",
204
+ "audio_vae.encoder.blocks.layers.2.res2.conv2.bias": "model-00001.safetensors",
205
+ "audio_vae.encoder.blocks.layers.2.res2.conv2.weight": "model-00001.safetensors",
206
+ "audio_vae.encoder.blocks.layers.2.res2.snake1.alpha": "model-00001.safetensors",
207
+ "audio_vae.encoder.blocks.layers.2.res2.snake2.alpha": "model-00001.safetensors",
208
+ "audio_vae.encoder.blocks.layers.2.res3.conv1.bias": "model-00001.safetensors",
209
+ "audio_vae.encoder.blocks.layers.2.res3.conv1.weight": "model-00001.safetensors",
210
+ "audio_vae.encoder.blocks.layers.2.res3.conv2.bias": "model-00001.safetensors",
211
+ "audio_vae.encoder.blocks.layers.2.res3.conv2.weight": "model-00001.safetensors",
212
+ "audio_vae.encoder.blocks.layers.2.res3.snake1.alpha": "model-00001.safetensors",
213
+ "audio_vae.encoder.blocks.layers.2.res3.snake2.alpha": "model-00001.safetensors",
214
+ "audio_vae.encoder.blocks.layers.2.snake.alpha": "model-00001.safetensors",
215
+ "audio_vae.encoder.blocks.layers.3.conv.bias": "model-00001.safetensors",
216
+ "audio_vae.encoder.blocks.layers.3.conv.weight": "model-00001.safetensors",
217
+ "audio_vae.encoder.blocks.layers.3.res1.conv1.bias": "model-00001.safetensors",
218
+ "audio_vae.encoder.blocks.layers.3.res1.conv1.weight": "model-00001.safetensors",
219
+ "audio_vae.encoder.blocks.layers.3.res1.conv2.bias": "model-00001.safetensors",
220
+ "audio_vae.encoder.blocks.layers.3.res1.conv2.weight": "model-00001.safetensors",
221
+ "audio_vae.encoder.blocks.layers.3.res1.snake1.alpha": "model-00001.safetensors",
222
+ "audio_vae.encoder.blocks.layers.3.res1.snake2.alpha": "model-00001.safetensors",
223
+ "audio_vae.encoder.blocks.layers.3.res2.conv1.bias": "model-00001.safetensors",
224
+ "audio_vae.encoder.blocks.layers.3.res2.conv1.weight": "model-00001.safetensors",
225
+ "audio_vae.encoder.blocks.layers.3.res2.conv2.bias": "model-00001.safetensors",
226
+ "audio_vae.encoder.blocks.layers.3.res2.conv2.weight": "model-00001.safetensors",
227
+ "audio_vae.encoder.blocks.layers.3.res2.snake1.alpha": "model-00001.safetensors",
228
+ "audio_vae.encoder.blocks.layers.3.res2.snake2.alpha": "model-00001.safetensors",
229
+ "audio_vae.encoder.blocks.layers.3.res3.conv1.bias": "model-00001.safetensors",
230
+ "audio_vae.encoder.blocks.layers.3.res3.conv1.weight": "model-00001.safetensors",
231
+ "audio_vae.encoder.blocks.layers.3.res3.conv2.bias": "model-00001.safetensors",
232
+ "audio_vae.encoder.blocks.layers.3.res3.conv2.weight": "model-00001.safetensors",
233
+ "audio_vae.encoder.blocks.layers.3.res3.snake1.alpha": "model-00001.safetensors",
234
+ "audio_vae.encoder.blocks.layers.3.res3.snake2.alpha": "model-00001.safetensors",
235
+ "audio_vae.encoder.blocks.layers.3.snake.alpha": "model-00001.safetensors",
236
+ "audio_vae.encoder.conv_in.bias": "model-00001.safetensors",
237
+ "audio_vae.encoder.conv_in.weight": "model-00001.safetensors",
238
+ "audio_vae.encoder.fc_mu.bias": "model-00001.safetensors",
239
+ "audio_vae.encoder.fc_mu.weight": "model-00001.safetensors",
240
+ "base_lm.embed_tokens.weight": "model-00001.safetensors",
241
+ "base_lm.layers.0.input_layernorm.weight": "model-00001.safetensors",
242
+ "base_lm.layers.0.mlp.down_proj.weight": "model-00001.safetensors",
243
+ "base_lm.layers.0.mlp.gate_proj.weight": "model-00001.safetensors",
244
+ "base_lm.layers.0.mlp.up_proj.weight": "model-00001.safetensors",
245
+ "base_lm.layers.0.post_attention_layernorm.weight": "model-00001.safetensors",
246
+ "base_lm.layers.0.self_attn.k_proj.weight": "model-00001.safetensors",
247
+ "base_lm.layers.0.self_attn.o_proj.weight": "model-00001.safetensors",
248
+ "base_lm.layers.0.self_attn.q_proj.weight": "model-00001.safetensors",
249
+ "base_lm.layers.0.self_attn.v_proj.weight": "model-00001.safetensors",
250
+ "base_lm.layers.1.input_layernorm.weight": "model-00001.safetensors",
251
+ "base_lm.layers.1.mlp.down_proj.weight": "model-00001.safetensors",
252
+ "base_lm.layers.1.mlp.gate_proj.weight": "model-00001.safetensors",
253
+ "base_lm.layers.1.mlp.up_proj.weight": "model-00001.safetensors",
254
+ "base_lm.layers.1.post_attention_layernorm.weight": "model-00001.safetensors",
255
+ "base_lm.layers.1.self_attn.k_proj.weight": "model-00001.safetensors",
256
+ "base_lm.layers.1.self_attn.o_proj.weight": "model-00001.safetensors",
257
+ "base_lm.layers.1.self_attn.q_proj.weight": "model-00001.safetensors",
258
+ "base_lm.layers.1.self_attn.v_proj.weight": "model-00001.safetensors",
259
+ "base_lm.layers.10.input_layernorm.weight": "model-00001.safetensors",
260
+ "base_lm.layers.10.mlp.down_proj.weight": "model-00001.safetensors",
261
+ "base_lm.layers.10.mlp.gate_proj.weight": "model-00001.safetensors",
262
+ "base_lm.layers.10.mlp.up_proj.weight": "model-00001.safetensors",
263
+ "base_lm.layers.10.post_attention_layernorm.weight": "model-00001.safetensors",
264
+ "base_lm.layers.10.self_attn.k_proj.weight": "model-00001.safetensors",
265
+ "base_lm.layers.10.self_attn.o_proj.weight": "model-00001.safetensors",
266
+ "base_lm.layers.10.self_attn.q_proj.weight": "model-00001.safetensors",
267
+ "base_lm.layers.10.self_attn.v_proj.weight": "model-00001.safetensors",
268
+ "base_lm.layers.11.input_layernorm.weight": "model-00001.safetensors",
269
+ "base_lm.layers.11.mlp.down_proj.weight": "model-00001.safetensors",
270
+ "base_lm.layers.11.mlp.gate_proj.weight": "model-00001.safetensors",
271
+ "base_lm.layers.11.mlp.up_proj.weight": "model-00001.safetensors",
272
+ "base_lm.layers.11.post_attention_layernorm.weight": "model-00001.safetensors",
273
+ "base_lm.layers.11.self_attn.k_proj.weight": "model-00001.safetensors",
274
+ "base_lm.layers.11.self_attn.o_proj.weight": "model-00001.safetensors",
275
+ "base_lm.layers.11.self_attn.q_proj.weight": "model-00001.safetensors",
276
+ "base_lm.layers.11.self_attn.v_proj.weight": "model-00001.safetensors",
277
+ "base_lm.layers.12.input_layernorm.weight": "model-00001.safetensors",
278
+ "base_lm.layers.12.mlp.down_proj.weight": "model-00001.safetensors",
279
+ "base_lm.layers.12.mlp.gate_proj.weight": "model-00001.safetensors",
280
+ "base_lm.layers.12.mlp.up_proj.weight": "model-00001.safetensors",
281
+ "base_lm.layers.12.post_attention_layernorm.weight": "model-00001.safetensors",
282
+ "base_lm.layers.12.self_attn.k_proj.weight": "model-00001.safetensors",
283
+ "base_lm.layers.12.self_attn.o_proj.weight": "model-00001.safetensors",
284
+ "base_lm.layers.12.self_attn.q_proj.weight": "model-00001.safetensors",
285
+ "base_lm.layers.12.self_attn.v_proj.weight": "model-00001.safetensors",
286
+ "base_lm.layers.13.input_layernorm.weight": "model-00001.safetensors",
287
+ "base_lm.layers.13.mlp.down_proj.weight": "model-00001.safetensors",
288
+ "base_lm.layers.13.mlp.gate_proj.weight": "model-00001.safetensors",
289
+ "base_lm.layers.13.mlp.up_proj.weight": "model-00001.safetensors",
290
+ "base_lm.layers.13.post_attention_layernorm.weight": "model-00001.safetensors",
291
+ "base_lm.layers.13.self_attn.k_proj.weight": "model-00001.safetensors",
292
+ "base_lm.layers.13.self_attn.o_proj.weight": "model-00001.safetensors",
293
+ "base_lm.layers.13.self_attn.q_proj.weight": "model-00001.safetensors",
294
+ "base_lm.layers.13.self_attn.v_proj.weight": "model-00001.safetensors",
295
+ "base_lm.layers.14.input_layernorm.weight": "model-00001.safetensors",
296
+ "base_lm.layers.14.mlp.down_proj.weight": "model-00001.safetensors",
297
+ "base_lm.layers.14.mlp.gate_proj.weight": "model-00001.safetensors",
298
+ "base_lm.layers.14.mlp.up_proj.weight": "model-00001.safetensors",
299
+ "base_lm.layers.14.post_attention_layernorm.weight": "model-00001.safetensors",
300
+ "base_lm.layers.14.self_attn.k_proj.weight": "model-00001.safetensors",
301
+ "base_lm.layers.14.self_attn.o_proj.weight": "model-00001.safetensors",
302
+ "base_lm.layers.14.self_attn.q_proj.weight": "model-00001.safetensors",
303
+ "base_lm.layers.14.self_attn.v_proj.weight": "model-00001.safetensors",
304
+ "base_lm.layers.15.input_layernorm.weight": "model-00001.safetensors",
305
+ "base_lm.layers.15.mlp.down_proj.weight": "model-00001.safetensors",
306
+ "base_lm.layers.15.mlp.gate_proj.weight": "model-00001.safetensors",
307
+ "base_lm.layers.15.mlp.up_proj.weight": "model-00001.safetensors",
308
+ "base_lm.layers.15.post_attention_layernorm.weight": "model-00001.safetensors",
309
+ "base_lm.layers.15.self_attn.k_proj.weight": "model-00001.safetensors",
310
+ "base_lm.layers.15.self_attn.o_proj.weight": "model-00001.safetensors",
311
+ "base_lm.layers.15.self_attn.q_proj.weight": "model-00001.safetensors",
312
+ "base_lm.layers.15.self_attn.v_proj.weight": "model-00001.safetensors",
313
+ "base_lm.layers.16.input_layernorm.weight": "model-00001.safetensors",
314
+ "base_lm.layers.16.mlp.down_proj.weight": "model-00001.safetensors",
315
+ "base_lm.layers.16.mlp.gate_proj.weight": "model-00001.safetensors",
316
+ "base_lm.layers.16.mlp.up_proj.weight": "model-00001.safetensors",
317
+ "base_lm.layers.16.post_attention_layernorm.weight": "model-00001.safetensors",
318
+ "base_lm.layers.16.self_attn.k_proj.weight": "model-00001.safetensors",
319
+ "base_lm.layers.16.self_attn.o_proj.weight": "model-00001.safetensors",
320
+ "base_lm.layers.16.self_attn.q_proj.weight": "model-00001.safetensors",
321
+ "base_lm.layers.16.self_attn.v_proj.weight": "model-00001.safetensors",
322
+ "base_lm.layers.17.input_layernorm.weight": "model-00001.safetensors",
323
+ "base_lm.layers.17.mlp.down_proj.weight": "model-00001.safetensors",
324
+ "base_lm.layers.17.mlp.gate_proj.weight": "model-00001.safetensors",
325
+ "base_lm.layers.17.mlp.up_proj.weight": "model-00001.safetensors",
326
+ "base_lm.layers.17.post_attention_layernorm.weight": "model-00001.safetensors",
327
+ "base_lm.layers.17.self_attn.k_proj.weight": "model-00001.safetensors",
328
+ "base_lm.layers.17.self_attn.o_proj.weight": "model-00001.safetensors",
329
+ "base_lm.layers.17.self_attn.q_proj.weight": "model-00001.safetensors",
330
+ "base_lm.layers.17.self_attn.v_proj.weight": "model-00001.safetensors",
331
+ "base_lm.layers.18.input_layernorm.weight": "model-00001.safetensors",
332
+ "base_lm.layers.18.mlp.down_proj.weight": "model-00001.safetensors",
333
+ "base_lm.layers.18.mlp.gate_proj.weight": "model-00001.safetensors",
334
+ "base_lm.layers.18.mlp.up_proj.weight": "model-00001.safetensors",
335
+ "base_lm.layers.18.post_attention_layernorm.weight": "model-00001.safetensors",
336
+ "base_lm.layers.18.self_attn.k_proj.weight": "model-00001.safetensors",
337
+ "base_lm.layers.18.self_attn.o_proj.weight": "model-00001.safetensors",
338
+ "base_lm.layers.18.self_attn.q_proj.weight": "model-00001.safetensors",
339
+ "base_lm.layers.18.self_attn.v_proj.weight": "model-00001.safetensors",
340
+ "base_lm.layers.19.input_layernorm.weight": "model-00001.safetensors",
341
+ "base_lm.layers.19.mlp.down_proj.weight": "model-00001.safetensors",
342
+ "base_lm.layers.19.mlp.gate_proj.weight": "model-00001.safetensors",
343
+ "base_lm.layers.19.mlp.up_proj.weight": "model-00001.safetensors",
344
+ "base_lm.layers.19.post_attention_layernorm.weight": "model-00001.safetensors",
345
+ "base_lm.layers.19.self_attn.k_proj.weight": "model-00001.safetensors",
346
+ "base_lm.layers.19.self_attn.o_proj.weight": "model-00001.safetensors",
347
+ "base_lm.layers.19.self_attn.q_proj.weight": "model-00001.safetensors",
348
+ "base_lm.layers.19.self_attn.v_proj.weight": "model-00001.safetensors",
349
+ "base_lm.layers.2.input_layernorm.weight": "model-00001.safetensors",
350
+ "base_lm.layers.2.mlp.down_proj.weight": "model-00001.safetensors",
351
+ "base_lm.layers.2.mlp.gate_proj.weight": "model-00001.safetensors",
352
+ "base_lm.layers.2.mlp.up_proj.weight": "model-00001.safetensors",
353
+ "base_lm.layers.2.post_attention_layernorm.weight": "model-00001.safetensors",
354
+ "base_lm.layers.2.self_attn.k_proj.weight": "model-00001.safetensors",
355
+ "base_lm.layers.2.self_attn.o_proj.weight": "model-00001.safetensors",
356
+ "base_lm.layers.2.self_attn.q_proj.weight": "model-00001.safetensors",
357
+ "base_lm.layers.2.self_attn.v_proj.weight": "model-00001.safetensors",
358
+ "base_lm.layers.20.input_layernorm.weight": "model-00001.safetensors",
359
+ "base_lm.layers.20.mlp.down_proj.weight": "model-00001.safetensors",
360
+ "base_lm.layers.20.mlp.gate_proj.weight": "model-00001.safetensors",
361
+ "base_lm.layers.20.mlp.up_proj.weight": "model-00001.safetensors",
362
+ "base_lm.layers.20.post_attention_layernorm.weight": "model-00001.safetensors",
363
+ "base_lm.layers.20.self_attn.k_proj.weight": "model-00001.safetensors",
364
+ "base_lm.layers.20.self_attn.o_proj.weight": "model-00001.safetensors",
365
+ "base_lm.layers.20.self_attn.q_proj.weight": "model-00001.safetensors",
366
+ "base_lm.layers.20.self_attn.v_proj.weight": "model-00001.safetensors",
367
+ "base_lm.layers.21.input_layernorm.weight": "model-00001.safetensors",
368
+ "base_lm.layers.21.mlp.down_proj.weight": "model-00001.safetensors",
369
+ "base_lm.layers.21.mlp.gate_proj.weight": "model-00001.safetensors",
370
+ "base_lm.layers.21.mlp.up_proj.weight": "model-00001.safetensors",
371
+ "base_lm.layers.21.post_attention_layernorm.weight": "model-00001.safetensors",
372
+ "base_lm.layers.21.self_attn.k_proj.weight": "model-00001.safetensors",
373
+ "base_lm.layers.21.self_attn.o_proj.weight": "model-00001.safetensors",
374
+ "base_lm.layers.21.self_attn.q_proj.weight": "model-00001.safetensors",
375
+ "base_lm.layers.21.self_attn.v_proj.weight": "model-00001.safetensors",
376
+ "base_lm.layers.22.input_layernorm.weight": "model-00001.safetensors",
377
+ "base_lm.layers.22.mlp.down_proj.weight": "model-00001.safetensors",
378
+ "base_lm.layers.22.mlp.gate_proj.weight": "model-00001.safetensors",
379
+ "base_lm.layers.22.mlp.up_proj.weight": "model-00001.safetensors",
380
+ "base_lm.layers.22.post_attention_layernorm.weight": "model-00001.safetensors",
381
+ "base_lm.layers.22.self_attn.k_proj.weight": "model-00001.safetensors",
382
+ "base_lm.layers.22.self_attn.o_proj.weight": "model-00001.safetensors",
383
+ "base_lm.layers.22.self_attn.q_proj.weight": "model-00001.safetensors",
384
+ "base_lm.layers.22.self_attn.v_proj.weight": "model-00001.safetensors",
385
+ "base_lm.layers.23.input_layernorm.weight": "model-00001.safetensors",
386
+ "base_lm.layers.23.mlp.down_proj.weight": "model-00001.safetensors",
387
+ "base_lm.layers.23.mlp.gate_proj.weight": "model-00001.safetensors",
388
+ "base_lm.layers.23.mlp.up_proj.weight": "model-00001.safetensors",
389
+ "base_lm.layers.23.post_attention_layernorm.weight": "model-00001.safetensors",
390
+ "base_lm.layers.23.self_attn.k_proj.weight": "model-00001.safetensors",
391
+ "base_lm.layers.23.self_attn.o_proj.weight": "model-00001.safetensors",
392
+ "base_lm.layers.23.self_attn.q_proj.weight": "model-00001.safetensors",
393
+ "base_lm.layers.23.self_attn.v_proj.weight": "model-00001.safetensors",
394
+ "base_lm.layers.24.input_layernorm.weight": "model-00001.safetensors",
395
+ "base_lm.layers.24.mlp.down_proj.weight": "model-00001.safetensors",
396
+ "base_lm.layers.24.mlp.gate_proj.weight": "model-00001.safetensors",
397
+ "base_lm.layers.24.mlp.up_proj.weight": "model-00001.safetensors",
398
+ "base_lm.layers.24.post_attention_layernorm.weight": "model-00001.safetensors",
399
+ "base_lm.layers.24.self_attn.k_proj.weight": "model-00001.safetensors",
400
+ "base_lm.layers.24.self_attn.o_proj.weight": "model-00001.safetensors",
401
+ "base_lm.layers.24.self_attn.q_proj.weight": "model-00001.safetensors",
402
+ "base_lm.layers.24.self_attn.v_proj.weight": "model-00001.safetensors",
403
+ "base_lm.layers.25.input_layernorm.weight": "model-00001.safetensors",
404
+ "base_lm.layers.25.mlp.down_proj.weight": "model-00001.safetensors",
405
+ "base_lm.layers.25.mlp.gate_proj.weight": "model-00001.safetensors",
406
+ "base_lm.layers.25.mlp.up_proj.weight": "model-00001.safetensors",
407
+ "base_lm.layers.25.post_attention_layernorm.weight": "model-00001.safetensors",
408
+ "base_lm.layers.25.self_attn.k_proj.weight": "model-00001.safetensors",
409
+ "base_lm.layers.25.self_attn.o_proj.weight": "model-00001.safetensors",
410
+ "base_lm.layers.25.self_attn.q_proj.weight": "model-00001.safetensors",
411
+ "base_lm.layers.25.self_attn.v_proj.weight": "model-00001.safetensors",
412
+ "base_lm.layers.26.input_layernorm.weight": "model-00001.safetensors",
413
+ "base_lm.layers.26.mlp.down_proj.weight": "model-00001.safetensors",
414
+ "base_lm.layers.26.mlp.gate_proj.weight": "model-00001.safetensors",
415
+ "base_lm.layers.26.mlp.up_proj.weight": "model-00001.safetensors",
416
+ "base_lm.layers.26.post_attention_layernorm.weight": "model-00001.safetensors",
417
+ "base_lm.layers.26.self_attn.k_proj.weight": "model-00001.safetensors",
418
+ "base_lm.layers.26.self_attn.o_proj.weight": "model-00001.safetensors",
419
+ "base_lm.layers.26.self_attn.q_proj.weight": "model-00001.safetensors",
420
+ "base_lm.layers.26.self_attn.v_proj.weight": "model-00001.safetensors",
421
+ "base_lm.layers.27.input_layernorm.weight": "model-00001.safetensors",
422
+ "base_lm.layers.27.mlp.down_proj.weight": "model-00001.safetensors",
423
+ "base_lm.layers.27.mlp.gate_proj.weight": "model-00001.safetensors",
424
+ "base_lm.layers.27.mlp.up_proj.weight": "model-00001.safetensors",
425
+ "base_lm.layers.27.post_attention_layernorm.weight": "model-00001.safetensors",
426
+ "base_lm.layers.27.self_attn.k_proj.weight": "model-00001.safetensors",
427
+ "base_lm.layers.27.self_attn.o_proj.weight": "model-00001.safetensors",
428
+ "base_lm.layers.27.self_attn.q_proj.weight": "model-00001.safetensors",
429
+ "base_lm.layers.27.self_attn.v_proj.weight": "model-00001.safetensors",
430
+ "base_lm.layers.3.input_layernorm.weight": "model-00001.safetensors",
431
+ "base_lm.layers.3.mlp.down_proj.weight": "model-00001.safetensors",
432
+ "base_lm.layers.3.mlp.gate_proj.weight": "model-00001.safetensors",
433
+ "base_lm.layers.3.mlp.up_proj.weight": "model-00001.safetensors",
434
+ "base_lm.layers.3.post_attention_layernorm.weight": "model-00001.safetensors",
435
+ "base_lm.layers.3.self_attn.k_proj.weight": "model-00001.safetensors",
436
+ "base_lm.layers.3.self_attn.o_proj.weight": "model-00001.safetensors",
437
+ "base_lm.layers.3.self_attn.q_proj.weight": "model-00001.safetensors",
438
+ "base_lm.layers.3.self_attn.v_proj.weight": "model-00001.safetensors",
439
+ "base_lm.layers.4.input_layernorm.weight": "model-00001.safetensors",
440
+ "base_lm.layers.4.mlp.down_proj.weight": "model-00001.safetensors",
441
+ "base_lm.layers.4.mlp.gate_proj.weight": "model-00001.safetensors",
442
+ "base_lm.layers.4.mlp.up_proj.weight": "model-00001.safetensors",
443
+ "base_lm.layers.4.post_attention_layernorm.weight": "model-00001.safetensors",
444
+ "base_lm.layers.4.self_attn.k_proj.weight": "model-00001.safetensors",
445
+ "base_lm.layers.4.self_attn.o_proj.weight": "model-00001.safetensors",
446
+ "base_lm.layers.4.self_attn.q_proj.weight": "model-00001.safetensors",
447
+ "base_lm.layers.4.self_attn.v_proj.weight": "model-00001.safetensors",
448
+ "base_lm.layers.5.input_layernorm.weight": "model-00001.safetensors",
449
+ "base_lm.layers.5.mlp.down_proj.weight": "model-00001.safetensors",
450
+ "base_lm.layers.5.mlp.gate_proj.weight": "model-00001.safetensors",
451
+ "base_lm.layers.5.mlp.up_proj.weight": "model-00001.safetensors",
452
+ "base_lm.layers.5.post_attention_layernorm.weight": "model-00001.safetensors",
453
+ "base_lm.layers.5.self_attn.k_proj.weight": "model-00001.safetensors",
454
+ "base_lm.layers.5.self_attn.o_proj.weight": "model-00001.safetensors",
455
+ "base_lm.layers.5.self_attn.q_proj.weight": "model-00001.safetensors",
456
+ "base_lm.layers.5.self_attn.v_proj.weight": "model-00001.safetensors",
457
+ "base_lm.layers.6.input_layernorm.weight": "model-00001.safetensors",
458
+ "base_lm.layers.6.mlp.down_proj.weight": "model-00001.safetensors",
459
+ "base_lm.layers.6.mlp.gate_proj.weight": "model-00001.safetensors",
460
+ "base_lm.layers.6.mlp.up_proj.weight": "model-00001.safetensors",
461
+ "base_lm.layers.6.post_attention_layernorm.weight": "model-00001.safetensors",
462
+ "base_lm.layers.6.self_attn.k_proj.weight": "model-00001.safetensors",
463
+ "base_lm.layers.6.self_attn.o_proj.weight": "model-00001.safetensors",
464
+ "base_lm.layers.6.self_attn.q_proj.weight": "model-00001.safetensors",
465
+ "base_lm.layers.6.self_attn.v_proj.weight": "model-00001.safetensors",
466
+ "base_lm.layers.7.input_layernorm.weight": "model-00001.safetensors",
467
+ "base_lm.layers.7.mlp.down_proj.weight": "model-00001.safetensors",
468
+ "base_lm.layers.7.mlp.gate_proj.weight": "model-00001.safetensors",
469
+ "base_lm.layers.7.mlp.up_proj.weight": "model-00001.safetensors",
470
+ "base_lm.layers.7.post_attention_layernorm.weight": "model-00001.safetensors",
471
+ "base_lm.layers.7.self_attn.k_proj.weight": "model-00001.safetensors",
472
+ "base_lm.layers.7.self_attn.o_proj.weight": "model-00001.safetensors",
473
+ "base_lm.layers.7.self_attn.q_proj.weight": "model-00001.safetensors",
474
+ "base_lm.layers.7.self_attn.v_proj.weight": "model-00001.safetensors",
475
+ "base_lm.layers.8.input_layernorm.weight": "model-00001.safetensors",
476
+ "base_lm.layers.8.mlp.down_proj.weight": "model-00001.safetensors",
477
+ "base_lm.layers.8.mlp.gate_proj.weight": "model-00001.safetensors",
478
+ "base_lm.layers.8.mlp.up_proj.weight": "model-00001.safetensors",
479
+ "base_lm.layers.8.post_attention_layernorm.weight": "model-00001.safetensors",
480
+ "base_lm.layers.8.self_attn.k_proj.weight": "model-00001.safetensors",
481
+ "base_lm.layers.8.self_attn.o_proj.weight": "model-00001.safetensors",
482
+ "base_lm.layers.8.self_attn.q_proj.weight": "model-00001.safetensors",
483
+ "base_lm.layers.8.self_attn.v_proj.weight": "model-00001.safetensors",
484
+ "base_lm.layers.9.input_layernorm.weight": "model-00001.safetensors",
485
+ "base_lm.layers.9.mlp.down_proj.weight": "model-00001.safetensors",
486
+ "base_lm.layers.9.mlp.gate_proj.weight": "model-00001.safetensors",
487
+ "base_lm.layers.9.mlp.up_proj.weight": "model-00001.safetensors",
488
+ "base_lm.layers.9.post_attention_layernorm.weight": "model-00001.safetensors",
489
+ "base_lm.layers.9.self_attn.k_proj.weight": "model-00001.safetensors",
490
+ "base_lm.layers.9.self_attn.o_proj.weight": "model-00001.safetensors",
491
+ "base_lm.layers.9.self_attn.q_proj.weight": "model-00001.safetensors",
492
+ "base_lm.layers.9.self_attn.v_proj.weight": "model-00001.safetensors",
493
+ "base_lm.norm.weight": "model-00001.safetensors",
494
+ "base_lm.rope.inv_freq": "model-00001.safetensors",
495
+ "base_lm.rope.long_factor": "model-00001.safetensors",
496
+ "base_lm.rope.short_factor": "model-00001.safetensors",
497
+ "enc_to_lm_proj.bias": "model-00001.safetensors",
498
+ "enc_to_lm_proj.weight": "model-00001.safetensors",
499
+ "feat_decoder.estimator.cond_proj.bias": "model-00001.safetensors",
500
+ "feat_decoder.estimator.cond_proj.weight": "model-00001.safetensors",
501
+ "feat_decoder.estimator.decoder.layers.0.input_layernorm.weight": "model-00001.safetensors",
502
+ "feat_decoder.estimator.decoder.layers.0.mlp.down_proj.weight": "model-00001.safetensors",
503
+ "feat_decoder.estimator.decoder.layers.0.mlp.gate_proj.weight": "model-00001.safetensors",
504
+ "feat_decoder.estimator.decoder.layers.0.mlp.up_proj.weight": "model-00001.safetensors",
505
+ "feat_decoder.estimator.decoder.layers.0.post_attention_layernorm.weight": "model-00001.safetensors",
506
+ "feat_decoder.estimator.decoder.layers.0.self_attn.k_proj.weight": "model-00001.safetensors",
507
+ "feat_decoder.estimator.decoder.layers.0.self_attn.o_proj.weight": "model-00001.safetensors",
508
+ "feat_decoder.estimator.decoder.layers.0.self_attn.q_proj.weight": "model-00001.safetensors",
509
+ "feat_decoder.estimator.decoder.layers.0.self_attn.v_proj.weight": "model-00001.safetensors",
510
+ "feat_decoder.estimator.decoder.layers.1.input_layernorm.weight": "model-00001.safetensors",
511
+ "feat_decoder.estimator.decoder.layers.1.mlp.down_proj.weight": "model-00001.safetensors",
512
+ "feat_decoder.estimator.decoder.layers.1.mlp.gate_proj.weight": "model-00001.safetensors",
513
+ "feat_decoder.estimator.decoder.layers.1.mlp.up_proj.weight": "model-00001.safetensors",
514
+ "feat_decoder.estimator.decoder.layers.1.post_attention_layernorm.weight": "model-00001.safetensors",
515
+ "feat_decoder.estimator.decoder.layers.1.self_attn.k_proj.weight": "model-00001.safetensors",
516
+ "feat_decoder.estimator.decoder.layers.1.self_attn.o_proj.weight": "model-00001.safetensors",
517
+ "feat_decoder.estimator.decoder.layers.1.self_attn.q_proj.weight": "model-00001.safetensors",
518
+ "feat_decoder.estimator.decoder.layers.1.self_attn.v_proj.weight": "model-00001.safetensors",
519
+ "feat_decoder.estimator.decoder.layers.10.input_layernorm.weight": "model-00001.safetensors",
520
+ "feat_decoder.estimator.decoder.layers.10.mlp.down_proj.weight": "model-00001.safetensors",
521
+ "feat_decoder.estimator.decoder.layers.10.mlp.gate_proj.weight": "model-00001.safetensors",
522
+ "feat_decoder.estimator.decoder.layers.10.mlp.up_proj.weight": "model-00001.safetensors",
523
+ "feat_decoder.estimator.decoder.layers.10.post_attention_layernorm.weight": "model-00001.safetensors",
524
+ "feat_decoder.estimator.decoder.layers.10.self_attn.k_proj.weight": "model-00001.safetensors",
525
+ "feat_decoder.estimator.decoder.layers.10.self_attn.o_proj.weight": "model-00001.safetensors",
526
+ "feat_decoder.estimator.decoder.layers.10.self_attn.q_proj.weight": "model-00001.safetensors",
527
+ "feat_decoder.estimator.decoder.layers.10.self_attn.v_proj.weight": "model-00001.safetensors",
528
+ "feat_decoder.estimator.decoder.layers.11.input_layernorm.weight": "model-00001.safetensors",
529
+ "feat_decoder.estimator.decoder.layers.11.mlp.down_proj.weight": "model-00001.safetensors",
530
+ "feat_decoder.estimator.decoder.layers.11.mlp.gate_proj.weight": "model-00001.safetensors",
531
+ "feat_decoder.estimator.decoder.layers.11.mlp.up_proj.weight": "model-00001.safetensors",
532
+ "feat_decoder.estimator.decoder.layers.11.post_attention_layernorm.weight": "model-00001.safetensors",
533
+ "feat_decoder.estimator.decoder.layers.11.self_attn.k_proj.weight": "model-00001.safetensors",
534
+ "feat_decoder.estimator.decoder.layers.11.self_attn.o_proj.weight": "model-00001.safetensors",
535
+ "feat_decoder.estimator.decoder.layers.11.self_attn.q_proj.weight": "model-00001.safetensors",
536
+ "feat_decoder.estimator.decoder.layers.11.self_attn.v_proj.weight": "model-00001.safetensors",
537
+ "feat_decoder.estimator.decoder.layers.2.input_layernorm.weight": "model-00001.safetensors",
538
+ "feat_decoder.estimator.decoder.layers.2.mlp.down_proj.weight": "model-00001.safetensors",
539
+ "feat_decoder.estimator.decoder.layers.2.mlp.gate_proj.weight": "model-00001.safetensors",
540
+ "feat_decoder.estimator.decoder.layers.2.mlp.up_proj.weight": "model-00001.safetensors",
541
+ "feat_decoder.estimator.decoder.layers.2.post_attention_layernorm.weight": "model-00001.safetensors",
542
+ "feat_decoder.estimator.decoder.layers.2.self_attn.k_proj.weight": "model-00001.safetensors",
543
+ "feat_decoder.estimator.decoder.layers.2.self_attn.o_proj.weight": "model-00001.safetensors",
544
+ "feat_decoder.estimator.decoder.layers.2.self_attn.q_proj.weight": "model-00001.safetensors",
545
+ "feat_decoder.estimator.decoder.layers.2.self_attn.v_proj.weight": "model-00001.safetensors",
546
+ "feat_decoder.estimator.decoder.layers.3.input_layernorm.weight": "model-00001.safetensors",
547
+ "feat_decoder.estimator.decoder.layers.3.mlp.down_proj.weight": "model-00001.safetensors",
548
+ "feat_decoder.estimator.decoder.layers.3.mlp.gate_proj.weight": "model-00001.safetensors",
549
+ "feat_decoder.estimator.decoder.layers.3.mlp.up_proj.weight": "model-00001.safetensors",
550
+ "feat_decoder.estimator.decoder.layers.3.post_attention_layernorm.weight": "model-00001.safetensors",
551
+ "feat_decoder.estimator.decoder.layers.3.self_attn.k_proj.weight": "model-00001.safetensors",
552
+ "feat_decoder.estimator.decoder.layers.3.self_attn.o_proj.weight": "model-00001.safetensors",
553
+ "feat_decoder.estimator.decoder.layers.3.self_attn.q_proj.weight": "model-00001.safetensors",
554
+ "feat_decoder.estimator.decoder.layers.3.self_attn.v_proj.weight": "model-00001.safetensors",
555
+ "feat_decoder.estimator.decoder.layers.4.input_layernorm.weight": "model-00001.safetensors",
556
+ "feat_decoder.estimator.decoder.layers.4.mlp.down_proj.weight": "model-00001.safetensors",
557
+ "feat_decoder.estimator.decoder.layers.4.mlp.gate_proj.weight": "model-00001.safetensors",
558
+ "feat_decoder.estimator.decoder.layers.4.mlp.up_proj.weight": "model-00001.safetensors",
559
+ "feat_decoder.estimator.decoder.layers.4.post_attention_layernorm.weight": "model-00001.safetensors",
560
+ "feat_decoder.estimator.decoder.layers.4.self_attn.k_proj.weight": "model-00001.safetensors",
561
+ "feat_decoder.estimator.decoder.layers.4.self_attn.o_proj.weight": "model-00001.safetensors",
562
+ "feat_decoder.estimator.decoder.layers.4.self_attn.q_proj.weight": "model-00001.safetensors",
563
+ "feat_decoder.estimator.decoder.layers.4.self_attn.v_proj.weight": "model-00001.safetensors",
564
+ "feat_decoder.estimator.decoder.layers.5.input_layernorm.weight": "model-00001.safetensors",
565
+ "feat_decoder.estimator.decoder.layers.5.mlp.down_proj.weight": "model-00001.safetensors",
566
+ "feat_decoder.estimator.decoder.layers.5.mlp.gate_proj.weight": "model-00001.safetensors",
567
+ "feat_decoder.estimator.decoder.layers.5.mlp.up_proj.weight": "model-00001.safetensors",
568
+ "feat_decoder.estimator.decoder.layers.5.post_attention_layernorm.weight": "model-00001.safetensors",
569
+ "feat_decoder.estimator.decoder.layers.5.self_attn.k_proj.weight": "model-00001.safetensors",
570
+ "feat_decoder.estimator.decoder.layers.5.self_attn.o_proj.weight": "model-00001.safetensors",
571
+ "feat_decoder.estimator.decoder.layers.5.self_attn.q_proj.weight": "model-00001.safetensors",
572
+ "feat_decoder.estimator.decoder.layers.5.self_attn.v_proj.weight": "model-00001.safetensors",
573
+ "feat_decoder.estimator.decoder.layers.6.input_layernorm.weight": "model-00001.safetensors",
574
+ "feat_decoder.estimator.decoder.layers.6.mlp.down_proj.weight": "model-00001.safetensors",
575
+ "feat_decoder.estimator.decoder.layers.6.mlp.gate_proj.weight": "model-00001.safetensors",
576
+ "feat_decoder.estimator.decoder.layers.6.mlp.up_proj.weight": "model-00001.safetensors",
577
+ "feat_decoder.estimator.decoder.layers.6.post_attention_layernorm.weight": "model-00001.safetensors",
578
+ "feat_decoder.estimator.decoder.layers.6.self_attn.k_proj.weight": "model-00001.safetensors",
579
+ "feat_decoder.estimator.decoder.layers.6.self_attn.o_proj.weight": "model-00001.safetensors",
580
+ "feat_decoder.estimator.decoder.layers.6.self_attn.q_proj.weight": "model-00001.safetensors",
581
+ "feat_decoder.estimator.decoder.layers.6.self_attn.v_proj.weight": "model-00001.safetensors",
582
+ "feat_decoder.estimator.decoder.layers.7.input_layernorm.weight": "model-00001.safetensors",
583
+ "feat_decoder.estimator.decoder.layers.7.mlp.down_proj.weight": "model-00001.safetensors",
584
+ "feat_decoder.estimator.decoder.layers.7.mlp.gate_proj.weight": "model-00001.safetensors",
585
+ "feat_decoder.estimator.decoder.layers.7.mlp.up_proj.weight": "model-00001.safetensors",
586
+ "feat_decoder.estimator.decoder.layers.7.post_attention_layernorm.weight": "model-00001.safetensors",
587
+ "feat_decoder.estimator.decoder.layers.7.self_attn.k_proj.weight": "model-00001.safetensors",
588
+ "feat_decoder.estimator.decoder.layers.7.self_attn.o_proj.weight": "model-00001.safetensors",
589
+ "feat_decoder.estimator.decoder.layers.7.self_attn.q_proj.weight": "model-00001.safetensors",
590
+ "feat_decoder.estimator.decoder.layers.7.self_attn.v_proj.weight": "model-00001.safetensors",
591
+ "feat_decoder.estimator.decoder.layers.8.input_layernorm.weight": "model-00001.safetensors",
592
+ "feat_decoder.estimator.decoder.layers.8.mlp.down_proj.weight": "model-00001.safetensors",
593
+ "feat_decoder.estimator.decoder.layers.8.mlp.gate_proj.weight": "model-00001.safetensors",
594
+ "feat_decoder.estimator.decoder.layers.8.mlp.up_proj.weight": "model-00001.safetensors",
595
+ "feat_decoder.estimator.decoder.layers.8.post_attention_layernorm.weight": "model-00001.safetensors",
596
+ "feat_decoder.estimator.decoder.layers.8.self_attn.k_proj.weight": "model-00001.safetensors",
597
+ "feat_decoder.estimator.decoder.layers.8.self_attn.o_proj.weight": "model-00001.safetensors",
598
+ "feat_decoder.estimator.decoder.layers.8.self_attn.q_proj.weight": "model-00001.safetensors",
599
+ "feat_decoder.estimator.decoder.layers.8.self_attn.v_proj.weight": "model-00001.safetensors",
600
+ "feat_decoder.estimator.decoder.layers.9.input_layernorm.weight": "model-00001.safetensors",
601
+ "feat_decoder.estimator.decoder.layers.9.mlp.down_proj.weight": "model-00001.safetensors",
602
+ "feat_decoder.estimator.decoder.layers.9.mlp.gate_proj.weight": "model-00001.safetensors",
603
+ "feat_decoder.estimator.decoder.layers.9.mlp.up_proj.weight": "model-00001.safetensors",
604
+ "feat_decoder.estimator.decoder.layers.9.post_attention_layernorm.weight": "model-00001.safetensors",
605
+ "feat_decoder.estimator.decoder.layers.9.self_attn.k_proj.weight": "model-00001.safetensors",
606
+ "feat_decoder.estimator.decoder.layers.9.self_attn.o_proj.weight": "model-00001.safetensors",
607
+ "feat_decoder.estimator.decoder.layers.9.self_attn.q_proj.weight": "model-00001.safetensors",
608
+ "feat_decoder.estimator.decoder.layers.9.self_attn.v_proj.weight": "model-00001.safetensors",
609
+ "feat_decoder.estimator.decoder.norm.weight": "model-00001.safetensors",
610
+ "feat_decoder.estimator.decoder.rope.inv_freq": "model-00001.safetensors",
611
+ "feat_decoder.estimator.decoder.rope.long_factor": "model-00001.safetensors",
612
+ "feat_decoder.estimator.decoder.rope.short_factor": "model-00001.safetensors",
613
+ "feat_decoder.estimator.delta_time_mlp.linear_1.bias": "model-00001.safetensors",
614
+ "feat_decoder.estimator.delta_time_mlp.linear_1.weight": "model-00001.safetensors",
615
+ "feat_decoder.estimator.delta_time_mlp.linear_2.bias": "model-00001.safetensors",
616
+ "feat_decoder.estimator.delta_time_mlp.linear_2.weight": "model-00001.safetensors",
617
+ "feat_decoder.estimator.in_proj.bias": "model-00001.safetensors",
618
+ "feat_decoder.estimator.in_proj.weight": "model-00001.safetensors",
619
+ "feat_decoder.estimator.out_proj.bias": "model-00001.safetensors",
620
+ "feat_decoder.estimator.out_proj.weight": "model-00001.safetensors",
621
+ "feat_decoder.estimator.time_mlp.linear_1.bias": "model-00001.safetensors",
622
+ "feat_decoder.estimator.time_mlp.linear_1.weight": "model-00001.safetensors",
623
+ "feat_decoder.estimator.time_mlp.linear_2.bias": "model-00001.safetensors",
624
+ "feat_decoder.estimator.time_mlp.linear_2.weight": "model-00001.safetensors",
625
+ "feat_encoder.encoder.layers.0.input_layernorm.weight": "model-00001.safetensors",
626
+ "feat_encoder.encoder.layers.0.mlp.down_proj.weight": "model-00001.safetensors",
627
+ "feat_encoder.encoder.layers.0.mlp.gate_proj.weight": "model-00001.safetensors",
628
+ "feat_encoder.encoder.layers.0.mlp.up_proj.weight": "model-00001.safetensors",
629
+ "feat_encoder.encoder.layers.0.post_attention_layernorm.weight": "model-00001.safetensors",
630
+ "feat_encoder.encoder.layers.0.self_attn.k_proj.weight": "model-00001.safetensors",
631
+ "feat_encoder.encoder.layers.0.self_attn.o_proj.weight": "model-00001.safetensors",
632
+ "feat_encoder.encoder.layers.0.self_attn.q_proj.weight": "model-00001.safetensors",
633
+ "feat_encoder.encoder.layers.0.self_attn.v_proj.weight": "model-00001.safetensors",
634
+ "feat_encoder.encoder.layers.1.input_layernorm.weight": "model-00001.safetensors",
635
+ "feat_encoder.encoder.layers.1.mlp.down_proj.weight": "model-00001.safetensors",
636
+ "feat_encoder.encoder.layers.1.mlp.gate_proj.weight": "model-00001.safetensors",
637
+ "feat_encoder.encoder.layers.1.mlp.up_proj.weight": "model-00001.safetensors",
638
+ "feat_encoder.encoder.layers.1.post_attention_layernorm.weight": "model-00001.safetensors",
639
+ "feat_encoder.encoder.layers.1.self_attn.k_proj.weight": "model-00001.safetensors",
640
+ "feat_encoder.encoder.layers.1.self_attn.o_proj.weight": "model-00001.safetensors",
641
+ "feat_encoder.encoder.layers.1.self_attn.q_proj.weight": "model-00001.safetensors",
642
+ "feat_encoder.encoder.layers.1.self_attn.v_proj.weight": "model-00001.safetensors",
643
+ "feat_encoder.encoder.layers.10.input_layernorm.weight": "model-00001.safetensors",
644
+ "feat_encoder.encoder.layers.10.mlp.down_proj.weight": "model-00001.safetensors",
645
+ "feat_encoder.encoder.layers.10.mlp.gate_proj.weight": "model-00001.safetensors",
646
+ "feat_encoder.encoder.layers.10.mlp.up_proj.weight": "model-00001.safetensors",
647
+ "feat_encoder.encoder.layers.10.post_attention_layernorm.weight": "model-00001.safetensors",
648
+ "feat_encoder.encoder.layers.10.self_attn.k_proj.weight": "model-00001.safetensors",
649
+ "feat_encoder.encoder.layers.10.self_attn.o_proj.weight": "model-00001.safetensors",
650
+ "feat_encoder.encoder.layers.10.self_attn.q_proj.weight": "model-00001.safetensors",
651
+ "feat_encoder.encoder.layers.10.self_attn.v_proj.weight": "model-00001.safetensors",
652
+ "feat_encoder.encoder.layers.11.input_layernorm.weight": "model-00001.safetensors",
653
+ "feat_encoder.encoder.layers.11.mlp.down_proj.weight": "model-00001.safetensors",
654
+ "feat_encoder.encoder.layers.11.mlp.gate_proj.weight": "model-00001.safetensors",
655
+ "feat_encoder.encoder.layers.11.mlp.up_proj.weight": "model-00001.safetensors",
656
+ "feat_encoder.encoder.layers.11.post_attention_layernorm.weight": "model-00001.safetensors",
657
+ "feat_encoder.encoder.layers.11.self_attn.k_proj.weight": "model-00001.safetensors",
658
+ "feat_encoder.encoder.layers.11.self_attn.o_proj.weight": "model-00001.safetensors",
659
+ "feat_encoder.encoder.layers.11.self_attn.q_proj.weight": "model-00001.safetensors",
660
+ "feat_encoder.encoder.layers.11.self_attn.v_proj.weight": "model-00001.safetensors",
661
+ "feat_encoder.encoder.layers.2.input_layernorm.weight": "model-00001.safetensors",
662
+ "feat_encoder.encoder.layers.2.mlp.down_proj.weight": "model-00001.safetensors",
663
+ "feat_encoder.encoder.layers.2.mlp.gate_proj.weight": "model-00001.safetensors",
664
+ "feat_encoder.encoder.layers.2.mlp.up_proj.weight": "model-00001.safetensors",
665
+ "feat_encoder.encoder.layers.2.post_attention_layernorm.weight": "model-00001.safetensors",
666
+ "feat_encoder.encoder.layers.2.self_attn.k_proj.weight": "model-00001.safetensors",
667
+ "feat_encoder.encoder.layers.2.self_attn.o_proj.weight": "model-00001.safetensors",
668
+ "feat_encoder.encoder.layers.2.self_attn.q_proj.weight": "model-00001.safetensors",
669
+ "feat_encoder.encoder.layers.2.self_attn.v_proj.weight": "model-00001.safetensors",
670
+ "feat_encoder.encoder.layers.3.input_layernorm.weight": "model-00001.safetensors",
671
+ "feat_encoder.encoder.layers.3.mlp.down_proj.weight": "model-00001.safetensors",
672
+ "feat_encoder.encoder.layers.3.mlp.gate_proj.weight": "model-00001.safetensors",
673
+ "feat_encoder.encoder.layers.3.mlp.up_proj.weight": "model-00001.safetensors",
674
+ "feat_encoder.encoder.layers.3.post_attention_layernorm.weight": "model-00001.safetensors",
675
+ "feat_encoder.encoder.layers.3.self_attn.k_proj.weight": "model-00001.safetensors",
676
+ "feat_encoder.encoder.layers.3.self_attn.o_proj.weight": "model-00001.safetensors",
677
+ "feat_encoder.encoder.layers.3.self_attn.q_proj.weight": "model-00001.safetensors",
678
+ "feat_encoder.encoder.layers.3.self_attn.v_proj.weight": "model-00001.safetensors",
679
+ "feat_encoder.encoder.layers.4.input_layernorm.weight": "model-00001.safetensors",
680
+ "feat_encoder.encoder.layers.4.mlp.down_proj.weight": "model-00001.safetensors",
681
+ "feat_encoder.encoder.layers.4.mlp.gate_proj.weight": "model-00001.safetensors",
682
+ "feat_encoder.encoder.layers.4.mlp.up_proj.weight": "model-00001.safetensors",
683
+ "feat_encoder.encoder.layers.4.post_attention_layernorm.weight": "model-00001.safetensors",
684
+ "feat_encoder.encoder.layers.4.self_attn.k_proj.weight": "model-00001.safetensors",
685
+ "feat_encoder.encoder.layers.4.self_attn.o_proj.weight": "model-00001.safetensors",
686
+ "feat_encoder.encoder.layers.4.self_attn.q_proj.weight": "model-00001.safetensors",
687
+ "feat_encoder.encoder.layers.4.self_attn.v_proj.weight": "model-00001.safetensors",
688
+ "feat_encoder.encoder.layers.5.input_layernorm.weight": "model-00001.safetensors",
689
+ "feat_encoder.encoder.layers.5.mlp.down_proj.weight": "model-00001.safetensors",
690
+ "feat_encoder.encoder.layers.5.mlp.gate_proj.weight": "model-00001.safetensors",
691
+ "feat_encoder.encoder.layers.5.mlp.up_proj.weight": "model-00001.safetensors",
692
+ "feat_encoder.encoder.layers.5.post_attention_layernorm.weight": "model-00001.safetensors",
693
+ "feat_encoder.encoder.layers.5.self_attn.k_proj.weight": "model-00001.safetensors",
694
+ "feat_encoder.encoder.layers.5.self_attn.o_proj.weight": "model-00001.safetensors",
695
+ "feat_encoder.encoder.layers.5.self_attn.q_proj.weight": "model-00001.safetensors",
696
+ "feat_encoder.encoder.layers.5.self_attn.v_proj.weight": "model-00001.safetensors",
697
+ "feat_encoder.encoder.layers.6.input_layernorm.weight": "model-00001.safetensors",
698
+ "feat_encoder.encoder.layers.6.mlp.down_proj.weight": "model-00001.safetensors",
699
+ "feat_encoder.encoder.layers.6.mlp.gate_proj.weight": "model-00001.safetensors",
700
+ "feat_encoder.encoder.layers.6.mlp.up_proj.weight": "model-00001.safetensors",
701
+ "feat_encoder.encoder.layers.6.post_attention_layernorm.weight": "model-00001.safetensors",
702
+ "feat_encoder.encoder.layers.6.self_attn.k_proj.weight": "model-00001.safetensors",
703
+ "feat_encoder.encoder.layers.6.self_attn.o_proj.weight": "model-00001.safetensors",
704
+ "feat_encoder.encoder.layers.6.self_attn.q_proj.weight": "model-00001.safetensors",
705
+ "feat_encoder.encoder.layers.6.self_attn.v_proj.weight": "model-00001.safetensors",
706
+ "feat_encoder.encoder.layers.7.input_layernorm.weight": "model-00001.safetensors",
707
+ "feat_encoder.encoder.layers.7.mlp.down_proj.weight": "model-00001.safetensors",
708
+ "feat_encoder.encoder.layers.7.mlp.gate_proj.weight": "model-00001.safetensors",
709
+ "feat_encoder.encoder.layers.7.mlp.up_proj.weight": "model-00001.safetensors",
710
+ "feat_encoder.encoder.layers.7.post_attention_layernorm.weight": "model-00001.safetensors",
711
+ "feat_encoder.encoder.layers.7.self_attn.k_proj.weight": "model-00001.safetensors",
712
+ "feat_encoder.encoder.layers.7.self_attn.o_proj.weight": "model-00001.safetensors",
713
+ "feat_encoder.encoder.layers.7.self_attn.q_proj.weight": "model-00001.safetensors",
714
+ "feat_encoder.encoder.layers.7.self_attn.v_proj.weight": "model-00001.safetensors",
715
+ "feat_encoder.encoder.layers.8.input_layernorm.weight": "model-00001.safetensors",
716
+ "feat_encoder.encoder.layers.8.mlp.down_proj.weight": "model-00001.safetensors",
717
+ "feat_encoder.encoder.layers.8.mlp.gate_proj.weight": "model-00001.safetensors",
718
+ "feat_encoder.encoder.layers.8.mlp.up_proj.weight": "model-00001.safetensors",
719
+ "feat_encoder.encoder.layers.8.post_attention_layernorm.weight": "model-00001.safetensors",
720
+ "feat_encoder.encoder.layers.8.self_attn.k_proj.weight": "model-00001.safetensors",
721
+ "feat_encoder.encoder.layers.8.self_attn.o_proj.weight": "model-00001.safetensors",
722
+ "feat_encoder.encoder.layers.8.self_attn.q_proj.weight": "model-00001.safetensors",
723
+ "feat_encoder.encoder.layers.8.self_attn.v_proj.weight": "model-00001.safetensors",
724
+ "feat_encoder.encoder.layers.9.input_layernorm.weight": "model-00001.safetensors",
725
+ "feat_encoder.encoder.layers.9.mlp.down_proj.weight": "model-00001.safetensors",
726
+ "feat_encoder.encoder.layers.9.mlp.gate_proj.weight": "model-00001.safetensors",
727
+ "feat_encoder.encoder.layers.9.mlp.up_proj.weight": "model-00001.safetensors",
728
+ "feat_encoder.encoder.layers.9.post_attention_layernorm.weight": "model-00001.safetensors",
729
+ "feat_encoder.encoder.layers.9.self_attn.k_proj.weight": "model-00001.safetensors",
730
+ "feat_encoder.encoder.layers.9.self_attn.o_proj.weight": "model-00001.safetensors",
731
+ "feat_encoder.encoder.layers.9.self_attn.q_proj.weight": "model-00001.safetensors",
732
+ "feat_encoder.encoder.layers.9.self_attn.v_proj.weight": "model-00001.safetensors",
733
+ "feat_encoder.encoder.norm.weight": "model-00001.safetensors",
734
+ "feat_encoder.encoder.rope.inv_freq": "model-00001.safetensors",
735
+ "feat_encoder.encoder.rope.long_factor": "model-00001.safetensors",
736
+ "feat_encoder.encoder.rope.short_factor": "model-00001.safetensors",
737
+ "feat_encoder.in_proj.bias": "model-00001.safetensors",
738
+ "feat_encoder.in_proj.weight": "model-00001.safetensors",
739
+ "feat_encoder.special_token": "model-00001.safetensors",
740
+ "fsq_layer.in_proj.bias": "model-00001.safetensors",
741
+ "fsq_layer.in_proj.weight": "model-00001.safetensors",
742
+ "fsq_layer.out_proj.bias": "model-00001.safetensors",
743
+ "fsq_layer.out_proj.weight": "model-00001.safetensors",
744
+ "fusion_concat_proj.bias": "model-00001.safetensors",
745
+ "fusion_concat_proj.weight": "model-00001.safetensors",
746
+ "lm_to_dit_proj.bias": "model-00001.safetensors",
747
+ "lm_to_dit_proj.weight": "model-00001.safetensors",
748
+ "res_to_dit_proj.bias": "model-00001.safetensors",
749
+ "res_to_dit_proj.weight": "model-00001.safetensors",
750
+ "residual_lm.layers.0.input_layernorm.weight": "model-00001.safetensors",
751
+ "residual_lm.layers.0.mlp.down_proj.weight": "model-00001.safetensors",
752
+ "residual_lm.layers.0.mlp.gate_proj.weight": "model-00001.safetensors",
753
+ "residual_lm.layers.0.mlp.up_proj.weight": "model-00001.safetensors",
754
+ "residual_lm.layers.0.post_attention_layernorm.weight": "model-00001.safetensors",
755
+ "residual_lm.layers.0.self_attn.k_proj.weight": "model-00001.safetensors",
756
+ "residual_lm.layers.0.self_attn.o_proj.weight": "model-00001.safetensors",
757
+ "residual_lm.layers.0.self_attn.q_proj.weight": "model-00001.safetensors",
758
+ "residual_lm.layers.0.self_attn.v_proj.weight": "model-00001.safetensors",
759
+ "residual_lm.layers.1.input_layernorm.weight": "model-00001.safetensors",
760
+ "residual_lm.layers.1.mlp.down_proj.weight": "model-00002.safetensors",
761
+ "residual_lm.layers.1.mlp.gate_proj.weight": "model-00002.safetensors",
762
+ "residual_lm.layers.1.mlp.up_proj.weight": "model-00002.safetensors",
763
+ "residual_lm.layers.1.post_attention_layernorm.weight": "model-00002.safetensors",
764
+ "residual_lm.layers.1.self_attn.k_proj.weight": "model-00002.safetensors",
765
+ "residual_lm.layers.1.self_attn.o_proj.weight": "model-00002.safetensors",
766
+ "residual_lm.layers.1.self_attn.q_proj.weight": "model-00002.safetensors",
767
+ "residual_lm.layers.1.self_attn.v_proj.weight": "model-00002.safetensors",
768
+ "residual_lm.layers.2.input_layernorm.weight": "model-00002.safetensors",
769
+ "residual_lm.layers.2.mlp.down_proj.weight": "model-00002.safetensors",
770
+ "residual_lm.layers.2.mlp.gate_proj.weight": "model-00002.safetensors",
771
+ "residual_lm.layers.2.mlp.up_proj.weight": "model-00002.safetensors",
772
+ "residual_lm.layers.2.post_attention_layernorm.weight": "model-00002.safetensors",
773
+ "residual_lm.layers.2.self_attn.k_proj.weight": "model-00002.safetensors",
774
+ "residual_lm.layers.2.self_attn.o_proj.weight": "model-00002.safetensors",
775
+ "residual_lm.layers.2.self_attn.q_proj.weight": "model-00002.safetensors",
776
+ "residual_lm.layers.2.self_attn.v_proj.weight": "model-00002.safetensors",
777
+ "residual_lm.layers.3.input_layernorm.weight": "model-00002.safetensors",
778
+ "residual_lm.layers.3.mlp.down_proj.weight": "model-00002.safetensors",
779
+ "residual_lm.layers.3.mlp.gate_proj.weight": "model-00002.safetensors",
780
+ "residual_lm.layers.3.mlp.up_proj.weight": "model-00002.safetensors",
781
+ "residual_lm.layers.3.post_attention_layernorm.weight": "model-00002.safetensors",
782
+ "residual_lm.layers.3.self_attn.k_proj.weight": "model-00002.safetensors",
783
+ "residual_lm.layers.3.self_attn.o_proj.weight": "model-00002.safetensors",
784
+ "residual_lm.layers.3.self_attn.q_proj.weight": "model-00002.safetensors",
785
+ "residual_lm.layers.3.self_attn.v_proj.weight": "model-00002.safetensors",
786
+ "residual_lm.layers.4.input_layernorm.weight": "model-00002.safetensors",
787
+ "residual_lm.layers.4.mlp.down_proj.weight": "model-00002.safetensors",
788
+ "residual_lm.layers.4.mlp.gate_proj.weight": "model-00002.safetensors",
789
+ "residual_lm.layers.4.mlp.up_proj.weight": "model-00002.safetensors",
790
+ "residual_lm.layers.4.post_attention_layernorm.weight": "model-00002.safetensors",
791
+ "residual_lm.layers.4.self_attn.k_proj.weight": "model-00002.safetensors",
792
+ "residual_lm.layers.4.self_attn.o_proj.weight": "model-00002.safetensors",
793
+ "residual_lm.layers.4.self_attn.q_proj.weight": "model-00002.safetensors",
794
+ "residual_lm.layers.4.self_attn.v_proj.weight": "model-00002.safetensors",
795
+ "residual_lm.layers.5.input_layernorm.weight": "model-00002.safetensors",
796
+ "residual_lm.layers.5.mlp.down_proj.weight": "model-00002.safetensors",
797
+ "residual_lm.layers.5.mlp.gate_proj.weight": "model-00002.safetensors",
798
+ "residual_lm.layers.5.mlp.up_proj.weight": "model-00002.safetensors",
799
+ "residual_lm.layers.5.post_attention_layernorm.weight": "model-00002.safetensors",
800
+ "residual_lm.layers.5.self_attn.k_proj.weight": "model-00002.safetensors",
801
+ "residual_lm.layers.5.self_attn.o_proj.weight": "model-00002.safetensors",
802
+ "residual_lm.layers.5.self_attn.q_proj.weight": "model-00002.safetensors",
803
+ "residual_lm.layers.5.self_attn.v_proj.weight": "model-00002.safetensors",
804
+ "residual_lm.layers.6.input_layernorm.weight": "model-00002.safetensors",
805
+ "residual_lm.layers.6.mlp.down_proj.weight": "model-00002.safetensors",
806
+ "residual_lm.layers.6.mlp.gate_proj.weight": "model-00002.safetensors",
807
+ "residual_lm.layers.6.mlp.up_proj.weight": "model-00002.safetensors",
808
+ "residual_lm.layers.6.post_attention_layernorm.weight": "model-00002.safetensors",
809
+ "residual_lm.layers.6.self_attn.k_proj.weight": "model-00002.safetensors",
810
+ "residual_lm.layers.6.self_attn.o_proj.weight": "model-00002.safetensors",
811
+ "residual_lm.layers.6.self_attn.q_proj.weight": "model-00002.safetensors",
812
+ "residual_lm.layers.6.self_attn.v_proj.weight": "model-00002.safetensors",
813
+ "residual_lm.layers.7.input_layernorm.weight": "model-00002.safetensors",
814
+ "residual_lm.layers.7.mlp.down_proj.weight": "model-00002.safetensors",
815
+ "residual_lm.layers.7.mlp.gate_proj.weight": "model-00002.safetensors",
816
+ "residual_lm.layers.7.mlp.up_proj.weight": "model-00002.safetensors",
817
+ "residual_lm.layers.7.post_attention_layernorm.weight": "model-00002.safetensors",
818
+ "residual_lm.layers.7.self_attn.k_proj.weight": "model-00002.safetensors",
819
+ "residual_lm.layers.7.self_attn.o_proj.weight": "model-00002.safetensors",
820
+ "residual_lm.layers.7.self_attn.q_proj.weight": "model-00002.safetensors",
821
+ "residual_lm.layers.7.self_attn.v_proj.weight": "model-00002.safetensors",
822
+ "residual_lm.norm.weight": "model-00002.safetensors",
823
+ "stop_head.weight": "model-00002.safetensors",
824
+ "stop_proj.bias": "model-00002.safetensors",
825
+ "stop_proj.weight": "model-00002.safetensors"
826
+ }
827
+ }