Upload folder using huggingface_hub
Browse files- .meta/model.log +274 -0
.meta/model.log
CHANGED
|
@@ -0,0 +1,274 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
HaruModel(
|
| 2 |
+
(lm): Qwen3_5TextModel(
|
| 3 |
+
(embed_tokens): Embedding(248320, 32)
|
| 4 |
+
(layers): ModuleList(
|
| 5 |
+
(0-2): 3 x Qwen3_5DecoderLayer(
|
| 6 |
+
(linear_attn): Qwen3_5GatedDeltaNet(
|
| 7 |
+
(conv1d): Conv1d(128, 128, kernel_size=(4,), stride=(1,), padding=(3,), groups=128, bias=False)
|
| 8 |
+
(norm): Qwen3_5RMSNormGated()
|
| 9 |
+
(out_proj): Linear(in_features=64, out_features=32, bias=False)
|
| 10 |
+
(in_proj_qkv): Linear(in_features=32, out_features=128, bias=False)
|
| 11 |
+
(in_proj_z): Linear(in_features=32, out_features=64, bias=False)
|
| 12 |
+
(in_proj_b): Linear(in_features=32, out_features=4, bias=False)
|
| 13 |
+
(in_proj_a): Linear(in_features=32, out_features=4, bias=False)
|
| 14 |
+
)
|
| 15 |
+
(mlp): Qwen3_5MLP(
|
| 16 |
+
(gate_proj): Linear(in_features=32, out_features=64, bias=False)
|
| 17 |
+
(up_proj): Linear(in_features=32, out_features=64, bias=False)
|
| 18 |
+
(down_proj): Linear(in_features=64, out_features=32, bias=False)
|
| 19 |
+
(act_fn): SiLUActivation()
|
| 20 |
+
)
|
| 21 |
+
(input_layernorm): Qwen3_5RMSNorm((32,), eps=1e-06)
|
| 22 |
+
(post_attention_layernorm): Qwen3_5RMSNorm((32,), eps=1e-06)
|
| 23 |
+
)
|
| 24 |
+
(3): Qwen3_5DecoderLayer(
|
| 25 |
+
(self_attn): Qwen3_5Attention(
|
| 26 |
+
(q_proj): Linear(in_features=32, out_features=128, bias=False)
|
| 27 |
+
(k_proj): Linear(in_features=32, out_features=16, bias=False)
|
| 28 |
+
(v_proj): Linear(in_features=32, out_features=16, bias=False)
|
| 29 |
+
(o_proj): Linear(in_features=64, out_features=32, bias=False)
|
| 30 |
+
(q_norm): Qwen3_5RMSNorm((16,), eps=1e-06)
|
| 31 |
+
(k_norm): Qwen3_5RMSNorm((16,), eps=1e-06)
|
| 32 |
+
)
|
| 33 |
+
(mlp): Qwen3_5MLP(
|
| 34 |
+
(gate_proj): Linear(in_features=32, out_features=64, bias=False)
|
| 35 |
+
(up_proj): Linear(in_features=32, out_features=64, bias=False)
|
| 36 |
+
(down_proj): Linear(in_features=64, out_features=32, bias=False)
|
| 37 |
+
(act_fn): SiLUActivation()
|
| 38 |
+
)
|
| 39 |
+
(input_layernorm): Qwen3_5RMSNorm((32,), eps=1e-06)
|
| 40 |
+
(post_attention_layernorm): Qwen3_5RMSNorm((32,), eps=1e-06)
|
| 41 |
+
)
|
| 42 |
+
(4-6): 3 x Qwen3_5DecoderLayer(
|
| 43 |
+
(linear_attn): Qwen3_5GatedDeltaNet(
|
| 44 |
+
(conv1d): Conv1d(128, 128, kernel_size=(4,), stride=(1,), padding=(3,), groups=128, bias=False)
|
| 45 |
+
(norm): Qwen3_5RMSNormGated()
|
| 46 |
+
(out_proj): Linear(in_features=64, out_features=32, bias=False)
|
| 47 |
+
(in_proj_qkv): Linear(in_features=32, out_features=128, bias=False)
|
| 48 |
+
(in_proj_z): Linear(in_features=32, out_features=64, bias=False)
|
| 49 |
+
(in_proj_b): Linear(in_features=32, out_features=4, bias=False)
|
| 50 |
+
(in_proj_a): Linear(in_features=32, out_features=4, bias=False)
|
| 51 |
+
)
|
| 52 |
+
(mlp): Qwen3_5MLP(
|
| 53 |
+
(gate_proj): Linear(in_features=32, out_features=64, bias=False)
|
| 54 |
+
(up_proj): Linear(in_features=32, out_features=64, bias=False)
|
| 55 |
+
(down_proj): Linear(in_features=64, out_features=32, bias=False)
|
| 56 |
+
(act_fn): SiLUActivation()
|
| 57 |
+
)
|
| 58 |
+
(input_layernorm): Qwen3_5RMSNorm((32,), eps=1e-06)
|
| 59 |
+
(post_attention_layernorm): Qwen3_5RMSNorm((32,), eps=1e-06)
|
| 60 |
+
)
|
| 61 |
+
(7): Qwen3_5DecoderLayer(
|
| 62 |
+
(self_attn): Qwen3_5Attention(
|
| 63 |
+
(q_proj): Linear(in_features=32, out_features=128, bias=False)
|
| 64 |
+
(k_proj): Linear(in_features=32, out_features=16, bias=False)
|
| 65 |
+
(v_proj): Linear(in_features=32, out_features=16, bias=False)
|
| 66 |
+
(o_proj): Linear(in_features=64, out_features=32, bias=False)
|
| 67 |
+
(q_norm): Qwen3_5RMSNorm((16,), eps=1e-06)
|
| 68 |
+
(k_norm): Qwen3_5RMSNorm((16,), eps=1e-06)
|
| 69 |
+
)
|
| 70 |
+
(mlp): Qwen3_5MLP(
|
| 71 |
+
(gate_proj): Linear(in_features=32, out_features=64, bias=False)
|
| 72 |
+
(up_proj): Linear(in_features=32, out_features=64, bias=False)
|
| 73 |
+
(down_proj): Linear(in_features=64, out_features=32, bias=False)
|
| 74 |
+
(act_fn): SiLUActivation()
|
| 75 |
+
)
|
| 76 |
+
(input_layernorm): Qwen3_5RMSNorm((32,), eps=1e-06)
|
| 77 |
+
(post_attention_layernorm): Qwen3_5RMSNorm((32,), eps=1e-06)
|
| 78 |
+
)
|
| 79 |
+
)
|
| 80 |
+
(norm): Qwen3_5RMSNorm((32,), eps=1e-06)
|
| 81 |
+
(rotary_emb): Qwen3_5TextRotaryEmbedding()
|
| 82 |
+
)
|
| 83 |
+
(model_audio_proj): AudioProjector(
|
| 84 |
+
(fc1): Linear(in_features=64, out_features=32, bias=True)
|
| 85 |
+
(norm): RMSNorm((32,), eps=1e-06, elementwise_affine=True)
|
| 86 |
+
(fc2): Linear(in_features=32, out_features=32, bias=True)
|
| 87 |
+
)
|
| 88 |
+
(user_audio_proj): AudioProjector(
|
| 89 |
+
(fc1): Linear(in_features=64, out_features=32, bias=True)
|
| 90 |
+
(norm): RMSNorm((32,), eps=1e-06, elementwise_affine=True)
|
| 91 |
+
(fc2): Linear(in_features=32, out_features=32, bias=True)
|
| 92 |
+
)
|
| 93 |
+
(head): MeanFlowHead(
|
| 94 |
+
(latent_proj): Linear(in_features=64, out_features=32, bias=False)
|
| 95 |
+
(cond_proj): Linear(in_features=32, out_features=32, bias=False)
|
| 96 |
+
(t_embed): ScalarEmbed(
|
| 97 |
+
(fc1): Linear(in_features=256, out_features=32, bias=False)
|
| 98 |
+
(fc2): Linear(in_features=32, out_features=32, bias=False)
|
| 99 |
+
)
|
| 100 |
+
(dt_embed): ScalarEmbed(
|
| 101 |
+
(fc1): Linear(in_features=256, out_features=32, bias=False)
|
| 102 |
+
(fc2): Linear(in_features=32, out_features=32, bias=False)
|
| 103 |
+
)
|
| 104 |
+
(h_embed): ScalarEmbed(
|
| 105 |
+
(fc1): Linear(in_features=256, out_features=32, bias=False)
|
| 106 |
+
(fc2): Linear(in_features=32, out_features=32, bias=False)
|
| 107 |
+
)
|
| 108 |
+
(omega_embed): ScalarEmbed(
|
| 109 |
+
(fc1): Linear(in_features=256, out_features=32, bias=False)
|
| 110 |
+
(fc2): Linear(in_features=32, out_features=32, bias=False)
|
| 111 |
+
)
|
| 112 |
+
(layers): ModuleList(
|
| 113 |
+
(0): HeadLayer(
|
| 114 |
+
(norm): Module()
|
| 115 |
+
(ada): Linear(in_features=32, out_features=96, bias=False)
|
| 116 |
+
(ffn): FeedForward(
|
| 117 |
+
(gate_proj): Linear(in_features=32, out_features=96, bias=False)
|
| 118 |
+
(up_proj): Linear(in_features=32, out_features=96, bias=False)
|
| 119 |
+
(down_proj): Linear(in_features=96, out_features=32, bias=False)
|
| 120 |
+
)
|
| 121 |
+
)
|
| 122 |
+
)
|
| 123 |
+
(final): FinalLayer(
|
| 124 |
+
(ada): Linear(in_features=32, out_features=64, bias=False)
|
| 125 |
+
(proj): Linear(in_features=32, out_features=64, bias=False)
|
| 126 |
+
)
|
| 127 |
+
)
|
| 128 |
+
(codec): VibeVoiceCodec(
|
| 129 |
+
(encoder): Encoder(
|
| 130 |
+
(stem): CausalConv1d()
|
| 131 |
+
(down): ModuleList(
|
| 132 |
+
(0-5): 6 x CausalConv1d()
|
| 133 |
+
)
|
| 134 |
+
(stages): ModuleList(
|
| 135 |
+
(0): ModuleList(
|
| 136 |
+
(0): Block(
|
| 137 |
+
(norm): RMSNorm()
|
| 138 |
+
(conv): CausalConv1d()
|
| 139 |
+
(ffn_norm): RMSNorm()
|
| 140 |
+
(fc1): Linear(in_features=1, out_features=4, bias=True)
|
| 141 |
+
(fc2): Linear(in_features=4, out_features=1, bias=True)
|
| 142 |
+
)
|
| 143 |
+
)
|
| 144 |
+
(1): ModuleList(
|
| 145 |
+
(0): Block(
|
| 146 |
+
(norm): RMSNorm()
|
| 147 |
+
(conv): CausalConv1d()
|
| 148 |
+
(ffn_norm): RMSNorm()
|
| 149 |
+
(fc1): Linear(in_features=2, out_features=8, bias=True)
|
| 150 |
+
(fc2): Linear(in_features=8, out_features=2, bias=True)
|
| 151 |
+
)
|
| 152 |
+
)
|
| 153 |
+
(2): ModuleList(
|
| 154 |
+
(0): Block(
|
| 155 |
+
(norm): RMSNorm()
|
| 156 |
+
(conv): CausalConv1d()
|
| 157 |
+
(ffn_norm): RMSNorm()
|
| 158 |
+
(fc1): Linear(in_features=4, out_features=16, bias=True)
|
| 159 |
+
(fc2): Linear(in_features=16, out_features=4, bias=True)
|
| 160 |
+
)
|
| 161 |
+
)
|
| 162 |
+
(3): ModuleList(
|
| 163 |
+
(0): Block(
|
| 164 |
+
(norm): RMSNorm()
|
| 165 |
+
(conv): CausalConv1d()
|
| 166 |
+
(ffn_norm): RMSNorm()
|
| 167 |
+
(fc1): Linear(in_features=8, out_features=32, bias=True)
|
| 168 |
+
(fc2): Linear(in_features=32, out_features=8, bias=True)
|
| 169 |
+
)
|
| 170 |
+
)
|
| 171 |
+
(4): ModuleList(
|
| 172 |
+
(0): Block(
|
| 173 |
+
(norm): RMSNorm()
|
| 174 |
+
(conv): CausalConv1d()
|
| 175 |
+
(ffn_norm): RMSNorm()
|
| 176 |
+
(fc1): Linear(in_features=16, out_features=64, bias=True)
|
| 177 |
+
(fc2): Linear(in_features=64, out_features=16, bias=True)
|
| 178 |
+
)
|
| 179 |
+
)
|
| 180 |
+
(5): ModuleList(
|
| 181 |
+
(0): Block(
|
| 182 |
+
(norm): RMSNorm()
|
| 183 |
+
(conv): CausalConv1d()
|
| 184 |
+
(ffn_norm): RMSNorm()
|
| 185 |
+
(fc1): Linear(in_features=32, out_features=128, bias=True)
|
| 186 |
+
(fc2): Linear(in_features=128, out_features=32, bias=True)
|
| 187 |
+
)
|
| 188 |
+
)
|
| 189 |
+
(6): ModuleList(
|
| 190 |
+
(0): Block(
|
| 191 |
+
(norm): RMSNorm()
|
| 192 |
+
(conv): CausalConv1d()
|
| 193 |
+
(ffn_norm): RMSNorm()
|
| 194 |
+
(fc1): Linear(in_features=64, out_features=256, bias=True)
|
| 195 |
+
(fc2): Linear(in_features=256, out_features=64, bias=True)
|
| 196 |
+
)
|
| 197 |
+
)
|
| 198 |
+
)
|
| 199 |
+
(head): CausalConv1d()
|
| 200 |
+
)
|
| 201 |
+
(decoder): Decoder(
|
| 202 |
+
(stem): CausalConv1d()
|
| 203 |
+
(up): ModuleList(
|
| 204 |
+
(0-5): 6 x CausalConvTranspose1d()
|
| 205 |
+
)
|
| 206 |
+
(stages): ModuleList(
|
| 207 |
+
(0): ModuleList(
|
| 208 |
+
(0): Block(
|
| 209 |
+
(norm): RMSNorm()
|
| 210 |
+
(conv): CausalConv1d()
|
| 211 |
+
(ffn_norm): RMSNorm()
|
| 212 |
+
(fc1): Linear(in_features=64, out_features=256, bias=True)
|
| 213 |
+
(fc2): Linear(in_features=256, out_features=64, bias=True)
|
| 214 |
+
)
|
| 215 |
+
)
|
| 216 |
+
(1): ModuleList(
|
| 217 |
+
(0): Block(
|
| 218 |
+
(norm): RMSNorm()
|
| 219 |
+
(conv): CausalConv1d()
|
| 220 |
+
(ffn_norm): RMSNorm()
|
| 221 |
+
(fc1): Linear(in_features=32, out_features=128, bias=True)
|
| 222 |
+
(fc2): Linear(in_features=128, out_features=32, bias=True)
|
| 223 |
+
)
|
| 224 |
+
)
|
| 225 |
+
(2): ModuleList(
|
| 226 |
+
(0): Block(
|
| 227 |
+
(norm): RMSNorm()
|
| 228 |
+
(conv): CausalConv1d()
|
| 229 |
+
(ffn_norm): RMSNorm()
|
| 230 |
+
(fc1): Linear(in_features=16, out_features=64, bias=True)
|
| 231 |
+
(fc2): Linear(in_features=64, out_features=16, bias=True)
|
| 232 |
+
)
|
| 233 |
+
)
|
| 234 |
+
(3): ModuleList(
|
| 235 |
+
(0): Block(
|
| 236 |
+
(norm): RMSNorm()
|
| 237 |
+
(conv): CausalConv1d()
|
| 238 |
+
(ffn_norm): RMSNorm()
|
| 239 |
+
(fc1): Linear(in_features=8, out_features=32, bias=True)
|
| 240 |
+
(fc2): Linear(in_features=32, out_features=8, bias=True)
|
| 241 |
+
)
|
| 242 |
+
)
|
| 243 |
+
(4): ModuleList(
|
| 244 |
+
(0): Block(
|
| 245 |
+
(norm): RMSNorm()
|
| 246 |
+
(conv): CausalConv1d()
|
| 247 |
+
(ffn_norm): RMSNorm()
|
| 248 |
+
(fc1): Linear(in_features=4, out_features=16, bias=True)
|
| 249 |
+
(fc2): Linear(in_features=16, out_features=4, bias=True)
|
| 250 |
+
)
|
| 251 |
+
)
|
| 252 |
+
(5): ModuleList(
|
| 253 |
+
(0): Block(
|
| 254 |
+
(norm): RMSNorm()
|
| 255 |
+
(conv): CausalConv1d()
|
| 256 |
+
(ffn_norm): RMSNorm()
|
| 257 |
+
(fc1): Linear(in_features=2, out_features=8, bias=True)
|
| 258 |
+
(fc2): Linear(in_features=8, out_features=2, bias=True)
|
| 259 |
+
)
|
| 260 |
+
)
|
| 261 |
+
(6): ModuleList(
|
| 262 |
+
(0): Block(
|
| 263 |
+
(norm): RMSNorm()
|
| 264 |
+
(conv): CausalConv1d()
|
| 265 |
+
(ffn_norm): RMSNorm()
|
| 266 |
+
(fc1): Linear(in_features=1, out_features=4, bias=True)
|
| 267 |
+
(fc2): Linear(in_features=4, out_features=1, bias=True)
|
| 268 |
+
)
|
| 269 |
+
)
|
| 270 |
+
)
|
| 271 |
+
(head): CausalConv1d()
|
| 272 |
+
)
|
| 273 |
+
)
|
| 274 |
+
)
|