File size: 21,808 Bytes
85a6d63 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 | {
"_attn_implementation_autoset": false,
"acoustic_tokenizer_config": {
"causal": true,
"channels": 1,
"conv_bias": true,
"conv_norm": "none",
"corpus_normalize": 0.0,
"decoder_depths": null,
"decoder_n_filters": 32,
"decoder_ratios": [
8,
5,
5,
4,
2,
2
],
"disable_last_norm": true,
"dtype": "bfloat16",
"encoder_depths": "3-3-3-3-3-3-8",
"encoder_n_filters": 32,
"encoder_ratios": [
8,
5,
5,
4,
2,
2
],
"fix_std": 0.5,
"layer_scale_init_value": 1e-06,
"layernorm": "RMSNorm",
"layernorm_elementwise_affine": true,
"layernorm_eps": 1e-05,
"mixer_layer": "depthwise_conv",
"model_type": "vibevoice_acoustic_tokenizer",
"pad_mode": "constant",
"std_dist_type": "gaussian",
"vae_dim": 64,
"weight_init_value": 0.01
},
"acoustic_vae_dim": 64,
"architectures": [
"VibeVoiceASRForConditionalGeneration"
],
"decoder_config": {
"attention_dropout": 0.0,
"bos_token_id": null,
"dtype": "bfloat16",
"eos_token_id": null,
"hidden_act": "silu",
"hidden_size": 3584,
"initializer_range": 0.02,
"intermediate_size": 18944,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 131072,
"max_window_layers": 28,
"model_type": "qwen2",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"pad_token_id": null,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000.0,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": false,
"use_cache": true,
"use_mrope": false,
"use_sliding_window": false,
"vocab_size": 152064
},
"diffusion_head_config": {
"ddpm_batch_mul": 4,
"ddpm_beta_schedule": "cosine",
"ddpm_num_inference_steps": 20,
"ddpm_num_steps": 1000,
"diffusion_type": "ddpm",
"head_ffn_ratio": 3.0,
"head_layers": 4,
"hidden_size": 3584,
"latent_size": 64,
"model_type": "vibepod_diffusion_head",
"prediction_type": "v_prediction",
"rms_norm_eps": 1e-05,
"speech_vae_dim": 64
},
"dtype": "bfloat16",
"model_type": "vibevoice",
"quantization_config": {
"config_groups": {
"group_0": {
"format": "nvfp4-pack-quantized",
"input_activations": {
"actorder": null,
"block_structure": null,
"dynamic": "local",
"group_size": 16,
"num_bits": 4,
"observer": "static_minmax",
"observer_kwargs": {},
"scale_dtype": "torch.float8_e4m3fn",
"strategy": "tensor_group",
"symmetric": true,
"type": "float",
"zp_dtype": null
},
"output_activations": null,
"targets": [
"re:.*mlp.gate_proj$",
"re:.*mlp.up_proj$",
"re:.*mlp.down_proj$"
],
"weights": {
"actorder": null,
"block_structure": null,
"dynamic": false,
"group_size": 16,
"num_bits": 4,
"observer": "memoryless_minmax",
"observer_kwargs": {},
"scale_dtype": "torch.float8_e4m3fn",
"strategy": "tensor_group",
"symmetric": true,
"type": "float",
"zp_dtype": null
}
}
},
"format": "nvfp4-pack-quantized",
"global_compression_ratio": null,
"ignore": [
"re:.*self_attn.*",
"model.language_model.layers.0.self_attn.q_proj",
"model.language_model.layers.0.self_attn.k_proj",
"model.language_model.layers.0.self_attn.v_proj",
"model.language_model.layers.0.self_attn.o_proj",
"model.language_model.layers.1.self_attn.q_proj",
"model.language_model.layers.1.self_attn.k_proj",
"model.language_model.layers.1.self_attn.v_proj",
"model.language_model.layers.1.self_attn.o_proj",
"model.language_model.layers.2.self_attn.q_proj",
"model.language_model.layers.2.self_attn.k_proj",
"model.language_model.layers.2.self_attn.v_proj",
"model.language_model.layers.2.self_attn.o_proj",
"model.language_model.layers.3.self_attn.q_proj",
"model.language_model.layers.3.self_attn.k_proj",
"model.language_model.layers.3.self_attn.v_proj",
"model.language_model.layers.3.self_attn.o_proj",
"model.language_model.layers.4.self_attn.q_proj",
"model.language_model.layers.4.self_attn.k_proj",
"model.language_model.layers.4.self_attn.v_proj",
"model.language_model.layers.4.self_attn.o_proj",
"model.language_model.layers.5.self_attn.q_proj",
"model.language_model.layers.5.self_attn.k_proj",
"model.language_model.layers.5.self_attn.v_proj",
"model.language_model.layers.5.self_attn.o_proj",
"model.language_model.layers.6.self_attn.q_proj",
"model.language_model.layers.6.self_attn.k_proj",
"model.language_model.layers.6.self_attn.v_proj",
"model.language_model.layers.6.self_attn.o_proj",
"model.language_model.layers.7.self_attn.q_proj",
"model.language_model.layers.7.self_attn.k_proj",
"model.language_model.layers.7.self_attn.v_proj",
"model.language_model.layers.7.self_attn.o_proj",
"model.language_model.layers.8.self_attn.q_proj",
"model.language_model.layers.8.self_attn.k_proj",
"model.language_model.layers.8.self_attn.v_proj",
"model.language_model.layers.8.self_attn.o_proj",
"model.language_model.layers.9.self_attn.q_proj",
"model.language_model.layers.9.self_attn.k_proj",
"model.language_model.layers.9.self_attn.v_proj",
"model.language_model.layers.9.self_attn.o_proj",
"model.language_model.layers.10.self_attn.q_proj",
"model.language_model.layers.10.self_attn.k_proj",
"model.language_model.layers.10.self_attn.v_proj",
"model.language_model.layers.10.self_attn.o_proj",
"model.language_model.layers.11.self_attn.q_proj",
"model.language_model.layers.11.self_attn.k_proj",
"model.language_model.layers.11.self_attn.v_proj",
"model.language_model.layers.11.self_attn.o_proj",
"model.language_model.layers.12.self_attn.q_proj",
"model.language_model.layers.12.self_attn.k_proj",
"model.language_model.layers.12.self_attn.v_proj",
"model.language_model.layers.12.self_attn.o_proj",
"model.language_model.layers.13.self_attn.q_proj",
"model.language_model.layers.13.self_attn.k_proj",
"model.language_model.layers.13.self_attn.v_proj",
"model.language_model.layers.13.self_attn.o_proj",
"model.language_model.layers.14.self_attn.q_proj",
"model.language_model.layers.14.self_attn.k_proj",
"model.language_model.layers.14.self_attn.v_proj",
"model.language_model.layers.14.self_attn.o_proj",
"model.language_model.layers.15.self_attn.q_proj",
"model.language_model.layers.15.self_attn.k_proj",
"model.language_model.layers.15.self_attn.v_proj",
"model.language_model.layers.15.self_attn.o_proj",
"model.language_model.layers.16.self_attn.q_proj",
"model.language_model.layers.16.self_attn.k_proj",
"model.language_model.layers.16.self_attn.v_proj",
"model.language_model.layers.16.self_attn.o_proj",
"model.language_model.layers.17.self_attn.q_proj",
"model.language_model.layers.17.self_attn.k_proj",
"model.language_model.layers.17.self_attn.v_proj",
"model.language_model.layers.17.self_attn.o_proj",
"model.language_model.layers.18.self_attn.q_proj",
"model.language_model.layers.18.self_attn.k_proj",
"model.language_model.layers.18.self_attn.v_proj",
"model.language_model.layers.18.self_attn.o_proj",
"model.language_model.layers.19.self_attn.q_proj",
"model.language_model.layers.19.self_attn.k_proj",
"model.language_model.layers.19.self_attn.v_proj",
"model.language_model.layers.19.self_attn.o_proj",
"model.language_model.layers.20.self_attn.q_proj",
"model.language_model.layers.20.self_attn.k_proj",
"model.language_model.layers.20.self_attn.v_proj",
"model.language_model.layers.20.self_attn.o_proj",
"model.language_model.layers.21.self_attn.q_proj",
"model.language_model.layers.21.self_attn.k_proj",
"model.language_model.layers.21.self_attn.v_proj",
"model.language_model.layers.21.self_attn.o_proj",
"model.language_model.layers.22.self_attn.q_proj",
"model.language_model.layers.22.self_attn.k_proj",
"model.language_model.layers.22.self_attn.v_proj",
"model.language_model.layers.22.self_attn.o_proj",
"model.language_model.layers.23.self_attn.q_proj",
"model.language_model.layers.23.self_attn.k_proj",
"model.language_model.layers.23.self_attn.v_proj",
"model.language_model.layers.23.self_attn.o_proj",
"model.language_model.layers.24.self_attn.q_proj",
"model.language_model.layers.24.self_attn.k_proj",
"model.language_model.layers.24.self_attn.v_proj",
"model.language_model.layers.24.self_attn.o_proj",
"model.language_model.layers.25.self_attn.q_proj",
"model.language_model.layers.25.self_attn.k_proj",
"model.language_model.layers.25.self_attn.v_proj",
"model.language_model.layers.25.self_attn.o_proj",
"model.language_model.layers.26.self_attn.q_proj",
"model.language_model.layers.26.self_attn.k_proj",
"model.language_model.layers.26.self_attn.v_proj",
"model.language_model.layers.26.self_attn.o_proj",
"model.language_model.layers.27.self_attn.q_proj",
"model.language_model.layers.27.self_attn.k_proj",
"model.language_model.layers.27.self_attn.v_proj",
"model.language_model.layers.27.self_attn.o_proj",
"model.acoustic_tokenizer.encoder.stages.0.0.ffn.linear1",
"model.acoustic_tokenizer.encoder.stages.0.0.ffn.linear2",
"model.acoustic_tokenizer.encoder.stages.0.1.ffn.linear1",
"model.acoustic_tokenizer.encoder.stages.0.1.ffn.linear2",
"model.acoustic_tokenizer.encoder.stages.0.2.ffn.linear1",
"model.acoustic_tokenizer.encoder.stages.0.2.ffn.linear2",
"model.acoustic_tokenizer.encoder.stages.1.0.ffn.linear1",
"model.acoustic_tokenizer.encoder.stages.1.0.ffn.linear2",
"model.acoustic_tokenizer.encoder.stages.1.1.ffn.linear1",
"model.acoustic_tokenizer.encoder.stages.1.1.ffn.linear2",
"model.acoustic_tokenizer.encoder.stages.1.2.ffn.linear1",
"model.acoustic_tokenizer.encoder.stages.1.2.ffn.linear2",
"model.acoustic_tokenizer.encoder.stages.2.0.ffn.linear1",
"model.acoustic_tokenizer.encoder.stages.2.0.ffn.linear2",
"model.acoustic_tokenizer.encoder.stages.2.1.ffn.linear1",
"model.acoustic_tokenizer.encoder.stages.2.1.ffn.linear2",
"model.acoustic_tokenizer.encoder.stages.2.2.ffn.linear1",
"model.acoustic_tokenizer.encoder.stages.2.2.ffn.linear2",
"model.acoustic_tokenizer.encoder.stages.3.0.ffn.linear1",
"model.acoustic_tokenizer.encoder.stages.3.0.ffn.linear2",
"model.acoustic_tokenizer.encoder.stages.3.1.ffn.linear1",
"model.acoustic_tokenizer.encoder.stages.3.1.ffn.linear2",
"model.acoustic_tokenizer.encoder.stages.3.2.ffn.linear1",
"model.acoustic_tokenizer.encoder.stages.3.2.ffn.linear2",
"model.acoustic_tokenizer.encoder.stages.4.0.ffn.linear1",
"model.acoustic_tokenizer.encoder.stages.4.0.ffn.linear2",
"model.acoustic_tokenizer.encoder.stages.4.1.ffn.linear1",
"model.acoustic_tokenizer.encoder.stages.4.1.ffn.linear2",
"model.acoustic_tokenizer.encoder.stages.4.2.ffn.linear1",
"model.acoustic_tokenizer.encoder.stages.4.2.ffn.linear2",
"model.acoustic_tokenizer.encoder.stages.5.0.ffn.linear1",
"model.acoustic_tokenizer.encoder.stages.5.0.ffn.linear2",
"model.acoustic_tokenizer.encoder.stages.5.1.ffn.linear1",
"model.acoustic_tokenizer.encoder.stages.5.1.ffn.linear2",
"model.acoustic_tokenizer.encoder.stages.5.2.ffn.linear1",
"model.acoustic_tokenizer.encoder.stages.5.2.ffn.linear2",
"model.acoustic_tokenizer.encoder.stages.6.0.ffn.linear1",
"model.acoustic_tokenizer.encoder.stages.6.0.ffn.linear2",
"model.acoustic_tokenizer.encoder.stages.6.1.ffn.linear1",
"model.acoustic_tokenizer.encoder.stages.6.1.ffn.linear2",
"model.acoustic_tokenizer.encoder.stages.6.2.ffn.linear1",
"model.acoustic_tokenizer.encoder.stages.6.2.ffn.linear2",
"model.acoustic_tokenizer.encoder.stages.6.3.ffn.linear1",
"model.acoustic_tokenizer.encoder.stages.6.3.ffn.linear2",
"model.acoustic_tokenizer.encoder.stages.6.4.ffn.linear1",
"model.acoustic_tokenizer.encoder.stages.6.4.ffn.linear2",
"model.acoustic_tokenizer.encoder.stages.6.5.ffn.linear1",
"model.acoustic_tokenizer.encoder.stages.6.5.ffn.linear2",
"model.acoustic_tokenizer.encoder.stages.6.6.ffn.linear1",
"model.acoustic_tokenizer.encoder.stages.6.6.ffn.linear2",
"model.acoustic_tokenizer.encoder.stages.6.7.ffn.linear1",
"model.acoustic_tokenizer.encoder.stages.6.7.ffn.linear2",
"model.acoustic_tokenizer.decoder.stages.0.0.ffn.linear1",
"model.acoustic_tokenizer.decoder.stages.0.0.ffn.linear2",
"model.acoustic_tokenizer.decoder.stages.0.1.ffn.linear1",
"model.acoustic_tokenizer.decoder.stages.0.1.ffn.linear2",
"model.acoustic_tokenizer.decoder.stages.0.2.ffn.linear1",
"model.acoustic_tokenizer.decoder.stages.0.2.ffn.linear2",
"model.acoustic_tokenizer.decoder.stages.0.3.ffn.linear1",
"model.acoustic_tokenizer.decoder.stages.0.3.ffn.linear2",
"model.acoustic_tokenizer.decoder.stages.0.4.ffn.linear1",
"model.acoustic_tokenizer.decoder.stages.0.4.ffn.linear2",
"model.acoustic_tokenizer.decoder.stages.0.5.ffn.linear1",
"model.acoustic_tokenizer.decoder.stages.0.5.ffn.linear2",
"model.acoustic_tokenizer.decoder.stages.0.6.ffn.linear1",
"model.acoustic_tokenizer.decoder.stages.0.6.ffn.linear2",
"model.acoustic_tokenizer.decoder.stages.0.7.ffn.linear1",
"model.acoustic_tokenizer.decoder.stages.0.7.ffn.linear2",
"model.acoustic_tokenizer.decoder.stages.1.0.ffn.linear1",
"model.acoustic_tokenizer.decoder.stages.1.0.ffn.linear2",
"model.acoustic_tokenizer.decoder.stages.1.1.ffn.linear1",
"model.acoustic_tokenizer.decoder.stages.1.1.ffn.linear2",
"model.acoustic_tokenizer.decoder.stages.1.2.ffn.linear1",
"model.acoustic_tokenizer.decoder.stages.1.2.ffn.linear2",
"model.acoustic_tokenizer.decoder.stages.2.0.ffn.linear1",
"model.acoustic_tokenizer.decoder.stages.2.0.ffn.linear2",
"model.acoustic_tokenizer.decoder.stages.2.1.ffn.linear1",
"model.acoustic_tokenizer.decoder.stages.2.1.ffn.linear2",
"model.acoustic_tokenizer.decoder.stages.2.2.ffn.linear1",
"model.acoustic_tokenizer.decoder.stages.2.2.ffn.linear2",
"model.acoustic_tokenizer.decoder.stages.3.0.ffn.linear1",
"model.acoustic_tokenizer.decoder.stages.3.0.ffn.linear2",
"model.acoustic_tokenizer.decoder.stages.3.1.ffn.linear1",
"model.acoustic_tokenizer.decoder.stages.3.1.ffn.linear2",
"model.acoustic_tokenizer.decoder.stages.3.2.ffn.linear1",
"model.acoustic_tokenizer.decoder.stages.3.2.ffn.linear2",
"model.acoustic_tokenizer.decoder.stages.4.0.ffn.linear1",
"model.acoustic_tokenizer.decoder.stages.4.0.ffn.linear2",
"model.acoustic_tokenizer.decoder.stages.4.1.ffn.linear1",
"model.acoustic_tokenizer.decoder.stages.4.1.ffn.linear2",
"model.acoustic_tokenizer.decoder.stages.4.2.ffn.linear1",
"model.acoustic_tokenizer.decoder.stages.4.2.ffn.linear2",
"model.acoustic_tokenizer.decoder.stages.5.0.ffn.linear1",
"model.acoustic_tokenizer.decoder.stages.5.0.ffn.linear2",
"model.acoustic_tokenizer.decoder.stages.5.1.ffn.linear1",
"model.acoustic_tokenizer.decoder.stages.5.1.ffn.linear2",
"model.acoustic_tokenizer.decoder.stages.5.2.ffn.linear1",
"model.acoustic_tokenizer.decoder.stages.5.2.ffn.linear2",
"model.acoustic_tokenizer.decoder.stages.6.0.ffn.linear1",
"model.acoustic_tokenizer.decoder.stages.6.0.ffn.linear2",
"model.acoustic_tokenizer.decoder.stages.6.1.ffn.linear1",
"model.acoustic_tokenizer.decoder.stages.6.1.ffn.linear2",
"model.acoustic_tokenizer.decoder.stages.6.2.ffn.linear1",
"model.acoustic_tokenizer.decoder.stages.6.2.ffn.linear2",
"model.semantic_tokenizer.encoder.stages.0.0.ffn.linear1",
"model.semantic_tokenizer.encoder.stages.0.0.ffn.linear2",
"model.semantic_tokenizer.encoder.stages.0.1.ffn.linear1",
"model.semantic_tokenizer.encoder.stages.0.1.ffn.linear2",
"model.semantic_tokenizer.encoder.stages.0.2.ffn.linear1",
"model.semantic_tokenizer.encoder.stages.0.2.ffn.linear2",
"model.semantic_tokenizer.encoder.stages.1.0.ffn.linear1",
"model.semantic_tokenizer.encoder.stages.1.0.ffn.linear2",
"model.semantic_tokenizer.encoder.stages.1.1.ffn.linear1",
"model.semantic_tokenizer.encoder.stages.1.1.ffn.linear2",
"model.semantic_tokenizer.encoder.stages.1.2.ffn.linear1",
"model.semantic_tokenizer.encoder.stages.1.2.ffn.linear2",
"model.semantic_tokenizer.encoder.stages.2.0.ffn.linear1",
"model.semantic_tokenizer.encoder.stages.2.0.ffn.linear2",
"model.semantic_tokenizer.encoder.stages.2.1.ffn.linear1",
"model.semantic_tokenizer.encoder.stages.2.1.ffn.linear2",
"model.semantic_tokenizer.encoder.stages.2.2.ffn.linear1",
"model.semantic_tokenizer.encoder.stages.2.2.ffn.linear2",
"model.semantic_tokenizer.encoder.stages.3.0.ffn.linear1",
"model.semantic_tokenizer.encoder.stages.3.0.ffn.linear2",
"model.semantic_tokenizer.encoder.stages.3.1.ffn.linear1",
"model.semantic_tokenizer.encoder.stages.3.1.ffn.linear2",
"model.semantic_tokenizer.encoder.stages.3.2.ffn.linear1",
"model.semantic_tokenizer.encoder.stages.3.2.ffn.linear2",
"model.semantic_tokenizer.encoder.stages.4.0.ffn.linear1",
"model.semantic_tokenizer.encoder.stages.4.0.ffn.linear2",
"model.semantic_tokenizer.encoder.stages.4.1.ffn.linear1",
"model.semantic_tokenizer.encoder.stages.4.1.ffn.linear2",
"model.semantic_tokenizer.encoder.stages.4.2.ffn.linear1",
"model.semantic_tokenizer.encoder.stages.4.2.ffn.linear2",
"model.semantic_tokenizer.encoder.stages.5.0.ffn.linear1",
"model.semantic_tokenizer.encoder.stages.5.0.ffn.linear2",
"model.semantic_tokenizer.encoder.stages.5.1.ffn.linear1",
"model.semantic_tokenizer.encoder.stages.5.1.ffn.linear2",
"model.semantic_tokenizer.encoder.stages.5.2.ffn.linear1",
"model.semantic_tokenizer.encoder.stages.5.2.ffn.linear2",
"model.semantic_tokenizer.encoder.stages.6.0.ffn.linear1",
"model.semantic_tokenizer.encoder.stages.6.0.ffn.linear2",
"model.semantic_tokenizer.encoder.stages.6.1.ffn.linear1",
"model.semantic_tokenizer.encoder.stages.6.1.ffn.linear2",
"model.semantic_tokenizer.encoder.stages.6.2.ffn.linear1",
"model.semantic_tokenizer.encoder.stages.6.2.ffn.linear2",
"model.semantic_tokenizer.encoder.stages.6.3.ffn.linear1",
"model.semantic_tokenizer.encoder.stages.6.3.ffn.linear2",
"model.semantic_tokenizer.encoder.stages.6.4.ffn.linear1",
"model.semantic_tokenizer.encoder.stages.6.4.ffn.linear2",
"model.semantic_tokenizer.encoder.stages.6.5.ffn.linear1",
"model.semantic_tokenizer.encoder.stages.6.5.ffn.linear2",
"model.semantic_tokenizer.encoder.stages.6.6.ffn.linear1",
"model.semantic_tokenizer.encoder.stages.6.6.ffn.linear2",
"model.semantic_tokenizer.encoder.stages.6.7.ffn.linear1",
"model.semantic_tokenizer.encoder.stages.6.7.ffn.linear2",
"model.acoustic_connector.fc1",
"model.acoustic_connector.fc2",
"model.semantic_connector.fc1",
"model.semantic_connector.fc2",
"lm_head"
],
"kv_cache_scheme": null,
"quant_method": "compressed-tensors",
"quantization_status": "compressed",
"sparsity_config": {},
"transform_config": {},
"version": "0.15.1.dev14+g01a1c9a"
},
"semantic_tokenizer_config": {
"causal": true,
"channels": 1,
"conv_bias": true,
"conv_norm": "none",
"corpus_normalize": 0.0,
"disable_last_norm": true,
"dtype": "bfloat16",
"encoder_depths": "3-3-3-3-3-3-8",
"encoder_n_filters": 32,
"encoder_ratios": [
8,
5,
5,
4,
2,
2
],
"fix_std": 0,
"layer_scale_init_value": 1e-06,
"layernorm": "RMSNorm",
"layernorm_elementwise_affine": true,
"layernorm_eps": 1e-05,
"mixer_layer": "depthwise_conv",
"model_type": "vibevoice_semantic_tokenizer",
"pad_mode": "constant",
"std_dist_type": "none",
"vae_dim": 128,
"weight_init_value": 0.01
},
"semantic_vae_dim": 128,
"transformers_version": "5.2.0"
} |