Upload folder using huggingface_hub
Browse files- config.json +279 -8
- generation_config.json +1 -1
- model-00001-of-00011.safetensors +1 -1
- model-00002-of-00011.safetensors +1 -1
- model-00003-of-00011.safetensors +1 -1
- model-00004-of-00011.safetensors +1 -1
- model-00005-of-00011.safetensors +1 -1
- model-00006-of-00011.safetensors +1 -1
- model-00007-of-00011.safetensors +1 -1
- model-00008-of-00011.safetensors +1 -1
- model-00009-of-00011.safetensors +1 -1
- model-00010-of-00011.safetensors +2 -2
- model-00011-of-00011.safetensors +2 -2
- model.safetensors.index.json +426 -426
- processor_config.json +1 -6
- quantization_config.json +273 -1
config.json
CHANGED
|
@@ -48,11 +48,283 @@
|
|
| 48 |
"initializer_range": 0.02,
|
| 49 |
"model_type": "qwen3_omni_moe",
|
| 50 |
"quantization_config": {
|
| 51 |
-
"autoround_version": "0.
|
| 52 |
"bits": 4,
|
| 53 |
"block_name_to_quantize": "thinker.model.layers,talker.model.layers",
|
| 54 |
"data_type": "int",
|
| 55 |
"extra_config": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
"talker.model.layers.0.mlp.shared_expert_gate": {
|
| 57 |
"bits": 16,
|
| 58 |
"data_type": "fp"
|
|
@@ -155,7 +427,7 @@
|
|
| 155 |
"chunk_size_feed_forward": 0,
|
| 156 |
"cross_attention_hidden_size": null,
|
| 157 |
"decoder_start_token_id": null,
|
| 158 |
-
"dtype":
|
| 159 |
"eos_token_id": null,
|
| 160 |
"finetuning_task": null,
|
| 161 |
"head_dim": 128,
|
|
@@ -240,7 +512,7 @@
|
|
| 240 |
"bos_token_id": null,
|
| 241 |
"chunk_size_feed_forward": 0,
|
| 242 |
"decoder_sparse_step": 1,
|
| 243 |
-
"dtype":
|
| 244 |
"eos_token_id": null,
|
| 245 |
"head_dim": 128,
|
| 246 |
"hidden_act": "silu",
|
|
@@ -312,7 +584,7 @@
|
|
| 312 |
"decoder_start_token_id": null,
|
| 313 |
"downsample_hidden_size": 480,
|
| 314 |
"dropout": 0,
|
| 315 |
-
"dtype":
|
| 316 |
"encoder_attention_heads": 20,
|
| 317 |
"encoder_ffn_dim": 5120,
|
| 318 |
"encoder_layers": 32,
|
|
@@ -333,7 +605,6 @@
|
|
| 333 |
"model_type": "qwen3_omni_moe_audio_encoder",
|
| 334 |
"n_window": 50,
|
| 335 |
"n_window_infer": 800,
|
| 336 |
-
"num_hidden_layers": 32,
|
| 337 |
"num_mel_bins": 128,
|
| 338 |
"output_attentions": false,
|
| 339 |
"output_dim": 2048,
|
|
@@ -373,7 +644,7 @@
|
|
| 373 |
"cross_attention_hidden_size": null,
|
| 374 |
"decoder_sparse_step": 1,
|
| 375 |
"decoder_start_token_id": null,
|
| 376 |
-
"dtype":
|
| 377 |
"eos_token_id": null,
|
| 378 |
"finetuning_task": null,
|
| 379 |
"head_dim": 128,
|
|
@@ -456,7 +727,7 @@
|
|
| 456 |
24
|
| 457 |
],
|
| 458 |
"depth": 27,
|
| 459 |
-
"dtype":
|
| 460 |
"eos_token_id": null,
|
| 461 |
"finetuning_task": null,
|
| 462 |
"hidden_act": "gelu_pytorch_tanh",
|
|
@@ -504,7 +775,7 @@
|
|
| 504 |
"vision_end_token_id": 151653,
|
| 505 |
"vision_start_token_id": 151652
|
| 506 |
},
|
| 507 |
-
"transformers_version": "5.
|
| 508 |
"tts_bos_token_id": 151672,
|
| 509 |
"tts_eos_token_id": 151673,
|
| 510 |
"tts_pad_token_id": 151671,
|
|
|
|
| 48 |
"initializer_range": 0.02,
|
| 49 |
"model_type": "qwen3_omni_moe",
|
| 50 |
"quantization_config": {
|
| 51 |
+
"autoround_version": "0.13.0",
|
| 52 |
"bits": 4,
|
| 53 |
"block_name_to_quantize": "thinker.model.layers,talker.model.layers",
|
| 54 |
"data_type": "int",
|
| 55 |
"extra_config": {
|
| 56 |
+
".*talker\\.model\\.layers\\.0\\.mlp\\.gate.*": {
|
| 57 |
+
"bits": 16,
|
| 58 |
+
"data_type": "float"
|
| 59 |
+
},
|
| 60 |
+
".*talker\\.model\\.layers\\.10\\.mlp\\.gate.*": {
|
| 61 |
+
"bits": 16,
|
| 62 |
+
"data_type": "float"
|
| 63 |
+
},
|
| 64 |
+
".*talker\\.model\\.layers\\.11\\.mlp\\.gate.*": {
|
| 65 |
+
"bits": 16,
|
| 66 |
+
"data_type": "float"
|
| 67 |
+
},
|
| 68 |
+
".*talker\\.model\\.layers\\.12\\.mlp\\.gate.*": {
|
| 69 |
+
"bits": 16,
|
| 70 |
+
"data_type": "float"
|
| 71 |
+
},
|
| 72 |
+
".*talker\\.model\\.layers\\.13\\.mlp\\.gate.*": {
|
| 73 |
+
"bits": 16,
|
| 74 |
+
"data_type": "float"
|
| 75 |
+
},
|
| 76 |
+
".*talker\\.model\\.layers\\.14\\.mlp\\.gate.*": {
|
| 77 |
+
"bits": 16,
|
| 78 |
+
"data_type": "float"
|
| 79 |
+
},
|
| 80 |
+
".*talker\\.model\\.layers\\.15\\.mlp\\.gate.*": {
|
| 81 |
+
"bits": 16,
|
| 82 |
+
"data_type": "float"
|
| 83 |
+
},
|
| 84 |
+
".*talker\\.model\\.layers\\.16\\.mlp\\.gate.*": {
|
| 85 |
+
"bits": 16,
|
| 86 |
+
"data_type": "float"
|
| 87 |
+
},
|
| 88 |
+
".*talker\\.model\\.layers\\.17\\.mlp\\.gate.*": {
|
| 89 |
+
"bits": 16,
|
| 90 |
+
"data_type": "float"
|
| 91 |
+
},
|
| 92 |
+
".*talker\\.model\\.layers\\.18\\.mlp\\.gate.*": {
|
| 93 |
+
"bits": 16,
|
| 94 |
+
"data_type": "float"
|
| 95 |
+
},
|
| 96 |
+
".*talker\\.model\\.layers\\.19\\.mlp\\.gate.*": {
|
| 97 |
+
"bits": 16,
|
| 98 |
+
"data_type": "float"
|
| 99 |
+
},
|
| 100 |
+
".*talker\\.model\\.layers\\.1\\.mlp\\.gate.*": {
|
| 101 |
+
"bits": 16,
|
| 102 |
+
"data_type": "float"
|
| 103 |
+
},
|
| 104 |
+
".*talker\\.model\\.layers\\.2\\.mlp\\.gate.*": {
|
| 105 |
+
"bits": 16,
|
| 106 |
+
"data_type": "float"
|
| 107 |
+
},
|
| 108 |
+
".*talker\\.model\\.layers\\.3\\.mlp\\.gate.*": {
|
| 109 |
+
"bits": 16,
|
| 110 |
+
"data_type": "float"
|
| 111 |
+
},
|
| 112 |
+
".*talker\\.model\\.layers\\.4\\.mlp\\.gate.*": {
|
| 113 |
+
"bits": 16,
|
| 114 |
+
"data_type": "float"
|
| 115 |
+
},
|
| 116 |
+
".*talker\\.model\\.layers\\.5\\.mlp\\.gate.*": {
|
| 117 |
+
"bits": 16,
|
| 118 |
+
"data_type": "float"
|
| 119 |
+
},
|
| 120 |
+
".*talker\\.model\\.layers\\.6\\.mlp\\.gate.*": {
|
| 121 |
+
"bits": 16,
|
| 122 |
+
"data_type": "float"
|
| 123 |
+
},
|
| 124 |
+
".*talker\\.model\\.layers\\.7\\.mlp\\.gate.*": {
|
| 125 |
+
"bits": 16,
|
| 126 |
+
"data_type": "float"
|
| 127 |
+
},
|
| 128 |
+
".*talker\\.model\\.layers\\.8\\.mlp\\.gate.*": {
|
| 129 |
+
"bits": 16,
|
| 130 |
+
"data_type": "float"
|
| 131 |
+
},
|
| 132 |
+
".*talker\\.model\\.layers\\.9\\.mlp\\.gate.*": {
|
| 133 |
+
"bits": 16,
|
| 134 |
+
"data_type": "float"
|
| 135 |
+
},
|
| 136 |
+
".*thinker\\.model\\.layers\\.0\\.mlp\\.gate.*": {
|
| 137 |
+
"bits": 16,
|
| 138 |
+
"data_type": "float"
|
| 139 |
+
},
|
| 140 |
+
".*thinker\\.model\\.layers\\.10\\.mlp\\.gate.*": {
|
| 141 |
+
"bits": 16,
|
| 142 |
+
"data_type": "float"
|
| 143 |
+
},
|
| 144 |
+
".*thinker\\.model\\.layers\\.11\\.mlp\\.gate.*": {
|
| 145 |
+
"bits": 16,
|
| 146 |
+
"data_type": "float"
|
| 147 |
+
},
|
| 148 |
+
".*thinker\\.model\\.layers\\.12\\.mlp\\.gate.*": {
|
| 149 |
+
"bits": 16,
|
| 150 |
+
"data_type": "float"
|
| 151 |
+
},
|
| 152 |
+
".*thinker\\.model\\.layers\\.13\\.mlp\\.gate.*": {
|
| 153 |
+
"bits": 16,
|
| 154 |
+
"data_type": "float"
|
| 155 |
+
},
|
| 156 |
+
".*thinker\\.model\\.layers\\.14\\.mlp\\.gate.*": {
|
| 157 |
+
"bits": 16,
|
| 158 |
+
"data_type": "float"
|
| 159 |
+
},
|
| 160 |
+
".*thinker\\.model\\.layers\\.15\\.mlp\\.gate.*": {
|
| 161 |
+
"bits": 16,
|
| 162 |
+
"data_type": "float"
|
| 163 |
+
},
|
| 164 |
+
".*thinker\\.model\\.layers\\.16\\.mlp\\.gate.*": {
|
| 165 |
+
"bits": 16,
|
| 166 |
+
"data_type": "float"
|
| 167 |
+
},
|
| 168 |
+
".*thinker\\.model\\.layers\\.17\\.mlp\\.gate.*": {
|
| 169 |
+
"bits": 16,
|
| 170 |
+
"data_type": "float"
|
| 171 |
+
},
|
| 172 |
+
".*thinker\\.model\\.layers\\.18\\.mlp\\.gate.*": {
|
| 173 |
+
"bits": 16,
|
| 174 |
+
"data_type": "float"
|
| 175 |
+
},
|
| 176 |
+
".*thinker\\.model\\.layers\\.19\\.mlp\\.gate.*": {
|
| 177 |
+
"bits": 16,
|
| 178 |
+
"data_type": "float"
|
| 179 |
+
},
|
| 180 |
+
".*thinker\\.model\\.layers\\.1\\.mlp\\.gate.*": {
|
| 181 |
+
"bits": 16,
|
| 182 |
+
"data_type": "float"
|
| 183 |
+
},
|
| 184 |
+
".*thinker\\.model\\.layers\\.20\\.mlp\\.gate.*": {
|
| 185 |
+
"bits": 16,
|
| 186 |
+
"data_type": "float"
|
| 187 |
+
},
|
| 188 |
+
".*thinker\\.model\\.layers\\.21\\.mlp\\.gate.*": {
|
| 189 |
+
"bits": 16,
|
| 190 |
+
"data_type": "float"
|
| 191 |
+
},
|
| 192 |
+
".*thinker\\.model\\.layers\\.22\\.mlp\\.gate.*": {
|
| 193 |
+
"bits": 16,
|
| 194 |
+
"data_type": "float"
|
| 195 |
+
},
|
| 196 |
+
".*thinker\\.model\\.layers\\.23\\.mlp\\.gate.*": {
|
| 197 |
+
"bits": 16,
|
| 198 |
+
"data_type": "float"
|
| 199 |
+
},
|
| 200 |
+
".*thinker\\.model\\.layers\\.24\\.mlp\\.gate.*": {
|
| 201 |
+
"bits": 16,
|
| 202 |
+
"data_type": "float"
|
| 203 |
+
},
|
| 204 |
+
".*thinker\\.model\\.layers\\.25\\.mlp\\.gate.*": {
|
| 205 |
+
"bits": 16,
|
| 206 |
+
"data_type": "float"
|
| 207 |
+
},
|
| 208 |
+
".*thinker\\.model\\.layers\\.26\\.mlp\\.gate.*": {
|
| 209 |
+
"bits": 16,
|
| 210 |
+
"data_type": "float"
|
| 211 |
+
},
|
| 212 |
+
".*thinker\\.model\\.layers\\.27\\.mlp\\.gate.*": {
|
| 213 |
+
"bits": 16,
|
| 214 |
+
"data_type": "float"
|
| 215 |
+
},
|
| 216 |
+
".*thinker\\.model\\.layers\\.28\\.mlp\\.gate.*": {
|
| 217 |
+
"bits": 16,
|
| 218 |
+
"data_type": "float"
|
| 219 |
+
},
|
| 220 |
+
".*thinker\\.model\\.layers\\.29\\.mlp\\.gate.*": {
|
| 221 |
+
"bits": 16,
|
| 222 |
+
"data_type": "float"
|
| 223 |
+
},
|
| 224 |
+
".*thinker\\.model\\.layers\\.2\\.mlp\\.gate.*": {
|
| 225 |
+
"bits": 16,
|
| 226 |
+
"data_type": "float"
|
| 227 |
+
},
|
| 228 |
+
".*thinker\\.model\\.layers\\.30\\.mlp\\.gate.*": {
|
| 229 |
+
"bits": 16,
|
| 230 |
+
"data_type": "float"
|
| 231 |
+
},
|
| 232 |
+
".*thinker\\.model\\.layers\\.31\\.mlp\\.gate.*": {
|
| 233 |
+
"bits": 16,
|
| 234 |
+
"data_type": "float"
|
| 235 |
+
},
|
| 236 |
+
".*thinker\\.model\\.layers\\.32\\.mlp\\.gate.*": {
|
| 237 |
+
"bits": 16,
|
| 238 |
+
"data_type": "float"
|
| 239 |
+
},
|
| 240 |
+
".*thinker\\.model\\.layers\\.33\\.mlp\\.gate.*": {
|
| 241 |
+
"bits": 16,
|
| 242 |
+
"data_type": "float"
|
| 243 |
+
},
|
| 244 |
+
".*thinker\\.model\\.layers\\.34\\.mlp\\.gate.*": {
|
| 245 |
+
"bits": 16,
|
| 246 |
+
"data_type": "float"
|
| 247 |
+
},
|
| 248 |
+
".*thinker\\.model\\.layers\\.35\\.mlp\\.gate.*": {
|
| 249 |
+
"bits": 16,
|
| 250 |
+
"data_type": "float"
|
| 251 |
+
},
|
| 252 |
+
".*thinker\\.model\\.layers\\.36\\.mlp\\.gate.*": {
|
| 253 |
+
"bits": 16,
|
| 254 |
+
"data_type": "float"
|
| 255 |
+
},
|
| 256 |
+
".*thinker\\.model\\.layers\\.37\\.mlp\\.gate.*": {
|
| 257 |
+
"bits": 16,
|
| 258 |
+
"data_type": "float"
|
| 259 |
+
},
|
| 260 |
+
".*thinker\\.model\\.layers\\.38\\.mlp\\.gate.*": {
|
| 261 |
+
"bits": 16,
|
| 262 |
+
"data_type": "float"
|
| 263 |
+
},
|
| 264 |
+
".*thinker\\.model\\.layers\\.39\\.mlp\\.gate.*": {
|
| 265 |
+
"bits": 16,
|
| 266 |
+
"data_type": "float"
|
| 267 |
+
},
|
| 268 |
+
".*thinker\\.model\\.layers\\.3\\.mlp\\.gate.*": {
|
| 269 |
+
"bits": 16,
|
| 270 |
+
"data_type": "float"
|
| 271 |
+
},
|
| 272 |
+
".*thinker\\.model\\.layers\\.40\\.mlp\\.gate.*": {
|
| 273 |
+
"bits": 16,
|
| 274 |
+
"data_type": "float"
|
| 275 |
+
},
|
| 276 |
+
".*thinker\\.model\\.layers\\.41\\.mlp\\.gate.*": {
|
| 277 |
+
"bits": 16,
|
| 278 |
+
"data_type": "float"
|
| 279 |
+
},
|
| 280 |
+
".*thinker\\.model\\.layers\\.42\\.mlp\\.gate.*": {
|
| 281 |
+
"bits": 16,
|
| 282 |
+
"data_type": "float"
|
| 283 |
+
},
|
| 284 |
+
".*thinker\\.model\\.layers\\.43\\.mlp\\.gate.*": {
|
| 285 |
+
"bits": 16,
|
| 286 |
+
"data_type": "float"
|
| 287 |
+
},
|
| 288 |
+
".*thinker\\.model\\.layers\\.44\\.mlp\\.gate.*": {
|
| 289 |
+
"bits": 16,
|
| 290 |
+
"data_type": "float"
|
| 291 |
+
},
|
| 292 |
+
".*thinker\\.model\\.layers\\.45\\.mlp\\.gate.*": {
|
| 293 |
+
"bits": 16,
|
| 294 |
+
"data_type": "float"
|
| 295 |
+
},
|
| 296 |
+
".*thinker\\.model\\.layers\\.46\\.mlp\\.gate.*": {
|
| 297 |
+
"bits": 16,
|
| 298 |
+
"data_type": "float"
|
| 299 |
+
},
|
| 300 |
+
".*thinker\\.model\\.layers\\.47\\.mlp\\.gate.*": {
|
| 301 |
+
"bits": 16,
|
| 302 |
+
"data_type": "float"
|
| 303 |
+
},
|
| 304 |
+
".*thinker\\.model\\.layers\\.4\\.mlp\\.gate.*": {
|
| 305 |
+
"bits": 16,
|
| 306 |
+
"data_type": "float"
|
| 307 |
+
},
|
| 308 |
+
".*thinker\\.model\\.layers\\.5\\.mlp\\.gate.*": {
|
| 309 |
+
"bits": 16,
|
| 310 |
+
"data_type": "float"
|
| 311 |
+
},
|
| 312 |
+
".*thinker\\.model\\.layers\\.6\\.mlp\\.gate.*": {
|
| 313 |
+
"bits": 16,
|
| 314 |
+
"data_type": "float"
|
| 315 |
+
},
|
| 316 |
+
".*thinker\\.model\\.layers\\.7\\.mlp\\.gate.*": {
|
| 317 |
+
"bits": 16,
|
| 318 |
+
"data_type": "float"
|
| 319 |
+
},
|
| 320 |
+
".*thinker\\.model\\.layers\\.8\\.mlp\\.gate.*": {
|
| 321 |
+
"bits": 16,
|
| 322 |
+
"data_type": "float"
|
| 323 |
+
},
|
| 324 |
+
".*thinker\\.model\\.layers\\.9\\.mlp\\.gate.*": {
|
| 325 |
+
"bits": 16,
|
| 326 |
+
"data_type": "float"
|
| 327 |
+
},
|
| 328 |
"talker.model.layers.0.mlp.shared_expert_gate": {
|
| 329 |
"bits": 16,
|
| 330 |
"data_type": "fp"
|
|
|
|
| 427 |
"chunk_size_feed_forward": 0,
|
| 428 |
"cross_attention_hidden_size": null,
|
| 429 |
"decoder_start_token_id": null,
|
| 430 |
+
"dtype": "bfloat16",
|
| 431 |
"eos_token_id": null,
|
| 432 |
"finetuning_task": null,
|
| 433 |
"head_dim": 128,
|
|
|
|
| 512 |
"bos_token_id": null,
|
| 513 |
"chunk_size_feed_forward": 0,
|
| 514 |
"decoder_sparse_step": 1,
|
| 515 |
+
"dtype": "bfloat16",
|
| 516 |
"eos_token_id": null,
|
| 517 |
"head_dim": 128,
|
| 518 |
"hidden_act": "silu",
|
|
|
|
| 584 |
"decoder_start_token_id": null,
|
| 585 |
"downsample_hidden_size": 480,
|
| 586 |
"dropout": 0,
|
| 587 |
+
"dtype": "bfloat16",
|
| 588 |
"encoder_attention_heads": 20,
|
| 589 |
"encoder_ffn_dim": 5120,
|
| 590 |
"encoder_layers": 32,
|
|
|
|
| 605 |
"model_type": "qwen3_omni_moe_audio_encoder",
|
| 606 |
"n_window": 50,
|
| 607 |
"n_window_infer": 800,
|
|
|
|
| 608 |
"num_mel_bins": 128,
|
| 609 |
"output_attentions": false,
|
| 610 |
"output_dim": 2048,
|
|
|
|
| 644 |
"cross_attention_hidden_size": null,
|
| 645 |
"decoder_sparse_step": 1,
|
| 646 |
"decoder_start_token_id": null,
|
| 647 |
+
"dtype": "bfloat16",
|
| 648 |
"eos_token_id": null,
|
| 649 |
"finetuning_task": null,
|
| 650 |
"head_dim": 128,
|
|
|
|
| 727 |
24
|
| 728 |
],
|
| 729 |
"depth": 27,
|
| 730 |
+
"dtype": "bfloat16",
|
| 731 |
"eos_token_id": null,
|
| 732 |
"finetuning_task": null,
|
| 733 |
"hidden_act": "gelu_pytorch_tanh",
|
|
|
|
| 775 |
"vision_end_token_id": 151653,
|
| 776 |
"vision_start_token_id": 151652
|
| 777 |
},
|
| 778 |
+
"transformers_version": "5.4.0",
|
| 779 |
"tts_bos_token_id": 151672,
|
| 780 |
"tts_eos_token_id": 151673,
|
| 781 |
"tts_pad_token_id": 151671,
|
generation_config.json
CHANGED
|
@@ -4,5 +4,5 @@
|
|
| 4 |
"talker_temperature": 0.9,
|
| 5 |
"talker_top_k": 50,
|
| 6 |
"talker_top_p": 1.0,
|
| 7 |
-
"transformers_version": "5.
|
| 8 |
}
|
|
|
|
| 4 |
"talker_temperature": 0.9,
|
| 5 |
"talker_top_k": 50,
|
| 6 |
"talker_top_p": 1.0,
|
| 7 |
+
"transformers_version": "5.4.0"
|
| 8 |
}
|
model-00001-of-00011.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2148102080
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f819e2dfd5876c5bf5ac14ffd048ab20c85d1baaa85b75549aaab8d81f96e903
|
| 3 |
size 2148102080
|
model-00002-of-00011.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2148114544
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77627299a3bcdd734799ef4ac63e3a90f8ba206944179d7853dc7dea1f0c7b7c
|
| 3 |
size 2148114544
|
model-00003-of-00011.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2148405552
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbfc06b4ce06d3df375f133b87cdb86ba93f4e630cd6773e187becbb76182ab2
|
| 3 |
size 2148405552
|
model-00004-of-00011.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2148118400
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d9b2d4fa17dfc8a4b90bde306dec19eaac8a07df19edaeadda625cb9dad4ce4
|
| 3 |
size 2148118400
|
model-00005-of-00011.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2148118472
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ca5f2da29b2d36e947c9a0129a454a44b83d7872aa3f8834eefb19ed9f2a282
|
| 3 |
size 2148118472
|
model-00006-of-00011.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2148405448
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d133b7cf20e226723296a492835dc15f202a008a74074f6fda188c9b59a6675
|
| 3 |
size 2148405448
|
model-00007-of-00011.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2148118472
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03c2c40376e6c83efaccdb34be3a6c11f0cd696e862bf1ff05f6b2e6f055e648
|
| 3 |
size 2148118472
|
model-00008-of-00011.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2150651144
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84a741513c977e19dd3c965f04e4920733a70ccdffab200547220b1266e61cbc
|
| 3 |
size 2150651144
|
model-00009-of-00011.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2147104056
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8402c6ef34a8b0ec7b5010c2d971ea45147bad26b3d0f9541672dcaf364c534
|
| 3 |
size 2147104056
|
model-00010-of-00011.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84205138e153425351ca30604e01e11043778b3dc88c782d6dc38430764a5c58
|
| 3 |
+
size 2139706640
|
model-00011-of-00011.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4412b4c0159c8347de817e35d373eb21d9a6c5e11455d110675d8c6577c57210
|
| 3 |
+
size 113144042
|
model.safetensors.index.json
CHANGED
|
@@ -2,8 +2,8 @@
|
|
| 2 |
"metadata": {
|
| 3 |
"format": "safetensors",
|
| 4 |
"total_shards": 11,
|
| 5 |
-
"total_parameters":
|
| 6 |
-
"total_size":
|
| 7 |
},
|
| 8 |
"weight_map": {
|
| 9 |
"thinker.model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00011.safetensors",
|
|
@@ -79285,419 +79285,419 @@
|
|
| 79285 |
"talker.model.layers.19.mlp.experts.82.gate_proj.qweight": "model-00008-of-00011.safetensors",
|
| 79286 |
"talker.model.layers.19.mlp.experts.82.gate_proj.qzeros": "model-00008-of-00011.safetensors",
|
| 79287 |
"talker.model.layers.19.mlp.experts.82.gate_proj.scales": "model-00008-of-00011.safetensors",
|
| 79288 |
-
"talker.model.layers.19.mlp.experts.82.up_proj.qweight": "model-
|
| 79289 |
-
"talker.model.layers.19.mlp.experts.82.up_proj.qzeros": "model-
|
| 79290 |
-
"talker.model.layers.19.mlp.experts.82.up_proj.scales": "model-
|
| 79291 |
-
"talker.model.layers.19.mlp.experts.82.down_proj.qweight": "model-
|
| 79292 |
-
"talker.model.layers.19.mlp.experts.82.down_proj.qzeros": "model-
|
| 79293 |
-
"talker.model.layers.19.mlp.experts.82.down_proj.scales": "model-
|
| 79294 |
-
"talker.model.layers.19.mlp.experts.83.gate_proj.qweight": "model-
|
| 79295 |
-
"talker.model.layers.19.mlp.experts.83.gate_proj.qzeros": "model-
|
| 79296 |
-
"talker.model.layers.19.mlp.experts.83.gate_proj.scales": "model-
|
| 79297 |
-
"talker.model.layers.19.mlp.experts.83.up_proj.qweight": "model-
|
| 79298 |
-
"talker.model.layers.19.mlp.experts.83.up_proj.qzeros": "model-
|
| 79299 |
-
"talker.model.layers.19.mlp.experts.83.up_proj.scales": "model-
|
| 79300 |
-
"talker.model.layers.19.mlp.experts.83.down_proj.qweight": "model-
|
| 79301 |
-
"talker.model.layers.19.mlp.experts.83.down_proj.qzeros": "model-
|
| 79302 |
-
"talker.model.layers.19.mlp.experts.83.down_proj.scales": "model-
|
| 79303 |
-
"talker.model.layers.19.mlp.experts.84.gate_proj.qweight": "model-
|
| 79304 |
-
"talker.model.layers.19.mlp.experts.84.gate_proj.qzeros": "model-
|
| 79305 |
-
"talker.model.layers.19.mlp.experts.84.gate_proj.scales": "model-
|
| 79306 |
-
"talker.model.layers.19.mlp.experts.84.up_proj.qweight": "model-
|
| 79307 |
-
"talker.model.layers.19.mlp.experts.84.up_proj.qzeros": "model-
|
| 79308 |
-
"talker.model.layers.19.mlp.experts.84.up_proj.scales": "model-
|
| 79309 |
-
"talker.model.layers.19.mlp.experts.84.down_proj.qweight": "model-
|
| 79310 |
-
"talker.model.layers.19.mlp.experts.84.down_proj.qzeros": "model-
|
| 79311 |
-
"talker.model.layers.19.mlp.experts.84.down_proj.scales": "model-
|
| 79312 |
-
"talker.model.layers.19.mlp.experts.85.gate_proj.qweight": "model-
|
| 79313 |
-
"talker.model.layers.19.mlp.experts.85.gate_proj.qzeros": "model-
|
| 79314 |
-
"talker.model.layers.19.mlp.experts.85.gate_proj.scales": "model-
|
| 79315 |
-
"talker.model.layers.19.mlp.experts.85.up_proj.qweight": "model-
|
| 79316 |
-
"talker.model.layers.19.mlp.experts.85.up_proj.qzeros": "model-
|
| 79317 |
-
"talker.model.layers.19.mlp.experts.85.up_proj.scales": "model-
|
| 79318 |
-
"talker.model.layers.19.mlp.experts.85.down_proj.qweight": "model-
|
| 79319 |
-
"talker.model.layers.19.mlp.experts.85.down_proj.qzeros": "model-
|
| 79320 |
-
"talker.model.layers.19.mlp.experts.85.down_proj.scales": "model-
|
| 79321 |
-
"talker.model.layers.19.mlp.experts.86.gate_proj.qweight": "model-
|
| 79322 |
-
"talker.model.layers.19.mlp.experts.86.gate_proj.qzeros": "model-
|
| 79323 |
-
"talker.model.layers.19.mlp.experts.86.gate_proj.scales": "model-
|
| 79324 |
-
"talker.model.layers.19.mlp.experts.86.up_proj.qweight": "model-
|
| 79325 |
-
"talker.model.layers.19.mlp.experts.86.up_proj.qzeros": "model-
|
| 79326 |
-
"talker.model.layers.19.mlp.experts.86.up_proj.scales": "model-
|
| 79327 |
-
"talker.model.layers.19.mlp.experts.86.down_proj.qweight": "model-
|
| 79328 |
-
"talker.model.layers.19.mlp.experts.86.down_proj.qzeros": "model-
|
| 79329 |
-
"talker.model.layers.19.mlp.experts.86.down_proj.scales": "model-
|
| 79330 |
-
"talker.model.layers.19.mlp.experts.87.gate_proj.qweight": "model-
|
| 79331 |
-
"talker.model.layers.19.mlp.experts.87.gate_proj.qzeros": "model-
|
| 79332 |
-
"talker.model.layers.19.mlp.experts.87.gate_proj.scales": "model-
|
| 79333 |
-
"talker.model.layers.19.mlp.experts.87.up_proj.qweight": "model-
|
| 79334 |
-
"talker.model.layers.19.mlp.experts.87.up_proj.qzeros": "model-
|
| 79335 |
-
"talker.model.layers.19.mlp.experts.87.up_proj.scales": "model-
|
| 79336 |
-
"talker.model.layers.19.mlp.experts.87.down_proj.qweight": "model-
|
| 79337 |
-
"talker.model.layers.19.mlp.experts.87.down_proj.qzeros": "model-
|
| 79338 |
-
"talker.model.layers.19.mlp.experts.87.down_proj.scales": "model-
|
| 79339 |
-
"talker.model.layers.19.mlp.experts.88.gate_proj.qweight": "model-
|
| 79340 |
-
"talker.model.layers.19.mlp.experts.88.gate_proj.qzeros": "model-
|
| 79341 |
-
"talker.model.layers.19.mlp.experts.88.gate_proj.scales": "model-
|
| 79342 |
-
"talker.model.layers.19.mlp.experts.88.up_proj.qweight": "model-
|
| 79343 |
-
"talker.model.layers.19.mlp.experts.88.up_proj.qzeros": "model-
|
| 79344 |
-
"talker.model.layers.19.mlp.experts.88.up_proj.scales": "model-
|
| 79345 |
-
"talker.model.layers.19.mlp.experts.88.down_proj.qweight": "model-
|
| 79346 |
-
"talker.model.layers.19.mlp.experts.88.down_proj.qzeros": "model-
|
| 79347 |
-
"talker.model.layers.19.mlp.experts.88.down_proj.scales": "model-
|
| 79348 |
-
"talker.model.layers.19.mlp.experts.89.gate_proj.qweight": "model-
|
| 79349 |
-
"talker.model.layers.19.mlp.experts.89.gate_proj.qzeros": "model-
|
| 79350 |
-
"talker.model.layers.19.mlp.experts.89.gate_proj.scales": "model-
|
| 79351 |
-
"talker.model.layers.19.mlp.experts.89.up_proj.qweight": "model-
|
| 79352 |
-
"talker.model.layers.19.mlp.experts.89.up_proj.qzeros": "model-
|
| 79353 |
-
"talker.model.layers.19.mlp.experts.89.up_proj.scales": "model-
|
| 79354 |
-
"talker.model.layers.19.mlp.experts.89.down_proj.qweight": "model-
|
| 79355 |
-
"talker.model.layers.19.mlp.experts.89.down_proj.qzeros": "model-
|
| 79356 |
-
"talker.model.layers.19.mlp.experts.89.down_proj.scales": "model-
|
| 79357 |
-
"talker.model.layers.19.mlp.experts.90.gate_proj.qweight": "model-
|
| 79358 |
-
"talker.model.layers.19.mlp.experts.90.gate_proj.qzeros": "model-
|
| 79359 |
-
"talker.model.layers.19.mlp.experts.90.gate_proj.scales": "model-
|
| 79360 |
-
"talker.model.layers.19.mlp.experts.90.up_proj.qweight": "model-
|
| 79361 |
-
"talker.model.layers.19.mlp.experts.90.up_proj.qzeros": "model-
|
| 79362 |
-
"talker.model.layers.19.mlp.experts.90.up_proj.scales": "model-
|
| 79363 |
-
"talker.model.layers.19.mlp.experts.90.down_proj.qweight": "model-
|
| 79364 |
-
"talker.model.layers.19.mlp.experts.90.down_proj.qzeros": "model-
|
| 79365 |
-
"talker.model.layers.19.mlp.experts.90.down_proj.scales": "model-
|
| 79366 |
-
"talker.model.layers.19.mlp.experts.91.gate_proj.qweight": "model-
|
| 79367 |
-
"talker.model.layers.19.mlp.experts.91.gate_proj.qzeros": "model-
|
| 79368 |
-
"talker.model.layers.19.mlp.experts.91.gate_proj.scales": "model-
|
| 79369 |
-
"talker.model.layers.19.mlp.experts.91.up_proj.qweight": "model-
|
| 79370 |
-
"talker.model.layers.19.mlp.experts.91.up_proj.qzeros": "model-
|
| 79371 |
-
"talker.model.layers.19.mlp.experts.91.up_proj.scales": "model-
|
| 79372 |
-
"talker.model.layers.19.mlp.experts.91.down_proj.qweight": "model-
|
| 79373 |
-
"talker.model.layers.19.mlp.experts.91.down_proj.qzeros": "model-
|
| 79374 |
-
"talker.model.layers.19.mlp.experts.91.down_proj.scales": "model-
|
| 79375 |
-
"talker.model.layers.19.mlp.experts.92.gate_proj.qweight": "model-
|
| 79376 |
-
"talker.model.layers.19.mlp.experts.92.gate_proj.qzeros": "model-
|
| 79377 |
-
"talker.model.layers.19.mlp.experts.92.gate_proj.scales": "model-
|
| 79378 |
-
"talker.model.layers.19.mlp.experts.92.up_proj.qweight": "model-
|
| 79379 |
-
"talker.model.layers.19.mlp.experts.92.up_proj.qzeros": "model-
|
| 79380 |
-
"talker.model.layers.19.mlp.experts.92.up_proj.scales": "model-
|
| 79381 |
-
"talker.model.layers.19.mlp.experts.92.down_proj.qweight": "model-
|
| 79382 |
-
"talker.model.layers.19.mlp.experts.92.down_proj.qzeros": "model-
|
| 79383 |
-
"talker.model.layers.19.mlp.experts.92.down_proj.scales": "model-
|
| 79384 |
-
"talker.model.layers.19.mlp.experts.93.gate_proj.qweight": "model-
|
| 79385 |
-
"talker.model.layers.19.mlp.experts.93.gate_proj.qzeros": "model-
|
| 79386 |
-
"talker.model.layers.19.mlp.experts.93.gate_proj.scales": "model-
|
| 79387 |
-
"talker.model.layers.19.mlp.experts.93.up_proj.qweight": "model-
|
| 79388 |
-
"talker.model.layers.19.mlp.experts.93.up_proj.qzeros": "model-
|
| 79389 |
-
"talker.model.layers.19.mlp.experts.93.up_proj.scales": "model-
|
| 79390 |
-
"talker.model.layers.19.mlp.experts.93.down_proj.qweight": "model-
|
| 79391 |
-
"talker.model.layers.19.mlp.experts.93.down_proj.qzeros": "model-
|
| 79392 |
-
"talker.model.layers.19.mlp.experts.93.down_proj.scales": "model-
|
| 79393 |
-
"talker.model.layers.19.mlp.experts.94.gate_proj.qweight": "model-
|
| 79394 |
-
"talker.model.layers.19.mlp.experts.94.gate_proj.qzeros": "model-
|
| 79395 |
-
"talker.model.layers.19.mlp.experts.94.gate_proj.scales": "model-
|
| 79396 |
-
"talker.model.layers.19.mlp.experts.94.up_proj.qweight": "model-
|
| 79397 |
-
"talker.model.layers.19.mlp.experts.94.up_proj.qzeros": "model-
|
| 79398 |
-
"talker.model.layers.19.mlp.experts.94.up_proj.scales": "model-
|
| 79399 |
-
"talker.model.layers.19.mlp.experts.94.down_proj.qweight": "model-
|
| 79400 |
-
"talker.model.layers.19.mlp.experts.94.down_proj.qzeros": "model-
|
| 79401 |
-
"talker.model.layers.19.mlp.experts.94.down_proj.scales": "model-
|
| 79402 |
-
"talker.model.layers.19.mlp.experts.95.gate_proj.qweight": "model-
|
| 79403 |
-
"talker.model.layers.19.mlp.experts.95.gate_proj.qzeros": "model-
|
| 79404 |
-
"talker.model.layers.19.mlp.experts.95.gate_proj.scales": "model-
|
| 79405 |
-
"talker.model.layers.19.mlp.experts.95.up_proj.qweight": "model-
|
| 79406 |
-
"talker.model.layers.19.mlp.experts.95.up_proj.qzeros": "model-
|
| 79407 |
-
"talker.model.layers.19.mlp.experts.95.up_proj.scales": "model-
|
| 79408 |
-
"talker.model.layers.19.mlp.experts.95.down_proj.qweight": "model-
|
| 79409 |
-
"talker.model.layers.19.mlp.experts.95.down_proj.qzeros": "model-
|
| 79410 |
-
"talker.model.layers.19.mlp.experts.95.down_proj.scales": "model-
|
| 79411 |
-
"talker.model.layers.19.mlp.experts.96.gate_proj.qweight": "model-
|
| 79412 |
-
"talker.model.layers.19.mlp.experts.96.gate_proj.qzeros": "model-
|
| 79413 |
-
"talker.model.layers.19.mlp.experts.96.gate_proj.scales": "model-
|
| 79414 |
-
"talker.model.layers.19.mlp.experts.96.up_proj.qweight": "model-
|
| 79415 |
-
"talker.model.layers.19.mlp.experts.96.up_proj.qzeros": "model-
|
| 79416 |
-
"talker.model.layers.19.mlp.experts.96.up_proj.scales": "model-
|
| 79417 |
-
"talker.model.layers.19.mlp.experts.96.down_proj.qweight": "model-
|
| 79418 |
-
"talker.model.layers.19.mlp.experts.96.down_proj.qzeros": "model-
|
| 79419 |
-
"talker.model.layers.19.mlp.experts.96.down_proj.scales": "model-
|
| 79420 |
-
"talker.model.layers.19.mlp.experts.97.gate_proj.qweight": "model-
|
| 79421 |
-
"talker.model.layers.19.mlp.experts.97.gate_proj.qzeros": "model-
|
| 79422 |
-
"talker.model.layers.19.mlp.experts.97.gate_proj.scales": "model-
|
| 79423 |
-
"talker.model.layers.19.mlp.experts.97.up_proj.qweight": "model-
|
| 79424 |
-
"talker.model.layers.19.mlp.experts.97.up_proj.qzeros": "model-
|
| 79425 |
-
"talker.model.layers.19.mlp.experts.97.up_proj.scales": "model-
|
| 79426 |
-
"talker.model.layers.19.mlp.experts.97.down_proj.qweight": "model-
|
| 79427 |
-
"talker.model.layers.19.mlp.experts.97.down_proj.qzeros": "model-
|
| 79428 |
-
"talker.model.layers.19.mlp.experts.97.down_proj.scales": "model-
|
| 79429 |
-
"talker.model.layers.19.mlp.experts.98.gate_proj.qweight": "model-
|
| 79430 |
-
"talker.model.layers.19.mlp.experts.98.gate_proj.qzeros": "model-
|
| 79431 |
-
"talker.model.layers.19.mlp.experts.98.gate_proj.scales": "model-
|
| 79432 |
-
"talker.model.layers.19.mlp.experts.98.up_proj.qweight": "model-
|
| 79433 |
-
"talker.model.layers.19.mlp.experts.98.up_proj.qzeros": "model-
|
| 79434 |
-
"talker.model.layers.19.mlp.experts.98.up_proj.scales": "model-
|
| 79435 |
-
"talker.model.layers.19.mlp.experts.98.down_proj.qweight": "model-
|
| 79436 |
-
"talker.model.layers.19.mlp.experts.98.down_proj.qzeros": "model-
|
| 79437 |
-
"talker.model.layers.19.mlp.experts.98.down_proj.scales": "model-
|
| 79438 |
-
"talker.model.layers.19.mlp.experts.99.gate_proj.qweight": "model-
|
| 79439 |
-
"talker.model.layers.19.mlp.experts.99.gate_proj.qzeros": "model-
|
| 79440 |
-
"talker.model.layers.19.mlp.experts.99.gate_proj.scales": "model-
|
| 79441 |
-
"talker.model.layers.19.mlp.experts.99.up_proj.qweight": "model-
|
| 79442 |
-
"talker.model.layers.19.mlp.experts.99.up_proj.qzeros": "model-
|
| 79443 |
-
"talker.model.layers.19.mlp.experts.99.up_proj.scales": "model-
|
| 79444 |
-
"talker.model.layers.19.mlp.experts.99.down_proj.qweight": "model-
|
| 79445 |
-
"talker.model.layers.19.mlp.experts.99.down_proj.qzeros": "model-
|
| 79446 |
-
"talker.model.layers.19.mlp.experts.99.down_proj.scales": "model-
|
| 79447 |
-
"talker.model.layers.19.mlp.experts.100.gate_proj.qweight": "model-
|
| 79448 |
-
"talker.model.layers.19.mlp.experts.100.gate_proj.qzeros": "model-
|
| 79449 |
-
"talker.model.layers.19.mlp.experts.100.gate_proj.scales": "model-
|
| 79450 |
-
"talker.model.layers.19.mlp.experts.100.up_proj.qweight": "model-
|
| 79451 |
-
"talker.model.layers.19.mlp.experts.100.up_proj.qzeros": "model-
|
| 79452 |
-
"talker.model.layers.19.mlp.experts.100.up_proj.scales": "model-
|
| 79453 |
-
"talker.model.layers.19.mlp.experts.100.down_proj.qweight": "model-
|
| 79454 |
-
"talker.model.layers.19.mlp.experts.100.down_proj.qzeros": "model-
|
| 79455 |
-
"talker.model.layers.19.mlp.experts.100.down_proj.scales": "model-
|
| 79456 |
-
"talker.model.layers.19.mlp.experts.101.gate_proj.qweight": "model-
|
| 79457 |
-
"talker.model.layers.19.mlp.experts.101.gate_proj.qzeros": "model-
|
| 79458 |
-
"talker.model.layers.19.mlp.experts.101.gate_proj.scales": "model-
|
| 79459 |
-
"talker.model.layers.19.mlp.experts.101.up_proj.qweight": "model-
|
| 79460 |
-
"talker.model.layers.19.mlp.experts.101.up_proj.qzeros": "model-
|
| 79461 |
-
"talker.model.layers.19.mlp.experts.101.up_proj.scales": "model-
|
| 79462 |
-
"talker.model.layers.19.mlp.experts.101.down_proj.qweight": "model-
|
| 79463 |
-
"talker.model.layers.19.mlp.experts.101.down_proj.qzeros": "model-
|
| 79464 |
-
"talker.model.layers.19.mlp.experts.101.down_proj.scales": "model-
|
| 79465 |
-
"talker.model.layers.19.mlp.experts.102.gate_proj.qweight": "model-
|
| 79466 |
-
"talker.model.layers.19.mlp.experts.102.gate_proj.qzeros": "model-
|
| 79467 |
-
"talker.model.layers.19.mlp.experts.102.gate_proj.scales": "model-
|
| 79468 |
-
"talker.model.layers.19.mlp.experts.102.up_proj.qweight": "model-
|
| 79469 |
-
"talker.model.layers.19.mlp.experts.102.up_proj.qzeros": "model-
|
| 79470 |
-
"talker.model.layers.19.mlp.experts.102.up_proj.scales": "model-
|
| 79471 |
-
"talker.model.layers.19.mlp.experts.102.down_proj.qweight": "model-
|
| 79472 |
-
"talker.model.layers.19.mlp.experts.102.down_proj.qzeros": "model-
|
| 79473 |
-
"talker.model.layers.19.mlp.experts.102.down_proj.scales": "model-
|
| 79474 |
-
"talker.model.layers.19.mlp.experts.103.gate_proj.qweight": "model-
|
| 79475 |
-
"talker.model.layers.19.mlp.experts.103.gate_proj.qzeros": "model-
|
| 79476 |
-
"talker.model.layers.19.mlp.experts.103.gate_proj.scales": "model-
|
| 79477 |
-
"talker.model.layers.19.mlp.experts.103.up_proj.qweight": "model-
|
| 79478 |
-
"talker.model.layers.19.mlp.experts.103.up_proj.qzeros": "model-
|
| 79479 |
-
"talker.model.layers.19.mlp.experts.103.up_proj.scales": "model-
|
| 79480 |
-
"talker.model.layers.19.mlp.experts.103.down_proj.qweight": "model-
|
| 79481 |
-
"talker.model.layers.19.mlp.experts.103.down_proj.qzeros": "model-
|
| 79482 |
-
"talker.model.layers.19.mlp.experts.103.down_proj.scales": "model-
|
| 79483 |
-
"talker.model.layers.19.mlp.experts.104.gate_proj.qweight": "model-
|
| 79484 |
-
"talker.model.layers.19.mlp.experts.104.gate_proj.qzeros": "model-
|
| 79485 |
-
"talker.model.layers.19.mlp.experts.104.gate_proj.scales": "model-
|
| 79486 |
-
"talker.model.layers.19.mlp.experts.104.up_proj.qweight": "model-
|
| 79487 |
-
"talker.model.layers.19.mlp.experts.104.up_proj.qzeros": "model-
|
| 79488 |
-
"talker.model.layers.19.mlp.experts.104.up_proj.scales": "model-
|
| 79489 |
-
"talker.model.layers.19.mlp.experts.104.down_proj.qweight": "model-
|
| 79490 |
-
"talker.model.layers.19.mlp.experts.104.down_proj.qzeros": "model-
|
| 79491 |
-
"talker.model.layers.19.mlp.experts.104.down_proj.scales": "model-
|
| 79492 |
-
"talker.model.layers.19.mlp.experts.105.gate_proj.qweight": "model-
|
| 79493 |
-
"talker.model.layers.19.mlp.experts.105.gate_proj.qzeros": "model-
|
| 79494 |
-
"talker.model.layers.19.mlp.experts.105.gate_proj.scales": "model-
|
| 79495 |
-
"talker.model.layers.19.mlp.experts.105.up_proj.qweight": "model-
|
| 79496 |
-
"talker.model.layers.19.mlp.experts.105.up_proj.qzeros": "model-
|
| 79497 |
-
"talker.model.layers.19.mlp.experts.105.up_proj.scales": "model-
|
| 79498 |
-
"talker.model.layers.19.mlp.experts.105.down_proj.qweight": "model-
|
| 79499 |
-
"talker.model.layers.19.mlp.experts.105.down_proj.qzeros": "model-
|
| 79500 |
-
"talker.model.layers.19.mlp.experts.105.down_proj.scales": "model-
|
| 79501 |
-
"talker.model.layers.19.mlp.experts.106.gate_proj.qweight": "model-
|
| 79502 |
-
"talker.model.layers.19.mlp.experts.106.gate_proj.qzeros": "model-
|
| 79503 |
-
"talker.model.layers.19.mlp.experts.106.gate_proj.scales": "model-
|
| 79504 |
-
"talker.model.layers.19.mlp.experts.106.up_proj.qweight": "model-
|
| 79505 |
-
"talker.model.layers.19.mlp.experts.106.up_proj.qzeros": "model-
|
| 79506 |
-
"talker.model.layers.19.mlp.experts.106.up_proj.scales": "model-
|
| 79507 |
-
"talker.model.layers.19.mlp.experts.106.down_proj.qweight": "model-
|
| 79508 |
-
"talker.model.layers.19.mlp.experts.106.down_proj.qzeros": "model-
|
| 79509 |
-
"talker.model.layers.19.mlp.experts.106.down_proj.scales": "model-
|
| 79510 |
-
"talker.model.layers.19.mlp.experts.107.gate_proj.qweight": "model-
|
| 79511 |
-
"talker.model.layers.19.mlp.experts.107.gate_proj.qzeros": "model-
|
| 79512 |
-
"talker.model.layers.19.mlp.experts.107.gate_proj.scales": "model-
|
| 79513 |
-
"talker.model.layers.19.mlp.experts.107.up_proj.qweight": "model-
|
| 79514 |
-
"talker.model.layers.19.mlp.experts.107.up_proj.qzeros": "model-
|
| 79515 |
-
"talker.model.layers.19.mlp.experts.107.up_proj.scales": "model-
|
| 79516 |
-
"talker.model.layers.19.mlp.experts.107.down_proj.qweight": "model-
|
| 79517 |
-
"talker.model.layers.19.mlp.experts.107.down_proj.qzeros": "model-
|
| 79518 |
-
"talker.model.layers.19.mlp.experts.107.down_proj.scales": "model-
|
| 79519 |
-
"talker.model.layers.19.mlp.experts.108.gate_proj.qweight": "model-
|
| 79520 |
-
"talker.model.layers.19.mlp.experts.108.gate_proj.qzeros": "model-
|
| 79521 |
-
"talker.model.layers.19.mlp.experts.108.gate_proj.scales": "model-
|
| 79522 |
-
"talker.model.layers.19.mlp.experts.108.up_proj.qweight": "model-
|
| 79523 |
-
"talker.model.layers.19.mlp.experts.108.up_proj.qzeros": "model-
|
| 79524 |
-
"talker.model.layers.19.mlp.experts.108.up_proj.scales": "model-
|
| 79525 |
-
"talker.model.layers.19.mlp.experts.108.down_proj.qweight": "model-
|
| 79526 |
-
"talker.model.layers.19.mlp.experts.108.down_proj.qzeros": "model-
|
| 79527 |
-
"talker.model.layers.19.mlp.experts.108.down_proj.scales": "model-
|
| 79528 |
-
"talker.model.layers.19.mlp.experts.109.gate_proj.qweight": "model-
|
| 79529 |
-
"talker.model.layers.19.mlp.experts.109.gate_proj.qzeros": "model-
|
| 79530 |
-
"talker.model.layers.19.mlp.experts.109.gate_proj.scales": "model-
|
| 79531 |
-
"talker.model.layers.19.mlp.experts.109.up_proj.qweight": "model-
|
| 79532 |
-
"talker.model.layers.19.mlp.experts.109.up_proj.qzeros": "model-
|
| 79533 |
-
"talker.model.layers.19.mlp.experts.109.up_proj.scales": "model-
|
| 79534 |
-
"talker.model.layers.19.mlp.experts.109.down_proj.qweight": "model-
|
| 79535 |
-
"talker.model.layers.19.mlp.experts.109.down_proj.qzeros": "model-
|
| 79536 |
-
"talker.model.layers.19.mlp.experts.109.down_proj.scales": "model-
|
| 79537 |
-
"talker.model.layers.19.mlp.experts.110.gate_proj.qweight": "model-
|
| 79538 |
-
"talker.model.layers.19.mlp.experts.110.gate_proj.qzeros": "model-
|
| 79539 |
-
"talker.model.layers.19.mlp.experts.110.gate_proj.scales": "model-
|
| 79540 |
-
"talker.model.layers.19.mlp.experts.110.up_proj.qweight": "model-
|
| 79541 |
-
"talker.model.layers.19.mlp.experts.110.up_proj.qzeros": "model-
|
| 79542 |
-
"talker.model.layers.19.mlp.experts.110.up_proj.scales": "model-
|
| 79543 |
-
"talker.model.layers.19.mlp.experts.110.down_proj.qweight": "model-
|
| 79544 |
-
"talker.model.layers.19.mlp.experts.110.down_proj.qzeros": "model-
|
| 79545 |
-
"talker.model.layers.19.mlp.experts.110.down_proj.scales": "model-
|
| 79546 |
-
"talker.model.layers.19.mlp.experts.111.gate_proj.qweight": "model-
|
| 79547 |
-
"talker.model.layers.19.mlp.experts.111.gate_proj.qzeros": "model-
|
| 79548 |
-
"talker.model.layers.19.mlp.experts.111.gate_proj.scales": "model-
|
| 79549 |
-
"talker.model.layers.19.mlp.experts.111.up_proj.qweight": "model-
|
| 79550 |
-
"talker.model.layers.19.mlp.experts.111.up_proj.qzeros": "model-
|
| 79551 |
-
"talker.model.layers.19.mlp.experts.111.up_proj.scales": "model-
|
| 79552 |
-
"talker.model.layers.19.mlp.experts.111.down_proj.qweight": "model-
|
| 79553 |
-
"talker.model.layers.19.mlp.experts.111.down_proj.qzeros": "model-
|
| 79554 |
-
"talker.model.layers.19.mlp.experts.111.down_proj.scales": "model-
|
| 79555 |
-
"talker.model.layers.19.mlp.experts.112.gate_proj.qweight": "model-
|
| 79556 |
-
"talker.model.layers.19.mlp.experts.112.gate_proj.qzeros": "model-
|
| 79557 |
-
"talker.model.layers.19.mlp.experts.112.gate_proj.scales": "model-
|
| 79558 |
-
"talker.model.layers.19.mlp.experts.112.up_proj.qweight": "model-
|
| 79559 |
-
"talker.model.layers.19.mlp.experts.112.up_proj.qzeros": "model-
|
| 79560 |
-
"talker.model.layers.19.mlp.experts.112.up_proj.scales": "model-
|
| 79561 |
-
"talker.model.layers.19.mlp.experts.112.down_proj.qweight": "model-
|
| 79562 |
-
"talker.model.layers.19.mlp.experts.112.down_proj.qzeros": "model-
|
| 79563 |
-
"talker.model.layers.19.mlp.experts.112.down_proj.scales": "model-
|
| 79564 |
-
"talker.model.layers.19.mlp.experts.113.gate_proj.qweight": "model-
|
| 79565 |
-
"talker.model.layers.19.mlp.experts.113.gate_proj.qzeros": "model-
|
| 79566 |
-
"talker.model.layers.19.mlp.experts.113.gate_proj.scales": "model-
|
| 79567 |
-
"talker.model.layers.19.mlp.experts.113.up_proj.qweight": "model-
|
| 79568 |
-
"talker.model.layers.19.mlp.experts.113.up_proj.qzeros": "model-
|
| 79569 |
-
"talker.model.layers.19.mlp.experts.113.up_proj.scales": "model-
|
| 79570 |
-
"talker.model.layers.19.mlp.experts.113.down_proj.qweight": "model-
|
| 79571 |
-
"talker.model.layers.19.mlp.experts.113.down_proj.qzeros": "model-
|
| 79572 |
-
"talker.model.layers.19.mlp.experts.113.down_proj.scales": "model-
|
| 79573 |
-
"talker.model.layers.19.mlp.experts.114.gate_proj.qweight": "model-
|
| 79574 |
-
"talker.model.layers.19.mlp.experts.114.gate_proj.qzeros": "model-
|
| 79575 |
-
"talker.model.layers.19.mlp.experts.114.gate_proj.scales": "model-
|
| 79576 |
-
"talker.model.layers.19.mlp.experts.114.up_proj.qweight": "model-
|
| 79577 |
-
"talker.model.layers.19.mlp.experts.114.up_proj.qzeros": "model-
|
| 79578 |
-
"talker.model.layers.19.mlp.experts.114.up_proj.scales": "model-
|
| 79579 |
-
"talker.model.layers.19.mlp.experts.114.down_proj.qweight": "model-
|
| 79580 |
-
"talker.model.layers.19.mlp.experts.114.down_proj.qzeros": "model-
|
| 79581 |
-
"talker.model.layers.19.mlp.experts.114.down_proj.scales": "model-
|
| 79582 |
-
"talker.model.layers.19.mlp.experts.115.gate_proj.qweight": "model-
|
| 79583 |
-
"talker.model.layers.19.mlp.experts.115.gate_proj.qzeros": "model-
|
| 79584 |
-
"talker.model.layers.19.mlp.experts.115.gate_proj.scales": "model-
|
| 79585 |
-
"talker.model.layers.19.mlp.experts.115.up_proj.qweight": "model-
|
| 79586 |
-
"talker.model.layers.19.mlp.experts.115.up_proj.qzeros": "model-
|
| 79587 |
-
"talker.model.layers.19.mlp.experts.115.up_proj.scales": "model-
|
| 79588 |
-
"talker.model.layers.19.mlp.experts.115.down_proj.qweight": "model-
|
| 79589 |
-
"talker.model.layers.19.mlp.experts.115.down_proj.qzeros": "model-
|
| 79590 |
-
"talker.model.layers.19.mlp.experts.115.down_proj.scales": "model-
|
| 79591 |
-
"talker.model.layers.19.mlp.experts.116.gate_proj.qweight": "model-
|
| 79592 |
-
"talker.model.layers.19.mlp.experts.116.gate_proj.qzeros": "model-
|
| 79593 |
-
"talker.model.layers.19.mlp.experts.116.gate_proj.scales": "model-
|
| 79594 |
-
"talker.model.layers.19.mlp.experts.116.up_proj.qweight": "model-
|
| 79595 |
-
"talker.model.layers.19.mlp.experts.116.up_proj.qzeros": "model-
|
| 79596 |
-
"talker.model.layers.19.mlp.experts.116.up_proj.scales": "model-
|
| 79597 |
-
"talker.model.layers.19.mlp.experts.116.down_proj.qweight": "model-
|
| 79598 |
-
"talker.model.layers.19.mlp.experts.116.down_proj.qzeros": "model-
|
| 79599 |
-
"talker.model.layers.19.mlp.experts.116.down_proj.scales": "model-
|
| 79600 |
-
"talker.model.layers.19.mlp.experts.117.gate_proj.qweight": "model-
|
| 79601 |
-
"talker.model.layers.19.mlp.experts.117.gate_proj.qzeros": "model-
|
| 79602 |
-
"talker.model.layers.19.mlp.experts.117.gate_proj.scales": "model-
|
| 79603 |
-
"talker.model.layers.19.mlp.experts.117.up_proj.qweight": "model-
|
| 79604 |
-
"talker.model.layers.19.mlp.experts.117.up_proj.qzeros": "model-
|
| 79605 |
-
"talker.model.layers.19.mlp.experts.117.up_proj.scales": "model-
|
| 79606 |
-
"talker.model.layers.19.mlp.experts.117.down_proj.qweight": "model-
|
| 79607 |
-
"talker.model.layers.19.mlp.experts.117.down_proj.qzeros": "model-
|
| 79608 |
-
"talker.model.layers.19.mlp.experts.117.down_proj.scales": "model-
|
| 79609 |
-
"talker.model.layers.19.mlp.experts.118.gate_proj.qweight": "model-
|
| 79610 |
-
"talker.model.layers.19.mlp.experts.118.gate_proj.qzeros": "model-
|
| 79611 |
-
"talker.model.layers.19.mlp.experts.118.gate_proj.scales": "model-
|
| 79612 |
-
"talker.model.layers.19.mlp.experts.118.up_proj.qweight": "model-
|
| 79613 |
-
"talker.model.layers.19.mlp.experts.118.up_proj.qzeros": "model-
|
| 79614 |
-
"talker.model.layers.19.mlp.experts.118.up_proj.scales": "model-
|
| 79615 |
-
"talker.model.layers.19.mlp.experts.118.down_proj.qweight": "model-
|
| 79616 |
-
"talker.model.layers.19.mlp.experts.118.down_proj.qzeros": "model-
|
| 79617 |
-
"talker.model.layers.19.mlp.experts.118.down_proj.scales": "model-
|
| 79618 |
-
"talker.model.layers.19.mlp.experts.119.gate_proj.qweight": "model-
|
| 79619 |
-
"talker.model.layers.19.mlp.experts.119.gate_proj.qzeros": "model-
|
| 79620 |
-
"talker.model.layers.19.mlp.experts.119.gate_proj.scales": "model-
|
| 79621 |
-
"talker.model.layers.19.mlp.experts.119.up_proj.qweight": "model-
|
| 79622 |
-
"talker.model.layers.19.mlp.experts.119.up_proj.qzeros": "model-
|
| 79623 |
-
"talker.model.layers.19.mlp.experts.119.up_proj.scales": "model-
|
| 79624 |
-
"talker.model.layers.19.mlp.experts.119.down_proj.qweight": "model-
|
| 79625 |
-
"talker.model.layers.19.mlp.experts.119.down_proj.qzeros": "model-
|
| 79626 |
-
"talker.model.layers.19.mlp.experts.119.down_proj.scales": "model-
|
| 79627 |
-
"talker.model.layers.19.mlp.experts.120.gate_proj.qweight": "model-
|
| 79628 |
-
"talker.model.layers.19.mlp.experts.120.gate_proj.qzeros": "model-
|
| 79629 |
-
"talker.model.layers.19.mlp.experts.120.gate_proj.scales": "model-
|
| 79630 |
-
"talker.model.layers.19.mlp.experts.120.up_proj.qweight": "model-
|
| 79631 |
-
"talker.model.layers.19.mlp.experts.120.up_proj.qzeros": "model-
|
| 79632 |
-
"talker.model.layers.19.mlp.experts.120.up_proj.scales": "model-
|
| 79633 |
-
"talker.model.layers.19.mlp.experts.120.down_proj.qweight": "model-
|
| 79634 |
-
"talker.model.layers.19.mlp.experts.120.down_proj.qzeros": "model-
|
| 79635 |
-
"talker.model.layers.19.mlp.experts.120.down_proj.scales": "model-
|
| 79636 |
-
"talker.model.layers.19.mlp.experts.121.gate_proj.qweight": "model-
|
| 79637 |
-
"talker.model.layers.19.mlp.experts.121.gate_proj.qzeros": "model-
|
| 79638 |
-
"talker.model.layers.19.mlp.experts.121.gate_proj.scales": "model-
|
| 79639 |
-
"talker.model.layers.19.mlp.experts.121.up_proj.qweight": "model-
|
| 79640 |
-
"talker.model.layers.19.mlp.experts.121.up_proj.qzeros": "model-
|
| 79641 |
-
"talker.model.layers.19.mlp.experts.121.up_proj.scales": "model-
|
| 79642 |
-
"talker.model.layers.19.mlp.experts.121.down_proj.qweight": "model-
|
| 79643 |
-
"talker.model.layers.19.mlp.experts.121.down_proj.qzeros": "model-
|
| 79644 |
-
"talker.model.layers.19.mlp.experts.121.down_proj.scales": "model-
|
| 79645 |
-
"talker.model.layers.19.mlp.experts.122.gate_proj.qweight": "model-
|
| 79646 |
-
"talker.model.layers.19.mlp.experts.122.gate_proj.qzeros": "model-
|
| 79647 |
-
"talker.model.layers.19.mlp.experts.122.gate_proj.scales": "model-
|
| 79648 |
-
"talker.model.layers.19.mlp.experts.122.up_proj.qweight": "model-
|
| 79649 |
-
"talker.model.layers.19.mlp.experts.122.up_proj.qzeros": "model-
|
| 79650 |
-
"talker.model.layers.19.mlp.experts.122.up_proj.scales": "model-
|
| 79651 |
-
"talker.model.layers.19.mlp.experts.122.down_proj.qweight": "model-
|
| 79652 |
-
"talker.model.layers.19.mlp.experts.122.down_proj.qzeros": "model-
|
| 79653 |
-
"talker.model.layers.19.mlp.experts.122.down_proj.scales": "model-
|
| 79654 |
-
"talker.model.layers.19.mlp.experts.123.gate_proj.qweight": "model-
|
| 79655 |
-
"talker.model.layers.19.mlp.experts.123.gate_proj.qzeros": "model-
|
| 79656 |
-
"talker.model.layers.19.mlp.experts.123.gate_proj.scales": "model-
|
| 79657 |
-
"talker.model.layers.19.mlp.experts.123.up_proj.qweight": "model-
|
| 79658 |
-
"talker.model.layers.19.mlp.experts.123.up_proj.qzeros": "model-
|
| 79659 |
-
"talker.model.layers.19.mlp.experts.123.up_proj.scales": "model-
|
| 79660 |
-
"talker.model.layers.19.mlp.experts.123.down_proj.qweight": "model-
|
| 79661 |
-
"talker.model.layers.19.mlp.experts.123.down_proj.qzeros": "model-
|
| 79662 |
-
"talker.model.layers.19.mlp.experts.123.down_proj.scales": "model-
|
| 79663 |
-
"talker.model.layers.19.mlp.experts.124.gate_proj.qweight": "model-
|
| 79664 |
-
"talker.model.layers.19.mlp.experts.124.gate_proj.qzeros": "model-
|
| 79665 |
-
"talker.model.layers.19.mlp.experts.124.gate_proj.scales": "model-
|
| 79666 |
-
"talker.model.layers.19.mlp.experts.124.up_proj.qweight": "model-
|
| 79667 |
-
"talker.model.layers.19.mlp.experts.124.up_proj.qzeros": "model-
|
| 79668 |
-
"talker.model.layers.19.mlp.experts.124.up_proj.scales": "model-
|
| 79669 |
-
"talker.model.layers.19.mlp.experts.124.down_proj.qweight": "model-
|
| 79670 |
-
"talker.model.layers.19.mlp.experts.124.down_proj.qzeros": "model-
|
| 79671 |
-
"talker.model.layers.19.mlp.experts.124.down_proj.scales": "model-
|
| 79672 |
-
"talker.model.layers.19.mlp.experts.125.gate_proj.qweight": "model-
|
| 79673 |
-
"talker.model.layers.19.mlp.experts.125.gate_proj.qzeros": "model-
|
| 79674 |
-
"talker.model.layers.19.mlp.experts.125.gate_proj.scales": "model-
|
| 79675 |
-
"talker.model.layers.19.mlp.experts.125.up_proj.qweight": "model-
|
| 79676 |
-
"talker.model.layers.19.mlp.experts.125.up_proj.qzeros": "model-
|
| 79677 |
-
"talker.model.layers.19.mlp.experts.125.up_proj.scales": "model-
|
| 79678 |
-
"talker.model.layers.19.mlp.experts.125.down_proj.qweight": "model-
|
| 79679 |
-
"talker.model.layers.19.mlp.experts.125.down_proj.qzeros": "model-
|
| 79680 |
-
"talker.model.layers.19.mlp.experts.125.down_proj.scales": "model-
|
| 79681 |
-
"talker.model.layers.19.mlp.experts.126.gate_proj.qweight": "model-
|
| 79682 |
-
"talker.model.layers.19.mlp.experts.126.gate_proj.qzeros": "model-
|
| 79683 |
-
"talker.model.layers.19.mlp.experts.126.gate_proj.scales": "model-
|
| 79684 |
-
"talker.model.layers.19.mlp.experts.126.up_proj.qweight": "model-
|
| 79685 |
-
"talker.model.layers.19.mlp.experts.126.up_proj.qzeros": "model-
|
| 79686 |
-
"talker.model.layers.19.mlp.experts.126.up_proj.scales": "model-
|
| 79687 |
-
"talker.model.layers.19.mlp.experts.126.down_proj.qweight": "model-
|
| 79688 |
-
"talker.model.layers.19.mlp.experts.126.down_proj.qzeros": "model-
|
| 79689 |
-
"talker.model.layers.19.mlp.experts.126.down_proj.scales": "model-
|
| 79690 |
-
"talker.model.layers.19.mlp.experts.127.gate_proj.qweight": "model-
|
| 79691 |
-
"talker.model.layers.19.mlp.experts.127.gate_proj.qzeros": "model-
|
| 79692 |
-
"talker.model.layers.19.mlp.experts.127.gate_proj.scales": "model-
|
| 79693 |
-
"talker.model.layers.19.mlp.experts.127.up_proj.qweight": "model-
|
| 79694 |
-
"talker.model.layers.19.mlp.experts.127.up_proj.qzeros": "model-
|
| 79695 |
-
"talker.model.layers.19.mlp.experts.127.up_proj.scales": "model-
|
| 79696 |
-
"talker.model.layers.19.mlp.experts.127.down_proj.qweight": "model-
|
| 79697 |
-
"talker.model.layers.19.mlp.experts.127.down_proj.qzeros": "model-
|
| 79698 |
-
"talker.model.layers.19.mlp.experts.127.down_proj.scales": "model-
|
| 79699 |
-
"talker.model.layers.19.input_layernorm.weight": "model-
|
| 79700 |
-
"talker.model.layers.19.post_attention_layernorm.weight": "model-
|
| 79701 |
"thinker.audio_tower.layers.0.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
| 79702 |
"thinker.audio_tower.layers.0.self_attn.k_proj.bias": "model-00009-of-00011.safetensors",
|
| 79703 |
"thinker.audio_tower.layers.0.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
|
@@ -80773,17 +80773,17 @@
|
|
| 80773 |
"code2wav.upsample.0.1.norm.bias": "model-00010-of-00011.safetensors",
|
| 80774 |
"code2wav.upsample.0.1.pwconv1.weight": "model-00010-of-00011.safetensors",
|
| 80775 |
"code2wav.upsample.0.1.pwconv1.bias": "model-00010-of-00011.safetensors",
|
| 80776 |
-
"code2wav.upsample.0.1.pwconv2.weight": "model-
|
| 80777 |
-
"code2wav.upsample.0.1.pwconv2.bias": "model-
|
| 80778 |
-
"code2wav.upsample.1.0.conv.weight": "model-
|
| 80779 |
-
"code2wav.upsample.1.0.conv.bias": "model-
|
| 80780 |
-
"code2wav.upsample.1.1.gamma": "model-
|
| 80781 |
-
"code2wav.upsample.1.1.dwconv.conv.weight": "model-
|
| 80782 |
-
"code2wav.upsample.1.1.dwconv.conv.bias": "model-
|
| 80783 |
-
"code2wav.upsample.1.1.norm.weight": "model-
|
| 80784 |
-
"code2wav.upsample.1.1.norm.bias": "model-
|
| 80785 |
-
"code2wav.upsample.1.1.pwconv1.weight": "model-
|
| 80786 |
-
"code2wav.upsample.1.1.pwconv1.bias": "model-
|
| 80787 |
"code2wav.upsample.1.1.pwconv2.weight": "model-00011-of-00011.safetensors",
|
| 80788 |
"code2wav.upsample.1.1.pwconv2.bias": "model-00011-of-00011.safetensors",
|
| 80789 |
"code2wav.decoder.0.conv.weight": "model-00011-of-00011.safetensors",
|
|
|
|
| 2 |
"metadata": {
|
| 3 |
"format": "safetensors",
|
| 4 |
"total_shards": 11,
|
| 5 |
+
"total_parameters": 6624222769,
|
| 6 |
+
"total_size": 21577626722
|
| 7 |
},
|
| 8 |
"weight_map": {
|
| 9 |
"thinker.model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00011.safetensors",
|
|
|
|
| 79285 |
"talker.model.layers.19.mlp.experts.82.gate_proj.qweight": "model-00008-of-00011.safetensors",
|
| 79286 |
"talker.model.layers.19.mlp.experts.82.gate_proj.qzeros": "model-00008-of-00011.safetensors",
|
| 79287 |
"talker.model.layers.19.mlp.experts.82.gate_proj.scales": "model-00008-of-00011.safetensors",
|
| 79288 |
+
"talker.model.layers.19.mlp.experts.82.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79289 |
+
"talker.model.layers.19.mlp.experts.82.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79290 |
+
"talker.model.layers.19.mlp.experts.82.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79291 |
+
"talker.model.layers.19.mlp.experts.82.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79292 |
+
"talker.model.layers.19.mlp.experts.82.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79293 |
+
"talker.model.layers.19.mlp.experts.82.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79294 |
+
"talker.model.layers.19.mlp.experts.83.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79295 |
+
"talker.model.layers.19.mlp.experts.83.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79296 |
+
"talker.model.layers.19.mlp.experts.83.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79297 |
+
"talker.model.layers.19.mlp.experts.83.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79298 |
+
"talker.model.layers.19.mlp.experts.83.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79299 |
+
"talker.model.layers.19.mlp.experts.83.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79300 |
+
"talker.model.layers.19.mlp.experts.83.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79301 |
+
"talker.model.layers.19.mlp.experts.83.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79302 |
+
"talker.model.layers.19.mlp.experts.83.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79303 |
+
"talker.model.layers.19.mlp.experts.84.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79304 |
+
"talker.model.layers.19.mlp.experts.84.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79305 |
+
"talker.model.layers.19.mlp.experts.84.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79306 |
+
"talker.model.layers.19.mlp.experts.84.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79307 |
+
"talker.model.layers.19.mlp.experts.84.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79308 |
+
"talker.model.layers.19.mlp.experts.84.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79309 |
+
"talker.model.layers.19.mlp.experts.84.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79310 |
+
"talker.model.layers.19.mlp.experts.84.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79311 |
+
"talker.model.layers.19.mlp.experts.84.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79312 |
+
"talker.model.layers.19.mlp.experts.85.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79313 |
+
"talker.model.layers.19.mlp.experts.85.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79314 |
+
"talker.model.layers.19.mlp.experts.85.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79315 |
+
"talker.model.layers.19.mlp.experts.85.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79316 |
+
"talker.model.layers.19.mlp.experts.85.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79317 |
+
"talker.model.layers.19.mlp.experts.85.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79318 |
+
"talker.model.layers.19.mlp.experts.85.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79319 |
+
"talker.model.layers.19.mlp.experts.85.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79320 |
+
"talker.model.layers.19.mlp.experts.85.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79321 |
+
"talker.model.layers.19.mlp.experts.86.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79322 |
+
"talker.model.layers.19.mlp.experts.86.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79323 |
+
"talker.model.layers.19.mlp.experts.86.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79324 |
+
"talker.model.layers.19.mlp.experts.86.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79325 |
+
"talker.model.layers.19.mlp.experts.86.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79326 |
+
"talker.model.layers.19.mlp.experts.86.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79327 |
+
"talker.model.layers.19.mlp.experts.86.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79328 |
+
"talker.model.layers.19.mlp.experts.86.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79329 |
+
"talker.model.layers.19.mlp.experts.86.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79330 |
+
"talker.model.layers.19.mlp.experts.87.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79331 |
+
"talker.model.layers.19.mlp.experts.87.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79332 |
+
"talker.model.layers.19.mlp.experts.87.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79333 |
+
"talker.model.layers.19.mlp.experts.87.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79334 |
+
"talker.model.layers.19.mlp.experts.87.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79335 |
+
"talker.model.layers.19.mlp.experts.87.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79336 |
+
"talker.model.layers.19.mlp.experts.87.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79337 |
+
"talker.model.layers.19.mlp.experts.87.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79338 |
+
"talker.model.layers.19.mlp.experts.87.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79339 |
+
"talker.model.layers.19.mlp.experts.88.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79340 |
+
"talker.model.layers.19.mlp.experts.88.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79341 |
+
"talker.model.layers.19.mlp.experts.88.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79342 |
+
"talker.model.layers.19.mlp.experts.88.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79343 |
+
"talker.model.layers.19.mlp.experts.88.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79344 |
+
"talker.model.layers.19.mlp.experts.88.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79345 |
+
"talker.model.layers.19.mlp.experts.88.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79346 |
+
"talker.model.layers.19.mlp.experts.88.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79347 |
+
"talker.model.layers.19.mlp.experts.88.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79348 |
+
"talker.model.layers.19.mlp.experts.89.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79349 |
+
"talker.model.layers.19.mlp.experts.89.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79350 |
+
"talker.model.layers.19.mlp.experts.89.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79351 |
+
"talker.model.layers.19.mlp.experts.89.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79352 |
+
"talker.model.layers.19.mlp.experts.89.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79353 |
+
"talker.model.layers.19.mlp.experts.89.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79354 |
+
"talker.model.layers.19.mlp.experts.89.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79355 |
+
"talker.model.layers.19.mlp.experts.89.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79356 |
+
"talker.model.layers.19.mlp.experts.89.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79357 |
+
"talker.model.layers.19.mlp.experts.90.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79358 |
+
"talker.model.layers.19.mlp.experts.90.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79359 |
+
"talker.model.layers.19.mlp.experts.90.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79360 |
+
"talker.model.layers.19.mlp.experts.90.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79361 |
+
"talker.model.layers.19.mlp.experts.90.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79362 |
+
"talker.model.layers.19.mlp.experts.90.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79363 |
+
"talker.model.layers.19.mlp.experts.90.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79364 |
+
"talker.model.layers.19.mlp.experts.90.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79365 |
+
"talker.model.layers.19.mlp.experts.90.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79366 |
+
"talker.model.layers.19.mlp.experts.91.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79367 |
+
"talker.model.layers.19.mlp.experts.91.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79368 |
+
"talker.model.layers.19.mlp.experts.91.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79369 |
+
"talker.model.layers.19.mlp.experts.91.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79370 |
+
"talker.model.layers.19.mlp.experts.91.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79371 |
+
"talker.model.layers.19.mlp.experts.91.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79372 |
+
"talker.model.layers.19.mlp.experts.91.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79373 |
+
"talker.model.layers.19.mlp.experts.91.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79374 |
+
"talker.model.layers.19.mlp.experts.91.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79375 |
+
"talker.model.layers.19.mlp.experts.92.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79376 |
+
"talker.model.layers.19.mlp.experts.92.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79377 |
+
"talker.model.layers.19.mlp.experts.92.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79378 |
+
"talker.model.layers.19.mlp.experts.92.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79379 |
+
"talker.model.layers.19.mlp.experts.92.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79380 |
+
"talker.model.layers.19.mlp.experts.92.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79381 |
+
"talker.model.layers.19.mlp.experts.92.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79382 |
+
"talker.model.layers.19.mlp.experts.92.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79383 |
+
"talker.model.layers.19.mlp.experts.92.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79384 |
+
"talker.model.layers.19.mlp.experts.93.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79385 |
+
"talker.model.layers.19.mlp.experts.93.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79386 |
+
"talker.model.layers.19.mlp.experts.93.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79387 |
+
"talker.model.layers.19.mlp.experts.93.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79388 |
+
"talker.model.layers.19.mlp.experts.93.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79389 |
+
"talker.model.layers.19.mlp.experts.93.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79390 |
+
"talker.model.layers.19.mlp.experts.93.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79391 |
+
"talker.model.layers.19.mlp.experts.93.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79392 |
+
"talker.model.layers.19.mlp.experts.93.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79393 |
+
"talker.model.layers.19.mlp.experts.94.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79394 |
+
"talker.model.layers.19.mlp.experts.94.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79395 |
+
"talker.model.layers.19.mlp.experts.94.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79396 |
+
"talker.model.layers.19.mlp.experts.94.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79397 |
+
"talker.model.layers.19.mlp.experts.94.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79398 |
+
"talker.model.layers.19.mlp.experts.94.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79399 |
+
"talker.model.layers.19.mlp.experts.94.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79400 |
+
"talker.model.layers.19.mlp.experts.94.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79401 |
+
"talker.model.layers.19.mlp.experts.94.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79402 |
+
"talker.model.layers.19.mlp.experts.95.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79403 |
+
"talker.model.layers.19.mlp.experts.95.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79404 |
+
"talker.model.layers.19.mlp.experts.95.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79405 |
+
"talker.model.layers.19.mlp.experts.95.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79406 |
+
"talker.model.layers.19.mlp.experts.95.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79407 |
+
"talker.model.layers.19.mlp.experts.95.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79408 |
+
"talker.model.layers.19.mlp.experts.95.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79409 |
+
"talker.model.layers.19.mlp.experts.95.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79410 |
+
"talker.model.layers.19.mlp.experts.95.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79411 |
+
"talker.model.layers.19.mlp.experts.96.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79412 |
+
"talker.model.layers.19.mlp.experts.96.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79413 |
+
"talker.model.layers.19.mlp.experts.96.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79414 |
+
"talker.model.layers.19.mlp.experts.96.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79415 |
+
"talker.model.layers.19.mlp.experts.96.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79416 |
+
"talker.model.layers.19.mlp.experts.96.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79417 |
+
"talker.model.layers.19.mlp.experts.96.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79418 |
+
"talker.model.layers.19.mlp.experts.96.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79419 |
+
"talker.model.layers.19.mlp.experts.96.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79420 |
+
"talker.model.layers.19.mlp.experts.97.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79421 |
+
"talker.model.layers.19.mlp.experts.97.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79422 |
+
"talker.model.layers.19.mlp.experts.97.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79423 |
+
"talker.model.layers.19.mlp.experts.97.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79424 |
+
"talker.model.layers.19.mlp.experts.97.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79425 |
+
"talker.model.layers.19.mlp.experts.97.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79426 |
+
"talker.model.layers.19.mlp.experts.97.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79427 |
+
"talker.model.layers.19.mlp.experts.97.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79428 |
+
"talker.model.layers.19.mlp.experts.97.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79429 |
+
"talker.model.layers.19.mlp.experts.98.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79430 |
+
"talker.model.layers.19.mlp.experts.98.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79431 |
+
"talker.model.layers.19.mlp.experts.98.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79432 |
+
"talker.model.layers.19.mlp.experts.98.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79433 |
+
"talker.model.layers.19.mlp.experts.98.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79434 |
+
"talker.model.layers.19.mlp.experts.98.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79435 |
+
"talker.model.layers.19.mlp.experts.98.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79436 |
+
"talker.model.layers.19.mlp.experts.98.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79437 |
+
"talker.model.layers.19.mlp.experts.98.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79438 |
+
"talker.model.layers.19.mlp.experts.99.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79439 |
+
"talker.model.layers.19.mlp.experts.99.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79440 |
+
"talker.model.layers.19.mlp.experts.99.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79441 |
+
"talker.model.layers.19.mlp.experts.99.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79442 |
+
"talker.model.layers.19.mlp.experts.99.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79443 |
+
"talker.model.layers.19.mlp.experts.99.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79444 |
+
"talker.model.layers.19.mlp.experts.99.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79445 |
+
"talker.model.layers.19.mlp.experts.99.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79446 |
+
"talker.model.layers.19.mlp.experts.99.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79447 |
+
"talker.model.layers.19.mlp.experts.100.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79448 |
+
"talker.model.layers.19.mlp.experts.100.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79449 |
+
"talker.model.layers.19.mlp.experts.100.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79450 |
+
"talker.model.layers.19.mlp.experts.100.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79451 |
+
"talker.model.layers.19.mlp.experts.100.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79452 |
+
"talker.model.layers.19.mlp.experts.100.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79453 |
+
"talker.model.layers.19.mlp.experts.100.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79454 |
+
"talker.model.layers.19.mlp.experts.100.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79455 |
+
"talker.model.layers.19.mlp.experts.100.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79456 |
+
"talker.model.layers.19.mlp.experts.101.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79457 |
+
"talker.model.layers.19.mlp.experts.101.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79458 |
+
"talker.model.layers.19.mlp.experts.101.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79459 |
+
"talker.model.layers.19.mlp.experts.101.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79460 |
+
"talker.model.layers.19.mlp.experts.101.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79461 |
+
"talker.model.layers.19.mlp.experts.101.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79462 |
+
"talker.model.layers.19.mlp.experts.101.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79463 |
+
"talker.model.layers.19.mlp.experts.101.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79464 |
+
"talker.model.layers.19.mlp.experts.101.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79465 |
+
"talker.model.layers.19.mlp.experts.102.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79466 |
+
"talker.model.layers.19.mlp.experts.102.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79467 |
+
"talker.model.layers.19.mlp.experts.102.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79468 |
+
"talker.model.layers.19.mlp.experts.102.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79469 |
+
"talker.model.layers.19.mlp.experts.102.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79470 |
+
"talker.model.layers.19.mlp.experts.102.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79471 |
+
"talker.model.layers.19.mlp.experts.102.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79472 |
+
"talker.model.layers.19.mlp.experts.102.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79473 |
+
"talker.model.layers.19.mlp.experts.102.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79474 |
+
"talker.model.layers.19.mlp.experts.103.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79475 |
+
"talker.model.layers.19.mlp.experts.103.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79476 |
+
"talker.model.layers.19.mlp.experts.103.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79477 |
+
"talker.model.layers.19.mlp.experts.103.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79478 |
+
"talker.model.layers.19.mlp.experts.103.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79479 |
+
"talker.model.layers.19.mlp.experts.103.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79480 |
+
"talker.model.layers.19.mlp.experts.103.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79481 |
+
"talker.model.layers.19.mlp.experts.103.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79482 |
+
"talker.model.layers.19.mlp.experts.103.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79483 |
+
"talker.model.layers.19.mlp.experts.104.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79484 |
+
"talker.model.layers.19.mlp.experts.104.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79485 |
+
"talker.model.layers.19.mlp.experts.104.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79486 |
+
"talker.model.layers.19.mlp.experts.104.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79487 |
+
"talker.model.layers.19.mlp.experts.104.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79488 |
+
"talker.model.layers.19.mlp.experts.104.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79489 |
+
"talker.model.layers.19.mlp.experts.104.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79490 |
+
"talker.model.layers.19.mlp.experts.104.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79491 |
+
"talker.model.layers.19.mlp.experts.104.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79492 |
+
"talker.model.layers.19.mlp.experts.105.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79493 |
+
"talker.model.layers.19.mlp.experts.105.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79494 |
+
"talker.model.layers.19.mlp.experts.105.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79495 |
+
"talker.model.layers.19.mlp.experts.105.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79496 |
+
"talker.model.layers.19.mlp.experts.105.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79497 |
+
"talker.model.layers.19.mlp.experts.105.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79498 |
+
"talker.model.layers.19.mlp.experts.105.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79499 |
+
"talker.model.layers.19.mlp.experts.105.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79500 |
+
"talker.model.layers.19.mlp.experts.105.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79501 |
+
"talker.model.layers.19.mlp.experts.106.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79502 |
+
"talker.model.layers.19.mlp.experts.106.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79503 |
+
"talker.model.layers.19.mlp.experts.106.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79504 |
+
"talker.model.layers.19.mlp.experts.106.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79505 |
+
"talker.model.layers.19.mlp.experts.106.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79506 |
+
"talker.model.layers.19.mlp.experts.106.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79507 |
+
"talker.model.layers.19.mlp.experts.106.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79508 |
+
"talker.model.layers.19.mlp.experts.106.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79509 |
+
"talker.model.layers.19.mlp.experts.106.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79510 |
+
"talker.model.layers.19.mlp.experts.107.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79511 |
+
"talker.model.layers.19.mlp.experts.107.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79512 |
+
"talker.model.layers.19.mlp.experts.107.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79513 |
+
"talker.model.layers.19.mlp.experts.107.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79514 |
+
"talker.model.layers.19.mlp.experts.107.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79515 |
+
"talker.model.layers.19.mlp.experts.107.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79516 |
+
"talker.model.layers.19.mlp.experts.107.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79517 |
+
"talker.model.layers.19.mlp.experts.107.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79518 |
+
"talker.model.layers.19.mlp.experts.107.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79519 |
+
"talker.model.layers.19.mlp.experts.108.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79520 |
+
"talker.model.layers.19.mlp.experts.108.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79521 |
+
"talker.model.layers.19.mlp.experts.108.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79522 |
+
"talker.model.layers.19.mlp.experts.108.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79523 |
+
"talker.model.layers.19.mlp.experts.108.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79524 |
+
"talker.model.layers.19.mlp.experts.108.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79525 |
+
"talker.model.layers.19.mlp.experts.108.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79526 |
+
"talker.model.layers.19.mlp.experts.108.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79527 |
+
"talker.model.layers.19.mlp.experts.108.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79528 |
+
"talker.model.layers.19.mlp.experts.109.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79529 |
+
"talker.model.layers.19.mlp.experts.109.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79530 |
+
"talker.model.layers.19.mlp.experts.109.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79531 |
+
"talker.model.layers.19.mlp.experts.109.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79532 |
+
"talker.model.layers.19.mlp.experts.109.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79533 |
+
"talker.model.layers.19.mlp.experts.109.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79534 |
+
"talker.model.layers.19.mlp.experts.109.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79535 |
+
"talker.model.layers.19.mlp.experts.109.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79536 |
+
"talker.model.layers.19.mlp.experts.109.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79537 |
+
"talker.model.layers.19.mlp.experts.110.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79538 |
+
"talker.model.layers.19.mlp.experts.110.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79539 |
+
"talker.model.layers.19.mlp.experts.110.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79540 |
+
"talker.model.layers.19.mlp.experts.110.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79541 |
+
"talker.model.layers.19.mlp.experts.110.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79542 |
+
"talker.model.layers.19.mlp.experts.110.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79543 |
+
"talker.model.layers.19.mlp.experts.110.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79544 |
+
"talker.model.layers.19.mlp.experts.110.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79545 |
+
"talker.model.layers.19.mlp.experts.110.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79546 |
+
"talker.model.layers.19.mlp.experts.111.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79547 |
+
"talker.model.layers.19.mlp.experts.111.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79548 |
+
"talker.model.layers.19.mlp.experts.111.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79549 |
+
"talker.model.layers.19.mlp.experts.111.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79550 |
+
"talker.model.layers.19.mlp.experts.111.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79551 |
+
"talker.model.layers.19.mlp.experts.111.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79552 |
+
"talker.model.layers.19.mlp.experts.111.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79553 |
+
"talker.model.layers.19.mlp.experts.111.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79554 |
+
"talker.model.layers.19.mlp.experts.111.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79555 |
+
"talker.model.layers.19.mlp.experts.112.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79556 |
+
"talker.model.layers.19.mlp.experts.112.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79557 |
+
"talker.model.layers.19.mlp.experts.112.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79558 |
+
"talker.model.layers.19.mlp.experts.112.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79559 |
+
"talker.model.layers.19.mlp.experts.112.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79560 |
+
"talker.model.layers.19.mlp.experts.112.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79561 |
+
"talker.model.layers.19.mlp.experts.112.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79562 |
+
"talker.model.layers.19.mlp.experts.112.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79563 |
+
"talker.model.layers.19.mlp.experts.112.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79564 |
+
"talker.model.layers.19.mlp.experts.113.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79565 |
+
"talker.model.layers.19.mlp.experts.113.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79566 |
+
"talker.model.layers.19.mlp.experts.113.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79567 |
+
"talker.model.layers.19.mlp.experts.113.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79568 |
+
"talker.model.layers.19.mlp.experts.113.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79569 |
+
"talker.model.layers.19.mlp.experts.113.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79570 |
+
"talker.model.layers.19.mlp.experts.113.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79571 |
+
"talker.model.layers.19.mlp.experts.113.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79572 |
+
"talker.model.layers.19.mlp.experts.113.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79573 |
+
"talker.model.layers.19.mlp.experts.114.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79574 |
+
"talker.model.layers.19.mlp.experts.114.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79575 |
+
"talker.model.layers.19.mlp.experts.114.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79576 |
+
"talker.model.layers.19.mlp.experts.114.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79577 |
+
"talker.model.layers.19.mlp.experts.114.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79578 |
+
"talker.model.layers.19.mlp.experts.114.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79579 |
+
"talker.model.layers.19.mlp.experts.114.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79580 |
+
"talker.model.layers.19.mlp.experts.114.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79581 |
+
"talker.model.layers.19.mlp.experts.114.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79582 |
+
"talker.model.layers.19.mlp.experts.115.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79583 |
+
"talker.model.layers.19.mlp.experts.115.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79584 |
+
"talker.model.layers.19.mlp.experts.115.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79585 |
+
"talker.model.layers.19.mlp.experts.115.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79586 |
+
"talker.model.layers.19.mlp.experts.115.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79587 |
+
"talker.model.layers.19.mlp.experts.115.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79588 |
+
"talker.model.layers.19.mlp.experts.115.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79589 |
+
"talker.model.layers.19.mlp.experts.115.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79590 |
+
"talker.model.layers.19.mlp.experts.115.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79591 |
+
"talker.model.layers.19.mlp.experts.116.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79592 |
+
"talker.model.layers.19.mlp.experts.116.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79593 |
+
"talker.model.layers.19.mlp.experts.116.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79594 |
+
"talker.model.layers.19.mlp.experts.116.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79595 |
+
"talker.model.layers.19.mlp.experts.116.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79596 |
+
"talker.model.layers.19.mlp.experts.116.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79597 |
+
"talker.model.layers.19.mlp.experts.116.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79598 |
+
"talker.model.layers.19.mlp.experts.116.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79599 |
+
"talker.model.layers.19.mlp.experts.116.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79600 |
+
"talker.model.layers.19.mlp.experts.117.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79601 |
+
"talker.model.layers.19.mlp.experts.117.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79602 |
+
"talker.model.layers.19.mlp.experts.117.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79603 |
+
"talker.model.layers.19.mlp.experts.117.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79604 |
+
"talker.model.layers.19.mlp.experts.117.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79605 |
+
"talker.model.layers.19.mlp.experts.117.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79606 |
+
"talker.model.layers.19.mlp.experts.117.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79607 |
+
"talker.model.layers.19.mlp.experts.117.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79608 |
+
"talker.model.layers.19.mlp.experts.117.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79609 |
+
"talker.model.layers.19.mlp.experts.118.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79610 |
+
"talker.model.layers.19.mlp.experts.118.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79611 |
+
"talker.model.layers.19.mlp.experts.118.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79612 |
+
"talker.model.layers.19.mlp.experts.118.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79613 |
+
"talker.model.layers.19.mlp.experts.118.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79614 |
+
"talker.model.layers.19.mlp.experts.118.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79615 |
+
"talker.model.layers.19.mlp.experts.118.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79616 |
+
"talker.model.layers.19.mlp.experts.118.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79617 |
+
"talker.model.layers.19.mlp.experts.118.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79618 |
+
"talker.model.layers.19.mlp.experts.119.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79619 |
+
"talker.model.layers.19.mlp.experts.119.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79620 |
+
"talker.model.layers.19.mlp.experts.119.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79621 |
+
"talker.model.layers.19.mlp.experts.119.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79622 |
+
"talker.model.layers.19.mlp.experts.119.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79623 |
+
"talker.model.layers.19.mlp.experts.119.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79624 |
+
"talker.model.layers.19.mlp.experts.119.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79625 |
+
"talker.model.layers.19.mlp.experts.119.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79626 |
+
"talker.model.layers.19.mlp.experts.119.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79627 |
+
"talker.model.layers.19.mlp.experts.120.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79628 |
+
"talker.model.layers.19.mlp.experts.120.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79629 |
+
"talker.model.layers.19.mlp.experts.120.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79630 |
+
"talker.model.layers.19.mlp.experts.120.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79631 |
+
"talker.model.layers.19.mlp.experts.120.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79632 |
+
"talker.model.layers.19.mlp.experts.120.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79633 |
+
"talker.model.layers.19.mlp.experts.120.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79634 |
+
"talker.model.layers.19.mlp.experts.120.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79635 |
+
"talker.model.layers.19.mlp.experts.120.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79636 |
+
"talker.model.layers.19.mlp.experts.121.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79637 |
+
"talker.model.layers.19.mlp.experts.121.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79638 |
+
"talker.model.layers.19.mlp.experts.121.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79639 |
+
"talker.model.layers.19.mlp.experts.121.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79640 |
+
"talker.model.layers.19.mlp.experts.121.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79641 |
+
"talker.model.layers.19.mlp.experts.121.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79642 |
+
"talker.model.layers.19.mlp.experts.121.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79643 |
+
"talker.model.layers.19.mlp.experts.121.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79644 |
+
"talker.model.layers.19.mlp.experts.121.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79645 |
+
"talker.model.layers.19.mlp.experts.122.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79646 |
+
"talker.model.layers.19.mlp.experts.122.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79647 |
+
"talker.model.layers.19.mlp.experts.122.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79648 |
+
"talker.model.layers.19.mlp.experts.122.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79649 |
+
"talker.model.layers.19.mlp.experts.122.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79650 |
+
"talker.model.layers.19.mlp.experts.122.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79651 |
+
"talker.model.layers.19.mlp.experts.122.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79652 |
+
"talker.model.layers.19.mlp.experts.122.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79653 |
+
"talker.model.layers.19.mlp.experts.122.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79654 |
+
"talker.model.layers.19.mlp.experts.123.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79655 |
+
"talker.model.layers.19.mlp.experts.123.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79656 |
+
"talker.model.layers.19.mlp.experts.123.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79657 |
+
"talker.model.layers.19.mlp.experts.123.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79658 |
+
"talker.model.layers.19.mlp.experts.123.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79659 |
+
"talker.model.layers.19.mlp.experts.123.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79660 |
+
"talker.model.layers.19.mlp.experts.123.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79661 |
+
"talker.model.layers.19.mlp.experts.123.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79662 |
+
"talker.model.layers.19.mlp.experts.123.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79663 |
+
"talker.model.layers.19.mlp.experts.124.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79664 |
+
"talker.model.layers.19.mlp.experts.124.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79665 |
+
"talker.model.layers.19.mlp.experts.124.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79666 |
+
"talker.model.layers.19.mlp.experts.124.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79667 |
+
"talker.model.layers.19.mlp.experts.124.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79668 |
+
"talker.model.layers.19.mlp.experts.124.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79669 |
+
"talker.model.layers.19.mlp.experts.124.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79670 |
+
"talker.model.layers.19.mlp.experts.124.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79671 |
+
"talker.model.layers.19.mlp.experts.124.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79672 |
+
"talker.model.layers.19.mlp.experts.125.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79673 |
+
"talker.model.layers.19.mlp.experts.125.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79674 |
+
"talker.model.layers.19.mlp.experts.125.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79675 |
+
"talker.model.layers.19.mlp.experts.125.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79676 |
+
"talker.model.layers.19.mlp.experts.125.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79677 |
+
"talker.model.layers.19.mlp.experts.125.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79678 |
+
"talker.model.layers.19.mlp.experts.125.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79679 |
+
"talker.model.layers.19.mlp.experts.125.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79680 |
+
"talker.model.layers.19.mlp.experts.125.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79681 |
+
"talker.model.layers.19.mlp.experts.126.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79682 |
+
"talker.model.layers.19.mlp.experts.126.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79683 |
+
"talker.model.layers.19.mlp.experts.126.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79684 |
+
"talker.model.layers.19.mlp.experts.126.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79685 |
+
"talker.model.layers.19.mlp.experts.126.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79686 |
+
"talker.model.layers.19.mlp.experts.126.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79687 |
+
"talker.model.layers.19.mlp.experts.126.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79688 |
+
"talker.model.layers.19.mlp.experts.126.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79689 |
+
"talker.model.layers.19.mlp.experts.126.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79690 |
+
"talker.model.layers.19.mlp.experts.127.gate_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79691 |
+
"talker.model.layers.19.mlp.experts.127.gate_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79692 |
+
"talker.model.layers.19.mlp.experts.127.gate_proj.scales": "model-00009-of-00011.safetensors",
|
| 79693 |
+
"talker.model.layers.19.mlp.experts.127.up_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79694 |
+
"talker.model.layers.19.mlp.experts.127.up_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79695 |
+
"talker.model.layers.19.mlp.experts.127.up_proj.scales": "model-00009-of-00011.safetensors",
|
| 79696 |
+
"talker.model.layers.19.mlp.experts.127.down_proj.qweight": "model-00009-of-00011.safetensors",
|
| 79697 |
+
"talker.model.layers.19.mlp.experts.127.down_proj.qzeros": "model-00009-of-00011.safetensors",
|
| 79698 |
+
"talker.model.layers.19.mlp.experts.127.down_proj.scales": "model-00009-of-00011.safetensors",
|
| 79699 |
+
"talker.model.layers.19.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
| 79700 |
+
"talker.model.layers.19.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
| 79701 |
"thinker.audio_tower.layers.0.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
| 79702 |
"thinker.audio_tower.layers.0.self_attn.k_proj.bias": "model-00009-of-00011.safetensors",
|
| 79703 |
"thinker.audio_tower.layers.0.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
|
|
|
| 80773 |
"code2wav.upsample.0.1.norm.bias": "model-00010-of-00011.safetensors",
|
| 80774 |
"code2wav.upsample.0.1.pwconv1.weight": "model-00010-of-00011.safetensors",
|
| 80775 |
"code2wav.upsample.0.1.pwconv1.bias": "model-00010-of-00011.safetensors",
|
| 80776 |
+
"code2wav.upsample.0.1.pwconv2.weight": "model-00010-of-00011.safetensors",
|
| 80777 |
+
"code2wav.upsample.0.1.pwconv2.bias": "model-00010-of-00011.safetensors",
|
| 80778 |
+
"code2wav.upsample.1.0.conv.weight": "model-00010-of-00011.safetensors",
|
| 80779 |
+
"code2wav.upsample.1.0.conv.bias": "model-00010-of-00011.safetensors",
|
| 80780 |
+
"code2wav.upsample.1.1.gamma": "model-00010-of-00011.safetensors",
|
| 80781 |
+
"code2wav.upsample.1.1.dwconv.conv.weight": "model-00010-of-00011.safetensors",
|
| 80782 |
+
"code2wav.upsample.1.1.dwconv.conv.bias": "model-00010-of-00011.safetensors",
|
| 80783 |
+
"code2wav.upsample.1.1.norm.weight": "model-00010-of-00011.safetensors",
|
| 80784 |
+
"code2wav.upsample.1.1.norm.bias": "model-00010-of-00011.safetensors",
|
| 80785 |
+
"code2wav.upsample.1.1.pwconv1.weight": "model-00010-of-00011.safetensors",
|
| 80786 |
+
"code2wav.upsample.1.1.pwconv1.bias": "model-00010-of-00011.safetensors",
|
| 80787 |
"code2wav.upsample.1.1.pwconv2.weight": "model-00011-of-00011.safetensors",
|
| 80788 |
"code2wav.upsample.1.1.pwconv2.bias": "model-00011-of-00011.safetensors",
|
| 80789 |
"code2wav.decoder.0.conv.weight": "model-00011-of-00011.safetensors",
|
processor_config.json
CHANGED
|
@@ -30,7 +30,6 @@
|
|
| 30 |
"temporal_patch_size": 2
|
| 31 |
},
|
| 32 |
"image_processor": {
|
| 33 |
-
"data_format": "channels_first",
|
| 34 |
"dither": 0.0,
|
| 35 |
"do_convert_rgb": true,
|
| 36 |
"do_normalize": true,
|
|
@@ -43,7 +42,7 @@
|
|
| 43 |
0.5,
|
| 44 |
0.5
|
| 45 |
],
|
| 46 |
-
"image_processor_type": "
|
| 47 |
"image_std": [
|
| 48 |
0.5,
|
| 49 |
0.5,
|
|
@@ -68,15 +67,12 @@
|
|
| 68 |
},
|
| 69 |
"processor_class": "Qwen3OmniMoeProcessor",
|
| 70 |
"video_processor": {
|
| 71 |
-
"data_format": "channels_first",
|
| 72 |
-
"default_to_square": true,
|
| 73 |
"dither": 0.0,
|
| 74 |
"do_convert_rgb": true,
|
| 75 |
"do_normalize": true,
|
| 76 |
"do_rescale": true,
|
| 77 |
"do_resize": true,
|
| 78 |
"do_sample_frames": false,
|
| 79 |
-
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 80 |
"feature_size": 128,
|
| 81 |
"hop_length": 160,
|
| 82 |
"image_mean": [
|
|
@@ -84,7 +80,6 @@
|
|
| 84 |
0.5,
|
| 85 |
0.5
|
| 86 |
],
|
| 87 |
-
"image_processor_type": "Qwen2VLImageProcessor",
|
| 88 |
"image_std": [
|
| 89 |
0.5,
|
| 90 |
0.5,
|
|
|
|
| 30 |
"temporal_patch_size": 2
|
| 31 |
},
|
| 32 |
"image_processor": {
|
|
|
|
| 33 |
"dither": 0.0,
|
| 34 |
"do_convert_rgb": true,
|
| 35 |
"do_normalize": true,
|
|
|
|
| 42 |
0.5,
|
| 43 |
0.5
|
| 44 |
],
|
| 45 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 46 |
"image_std": [
|
| 47 |
0.5,
|
| 48 |
0.5,
|
|
|
|
| 67 |
},
|
| 68 |
"processor_class": "Qwen3OmniMoeProcessor",
|
| 69 |
"video_processor": {
|
|
|
|
|
|
|
| 70 |
"dither": 0.0,
|
| 71 |
"do_convert_rgb": true,
|
| 72 |
"do_normalize": true,
|
| 73 |
"do_rescale": true,
|
| 74 |
"do_resize": true,
|
| 75 |
"do_sample_frames": false,
|
|
|
|
| 76 |
"feature_size": 128,
|
| 77 |
"hop_length": 160,
|
| 78 |
"image_mean": [
|
|
|
|
| 80 |
0.5,
|
| 81 |
0.5
|
| 82 |
],
|
|
|
|
| 83 |
"image_std": [
|
| 84 |
0.5,
|
| 85 |
0.5,
|
quantization_config.json
CHANGED
|
@@ -3,7 +3,7 @@
|
|
| 3 |
"data_type": "int",
|
| 4 |
"group_size": 128,
|
| 5 |
"sym": true,
|
| 6 |
-
"autoround_version": "0.
|
| 7 |
"block_name_to_quantize": "thinker.model.layers,talker.model.layers",
|
| 8 |
"quant_method": "auto-round",
|
| 9 |
"packing_format": "auto_round:auto_gptq",
|
|
@@ -87,6 +87,278 @@
|
|
| 87 |
"talker.model.layers.19.mlp.shared_expert_gate": {
|
| 88 |
"bits": 16,
|
| 89 |
"data_type": "fp"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 90 |
}
|
| 91 |
}
|
| 92 |
}
|
|
|
|
| 3 |
"data_type": "int",
|
| 4 |
"group_size": 128,
|
| 5 |
"sym": true,
|
| 6 |
+
"autoround_version": "0.13.0",
|
| 7 |
"block_name_to_quantize": "thinker.model.layers,talker.model.layers",
|
| 8 |
"quant_method": "auto-round",
|
| 9 |
"packing_format": "auto_round:auto_gptq",
|
|
|
|
| 87 |
"talker.model.layers.19.mlp.shared_expert_gate": {
|
| 88 |
"bits": 16,
|
| 89 |
"data_type": "fp"
|
| 90 |
+
},
|
| 91 |
+
".*thinker\\.model\\.layers\\.0\\.mlp\\.gate.*": {
|
| 92 |
+
"bits": 16,
|
| 93 |
+
"data_type": "float"
|
| 94 |
+
},
|
| 95 |
+
".*thinker\\.model\\.layers\\.1\\.mlp\\.gate.*": {
|
| 96 |
+
"bits": 16,
|
| 97 |
+
"data_type": "float"
|
| 98 |
+
},
|
| 99 |
+
".*thinker\\.model\\.layers\\.2\\.mlp\\.gate.*": {
|
| 100 |
+
"bits": 16,
|
| 101 |
+
"data_type": "float"
|
| 102 |
+
},
|
| 103 |
+
".*thinker\\.model\\.layers\\.3\\.mlp\\.gate.*": {
|
| 104 |
+
"bits": 16,
|
| 105 |
+
"data_type": "float"
|
| 106 |
+
},
|
| 107 |
+
".*thinker\\.model\\.layers\\.4\\.mlp\\.gate.*": {
|
| 108 |
+
"bits": 16,
|
| 109 |
+
"data_type": "float"
|
| 110 |
+
},
|
| 111 |
+
".*thinker\\.model\\.layers\\.5\\.mlp\\.gate.*": {
|
| 112 |
+
"bits": 16,
|
| 113 |
+
"data_type": "float"
|
| 114 |
+
},
|
| 115 |
+
".*thinker\\.model\\.layers\\.6\\.mlp\\.gate.*": {
|
| 116 |
+
"bits": 16,
|
| 117 |
+
"data_type": "float"
|
| 118 |
+
},
|
| 119 |
+
".*thinker\\.model\\.layers\\.7\\.mlp\\.gate.*": {
|
| 120 |
+
"bits": 16,
|
| 121 |
+
"data_type": "float"
|
| 122 |
+
},
|
| 123 |
+
".*thinker\\.model\\.layers\\.8\\.mlp\\.gate.*": {
|
| 124 |
+
"bits": 16,
|
| 125 |
+
"data_type": "float"
|
| 126 |
+
},
|
| 127 |
+
".*thinker\\.model\\.layers\\.9\\.mlp\\.gate.*": {
|
| 128 |
+
"bits": 16,
|
| 129 |
+
"data_type": "float"
|
| 130 |
+
},
|
| 131 |
+
".*thinker\\.model\\.layers\\.10\\.mlp\\.gate.*": {
|
| 132 |
+
"bits": 16,
|
| 133 |
+
"data_type": "float"
|
| 134 |
+
},
|
| 135 |
+
".*thinker\\.model\\.layers\\.11\\.mlp\\.gate.*": {
|
| 136 |
+
"bits": 16,
|
| 137 |
+
"data_type": "float"
|
| 138 |
+
},
|
| 139 |
+
".*thinker\\.model\\.layers\\.12\\.mlp\\.gate.*": {
|
| 140 |
+
"bits": 16,
|
| 141 |
+
"data_type": "float"
|
| 142 |
+
},
|
| 143 |
+
".*thinker\\.model\\.layers\\.13\\.mlp\\.gate.*": {
|
| 144 |
+
"bits": 16,
|
| 145 |
+
"data_type": "float"
|
| 146 |
+
},
|
| 147 |
+
".*thinker\\.model\\.layers\\.14\\.mlp\\.gate.*": {
|
| 148 |
+
"bits": 16,
|
| 149 |
+
"data_type": "float"
|
| 150 |
+
},
|
| 151 |
+
".*thinker\\.model\\.layers\\.15\\.mlp\\.gate.*": {
|
| 152 |
+
"bits": 16,
|
| 153 |
+
"data_type": "float"
|
| 154 |
+
},
|
| 155 |
+
".*thinker\\.model\\.layers\\.16\\.mlp\\.gate.*": {
|
| 156 |
+
"bits": 16,
|
| 157 |
+
"data_type": "float"
|
| 158 |
+
},
|
| 159 |
+
".*thinker\\.model\\.layers\\.17\\.mlp\\.gate.*": {
|
| 160 |
+
"bits": 16,
|
| 161 |
+
"data_type": "float"
|
| 162 |
+
},
|
| 163 |
+
".*thinker\\.model\\.layers\\.18\\.mlp\\.gate.*": {
|
| 164 |
+
"bits": 16,
|
| 165 |
+
"data_type": "float"
|
| 166 |
+
},
|
| 167 |
+
".*thinker\\.model\\.layers\\.19\\.mlp\\.gate.*": {
|
| 168 |
+
"bits": 16,
|
| 169 |
+
"data_type": "float"
|
| 170 |
+
},
|
| 171 |
+
".*thinker\\.model\\.layers\\.20\\.mlp\\.gate.*": {
|
| 172 |
+
"bits": 16,
|
| 173 |
+
"data_type": "float"
|
| 174 |
+
},
|
| 175 |
+
".*thinker\\.model\\.layers\\.21\\.mlp\\.gate.*": {
|
| 176 |
+
"bits": 16,
|
| 177 |
+
"data_type": "float"
|
| 178 |
+
},
|
| 179 |
+
".*thinker\\.model\\.layers\\.22\\.mlp\\.gate.*": {
|
| 180 |
+
"bits": 16,
|
| 181 |
+
"data_type": "float"
|
| 182 |
+
},
|
| 183 |
+
".*thinker\\.model\\.layers\\.23\\.mlp\\.gate.*": {
|
| 184 |
+
"bits": 16,
|
| 185 |
+
"data_type": "float"
|
| 186 |
+
},
|
| 187 |
+
".*thinker\\.model\\.layers\\.24\\.mlp\\.gate.*": {
|
| 188 |
+
"bits": 16,
|
| 189 |
+
"data_type": "float"
|
| 190 |
+
},
|
| 191 |
+
".*thinker\\.model\\.layers\\.25\\.mlp\\.gate.*": {
|
| 192 |
+
"bits": 16,
|
| 193 |
+
"data_type": "float"
|
| 194 |
+
},
|
| 195 |
+
".*thinker\\.model\\.layers\\.26\\.mlp\\.gate.*": {
|
| 196 |
+
"bits": 16,
|
| 197 |
+
"data_type": "float"
|
| 198 |
+
},
|
| 199 |
+
".*thinker\\.model\\.layers\\.27\\.mlp\\.gate.*": {
|
| 200 |
+
"bits": 16,
|
| 201 |
+
"data_type": "float"
|
| 202 |
+
},
|
| 203 |
+
".*thinker\\.model\\.layers\\.28\\.mlp\\.gate.*": {
|
| 204 |
+
"bits": 16,
|
| 205 |
+
"data_type": "float"
|
| 206 |
+
},
|
| 207 |
+
".*thinker\\.model\\.layers\\.29\\.mlp\\.gate.*": {
|
| 208 |
+
"bits": 16,
|
| 209 |
+
"data_type": "float"
|
| 210 |
+
},
|
| 211 |
+
".*thinker\\.model\\.layers\\.30\\.mlp\\.gate.*": {
|
| 212 |
+
"bits": 16,
|
| 213 |
+
"data_type": "float"
|
| 214 |
+
},
|
| 215 |
+
".*thinker\\.model\\.layers\\.31\\.mlp\\.gate.*": {
|
| 216 |
+
"bits": 16,
|
| 217 |
+
"data_type": "float"
|
| 218 |
+
},
|
| 219 |
+
".*thinker\\.model\\.layers\\.32\\.mlp\\.gate.*": {
|
| 220 |
+
"bits": 16,
|
| 221 |
+
"data_type": "float"
|
| 222 |
+
},
|
| 223 |
+
".*thinker\\.model\\.layers\\.33\\.mlp\\.gate.*": {
|
| 224 |
+
"bits": 16,
|
| 225 |
+
"data_type": "float"
|
| 226 |
+
},
|
| 227 |
+
".*thinker\\.model\\.layers\\.34\\.mlp\\.gate.*": {
|
| 228 |
+
"bits": 16,
|
| 229 |
+
"data_type": "float"
|
| 230 |
+
},
|
| 231 |
+
".*thinker\\.model\\.layers\\.35\\.mlp\\.gate.*": {
|
| 232 |
+
"bits": 16,
|
| 233 |
+
"data_type": "float"
|
| 234 |
+
},
|
| 235 |
+
".*thinker\\.model\\.layers\\.36\\.mlp\\.gate.*": {
|
| 236 |
+
"bits": 16,
|
| 237 |
+
"data_type": "float"
|
| 238 |
+
},
|
| 239 |
+
".*thinker\\.model\\.layers\\.37\\.mlp\\.gate.*": {
|
| 240 |
+
"bits": 16,
|
| 241 |
+
"data_type": "float"
|
| 242 |
+
},
|
| 243 |
+
".*thinker\\.model\\.layers\\.38\\.mlp\\.gate.*": {
|
| 244 |
+
"bits": 16,
|
| 245 |
+
"data_type": "float"
|
| 246 |
+
},
|
| 247 |
+
".*thinker\\.model\\.layers\\.39\\.mlp\\.gate.*": {
|
| 248 |
+
"bits": 16,
|
| 249 |
+
"data_type": "float"
|
| 250 |
+
},
|
| 251 |
+
".*thinker\\.model\\.layers\\.40\\.mlp\\.gate.*": {
|
| 252 |
+
"bits": 16,
|
| 253 |
+
"data_type": "float"
|
| 254 |
+
},
|
| 255 |
+
".*thinker\\.model\\.layers\\.41\\.mlp\\.gate.*": {
|
| 256 |
+
"bits": 16,
|
| 257 |
+
"data_type": "float"
|
| 258 |
+
},
|
| 259 |
+
".*thinker\\.model\\.layers\\.42\\.mlp\\.gate.*": {
|
| 260 |
+
"bits": 16,
|
| 261 |
+
"data_type": "float"
|
| 262 |
+
},
|
| 263 |
+
".*thinker\\.model\\.layers\\.43\\.mlp\\.gate.*": {
|
| 264 |
+
"bits": 16,
|
| 265 |
+
"data_type": "float"
|
| 266 |
+
},
|
| 267 |
+
".*thinker\\.model\\.layers\\.44\\.mlp\\.gate.*": {
|
| 268 |
+
"bits": 16,
|
| 269 |
+
"data_type": "float"
|
| 270 |
+
},
|
| 271 |
+
".*thinker\\.model\\.layers\\.45\\.mlp\\.gate.*": {
|
| 272 |
+
"bits": 16,
|
| 273 |
+
"data_type": "float"
|
| 274 |
+
},
|
| 275 |
+
".*thinker\\.model\\.layers\\.46\\.mlp\\.gate.*": {
|
| 276 |
+
"bits": 16,
|
| 277 |
+
"data_type": "float"
|
| 278 |
+
},
|
| 279 |
+
".*thinker\\.model\\.layers\\.47\\.mlp\\.gate.*": {
|
| 280 |
+
"bits": 16,
|
| 281 |
+
"data_type": "float"
|
| 282 |
+
},
|
| 283 |
+
".*talker\\.model\\.layers\\.0\\.mlp\\.gate.*": {
|
| 284 |
+
"bits": 16,
|
| 285 |
+
"data_type": "float"
|
| 286 |
+
},
|
| 287 |
+
".*talker\\.model\\.layers\\.1\\.mlp\\.gate.*": {
|
| 288 |
+
"bits": 16,
|
| 289 |
+
"data_type": "float"
|
| 290 |
+
},
|
| 291 |
+
".*talker\\.model\\.layers\\.2\\.mlp\\.gate.*": {
|
| 292 |
+
"bits": 16,
|
| 293 |
+
"data_type": "float"
|
| 294 |
+
},
|
| 295 |
+
".*talker\\.model\\.layers\\.3\\.mlp\\.gate.*": {
|
| 296 |
+
"bits": 16,
|
| 297 |
+
"data_type": "float"
|
| 298 |
+
},
|
| 299 |
+
".*talker\\.model\\.layers\\.4\\.mlp\\.gate.*": {
|
| 300 |
+
"bits": 16,
|
| 301 |
+
"data_type": "float"
|
| 302 |
+
},
|
| 303 |
+
".*talker\\.model\\.layers\\.5\\.mlp\\.gate.*": {
|
| 304 |
+
"bits": 16,
|
| 305 |
+
"data_type": "float"
|
| 306 |
+
},
|
| 307 |
+
".*talker\\.model\\.layers\\.6\\.mlp\\.gate.*": {
|
| 308 |
+
"bits": 16,
|
| 309 |
+
"data_type": "float"
|
| 310 |
+
},
|
| 311 |
+
".*talker\\.model\\.layers\\.7\\.mlp\\.gate.*": {
|
| 312 |
+
"bits": 16,
|
| 313 |
+
"data_type": "float"
|
| 314 |
+
},
|
| 315 |
+
".*talker\\.model\\.layers\\.8\\.mlp\\.gate.*": {
|
| 316 |
+
"bits": 16,
|
| 317 |
+
"data_type": "float"
|
| 318 |
+
},
|
| 319 |
+
".*talker\\.model\\.layers\\.9\\.mlp\\.gate.*": {
|
| 320 |
+
"bits": 16,
|
| 321 |
+
"data_type": "float"
|
| 322 |
+
},
|
| 323 |
+
".*talker\\.model\\.layers\\.10\\.mlp\\.gate.*": {
|
| 324 |
+
"bits": 16,
|
| 325 |
+
"data_type": "float"
|
| 326 |
+
},
|
| 327 |
+
".*talker\\.model\\.layers\\.11\\.mlp\\.gate.*": {
|
| 328 |
+
"bits": 16,
|
| 329 |
+
"data_type": "float"
|
| 330 |
+
},
|
| 331 |
+
".*talker\\.model\\.layers\\.12\\.mlp\\.gate.*": {
|
| 332 |
+
"bits": 16,
|
| 333 |
+
"data_type": "float"
|
| 334 |
+
},
|
| 335 |
+
".*talker\\.model\\.layers\\.13\\.mlp\\.gate.*": {
|
| 336 |
+
"bits": 16,
|
| 337 |
+
"data_type": "float"
|
| 338 |
+
},
|
| 339 |
+
".*talker\\.model\\.layers\\.14\\.mlp\\.gate.*": {
|
| 340 |
+
"bits": 16,
|
| 341 |
+
"data_type": "float"
|
| 342 |
+
},
|
| 343 |
+
".*talker\\.model\\.layers\\.15\\.mlp\\.gate.*": {
|
| 344 |
+
"bits": 16,
|
| 345 |
+
"data_type": "float"
|
| 346 |
+
},
|
| 347 |
+
".*talker\\.model\\.layers\\.16\\.mlp\\.gate.*": {
|
| 348 |
+
"bits": 16,
|
| 349 |
+
"data_type": "float"
|
| 350 |
+
},
|
| 351 |
+
".*talker\\.model\\.layers\\.17\\.mlp\\.gate.*": {
|
| 352 |
+
"bits": 16,
|
| 353 |
+
"data_type": "float"
|
| 354 |
+
},
|
| 355 |
+
".*talker\\.model\\.layers\\.18\\.mlp\\.gate.*": {
|
| 356 |
+
"bits": 16,
|
| 357 |
+
"data_type": "float"
|
| 358 |
+
},
|
| 359 |
+
".*talker\\.model\\.layers\\.19\\.mlp\\.gate.*": {
|
| 360 |
+
"bits": 16,
|
| 361 |
+
"data_type": "float"
|
| 362 |
}
|
| 363 |
}
|
| 364 |
}
|