Update MiMo-V2.5 config
Browse files- enable_thinking = true by default in tokenizer_config.json
- update rope_theta, and length-related params in config.json
- config.json +367 -367
- tokenizer_config.json +1 -1
config.json
CHANGED
|
@@ -1,367 +1,367 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"MiMoV2ForCausalLM"
|
| 4 |
-
],
|
| 5 |
-
"auto_map": {
|
| 6 |
-
"AutoConfig": "configuration_mimo_v2.MiMoV2Config",
|
| 7 |
-
"AutoModel": "modeling_mimo_v2.MiMoV2Model",
|
| 8 |
-
"AutoModelForCausalLM": "modeling_mimo_v2.MiMoV2ForCausalLM"
|
| 9 |
-
},
|
| 10 |
-
"attention_bias": false,
|
| 11 |
-
"attention_chunk_size": 128,
|
| 12 |
-
"attention_dropout": 0.0,
|
| 13 |
-
"attention_value_scale": 0.707,
|
| 14 |
-
"attention_projection_layout": "fused_qkv",
|
| 15 |
-
"add_full_attention_sink_bias": false,
|
| 16 |
-
"add_swa_attention_sink_bias": true,
|
| 17 |
-
"audio_config": {
|
| 18 |
-
"add_post_norm": true,
|
| 19 |
-
"audio_channels": 20,
|
| 20 |
-
"audio_segment_size": 6000,
|
| 21 |
-
"group_size": 4,
|
| 22 |
-
"input_full_attention": true,
|
| 23 |
-
"input_local_attn_heads": 16,
|
| 24 |
-
"input_local_dim": 1024,
|
| 25 |
-
"input_local_head_dim": 64,
|
| 26 |
-
"input_local_hidden_dropout": 0.0,
|
| 27 |
-
"input_local_intermediate_size": 4096,
|
| 28 |
-
"input_local_layers": 6,
|
| 29 |
-
"out_hidden_size": 4096,
|
| 30 |
-
"partial_rotary_factor": 1.0,
|
| 31 |
-
"projection_layers": 2,
|
| 32 |
-
"rope_theta": 640000,
|
| 33 |
-
"speech_vocab_size": "1280",
|
| 34 |
-
"speech_zeroemb_idx": "1024"
|
| 35 |
-
},
|
| 36 |
-
"swa_num_key_value_heads": 8,
|
| 37 |
-
"swa_num_attention_heads": 64,
|
| 38 |
-
"swa_head_dim": 192,
|
| 39 |
-
"swa_v_head_dim": 128,
|
| 40 |
-
"dtype": "bfloat16",
|
| 41 |
-
"eos_token_id": 151645,
|
| 42 |
-
"head_dim": 192,
|
| 43 |
-
"hidden_act": "silu",
|
| 44 |
-
"hidden_size": 4096,
|
| 45 |
-
"hybrid_block_size": null,
|
| 46 |
-
"hybrid_layer_pattern": [
|
| 47 |
-
0,
|
| 48 |
-
1,
|
| 49 |
-
1,
|
| 50 |
-
1,
|
| 51 |
-
1,
|
| 52 |
-
0,
|
| 53 |
-
1,
|
| 54 |
-
1,
|
| 55 |
-
1,
|
| 56 |
-
1,
|
| 57 |
-
1,
|
| 58 |
-
0,
|
| 59 |
-
1,
|
| 60 |
-
1,
|
| 61 |
-
1,
|
| 62 |
-
1,
|
| 63 |
-
1,
|
| 64 |
-
0,
|
| 65 |
-
1,
|
| 66 |
-
1,
|
| 67 |
-
1,
|
| 68 |
-
1,
|
| 69 |
-
1,
|
| 70 |
-
0,
|
| 71 |
-
1,
|
| 72 |
-
1,
|
| 73 |
-
1,
|
| 74 |
-
1,
|
| 75 |
-
1,
|
| 76 |
-
0,
|
| 77 |
-
1,
|
| 78 |
-
1,
|
| 79 |
-
1,
|
| 80 |
-
1,
|
| 81 |
-
1,
|
| 82 |
-
0,
|
| 83 |
-
1,
|
| 84 |
-
1,
|
| 85 |
-
1,
|
| 86 |
-
1,
|
| 87 |
-
1,
|
| 88 |
-
0,
|
| 89 |
-
1,
|
| 90 |
-
1,
|
| 91 |
-
1,
|
| 92 |
-
1,
|
| 93 |
-
1,
|
| 94 |
-
0
|
| 95 |
-
],
|
| 96 |
-
"image_token_id": 151655,
|
| 97 |
-
"initializer_range": 0.02,
|
| 98 |
-
"intermediate_size": 16384,
|
| 99 |
-
"layernorm_epsilon": 1e-05,
|
| 100 |
-
"max_position_embeddings": 262144,
|
| 101 |
-
"model_type": "mimo_v2",
|
| 102 |
-
"moe_intermediate_size": 2048,
|
| 103 |
-
"moe_layer_freq": [
|
| 104 |
-
0,
|
| 105 |
-
1,
|
| 106 |
-
1,
|
| 107 |
-
1,
|
| 108 |
-
1,
|
| 109 |
-
1,
|
| 110 |
-
1,
|
| 111 |
-
1,
|
| 112 |
-
1,
|
| 113 |
-
1,
|
| 114 |
-
1,
|
| 115 |
-
1,
|
| 116 |
-
1,
|
| 117 |
-
1,
|
| 118 |
-
1,
|
| 119 |
-
1,
|
| 120 |
-
1,
|
| 121 |
-
1,
|
| 122 |
-
1,
|
| 123 |
-
1,
|
| 124 |
-
1,
|
| 125 |
-
1,
|
| 126 |
-
1,
|
| 127 |
-
1,
|
| 128 |
-
1,
|
| 129 |
-
1,
|
| 130 |
-
1,
|
| 131 |
-
1,
|
| 132 |
-
1,
|
| 133 |
-
1,
|
| 134 |
-
1,
|
| 135 |
-
1,
|
| 136 |
-
1,
|
| 137 |
-
1,
|
| 138 |
-
1,
|
| 139 |
-
1,
|
| 140 |
-
1,
|
| 141 |
-
1,
|
| 142 |
-
1,
|
| 143 |
-
1,
|
| 144 |
-
1,
|
| 145 |
-
1,
|
| 146 |
-
1,
|
| 147 |
-
1,
|
| 148 |
-
1,
|
| 149 |
-
1,
|
| 150 |
-
1,
|
| 151 |
-
1
|
| 152 |
-
],
|
| 153 |
-
"n_group": 1,
|
| 154 |
-
"n_routed_experts": 256,
|
| 155 |
-
"n_shared_experts": null,
|
| 156 |
-
"norm_topk_prob": true,
|
| 157 |
-
"num_attention_heads": 64,
|
| 158 |
-
"num_experts_per_tok": 8,
|
| 159 |
-
"num_hidden_layers": 48,
|
| 160 |
-
"num_key_value_heads": 4,
|
| 161 |
-
"pad_token_id": 151643,
|
| 162 |
-
"partial_rotary_factor": 0.334,
|
| 163 |
-
"processor_config": {
|
| 164 |
-
"audio_avg_pooler": 2,
|
| 165 |
-
"audio_channels": 20,
|
| 166 |
-
"audio_end_token_id": 151674,
|
| 167 |
-
"audio_fmax": null,
|
| 168 |
-
"audio_fmin": 0,
|
| 169 |
-
"audio_group_size": 4,
|
| 170 |
-
"audio_hop_length": 240,
|
| 171 |
-
"audio_input_id_per_second": 25.0,
|
| 172 |
-
"audio_kernel_size": 3,
|
| 173 |
-
"audio_n_mels": 128,
|
| 174 |
-
"audio_nfft": 960,
|
| 175 |
-
"audio_sampling_rate": 24000,
|
| 176 |
-
"audio_segment_size": 6000,
|
| 177 |
-
"audio_start_token_id": 151673,
|
| 178 |
-
"audio_stride_size": 2,
|
| 179 |
-
"audio_token_id": 151669,
|
| 180 |
-
"audio_window_size": 960,
|
| 181 |
-
"audio_zeroemb_idx": [
|
| 182 |
-
1024,
|
| 183 |
-
1024,
|
| 184 |
-
1024,
|
| 185 |
-
1024,
|
| 186 |
-
1024,
|
| 187 |
-
1024,
|
| 188 |
-
1024,
|
| 189 |
-
1024,
|
| 190 |
-
1024,
|
| 191 |
-
1024,
|
| 192 |
-
1024,
|
| 193 |
-
1024,
|
| 194 |
-
1024,
|
| 195 |
-
1024,
|
| 196 |
-
1024,
|
| 197 |
-
1024,
|
| 198 |
-
1024,
|
| 199 |
-
1024,
|
| 200 |
-
1024,
|
| 201 |
-
1024
|
| 202 |
-
],
|
| 203 |
-
"fps": 1.0,
|
| 204 |
-
"image_max_pixels": 8388608,
|
| 205 |
-
"image_min_pixels": 8192,
|
| 206 |
-
"image_token_id": 151655,
|
| 207 |
-
"max_frames": 1024,
|
| 208 |
-
"merge_size": 2,
|
| 209 |
-
"min_frames": null,
|
| 210 |
-
"num_frames": null,
|
| 211 |
-
"pad_token_id": 151643,
|
| 212 |
-
"patch_size": 16,
|
| 213 |
-
"rope_type": "rope",
|
| 214 |
-
"temporal_compression_ratio": 1,
|
| 215 |
-
"temporal_patch_size": 2,
|
| 216 |
-
"use_per_grid_t_timestamps": false,
|
| 217 |
-
"use_video_timestamps": true,
|
| 218 |
-
"video_audio_interleave_length": 0.0,
|
| 219 |
-
"video_end_token_id": 151671,
|
| 220 |
-
"video_max_pixels": 8388608,
|
| 221 |
-
"video_min_pixels": 8192,
|
| 222 |
-
"video_process_num_threads": 16,
|
| 223 |
-
"video_start_token_id": 151670,
|
| 224 |
-
"video_token_id": 151656,
|
| 225 |
-
"video_tokens_per_second": 2,
|
| 226 |
-
"video_total_max_pixels":
|
| 227 |
-
"vision_end_token_id": 151653,
|
| 228 |
-
"vision_start_token_id": 151652
|
| 229 |
-
},
|
| 230 |
-
"quantization_config": {
|
| 231 |
-
"activation_scheme": "dynamic",
|
| 232 |
-
"fmt": "e4m3",
|
| 233 |
-
"quant_method": "fp8",
|
| 234 |
-
"store_dtype": "fp8",
|
| 235 |
-
"ignored_layers": [
|
| 236 |
-
"model.layers.0.self_attn.o_proj",
|
| 237 |
-
"model.layers.1.self_attn.o_proj",
|
| 238 |
-
"model.layers.2.self_attn.o_proj",
|
| 239 |
-
"model.layers.3.self_attn.o_proj",
|
| 240 |
-
"model.layers.4.self_attn.o_proj",
|
| 241 |
-
"model.layers.5.self_attn.o_proj",
|
| 242 |
-
"model.layers.6.self_attn.o_proj",
|
| 243 |
-
"model.layers.7.self_attn.o_proj",
|
| 244 |
-
"model.layers.8.self_attn.o_proj",
|
| 245 |
-
"model.layers.9.self_attn.o_proj",
|
| 246 |
-
"model.layers.10.self_attn.o_proj",
|
| 247 |
-
"model.layers.11.self_attn.o_proj",
|
| 248 |
-
"model.layers.12.self_attn.o_proj",
|
| 249 |
-
"model.layers.13.self_attn.o_proj",
|
| 250 |
-
"model.layers.14.self_attn.o_proj",
|
| 251 |
-
"model.layers.15.self_attn.o_proj",
|
| 252 |
-
"model.layers.16.self_attn.o_proj",
|
| 253 |
-
"model.layers.17.self_attn.o_proj",
|
| 254 |
-
"model.layers.18.self_attn.o_proj",
|
| 255 |
-
"model.layers.19.self_attn.o_proj",
|
| 256 |
-
"model.layers.20.self_attn.o_proj",
|
| 257 |
-
"model.layers.21.self_attn.o_proj",
|
| 258 |
-
"model.layers.22.self_attn.o_proj",
|
| 259 |
-
"model.layers.23.self_attn.o_proj",
|
| 260 |
-
"model.layers.24.self_attn.o_proj",
|
| 261 |
-
"model.layers.25.self_attn.o_proj",
|
| 262 |
-
"model.layers.26.self_attn.o_proj",
|
| 263 |
-
"model.layers.27.self_attn.o_proj",
|
| 264 |
-
"model.layers.28.self_attn.o_proj",
|
| 265 |
-
"model.layers.29.self_attn.o_proj",
|
| 266 |
-
"model.layers.30.self_attn.o_proj",
|
| 267 |
-
"model.layers.31.self_attn.o_proj",
|
| 268 |
-
"model.layers.32.self_attn.o_proj",
|
| 269 |
-
"model.layers.33.self_attn.o_proj",
|
| 270 |
-
"model.layers.34.self_attn.o_proj",
|
| 271 |
-
"model.layers.35.self_attn.o_proj",
|
| 272 |
-
"model.layers.36.self_attn.o_proj",
|
| 273 |
-
"model.layers.37.self_attn.o_proj",
|
| 274 |
-
"model.layers.38.self_attn.o_proj",
|
| 275 |
-
"model.layers.39.self_attn.o_proj",
|
| 276 |
-
"model.layers.40.self_attn.o_proj",
|
| 277 |
-
"model.layers.41.self_attn.o_proj",
|
| 278 |
-
"model.layers.42.self_attn.o_proj",
|
| 279 |
-
"model.layers.43.self_attn.o_proj",
|
| 280 |
-
"model.layers.44.self_attn.o_proj",
|
| 281 |
-
"model.layers.45.self_attn.o_proj",
|
| 282 |
-
"model.layers.46.self_attn.o_proj",
|
| 283 |
-
"model.layers.47.self_attn.o_proj",
|
| 284 |
-
"model.decoder.self_attn.o_proj"
|
| 285 |
-
],
|
| 286 |
-
"weight_block_size": [
|
| 287 |
-
128,
|
| 288 |
-
128
|
| 289 |
-
]
|
| 290 |
-
},
|
| 291 |
-
"rope_scaling": {
|
| 292 |
-
"rope_type": "default",
|
| 293 |
-
"type": "default"
|
| 294 |
-
},
|
| 295 |
-
"rope_theta": 5000000,
|
| 296 |
-
"routed_scaling_factor": null,
|
| 297 |
-
"scoring_func": "sigmoid",
|
| 298 |
-
"sliding_window": 128,
|
| 299 |
-
"sliding_window_size": 128,
|
| 300 |
-
"swa_rope_theta": 10000,
|
| 301 |
-
"tie_word_embeddings": false,
|
| 302 |
-
"topk_group": 1,
|
| 303 |
-
"topk_method": "noaux_tc",
|
| 304 |
-
"transformers_version": "4.57.1",
|
| 305 |
-
"use_cache": true,
|
| 306 |
-
"v_head_dim": 128,
|
| 307 |
-
"video_token_id": 151656,
|
| 308 |
-
"vision_config": {
|
| 309 |
-
"depth": 28,
|
| 310 |
-
"fullatt_block_indexes": [
|
| 311 |
-
0,
|
| 312 |
-
9,
|
| 313 |
-
18,
|
| 314 |
-
27
|
| 315 |
-
],
|
| 316 |
-
"hidden_act": "silu",
|
| 317 |
-
"hidden_size": 1280,
|
| 318 |
-
"in_chans": 3,
|
| 319 |
-
"intermediate_size": 4608,
|
| 320 |
-
"num_heads": 32,
|
| 321 |
-
"num_key_value_heads": 8,
|
| 322 |
-
"num_query_groups": 4,
|
| 323 |
-
"out_hidden_size": 4096,
|
| 324 |
-
"patch_size": 16,
|
| 325 |
-
"spatial_merge_size": 2,
|
| 326 |
-
"spatial_patch_size": 16,
|
| 327 |
-
"temporal_patch_size": 2,
|
| 328 |
-
"tokens_per_second": 2,
|
| 329 |
-
"use_sink": true,
|
| 330 |
-
"visual_token_window_size": 64,
|
| 331 |
-
"vit_window_attn_types": [
|
| 332 |
-
-1,
|
| 333 |
-
0,
|
| 334 |
-
0,
|
| 335 |
-
0,
|
| 336 |
-
0,
|
| 337 |
-
1,
|
| 338 |
-
1,
|
| 339 |
-
1,
|
| 340 |
-
1,
|
| 341 |
-
-1,
|
| 342 |
-
0,
|
| 343 |
-
0,
|
| 344 |
-
0,
|
| 345 |
-
0,
|
| 346 |
-
1,
|
| 347 |
-
1,
|
| 348 |
-
1,
|
| 349 |
-
1,
|
| 350 |
-
-1,
|
| 351 |
-
0,
|
| 352 |
-
0,
|
| 353 |
-
0,
|
| 354 |
-
0,
|
| 355 |
-
1,
|
| 356 |
-
1,
|
| 357 |
-
1,
|
| 358 |
-
1,
|
| 359 |
-
-1
|
| 360 |
-
],
|
| 361 |
-
"window_size": 128
|
| 362 |
-
},
|
| 363 |
-
"vision_end_token_id": 151653,
|
| 364 |
-
"vision_model_type": "mimovl",
|
| 365 |
-
"vision_start_token_id": 151652,
|
| 366 |
-
"vocab_size": 152576
|
| 367 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"MiMoV2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"auto_map": {
|
| 6 |
+
"AutoConfig": "configuration_mimo_v2.MiMoV2Config",
|
| 7 |
+
"AutoModel": "modeling_mimo_v2.MiMoV2Model",
|
| 8 |
+
"AutoModelForCausalLM": "modeling_mimo_v2.MiMoV2ForCausalLM"
|
| 9 |
+
},
|
| 10 |
+
"attention_bias": false,
|
| 11 |
+
"attention_chunk_size": 128,
|
| 12 |
+
"attention_dropout": 0.0,
|
| 13 |
+
"attention_value_scale": 0.707,
|
| 14 |
+
"attention_projection_layout": "fused_qkv",
|
| 15 |
+
"add_full_attention_sink_bias": false,
|
| 16 |
+
"add_swa_attention_sink_bias": true,
|
| 17 |
+
"audio_config": {
|
| 18 |
+
"add_post_norm": true,
|
| 19 |
+
"audio_channels": 20,
|
| 20 |
+
"audio_segment_size": 6000,
|
| 21 |
+
"group_size": 4,
|
| 22 |
+
"input_full_attention": true,
|
| 23 |
+
"input_local_attn_heads": 16,
|
| 24 |
+
"input_local_dim": 1024,
|
| 25 |
+
"input_local_head_dim": 64,
|
| 26 |
+
"input_local_hidden_dropout": 0.0,
|
| 27 |
+
"input_local_intermediate_size": 4096,
|
| 28 |
+
"input_local_layers": 6,
|
| 29 |
+
"out_hidden_size": 4096,
|
| 30 |
+
"partial_rotary_factor": 1.0,
|
| 31 |
+
"projection_layers": 2,
|
| 32 |
+
"rope_theta": 640000,
|
| 33 |
+
"speech_vocab_size": "1280",
|
| 34 |
+
"speech_zeroemb_idx": "1024"
|
| 35 |
+
},
|
| 36 |
+
"swa_num_key_value_heads": 8,
|
| 37 |
+
"swa_num_attention_heads": 64,
|
| 38 |
+
"swa_head_dim": 192,
|
| 39 |
+
"swa_v_head_dim": 128,
|
| 40 |
+
"dtype": "bfloat16",
|
| 41 |
+
"eos_token_id": 151645,
|
| 42 |
+
"head_dim": 192,
|
| 43 |
+
"hidden_act": "silu",
|
| 44 |
+
"hidden_size": 4096,
|
| 45 |
+
"hybrid_block_size": null,
|
| 46 |
+
"hybrid_layer_pattern": [
|
| 47 |
+
0,
|
| 48 |
+
1,
|
| 49 |
+
1,
|
| 50 |
+
1,
|
| 51 |
+
1,
|
| 52 |
+
0,
|
| 53 |
+
1,
|
| 54 |
+
1,
|
| 55 |
+
1,
|
| 56 |
+
1,
|
| 57 |
+
1,
|
| 58 |
+
0,
|
| 59 |
+
1,
|
| 60 |
+
1,
|
| 61 |
+
1,
|
| 62 |
+
1,
|
| 63 |
+
1,
|
| 64 |
+
0,
|
| 65 |
+
1,
|
| 66 |
+
1,
|
| 67 |
+
1,
|
| 68 |
+
1,
|
| 69 |
+
1,
|
| 70 |
+
0,
|
| 71 |
+
1,
|
| 72 |
+
1,
|
| 73 |
+
1,
|
| 74 |
+
1,
|
| 75 |
+
1,
|
| 76 |
+
0,
|
| 77 |
+
1,
|
| 78 |
+
1,
|
| 79 |
+
1,
|
| 80 |
+
1,
|
| 81 |
+
1,
|
| 82 |
+
0,
|
| 83 |
+
1,
|
| 84 |
+
1,
|
| 85 |
+
1,
|
| 86 |
+
1,
|
| 87 |
+
1,
|
| 88 |
+
0,
|
| 89 |
+
1,
|
| 90 |
+
1,
|
| 91 |
+
1,
|
| 92 |
+
1,
|
| 93 |
+
1,
|
| 94 |
+
0
|
| 95 |
+
],
|
| 96 |
+
"image_token_id": 151655,
|
| 97 |
+
"initializer_range": 0.02,
|
| 98 |
+
"intermediate_size": 16384,
|
| 99 |
+
"layernorm_epsilon": 1e-05,
|
| 100 |
+
"max_position_embeddings": 262144,
|
| 101 |
+
"model_type": "mimo_v2",
|
| 102 |
+
"moe_intermediate_size": 2048,
|
| 103 |
+
"moe_layer_freq": [
|
| 104 |
+
0,
|
| 105 |
+
1,
|
| 106 |
+
1,
|
| 107 |
+
1,
|
| 108 |
+
1,
|
| 109 |
+
1,
|
| 110 |
+
1,
|
| 111 |
+
1,
|
| 112 |
+
1,
|
| 113 |
+
1,
|
| 114 |
+
1,
|
| 115 |
+
1,
|
| 116 |
+
1,
|
| 117 |
+
1,
|
| 118 |
+
1,
|
| 119 |
+
1,
|
| 120 |
+
1,
|
| 121 |
+
1,
|
| 122 |
+
1,
|
| 123 |
+
1,
|
| 124 |
+
1,
|
| 125 |
+
1,
|
| 126 |
+
1,
|
| 127 |
+
1,
|
| 128 |
+
1,
|
| 129 |
+
1,
|
| 130 |
+
1,
|
| 131 |
+
1,
|
| 132 |
+
1,
|
| 133 |
+
1,
|
| 134 |
+
1,
|
| 135 |
+
1,
|
| 136 |
+
1,
|
| 137 |
+
1,
|
| 138 |
+
1,
|
| 139 |
+
1,
|
| 140 |
+
1,
|
| 141 |
+
1,
|
| 142 |
+
1,
|
| 143 |
+
1,
|
| 144 |
+
1,
|
| 145 |
+
1,
|
| 146 |
+
1,
|
| 147 |
+
1,
|
| 148 |
+
1,
|
| 149 |
+
1,
|
| 150 |
+
1,
|
| 151 |
+
1
|
| 152 |
+
],
|
| 153 |
+
"n_group": 1,
|
| 154 |
+
"n_routed_experts": 256,
|
| 155 |
+
"n_shared_experts": null,
|
| 156 |
+
"norm_topk_prob": true,
|
| 157 |
+
"num_attention_heads": 64,
|
| 158 |
+
"num_experts_per_tok": 8,
|
| 159 |
+
"num_hidden_layers": 48,
|
| 160 |
+
"num_key_value_heads": 4,
|
| 161 |
+
"pad_token_id": 151643,
|
| 162 |
+
"partial_rotary_factor": 0.334,
|
| 163 |
+
"processor_config": {
|
| 164 |
+
"audio_avg_pooler": 2,
|
| 165 |
+
"audio_channels": 20,
|
| 166 |
+
"audio_end_token_id": 151674,
|
| 167 |
+
"audio_fmax": null,
|
| 168 |
+
"audio_fmin": 0,
|
| 169 |
+
"audio_group_size": 4,
|
| 170 |
+
"audio_hop_length": 240,
|
| 171 |
+
"audio_input_id_per_second": 25.0,
|
| 172 |
+
"audio_kernel_size": 3,
|
| 173 |
+
"audio_n_mels": 128,
|
| 174 |
+
"audio_nfft": 960,
|
| 175 |
+
"audio_sampling_rate": 24000,
|
| 176 |
+
"audio_segment_size": 6000,
|
| 177 |
+
"audio_start_token_id": 151673,
|
| 178 |
+
"audio_stride_size": 2,
|
| 179 |
+
"audio_token_id": 151669,
|
| 180 |
+
"audio_window_size": 960,
|
| 181 |
+
"audio_zeroemb_idx": [
|
| 182 |
+
1024,
|
| 183 |
+
1024,
|
| 184 |
+
1024,
|
| 185 |
+
1024,
|
| 186 |
+
1024,
|
| 187 |
+
1024,
|
| 188 |
+
1024,
|
| 189 |
+
1024,
|
| 190 |
+
1024,
|
| 191 |
+
1024,
|
| 192 |
+
1024,
|
| 193 |
+
1024,
|
| 194 |
+
1024,
|
| 195 |
+
1024,
|
| 196 |
+
1024,
|
| 197 |
+
1024,
|
| 198 |
+
1024,
|
| 199 |
+
1024,
|
| 200 |
+
1024,
|
| 201 |
+
1024
|
| 202 |
+
],
|
| 203 |
+
"fps": 1.0,
|
| 204 |
+
"image_max_pixels": 8388608,
|
| 205 |
+
"image_min_pixels": 8192,
|
| 206 |
+
"image_token_id": 151655,
|
| 207 |
+
"max_frames": 1024,
|
| 208 |
+
"merge_size": 2,
|
| 209 |
+
"min_frames": null,
|
| 210 |
+
"num_frames": null,
|
| 211 |
+
"pad_token_id": 151643,
|
| 212 |
+
"patch_size": 16,
|
| 213 |
+
"rope_type": "rope",
|
| 214 |
+
"temporal_compression_ratio": 1,
|
| 215 |
+
"temporal_patch_size": 2,
|
| 216 |
+
"use_per_grid_t_timestamps": false,
|
| 217 |
+
"use_video_timestamps": true,
|
| 218 |
+
"video_audio_interleave_length": 0.0,
|
| 219 |
+
"video_end_token_id": 151671,
|
| 220 |
+
"video_max_pixels": 8388608,
|
| 221 |
+
"video_min_pixels": 8192,
|
| 222 |
+
"video_process_num_threads": 16,
|
| 223 |
+
"video_start_token_id": 151670,
|
| 224 |
+
"video_token_id": 151656,
|
| 225 |
+
"video_tokens_per_second": 2,
|
| 226 |
+
"video_total_max_pixels": 134217728,
|
| 227 |
+
"vision_end_token_id": 151653,
|
| 228 |
+
"vision_start_token_id": 151652
|
| 229 |
+
},
|
| 230 |
+
"quantization_config": {
|
| 231 |
+
"activation_scheme": "dynamic",
|
| 232 |
+
"fmt": "e4m3",
|
| 233 |
+
"quant_method": "fp8",
|
| 234 |
+
"store_dtype": "fp8",
|
| 235 |
+
"ignored_layers": [
|
| 236 |
+
"model.layers.0.self_attn.o_proj",
|
| 237 |
+
"model.layers.1.self_attn.o_proj",
|
| 238 |
+
"model.layers.2.self_attn.o_proj",
|
| 239 |
+
"model.layers.3.self_attn.o_proj",
|
| 240 |
+
"model.layers.4.self_attn.o_proj",
|
| 241 |
+
"model.layers.5.self_attn.o_proj",
|
| 242 |
+
"model.layers.6.self_attn.o_proj",
|
| 243 |
+
"model.layers.7.self_attn.o_proj",
|
| 244 |
+
"model.layers.8.self_attn.o_proj",
|
| 245 |
+
"model.layers.9.self_attn.o_proj",
|
| 246 |
+
"model.layers.10.self_attn.o_proj",
|
| 247 |
+
"model.layers.11.self_attn.o_proj",
|
| 248 |
+
"model.layers.12.self_attn.o_proj",
|
| 249 |
+
"model.layers.13.self_attn.o_proj",
|
| 250 |
+
"model.layers.14.self_attn.o_proj",
|
| 251 |
+
"model.layers.15.self_attn.o_proj",
|
| 252 |
+
"model.layers.16.self_attn.o_proj",
|
| 253 |
+
"model.layers.17.self_attn.o_proj",
|
| 254 |
+
"model.layers.18.self_attn.o_proj",
|
| 255 |
+
"model.layers.19.self_attn.o_proj",
|
| 256 |
+
"model.layers.20.self_attn.o_proj",
|
| 257 |
+
"model.layers.21.self_attn.o_proj",
|
| 258 |
+
"model.layers.22.self_attn.o_proj",
|
| 259 |
+
"model.layers.23.self_attn.o_proj",
|
| 260 |
+
"model.layers.24.self_attn.o_proj",
|
| 261 |
+
"model.layers.25.self_attn.o_proj",
|
| 262 |
+
"model.layers.26.self_attn.o_proj",
|
| 263 |
+
"model.layers.27.self_attn.o_proj",
|
| 264 |
+
"model.layers.28.self_attn.o_proj",
|
| 265 |
+
"model.layers.29.self_attn.o_proj",
|
| 266 |
+
"model.layers.30.self_attn.o_proj",
|
| 267 |
+
"model.layers.31.self_attn.o_proj",
|
| 268 |
+
"model.layers.32.self_attn.o_proj",
|
| 269 |
+
"model.layers.33.self_attn.o_proj",
|
| 270 |
+
"model.layers.34.self_attn.o_proj",
|
| 271 |
+
"model.layers.35.self_attn.o_proj",
|
| 272 |
+
"model.layers.36.self_attn.o_proj",
|
| 273 |
+
"model.layers.37.self_attn.o_proj",
|
| 274 |
+
"model.layers.38.self_attn.o_proj",
|
| 275 |
+
"model.layers.39.self_attn.o_proj",
|
| 276 |
+
"model.layers.40.self_attn.o_proj",
|
| 277 |
+
"model.layers.41.self_attn.o_proj",
|
| 278 |
+
"model.layers.42.self_attn.o_proj",
|
| 279 |
+
"model.layers.43.self_attn.o_proj",
|
| 280 |
+
"model.layers.44.self_attn.o_proj",
|
| 281 |
+
"model.layers.45.self_attn.o_proj",
|
| 282 |
+
"model.layers.46.self_attn.o_proj",
|
| 283 |
+
"model.layers.47.self_attn.o_proj",
|
| 284 |
+
"model.decoder.self_attn.o_proj"
|
| 285 |
+
],
|
| 286 |
+
"weight_block_size": [
|
| 287 |
+
128,
|
| 288 |
+
128
|
| 289 |
+
]
|
| 290 |
+
},
|
| 291 |
+
"rope_scaling": {
|
| 292 |
+
"rope_type": "default",
|
| 293 |
+
"type": "default"
|
| 294 |
+
},
|
| 295 |
+
"rope_theta": 5000000,
|
| 296 |
+
"routed_scaling_factor": null,
|
| 297 |
+
"scoring_func": "sigmoid",
|
| 298 |
+
"sliding_window": 128,
|
| 299 |
+
"sliding_window_size": 128,
|
| 300 |
+
"swa_rope_theta": 10000,
|
| 301 |
+
"tie_word_embeddings": false,
|
| 302 |
+
"topk_group": 1,
|
| 303 |
+
"topk_method": "noaux_tc",
|
| 304 |
+
"transformers_version": "4.57.1",
|
| 305 |
+
"use_cache": true,
|
| 306 |
+
"v_head_dim": 128,
|
| 307 |
+
"video_token_id": 151656,
|
| 308 |
+
"vision_config": {
|
| 309 |
+
"depth": 28,
|
| 310 |
+
"fullatt_block_indexes": [
|
| 311 |
+
0,
|
| 312 |
+
9,
|
| 313 |
+
18,
|
| 314 |
+
27
|
| 315 |
+
],
|
| 316 |
+
"hidden_act": "silu",
|
| 317 |
+
"hidden_size": 1280,
|
| 318 |
+
"in_chans": 3,
|
| 319 |
+
"intermediate_size": 4608,
|
| 320 |
+
"num_heads": 32,
|
| 321 |
+
"num_key_value_heads": 8,
|
| 322 |
+
"num_query_groups": 4,
|
| 323 |
+
"out_hidden_size": 4096,
|
| 324 |
+
"patch_size": 16,
|
| 325 |
+
"spatial_merge_size": 2,
|
| 326 |
+
"spatial_patch_size": 16,
|
| 327 |
+
"temporal_patch_size": 2,
|
| 328 |
+
"tokens_per_second": 2,
|
| 329 |
+
"use_sink": true,
|
| 330 |
+
"visual_token_window_size": 64,
|
| 331 |
+
"vit_window_attn_types": [
|
| 332 |
+
-1,
|
| 333 |
+
0,
|
| 334 |
+
0,
|
| 335 |
+
0,
|
| 336 |
+
0,
|
| 337 |
+
1,
|
| 338 |
+
1,
|
| 339 |
+
1,
|
| 340 |
+
1,
|
| 341 |
+
-1,
|
| 342 |
+
0,
|
| 343 |
+
0,
|
| 344 |
+
0,
|
| 345 |
+
0,
|
| 346 |
+
1,
|
| 347 |
+
1,
|
| 348 |
+
1,
|
| 349 |
+
1,
|
| 350 |
+
-1,
|
| 351 |
+
0,
|
| 352 |
+
0,
|
| 353 |
+
0,
|
| 354 |
+
0,
|
| 355 |
+
1,
|
| 356 |
+
1,
|
| 357 |
+
1,
|
| 358 |
+
1,
|
| 359 |
+
-1
|
| 360 |
+
],
|
| 361 |
+
"window_size": 128
|
| 362 |
+
},
|
| 363 |
+
"vision_end_token_id": 151653,
|
| 364 |
+
"vision_model_type": "mimovl",
|
| 365 |
+
"vision_start_token_id": 151652,
|
| 366 |
+
"vocab_size": 152576
|
| 367 |
+
}
|
tokenizer_config.json
CHANGED
|
@@ -281,7 +281,7 @@
|
|
| 281 |
"<|mimo_audio_end|>"
|
| 282 |
],
|
| 283 |
"bos_token": null,
|
| 284 |
-
"chat_template": "{%- if not add_generation_prompt is defined -%}\n {%- set add_generation_prompt = false -%}\n{%- endif -%}\n{%- if not enable_thinking is defined -%}\n {%- set enable_thinking =
|
| 285 |
"clean_up_tokenization_spaces": false,
|
| 286 |
"eos_token": "<|im_end|>",
|
| 287 |
"errors": "replace",
|
|
|
|
| 281 |
"<|mimo_audio_end|>"
|
| 282 |
],
|
| 283 |
"bos_token": null,
|
| 284 |
+
"chat_template": "{%- if not add_generation_prompt is defined -%}\n {%- set add_generation_prompt = false -%}\n{%- endif -%}\n{%- if not enable_thinking is defined -%}\n {%- set enable_thinking = true -%}\n{%- endif -%}\n{%- if not keep_all_reasoning is defined -%}\n {%- set keep_all_reasoning = true -%}\n{%- endif -%}\n{%- macro render_extra_keys(json_dict, handled_keys) -%}\n {%- if json_dict is mapping %}\n {%- for json_key in json_dict if json_key not in handled_keys %}\n {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}\n {{- '\\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}\n {%- else %}\n {{-'\\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n{%- endmacro -%}\n{%- macro render_content(message_content) -%}\n {%- if message_content is string -%}\n {{- message_content -}}\n {%- else -%}\n {%- for content in message_content -%}\n {%- if content['type'] == 'image' or 'image' in content or 'image_url' in content -%}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' -}}\n {%- elif content['type'] == 'audio' or 'audio' in content or 'audio_url' in content -%}\n {{- '<|mimo_audio_start|><|audio_pad|><|mimo_audio_end|>' -}}\n {%- elif content['type'] == 'video' or 'video' in content or 'video_url' in content -%}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' -}}\n {%- elif 'text' in content -%}\n {{- content['text'] -}}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n{%- endmacro -%}\n{%- if messages[0][\"role\"] == \"system\" %}\n {%- set system_message = messages[0][\"content\"] %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set loop_messages = messages %}\n{%- endif %}\n{%- set ns = namespace(last_user_index=-1) %}\n{%- for m in loop_messages %}\n {%- if m.role == 'user' %}\n {%- set ns.last_user_index = loop.index0 -%}\n {%- endif %}\n{%- endfor %}\n{%- if not tools is defined %}\n {%- set tools = [] %}\n{%- endif %}\n{%- if system_message is defined %}\n {{- \"<|im_start|>system\\n\" + system_message }}\n{%- else %}\n {{- \"<|im_start|>system\\nYou are MiMo, a helpful AI assistant engineered by Xiaomi.\" }}\n{%- endif %}\n{%- if tools is iterable and tools | length > 0 %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou have access to the following functions:\\n\\n\" }}\n {{- \"<tools>\" }}\n {%- for tool in tools %}\n {%- if tool.function is defined %}\n {%- set tool = tool.function %}\n {%- endif %}\n {{- \"\\n<function>\\n<name>\" ~ tool.name ~ \"</name>\" }}\n {%- if tool.description is defined %}\n {{- '\\n<description>' ~ (tool.description | trim) ~ '</description>' }}\n {%- endif %}\n {{- '\\n<parameters>' }}\n {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {{- '\\n<parameter>' }}\n {{- '\\n<name>' ~ param_name ~ '</name>' }}\n {%- if param_fields.type is defined %}\n {{- '\\n<type>' ~ (param_fields.type | string) ~ '</type>' }}\n {%- endif %}\n {%- if param_fields.description is defined %}\n {{- '\\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}\n {%- endif %}\n {%- set handled_keys = ['name', 'type', 'description'] %}\n {{- render_extra_keys(param_fields, handled_keys) }}\n {{- '\\n</parameter>' }}\n {%- endfor %}\n {%- endif %}\n {%- set handled_keys = ['type', 'properties'] %}\n {{- render_extra_keys(tool.parameters, handled_keys) }}\n {{- '\\n</parameters>' }}\n {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}\n {{- render_extra_keys(tool, handled_keys) }}\n {{- '\\n</function>' }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\n {{- '\\n\\nFor each function call, output the function name and arguments in the following format:\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>value_1</parameter>\\n<parameter=example_parameter_2>This is the value for the second parameter\\nthat can span\\nmultiple lines</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- DO NOT use function calls inside <think></think> tags.\\n- The value enclosed between parameter tags is preserved exactly as-is, including newlines and spaces.\\n</IMPORTANT>' }}\n{%- endif %}\n{{- '<|im_end|>' }}\n{%- for message in loop_messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = render_content(message.content) %}\n {%- endif %}\n {%- if message.role == \"assistant\" %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- set reasoning_content = '' %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].split('<think>')[-1] %}\n {%- set content = content.split('</think>')[-1] %}\n {%- endif %}\n {%- endif %}\n {%- if (keep_all_reasoning or loop.index0 > ns.last_user_index) and reasoning_content -%}\n {{- '<|im_start|>' + message.role + '\\n<think>' + reasoning_content + '</think>' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n<think></think>' + content }}\n {%- endif %}\n {%- if message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- if tool_call.arguments is defined %}\n {%- for args_name, args_value in tool_call.arguments|items %}\n {{- '<parameter=' + args_name + '>' }}\n {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\n {{- args_value }}\n {{- '</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>' }}\n {%- elif message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' + render_content(message.content) + '<|im_end|>' }}\n {%- elif message.role == \"system\" %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>tool\\n' }}\n {%- endif %}\n {{- '<tool_response>\\n' }}\n {{- render_content(message.content) }}\n {{- '\\n</tool_response>\\n' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>' }}\n {%- elif loop.last %}\n {{- '<|im_end|>' }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if not enable_thinking -%}\n {{- '<think></think>' -}}\n {%- else -%}\n {{- '' -}}\n {%- endif -%}\n{%- endif %}\n",
|
| 285 |
"clean_up_tokenization_spaces": false,
|
| 286 |
"eos_token": "<|im_end|>",
|
| 287 |
"errors": "replace",
|