Upload model.safetensors.index.json with huggingface_hub
Browse files- model.safetensors.index.json +452 -449
model.safetensors.index.json
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"
|
|
|
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"lm_head.weight": "model-00004-of-00004.safetensors",
|
|
@@ -126,11 +127,11 @@
|
|
| 126 |
"model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 127 |
"model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 128 |
"model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 129 |
-
"model.language_model.layers.19.input_layernorm.weight": "model-
|
| 130 |
-
"model.language_model.layers.19.mlp.down_proj.weight": "model-
|
| 131 |
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 132 |
-
"model.language_model.layers.19.mlp.up_proj.weight": "model-
|
| 133 |
-
"model.language_model.layers.19.post_attention_layernorm.weight": "model-
|
| 134 |
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 135 |
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 136 |
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
|
@@ -148,39 +149,39 @@
|
|
| 148 |
"model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 149 |
"model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 150 |
"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 151 |
-
"model.language_model.layers.20.input_layernorm.weight": "model-
|
| 152 |
-
"model.language_model.layers.20.mlp.down_proj.weight": "model-
|
| 153 |
-
"model.language_model.layers.20.mlp.gate_proj.weight": "model-
|
| 154 |
-
"model.language_model.layers.20.mlp.up_proj.weight": "model-
|
| 155 |
-
"model.language_model.layers.20.post_attention_layernorm.weight": "model-
|
| 156 |
-
"model.language_model.layers.20.self_attn.k_norm.weight": "model-
|
| 157 |
-
"model.language_model.layers.20.self_attn.k_proj.weight": "model-
|
| 158 |
-
"model.language_model.layers.20.self_attn.o_proj.weight": "model-
|
| 159 |
-
"model.language_model.layers.20.self_attn.q_norm.weight": "model-
|
| 160 |
-
"model.language_model.layers.20.self_attn.q_proj.weight": "model-
|
| 161 |
-
"model.language_model.layers.20.self_attn.v_proj.weight": "model-
|
| 162 |
-
"model.language_model.layers.21.input_layernorm.weight": "model-
|
| 163 |
-
"model.language_model.layers.21.mlp.down_proj.weight": "model-
|
| 164 |
-
"model.language_model.layers.21.mlp.gate_proj.weight": "model-
|
| 165 |
-
"model.language_model.layers.21.mlp.up_proj.weight": "model-
|
| 166 |
-
"model.language_model.layers.21.post_attention_layernorm.weight": "model-
|
| 167 |
-
"model.language_model.layers.21.self_attn.k_norm.weight": "model-
|
| 168 |
-
"model.language_model.layers.21.self_attn.k_proj.weight": "model-
|
| 169 |
-
"model.language_model.layers.21.self_attn.o_proj.weight": "model-
|
| 170 |
-
"model.language_model.layers.21.self_attn.q_norm.weight": "model-
|
| 171 |
-
"model.language_model.layers.21.self_attn.q_proj.weight": "model-
|
| 172 |
-
"model.language_model.layers.21.self_attn.v_proj.weight": "model-
|
| 173 |
-
"model.language_model.layers.22.input_layernorm.weight": "model-
|
| 174 |
"model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 175 |
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 176 |
"model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
-
"model.language_model.layers.22.post_attention_layernorm.weight": "model-
|
| 178 |
-
"model.language_model.layers.22.self_attn.k_norm.weight": "model-
|
| 179 |
-
"model.language_model.layers.22.self_attn.k_proj.weight": "model-
|
| 180 |
-
"model.language_model.layers.22.self_attn.o_proj.weight": "model-
|
| 181 |
-
"model.language_model.layers.22.self_attn.q_norm.weight": "model-
|
| 182 |
-
"model.language_model.layers.22.self_attn.q_proj.weight": "model-
|
| 183 |
-
"model.language_model.layers.22.self_attn.v_proj.weight": "model-
|
| 184 |
"model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 185 |
"model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 186 |
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
|
@@ -291,39 +292,39 @@
|
|
| 291 |
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 292 |
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 293 |
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 294 |
-
"model.language_model.layers.32.input_layernorm.weight": "model-
|
| 295 |
-
"model.language_model.layers.32.mlp.down_proj.weight": "model-
|
| 296 |
-
"model.language_model.layers.32.mlp.gate_proj.weight": "model-
|
| 297 |
-
"model.language_model.layers.32.mlp.up_proj.weight": "model-
|
| 298 |
-
"model.language_model.layers.32.post_attention_layernorm.weight": "model-
|
| 299 |
"model.language_model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 300 |
"model.language_model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 301 |
"model.language_model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 302 |
"model.language_model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 303 |
"model.language_model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 304 |
"model.language_model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 305 |
-
"model.language_model.layers.33.input_layernorm.weight": "model-
|
| 306 |
-
"model.language_model.layers.33.mlp.down_proj.weight": "model-
|
| 307 |
-
"model.language_model.layers.33.mlp.gate_proj.weight": "model-
|
| 308 |
-
"model.language_model.layers.33.mlp.up_proj.weight": "model-
|
| 309 |
-
"model.language_model.layers.33.post_attention_layernorm.weight": "model-
|
| 310 |
-
"model.language_model.layers.33.self_attn.k_norm.weight": "model-
|
| 311 |
-
"model.language_model.layers.33.self_attn.k_proj.weight": "model-
|
| 312 |
-
"model.language_model.layers.33.self_attn.o_proj.weight": "model-
|
| 313 |
-
"model.language_model.layers.33.self_attn.q_norm.weight": "model-
|
| 314 |
-
"model.language_model.layers.33.self_attn.q_proj.weight": "model-
|
| 315 |
-
"model.language_model.layers.33.self_attn.v_proj.weight": "model-
|
| 316 |
-
"model.language_model.layers.34.input_layernorm.weight": "model-
|
| 317 |
-
"model.language_model.layers.34.mlp.down_proj.weight": "model-
|
| 318 |
-
"model.language_model.layers.34.mlp.gate_proj.weight": "model-
|
| 319 |
-
"model.language_model.layers.34.mlp.up_proj.weight": "model-
|
| 320 |
-
"model.language_model.layers.34.post_attention_layernorm.weight": "model-
|
| 321 |
-
"model.language_model.layers.34.self_attn.k_norm.weight": "model-
|
| 322 |
-
"model.language_model.layers.34.self_attn.k_proj.weight": "model-
|
| 323 |
-
"model.language_model.layers.34.self_attn.o_proj.weight": "model-
|
| 324 |
-
"model.language_model.layers.34.self_attn.q_norm.weight": "model-
|
| 325 |
-
"model.language_model.layers.34.self_attn.q_proj.weight": "model-
|
| 326 |
-
"model.language_model.layers.34.self_attn.v_proj.weight": "model-
|
| 327 |
"model.language_model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 328 |
"model.language_model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 329 |
"model.language_model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
|
@@ -331,9 +332,9 @@
|
|
| 331 |
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 332 |
"model.language_model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 333 |
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 334 |
-
"model.language_model.layers.35.self_attn.o_proj.weight": "model-
|
| 335 |
"model.language_model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 336 |
-
"model.language_model.layers.35.self_attn.q_proj.weight": "model-
|
| 337 |
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 338 |
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 339 |
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
|
@@ -357,401 +358,403 @@
|
|
| 357 |
"model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 358 |
"model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 359 |
"model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 360 |
-
"model.language_model.layers.6.input_layernorm.weight": "model-
|
| 361 |
-
"model.language_model.layers.6.mlp.down_proj.weight": "model-
|
| 362 |
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 363 |
"model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 364 |
-
"model.language_model.layers.6.post_attention_layernorm.weight": "model-
|
| 365 |
"model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 366 |
"model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 367 |
"model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 368 |
"model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 369 |
"model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 370 |
"model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 371 |
-
"model.language_model.layers.7.input_layernorm.weight": "model-
|
| 372 |
-
"model.language_model.layers.7.mlp.down_proj.weight": "model-
|
| 373 |
-
"model.language_model.layers.7.mlp.gate_proj.weight": "model-
|
| 374 |
-
"model.language_model.layers.7.mlp.up_proj.weight": "model-
|
| 375 |
-
"model.language_model.layers.7.post_attention_layernorm.weight": "model-
|
| 376 |
-
"model.language_model.layers.7.self_attn.k_norm.weight": "model-
|
| 377 |
-
"model.language_model.layers.7.self_attn.k_proj.weight": "model-
|
| 378 |
-
"model.language_model.layers.7.self_attn.o_proj.weight": "model-
|
| 379 |
-
"model.language_model.layers.7.self_attn.q_norm.weight": "model-
|
| 380 |
-
"model.language_model.layers.7.self_attn.q_proj.weight": "model-
|
| 381 |
-
"model.language_model.layers.7.self_attn.v_proj.weight": "model-
|
| 382 |
-
"model.language_model.layers.8.input_layernorm.weight": "model-
|
| 383 |
-
"model.language_model.layers.8.mlp.down_proj.weight": "model-
|
| 384 |
-
"model.language_model.layers.8.mlp.gate_proj.weight": "model-
|
| 385 |
-
"model.language_model.layers.8.mlp.up_proj.weight": "model-
|
| 386 |
-
"model.language_model.layers.8.post_attention_layernorm.weight": "model-
|
| 387 |
-
"model.language_model.layers.8.self_attn.k_norm.weight": "model-
|
| 388 |
-
"model.language_model.layers.8.self_attn.k_proj.weight": "model-
|
| 389 |
-
"model.language_model.layers.8.self_attn.o_proj.weight": "model-
|
| 390 |
-
"model.language_model.layers.8.self_attn.q_norm.weight": "model-
|
| 391 |
-
"model.language_model.layers.8.self_attn.q_proj.weight": "model-
|
| 392 |
-
"model.language_model.layers.8.self_attn.v_proj.weight": "model-
|
| 393 |
-
"model.language_model.layers.9.input_layernorm.weight": "model-
|
| 394 |
"model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 395 |
-
"model.language_model.layers.9.mlp.gate_proj.weight": "model-
|
| 396 |
"model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 397 |
-
"model.language_model.layers.9.post_attention_layernorm.weight": "model-
|
| 398 |
-
"model.language_model.layers.9.self_attn.k_norm.weight": "model-
|
| 399 |
-
"model.language_model.layers.9.self_attn.k_proj.weight": "model-
|
| 400 |
-
"model.language_model.layers.9.self_attn.o_proj.weight": "model-
|
| 401 |
-
"model.language_model.layers.9.self_attn.q_norm.weight": "model-
|
| 402 |
-
"model.language_model.layers.9.self_attn.q_proj.weight": "model-
|
| 403 |
-
"model.language_model.layers.9.self_attn.v_proj.weight": "model-
|
| 404 |
"model.language_model.norm.weight": "model-00004-of-00004.safetensors",
|
| 405 |
-
"model.
|
| 406 |
-
"model.
|
| 407 |
-
"model.visual.blocks.0.attn.
|
| 408 |
-
"model.visual.blocks.0.attn.
|
| 409 |
-
"model.visual.blocks.0.
|
| 410 |
-
"model.visual.blocks.0.
|
| 411 |
-
"model.visual.blocks.0.mlp.
|
| 412 |
-
"model.visual.blocks.0.mlp.
|
| 413 |
-
"model.visual.blocks.0.
|
| 414 |
-
"model.visual.blocks.0.
|
| 415 |
-
"model.visual.blocks.0.
|
| 416 |
-
"model.visual.blocks.0.
|
| 417 |
-
"model.visual.blocks.
|
| 418 |
-
"model.visual.blocks.
|
| 419 |
-
"model.visual.blocks.1.attn.
|
| 420 |
-
"model.visual.blocks.1.attn.
|
| 421 |
-
"model.visual.blocks.1.
|
| 422 |
-
"model.visual.blocks.1.
|
| 423 |
-
"model.visual.blocks.1.mlp.
|
| 424 |
-
"model.visual.blocks.1.mlp.
|
| 425 |
-
"model.visual.blocks.1.
|
| 426 |
-
"model.visual.blocks.1.
|
| 427 |
-
"model.visual.blocks.1.
|
| 428 |
-
"model.visual.blocks.1.
|
| 429 |
-
"model.visual.blocks.
|
| 430 |
-
"model.visual.blocks.
|
| 431 |
-
"model.visual.blocks.10.attn.
|
| 432 |
-
"model.visual.blocks.10.attn.
|
| 433 |
-
"model.visual.blocks.10.
|
| 434 |
-
"model.visual.blocks.10.
|
| 435 |
-
"model.visual.blocks.10.mlp.
|
| 436 |
-
"model.visual.blocks.10.mlp.
|
| 437 |
-
"model.visual.blocks.10.
|
| 438 |
-
"model.visual.blocks.10.
|
| 439 |
-
"model.visual.blocks.10.
|
| 440 |
-
"model.visual.blocks.10.
|
| 441 |
-
"model.visual.blocks.
|
| 442 |
-
"model.visual.blocks.
|
| 443 |
-
"model.visual.blocks.11.attn.
|
| 444 |
-
"model.visual.blocks.11.attn.
|
| 445 |
-
"model.visual.blocks.11.
|
| 446 |
-
"model.visual.blocks.11.
|
| 447 |
-
"model.visual.blocks.11.mlp.
|
| 448 |
-
"model.visual.blocks.11.mlp.
|
| 449 |
-
"model.visual.blocks.11.
|
| 450 |
-
"model.visual.blocks.11.
|
| 451 |
-
"model.visual.blocks.11.
|
| 452 |
-
"model.visual.blocks.11.
|
| 453 |
-
"model.visual.blocks.
|
| 454 |
-
"model.visual.blocks.
|
| 455 |
-
"model.visual.blocks.12.attn.
|
| 456 |
-
"model.visual.blocks.12.attn.
|
| 457 |
-
"model.visual.blocks.12.
|
| 458 |
-
"model.visual.blocks.12.
|
| 459 |
-
"model.visual.blocks.12.mlp.
|
| 460 |
-
"model.visual.blocks.12.mlp.
|
| 461 |
-
"model.visual.blocks.12.
|
| 462 |
-
"model.visual.blocks.12.
|
| 463 |
-
"model.visual.blocks.12.
|
| 464 |
-
"model.visual.blocks.12.
|
| 465 |
-
"model.visual.blocks.
|
| 466 |
-
"model.visual.blocks.
|
| 467 |
-
"model.visual.blocks.13.attn.
|
| 468 |
-
"model.visual.blocks.13.attn.
|
| 469 |
-
"model.visual.blocks.13.
|
| 470 |
-
"model.visual.blocks.13.
|
| 471 |
-
"model.visual.blocks.13.mlp.
|
| 472 |
-
"model.visual.blocks.13.mlp.
|
| 473 |
-
"model.visual.blocks.13.
|
| 474 |
-
"model.visual.blocks.13.
|
| 475 |
-
"model.visual.blocks.13.
|
| 476 |
-
"model.visual.blocks.13.
|
| 477 |
-
"model.visual.blocks.
|
| 478 |
-
"model.visual.blocks.
|
| 479 |
-
"model.visual.blocks.14.attn.
|
| 480 |
-
"model.visual.blocks.14.attn.
|
| 481 |
-
"model.visual.blocks.14.
|
| 482 |
-
"model.visual.blocks.14.
|
| 483 |
-
"model.visual.blocks.14.mlp.
|
| 484 |
-
"model.visual.blocks.14.mlp.
|
| 485 |
-
"model.visual.blocks.14.
|
| 486 |
-
"model.visual.blocks.14.
|
| 487 |
-
"model.visual.blocks.14.
|
| 488 |
-
"model.visual.blocks.14.
|
| 489 |
-
"model.visual.blocks.
|
| 490 |
-
"model.visual.blocks.
|
| 491 |
-
"model.visual.blocks.15.attn.
|
| 492 |
-
"model.visual.blocks.15.attn.
|
| 493 |
-
"model.visual.blocks.15.
|
| 494 |
-
"model.visual.blocks.15.
|
| 495 |
-
"model.visual.blocks.15.mlp.
|
| 496 |
-
"model.visual.blocks.15.mlp.
|
| 497 |
-
"model.visual.blocks.15.
|
| 498 |
-
"model.visual.blocks.15.
|
| 499 |
-
"model.visual.blocks.15.
|
| 500 |
-
"model.visual.blocks.15.
|
| 501 |
-
"model.visual.blocks.
|
| 502 |
-
"model.visual.blocks.
|
| 503 |
-
"model.visual.blocks.16.attn.
|
| 504 |
-
"model.visual.blocks.16.attn.
|
| 505 |
-
"model.visual.blocks.16.
|
| 506 |
-
"model.visual.blocks.16.
|
| 507 |
-
"model.visual.blocks.16.mlp.
|
| 508 |
-
"model.visual.blocks.16.mlp.
|
| 509 |
-
"model.visual.blocks.16.
|
| 510 |
-
"model.visual.blocks.16.
|
| 511 |
-
"model.visual.blocks.16.
|
| 512 |
-
"model.visual.blocks.16.
|
| 513 |
-
"model.visual.blocks.
|
| 514 |
-
"model.visual.blocks.
|
| 515 |
-
"model.visual.blocks.17.attn.
|
| 516 |
-
"model.visual.blocks.17.attn.
|
| 517 |
-
"model.visual.blocks.17.
|
| 518 |
-
"model.visual.blocks.17.
|
| 519 |
-
"model.visual.blocks.17.mlp.
|
| 520 |
-
"model.visual.blocks.17.mlp.
|
| 521 |
-
"model.visual.blocks.17.
|
| 522 |
-
"model.visual.blocks.17.
|
| 523 |
-
"model.visual.blocks.17.
|
| 524 |
-
"model.visual.blocks.17.
|
| 525 |
-
"model.visual.blocks.
|
| 526 |
-
"model.visual.blocks.
|
| 527 |
-
"model.visual.blocks.18.attn.
|
| 528 |
-
"model.visual.blocks.18.attn.
|
| 529 |
-
"model.visual.blocks.18.
|
| 530 |
-
"model.visual.blocks.18.
|
| 531 |
-
"model.visual.blocks.18.mlp.
|
| 532 |
-
"model.visual.blocks.18.mlp.
|
| 533 |
-
"model.visual.blocks.18.
|
| 534 |
-
"model.visual.blocks.18.
|
| 535 |
-
"model.visual.blocks.18.
|
| 536 |
-
"model.visual.blocks.18.
|
| 537 |
-
"model.visual.blocks.
|
| 538 |
-
"model.visual.blocks.
|
| 539 |
-
"model.visual.blocks.19.attn.
|
| 540 |
-
"model.visual.blocks.19.attn.
|
| 541 |
-
"model.visual.blocks.19.
|
| 542 |
-
"model.visual.blocks.19.
|
| 543 |
-
"model.visual.blocks.19.mlp.
|
| 544 |
-
"model.visual.blocks.19.mlp.
|
| 545 |
-
"model.visual.blocks.19.
|
| 546 |
-
"model.visual.blocks.19.
|
| 547 |
-
"model.visual.blocks.19.
|
| 548 |
-
"model.visual.blocks.19.
|
| 549 |
-
"model.visual.blocks.
|
| 550 |
-
"model.visual.blocks.
|
| 551 |
-
"model.visual.blocks.2.attn.
|
| 552 |
-
"model.visual.blocks.2.attn.
|
| 553 |
-
"model.visual.blocks.2.
|
| 554 |
-
"model.visual.blocks.2.
|
| 555 |
-
"model.visual.blocks.2.mlp.
|
| 556 |
-
"model.visual.blocks.2.mlp.
|
| 557 |
-
"model.visual.blocks.2.
|
| 558 |
-
"model.visual.blocks.2.
|
| 559 |
-
"model.visual.blocks.2.
|
| 560 |
-
"model.visual.blocks.2.
|
| 561 |
-
"model.visual.blocks.
|
| 562 |
-
"model.visual.blocks.
|
| 563 |
-
"model.visual.blocks.20.attn.
|
| 564 |
-
"model.visual.blocks.20.attn.
|
| 565 |
-
"model.visual.blocks.20.
|
| 566 |
-
"model.visual.blocks.20.
|
| 567 |
-
"model.visual.blocks.20.mlp.
|
| 568 |
-
"model.visual.blocks.20.mlp.
|
| 569 |
-
"model.visual.blocks.20.
|
| 570 |
-
"model.visual.blocks.20.
|
| 571 |
-
"model.visual.blocks.20.
|
| 572 |
-
"model.visual.blocks.20.
|
| 573 |
-
"model.visual.blocks.
|
| 574 |
-
"model.visual.blocks.
|
| 575 |
-
"model.visual.blocks.21.attn.
|
| 576 |
-
"model.visual.blocks.21.attn.
|
| 577 |
-
"model.visual.blocks.21.
|
| 578 |
-
"model.visual.blocks.21.
|
| 579 |
-
"model.visual.blocks.21.mlp.
|
| 580 |
-
"model.visual.blocks.21.mlp.
|
| 581 |
-
"model.visual.blocks.21.
|
| 582 |
-
"model.visual.blocks.21.
|
| 583 |
-
"model.visual.blocks.21.
|
| 584 |
-
"model.visual.blocks.21.
|
| 585 |
-
"model.visual.blocks.
|
| 586 |
-
"model.visual.blocks.
|
| 587 |
-
"model.visual.blocks.22.attn.
|
| 588 |
-
"model.visual.blocks.22.attn.
|
| 589 |
-
"model.visual.blocks.22.
|
| 590 |
-
"model.visual.blocks.22.
|
| 591 |
-
"model.visual.blocks.22.mlp.
|
| 592 |
-
"model.visual.blocks.22.mlp.
|
| 593 |
-
"model.visual.blocks.22.
|
| 594 |
-
"model.visual.blocks.22.
|
| 595 |
-
"model.visual.blocks.22.
|
| 596 |
-
"model.visual.blocks.22.
|
| 597 |
-
"model.visual.blocks.
|
| 598 |
-
"model.visual.blocks.
|
| 599 |
-
"model.visual.blocks.23.attn.
|
| 600 |
-
"model.visual.blocks.23.attn.
|
| 601 |
-
"model.visual.blocks.23.
|
| 602 |
-
"model.visual.blocks.23.
|
| 603 |
-
"model.visual.blocks.23.mlp.
|
| 604 |
-
"model.visual.blocks.23.mlp.
|
| 605 |
-
"model.visual.blocks.23.
|
| 606 |
-
"model.visual.blocks.23.
|
| 607 |
-
"model.visual.blocks.23.
|
| 608 |
-
"model.visual.blocks.23.
|
| 609 |
-
"model.visual.blocks.
|
| 610 |
-
"model.visual.blocks.
|
| 611 |
-
"model.visual.blocks.24.attn.
|
| 612 |
-
"model.visual.blocks.24.attn.
|
| 613 |
-
"model.visual.blocks.24.
|
| 614 |
-
"model.visual.blocks.24.
|
| 615 |
-
"model.visual.blocks.24.mlp.
|
| 616 |
-
"model.visual.blocks.24.mlp.
|
| 617 |
-
"model.visual.blocks.24.
|
| 618 |
-
"model.visual.blocks.24.
|
| 619 |
-
"model.visual.blocks.24.
|
| 620 |
-
"model.visual.blocks.24.
|
| 621 |
-
"model.visual.blocks.
|
| 622 |
-
"model.visual.blocks.
|
| 623 |
-
"model.visual.blocks.25.attn.
|
| 624 |
-
"model.visual.blocks.25.attn.
|
| 625 |
-
"model.visual.blocks.25.
|
| 626 |
-
"model.visual.blocks.25.
|
| 627 |
-
"model.visual.blocks.25.mlp.
|
| 628 |
-
"model.visual.blocks.25.mlp.
|
| 629 |
-
"model.visual.blocks.25.
|
| 630 |
-
"model.visual.blocks.25.
|
| 631 |
-
"model.visual.blocks.25.
|
| 632 |
-
"model.visual.blocks.25.
|
| 633 |
-
"model.visual.blocks.
|
| 634 |
-
"model.visual.blocks.
|
| 635 |
-
"model.visual.blocks.26.attn.
|
| 636 |
-
"model.visual.blocks.26.attn.
|
| 637 |
-
"model.visual.blocks.26.
|
| 638 |
-
"model.visual.blocks.26.
|
| 639 |
-
"model.visual.blocks.26.mlp.
|
| 640 |
-
"model.visual.blocks.26.mlp.
|
| 641 |
-
"model.visual.blocks.26.
|
| 642 |
-
"model.visual.blocks.26.
|
| 643 |
-
"model.visual.blocks.26.
|
| 644 |
-
"model.visual.blocks.26.
|
| 645 |
-
"model.visual.blocks.
|
| 646 |
-
"model.visual.blocks.
|
| 647 |
-
"model.visual.blocks.3.attn.
|
| 648 |
-
"model.visual.blocks.3.attn.
|
| 649 |
-
"model.visual.blocks.3.
|
| 650 |
-
"model.visual.blocks.3.
|
| 651 |
-
"model.visual.blocks.3.mlp.
|
| 652 |
-
"model.visual.blocks.3.mlp.
|
| 653 |
-
"model.visual.blocks.3.
|
| 654 |
-
"model.visual.blocks.3.
|
| 655 |
-
"model.visual.blocks.3.
|
| 656 |
-
"model.visual.blocks.3.
|
| 657 |
-
"model.visual.blocks.
|
| 658 |
-
"model.visual.blocks.
|
| 659 |
-
"model.visual.blocks.4.attn.
|
| 660 |
-
"model.visual.blocks.4.attn.
|
| 661 |
-
"model.visual.blocks.4.
|
| 662 |
-
"model.visual.blocks.4.
|
| 663 |
-
"model.visual.blocks.4.mlp.
|
| 664 |
-
"model.visual.blocks.4.mlp.
|
| 665 |
-
"model.visual.blocks.4.
|
| 666 |
-
"model.visual.blocks.4.
|
| 667 |
-
"model.visual.blocks.4.
|
| 668 |
-
"model.visual.blocks.4.
|
| 669 |
-
"model.visual.blocks.
|
| 670 |
-
"model.visual.blocks.
|
| 671 |
-
"model.visual.blocks.5.attn.
|
| 672 |
-
"model.visual.blocks.5.attn.
|
| 673 |
-
"model.visual.blocks.5.
|
| 674 |
-
"model.visual.blocks.5.
|
| 675 |
-
"model.visual.blocks.5.mlp.
|
| 676 |
-
"model.visual.blocks.5.mlp.
|
| 677 |
-
"model.visual.blocks.5.
|
| 678 |
-
"model.visual.blocks.5.
|
| 679 |
-
"model.visual.blocks.5.
|
| 680 |
-
"model.visual.blocks.5.
|
| 681 |
-
"model.visual.blocks.
|
| 682 |
-
"model.visual.blocks.
|
| 683 |
-
"model.visual.blocks.6.attn.
|
| 684 |
-
"model.visual.blocks.6.attn.
|
| 685 |
-
"model.visual.blocks.6.
|
| 686 |
-
"model.visual.blocks.6.
|
| 687 |
-
"model.visual.blocks.6.mlp.
|
| 688 |
-
"model.visual.blocks.6.mlp.
|
| 689 |
-
"model.visual.blocks.6.
|
| 690 |
-
"model.visual.blocks.6.
|
| 691 |
-
"model.visual.blocks.6.
|
| 692 |
-
"model.visual.blocks.6.
|
| 693 |
-
"model.visual.blocks.
|
| 694 |
-
"model.visual.blocks.
|
| 695 |
-
"model.visual.blocks.7.attn.
|
| 696 |
-
"model.visual.blocks.7.attn.
|
| 697 |
-
"model.visual.blocks.7.
|
| 698 |
-
"model.visual.blocks.7.
|
| 699 |
-
"model.visual.blocks.7.mlp.
|
| 700 |
-
"model.visual.blocks.7.mlp.
|
| 701 |
-
"model.visual.blocks.7.
|
| 702 |
-
"model.visual.blocks.7.
|
| 703 |
-
"model.visual.blocks.7.
|
| 704 |
-
"model.visual.blocks.7.
|
| 705 |
-
"model.visual.blocks.
|
| 706 |
-
"model.visual.blocks.
|
| 707 |
-
"model.visual.blocks.8.attn.
|
| 708 |
-
"model.visual.blocks.8.attn.
|
| 709 |
-
"model.visual.blocks.8.
|
| 710 |
-
"model.visual.blocks.8.
|
| 711 |
-
"model.visual.blocks.8.mlp.
|
| 712 |
-
"model.visual.blocks.8.mlp.
|
| 713 |
-
"model.visual.blocks.8.
|
| 714 |
-
"model.visual.blocks.8.
|
| 715 |
-
"model.visual.blocks.8.
|
| 716 |
-
"model.visual.blocks.8.
|
| 717 |
-
"model.visual.blocks.
|
| 718 |
-
"model.visual.blocks.
|
| 719 |
-
"model.visual.blocks.9.attn.
|
| 720 |
-
"model.visual.blocks.9.attn.
|
| 721 |
-
"model.visual.blocks.9.
|
| 722 |
-
"model.visual.blocks.9.
|
| 723 |
-
"model.visual.blocks.9.mlp.
|
| 724 |
-
"model.visual.blocks.9.mlp.
|
| 725 |
-
"model.visual.blocks.9.
|
| 726 |
-
"model.visual.blocks.9.
|
| 727 |
-
"model.visual.blocks.9.
|
| 728 |
-
"model.visual.blocks.9.
|
| 729 |
-
"model.visual.
|
| 730 |
-
"model.visual.
|
| 731 |
-
"model.visual.deepstack_merger_list.0.
|
| 732 |
-
"model.visual.deepstack_merger_list.0.
|
| 733 |
-
"model.visual.deepstack_merger_list.0.
|
| 734 |
-
"model.visual.deepstack_merger_list.0.
|
| 735 |
-
"model.visual.deepstack_merger_list.
|
| 736 |
-
"model.visual.deepstack_merger_list.
|
| 737 |
-
"model.visual.deepstack_merger_list.1.
|
| 738 |
-
"model.visual.deepstack_merger_list.1.
|
| 739 |
-
"model.visual.deepstack_merger_list.1.
|
| 740 |
-
"model.visual.deepstack_merger_list.1.
|
| 741 |
-
"model.visual.deepstack_merger_list.
|
| 742 |
-
"model.visual.deepstack_merger_list.
|
| 743 |
-
"model.visual.deepstack_merger_list.2.
|
| 744 |
-
"model.visual.deepstack_merger_list.2.
|
| 745 |
-
"model.visual.deepstack_merger_list.2.
|
| 746 |
-
"model.visual.deepstack_merger_list.2.
|
| 747 |
-
"model.visual.
|
| 748 |
-
"model.visual.
|
| 749 |
-
"model.visual.merger.
|
| 750 |
-
"model.visual.merger.
|
| 751 |
-
"model.visual.merger.
|
| 752 |
-
"model.visual.merger.
|
| 753 |
-
"model.visual.
|
| 754 |
-
"model.visual.
|
| 755 |
-
"model.visual.
|
|
|
|
|
|
|
| 756 |
}
|
| 757 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_parameters": 770288,
|
| 4 |
+
"total_size": 18071293408
|
| 5 |
},
|
| 6 |
"weight_map": {
|
| 7 |
"lm_head.weight": "model-00004-of-00004.safetensors",
|
|
|
|
| 127 |
"model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 128 |
"model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 129 |
"model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 130 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 131 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 132 |
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 133 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 134 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 135 |
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 136 |
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 137 |
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 149 |
"model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 150 |
"model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 151 |
"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 152 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 153 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 154 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 155 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 156 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 157 |
+
"model.language_model.layers.20.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 158 |
+
"model.language_model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 159 |
+
"model.language_model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 160 |
+
"model.language_model.layers.20.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 161 |
+
"model.language_model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 162 |
+
"model.language_model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 163 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 164 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 165 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.language_model.layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 169 |
+
"model.language_model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 170 |
+
"model.language_model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 171 |
+
"model.language_model.layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 172 |
+
"model.language_model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 173 |
+
"model.language_model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 174 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 175 |
"model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 176 |
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
"model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.language_model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 180 |
+
"model.language_model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 181 |
+
"model.language_model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 182 |
+
"model.language_model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 183 |
+
"model.language_model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 184 |
+
"model.language_model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 185 |
"model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 186 |
"model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 292 |
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 293 |
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 294 |
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 295 |
+
"model.language_model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 296 |
+
"model.language_model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 297 |
+
"model.language_model.layers.32.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 298 |
+
"model.language_model.layers.32.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 299 |
+
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 300 |
"model.language_model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 301 |
"model.language_model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 302 |
"model.language_model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 303 |
"model.language_model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 304 |
"model.language_model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 305 |
"model.language_model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 306 |
+
"model.language_model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 307 |
+
"model.language_model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 308 |
+
"model.language_model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 309 |
+
"model.language_model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 310 |
+
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 311 |
+
"model.language_model.layers.33.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 312 |
+
"model.language_model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 313 |
+
"model.language_model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 314 |
+
"model.language_model.layers.33.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 315 |
+
"model.language_model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 316 |
+
"model.language_model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 317 |
+
"model.language_model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 318 |
+
"model.language_model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 319 |
+
"model.language_model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 320 |
+
"model.language_model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 321 |
+
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 322 |
+
"model.language_model.layers.34.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 323 |
+
"model.language_model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 324 |
+
"model.language_model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 325 |
+
"model.language_model.layers.34.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 326 |
+
"model.language_model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 327 |
+
"model.language_model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 328 |
"model.language_model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 329 |
"model.language_model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 330 |
"model.language_model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
|
|
|
| 332 |
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 333 |
"model.language_model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 334 |
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 335 |
+
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 336 |
"model.language_model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 337 |
+
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 338 |
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 339 |
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 340 |
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
|
|
|
| 358 |
"model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 359 |
"model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 360 |
"model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 361 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 362 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 363 |
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 364 |
"model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 365 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 366 |
"model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 367 |
"model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 368 |
"model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 369 |
"model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 370 |
"model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 371 |
"model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 372 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 373 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 374 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 375 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 376 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 377 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 378 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 379 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 380 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 381 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 382 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 383 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 384 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 385 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 386 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 387 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 388 |
+
"model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 389 |
+
"model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 390 |
+
"model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 391 |
+
"model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 392 |
+
"model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 393 |
+
"model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 394 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 395 |
"model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 396 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 397 |
"model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 398 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 399 |
+
"model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 400 |
+
"model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 401 |
+
"model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 402 |
+
"model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 403 |
+
"model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 404 |
+
"model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 405 |
"model.language_model.norm.weight": "model-00004-of-00004.safetensors",
|
| 406 |
+
"model.prev_uncertainty_code": "model-00001-of-00004.safetensors",
|
| 407 |
+
"model.uncertainty_embeddings.weight": "model-00004-of-00004.safetensors",
|
| 408 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 409 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 410 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 411 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 412 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 413 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 414 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 415 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 416 |
+
"model.visual.blocks.0.norm1.bias": "model-00001-of-00004.safetensors",
|
| 417 |
+
"model.visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
|
| 418 |
+
"model.visual.blocks.0.norm2.bias": "model-00001-of-00004.safetensors",
|
| 419 |
+
"model.visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
|
| 420 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 421 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 422 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 423 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 424 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 425 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 426 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 427 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 428 |
+
"model.visual.blocks.1.norm1.bias": "model-00001-of-00004.safetensors",
|
| 429 |
+
"model.visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
|
| 430 |
+
"model.visual.blocks.1.norm2.bias": "model-00001-of-00004.safetensors",
|
| 431 |
+
"model.visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
|
| 432 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 433 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 434 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 435 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 436 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 437 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 438 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 439 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 440 |
+
"model.visual.blocks.10.norm1.bias": "model-00001-of-00004.safetensors",
|
| 441 |
+
"model.visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
|
| 442 |
+
"model.visual.blocks.10.norm2.bias": "model-00001-of-00004.safetensors",
|
| 443 |
+
"model.visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
|
| 444 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 445 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 446 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 447 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 448 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 449 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 450 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 451 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 452 |
+
"model.visual.blocks.11.norm1.bias": "model-00001-of-00004.safetensors",
|
| 453 |
+
"model.visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
|
| 454 |
+
"model.visual.blocks.11.norm2.bias": "model-00001-of-00004.safetensors",
|
| 455 |
+
"model.visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
|
| 456 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 457 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 458 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 459 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 460 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 461 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 462 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 463 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 464 |
+
"model.visual.blocks.12.norm1.bias": "model-00001-of-00004.safetensors",
|
| 465 |
+
"model.visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
|
| 466 |
+
"model.visual.blocks.12.norm2.bias": "model-00001-of-00004.safetensors",
|
| 467 |
+
"model.visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
|
| 468 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 469 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 470 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 471 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 472 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 473 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 474 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 475 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 476 |
+
"model.visual.blocks.13.norm1.bias": "model-00001-of-00004.safetensors",
|
| 477 |
+
"model.visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
|
| 478 |
+
"model.visual.blocks.13.norm2.bias": "model-00001-of-00004.safetensors",
|
| 479 |
+
"model.visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
|
| 480 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 481 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 482 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 483 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 484 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 485 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 486 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 487 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 488 |
+
"model.visual.blocks.14.norm1.bias": "model-00001-of-00004.safetensors",
|
| 489 |
+
"model.visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
|
| 490 |
+
"model.visual.blocks.14.norm2.bias": "model-00001-of-00004.safetensors",
|
| 491 |
+
"model.visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
|
| 492 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 493 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 494 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 495 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 496 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 497 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 498 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 499 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 500 |
+
"model.visual.blocks.15.norm1.bias": "model-00001-of-00004.safetensors",
|
| 501 |
+
"model.visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
|
| 502 |
+
"model.visual.blocks.15.norm2.bias": "model-00001-of-00004.safetensors",
|
| 503 |
+
"model.visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
|
| 504 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 505 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 506 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 507 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 508 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 509 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 510 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 511 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 512 |
+
"model.visual.blocks.16.norm1.bias": "model-00001-of-00004.safetensors",
|
| 513 |
+
"model.visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
|
| 514 |
+
"model.visual.blocks.16.norm2.bias": "model-00001-of-00004.safetensors",
|
| 515 |
+
"model.visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
|
| 516 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 517 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 518 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 519 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 520 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 521 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 522 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 523 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 524 |
+
"model.visual.blocks.17.norm1.bias": "model-00001-of-00004.safetensors",
|
| 525 |
+
"model.visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
|
| 526 |
+
"model.visual.blocks.17.norm2.bias": "model-00001-of-00004.safetensors",
|
| 527 |
+
"model.visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
|
| 528 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 529 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 530 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 531 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 532 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 533 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 534 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 535 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 536 |
+
"model.visual.blocks.18.norm1.bias": "model-00001-of-00004.safetensors",
|
| 537 |
+
"model.visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
|
| 538 |
+
"model.visual.blocks.18.norm2.bias": "model-00001-of-00004.safetensors",
|
| 539 |
+
"model.visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
|
| 540 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 541 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 542 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 543 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 544 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 545 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 546 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 547 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 548 |
+
"model.visual.blocks.19.norm1.bias": "model-00001-of-00004.safetensors",
|
| 549 |
+
"model.visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
|
| 550 |
+
"model.visual.blocks.19.norm2.bias": "model-00001-of-00004.safetensors",
|
| 551 |
+
"model.visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
|
| 552 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 553 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 554 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 555 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 556 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 557 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 558 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 559 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 560 |
+
"model.visual.blocks.2.norm1.bias": "model-00001-of-00004.safetensors",
|
| 561 |
+
"model.visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
|
| 562 |
+
"model.visual.blocks.2.norm2.bias": "model-00001-of-00004.safetensors",
|
| 563 |
+
"model.visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
|
| 564 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 565 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 566 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 567 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 568 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 569 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 570 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 571 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 572 |
+
"model.visual.blocks.20.norm1.bias": "model-00001-of-00004.safetensors",
|
| 573 |
+
"model.visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
|
| 574 |
+
"model.visual.blocks.20.norm2.bias": "model-00001-of-00004.safetensors",
|
| 575 |
+
"model.visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
|
| 576 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 577 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 578 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 579 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 580 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 581 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 582 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 583 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 584 |
+
"model.visual.blocks.21.norm1.bias": "model-00001-of-00004.safetensors",
|
| 585 |
+
"model.visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
|
| 586 |
+
"model.visual.blocks.21.norm2.bias": "model-00001-of-00004.safetensors",
|
| 587 |
+
"model.visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
|
| 588 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 589 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 590 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 591 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 592 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 593 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 594 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 595 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 596 |
+
"model.visual.blocks.22.norm1.bias": "model-00001-of-00004.safetensors",
|
| 597 |
+
"model.visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
|
| 598 |
+
"model.visual.blocks.22.norm2.bias": "model-00001-of-00004.safetensors",
|
| 599 |
+
"model.visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
|
| 600 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 601 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 602 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 603 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 604 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 605 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 606 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 607 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 608 |
+
"model.visual.blocks.23.norm1.bias": "model-00001-of-00004.safetensors",
|
| 609 |
+
"model.visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
|
| 610 |
+
"model.visual.blocks.23.norm2.bias": "model-00001-of-00004.safetensors",
|
| 611 |
+
"model.visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
|
| 612 |
+
"model.visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 613 |
+
"model.visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 614 |
+
"model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 615 |
+
"model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 616 |
+
"model.visual.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 617 |
+
"model.visual.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 618 |
+
"model.visual.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 619 |
+
"model.visual.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 620 |
+
"model.visual.blocks.24.norm1.bias": "model-00001-of-00004.safetensors",
|
| 621 |
+
"model.visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
|
| 622 |
+
"model.visual.blocks.24.norm2.bias": "model-00001-of-00004.safetensors",
|
| 623 |
+
"model.visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
|
| 624 |
+
"model.visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 625 |
+
"model.visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 626 |
+
"model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 627 |
+
"model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 628 |
+
"model.visual.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 629 |
+
"model.visual.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 630 |
+
"model.visual.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 631 |
+
"model.visual.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 632 |
+
"model.visual.blocks.25.norm1.bias": "model-00001-of-00004.safetensors",
|
| 633 |
+
"model.visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
|
| 634 |
+
"model.visual.blocks.25.norm2.bias": "model-00001-of-00004.safetensors",
|
| 635 |
+
"model.visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
|
| 636 |
+
"model.visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 637 |
+
"model.visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 638 |
+
"model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 639 |
+
"model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 640 |
+
"model.visual.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 641 |
+
"model.visual.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 642 |
+
"model.visual.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 643 |
+
"model.visual.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 644 |
+
"model.visual.blocks.26.norm1.bias": "model-00001-of-00004.safetensors",
|
| 645 |
+
"model.visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
|
| 646 |
+
"model.visual.blocks.26.norm2.bias": "model-00001-of-00004.safetensors",
|
| 647 |
+
"model.visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
|
| 648 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 649 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 650 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 651 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 652 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 653 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 654 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 655 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 656 |
+
"model.visual.blocks.3.norm1.bias": "model-00001-of-00004.safetensors",
|
| 657 |
+
"model.visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
|
| 658 |
+
"model.visual.blocks.3.norm2.bias": "model-00001-of-00004.safetensors",
|
| 659 |
+
"model.visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
|
| 660 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 661 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 662 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 663 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 664 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 665 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 666 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 667 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 668 |
+
"model.visual.blocks.4.norm1.bias": "model-00001-of-00004.safetensors",
|
| 669 |
+
"model.visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
|
| 670 |
+
"model.visual.blocks.4.norm2.bias": "model-00001-of-00004.safetensors",
|
| 671 |
+
"model.visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
|
| 672 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 673 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 674 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 675 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 676 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 677 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 678 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 679 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 680 |
+
"model.visual.blocks.5.norm1.bias": "model-00001-of-00004.safetensors",
|
| 681 |
+
"model.visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
|
| 682 |
+
"model.visual.blocks.5.norm2.bias": "model-00001-of-00004.safetensors",
|
| 683 |
+
"model.visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
|
| 684 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 685 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 686 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 687 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 688 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 689 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 690 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 691 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 692 |
+
"model.visual.blocks.6.norm1.bias": "model-00001-of-00004.safetensors",
|
| 693 |
+
"model.visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
|
| 694 |
+
"model.visual.blocks.6.norm2.bias": "model-00001-of-00004.safetensors",
|
| 695 |
+
"model.visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
|
| 696 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 697 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 698 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 699 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 700 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 701 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 702 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 703 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 704 |
+
"model.visual.blocks.7.norm1.bias": "model-00001-of-00004.safetensors",
|
| 705 |
+
"model.visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
|
| 706 |
+
"model.visual.blocks.7.norm2.bias": "model-00001-of-00004.safetensors",
|
| 707 |
+
"model.visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
|
| 708 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 709 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 710 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 711 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 712 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 713 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 714 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 715 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 716 |
+
"model.visual.blocks.8.norm1.bias": "model-00001-of-00004.safetensors",
|
| 717 |
+
"model.visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
|
| 718 |
+
"model.visual.blocks.8.norm2.bias": "model-00001-of-00004.safetensors",
|
| 719 |
+
"model.visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
|
| 720 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 721 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 722 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 723 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 724 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 725 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 726 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 727 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 728 |
+
"model.visual.blocks.9.norm1.bias": "model-00001-of-00004.safetensors",
|
| 729 |
+
"model.visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
|
| 730 |
+
"model.visual.blocks.9.norm2.bias": "model-00001-of-00004.safetensors",
|
| 731 |
+
"model.visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
|
| 732 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 733 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 734 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 735 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 736 |
+
"model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00004.safetensors",
|
| 737 |
+
"model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00004.safetensors",
|
| 738 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 739 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 740 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 741 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 742 |
+
"model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00004.safetensors",
|
| 743 |
+
"model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00004.safetensors",
|
| 744 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 745 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 746 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 747 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 748 |
+
"model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00004.safetensors",
|
| 749 |
+
"model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00004.safetensors",
|
| 750 |
+
"model.visual.merger.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 751 |
+
"model.visual.merger.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 752 |
+
"model.visual.merger.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 753 |
+
"model.visual.merger.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 754 |
+
"model.visual.merger.norm.bias": "model-00001-of-00004.safetensors",
|
| 755 |
+
"model.visual.merger.norm.weight": "model-00001-of-00004.safetensors",
|
| 756 |
+
"model.visual.patch_embed.proj.bias": "model-00001-of-00004.safetensors",
|
| 757 |
+
"model.visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors",
|
| 758 |
+
"model.visual.pos_embed.weight": "model-00001-of-00004.safetensors"
|
| 759 |
}
|
| 760 |
}
|