Publish translategemma-4b-1b-enes-q4k-ehf16-af32 RDRR artifact
Browse files- models/translategemma-4b-1b-enes-q4k-ehf16-af32/manifest.json +676 -218
- models/translategemma-4b-1b-enes-q4k-ehf16-af32/origin.json +6 -6
- models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00000.bin +1 -1
- models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00001.bin +1 -1
- models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00002.bin +1 -1
- models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00003.bin +1 -1
- models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00004.bin +1 -1
- models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00005.bin +1 -1
- models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00006.bin +1 -1
- models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00007.bin +1 -1
- models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00008.bin +1 -1
- models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00009.bin +1 -1
- models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00010.bin +1 -1
- models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00011.bin +1 -1
- models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00012.bin +1 -1
- models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00013.bin +1 -1
- models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00014.bin +1 -1
- models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00015.bin +1 -1
- models/translategemma-4b-1b-enes-q4k-ehf16-af32/tokenizer.json +2 -2
models/translategemma-4b-1b-enes-q4k-ehf16-af32/manifest.json
CHANGED
|
@@ -10,6 +10,21 @@
|
|
| 10 |
"layout": "row",
|
| 11 |
"variantTag": "q4k-ehf16-af32"
|
| 12 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
"architecture": {
|
| 14 |
"numLayers": 26,
|
| 15 |
"hiddenSize": 1152,
|
|
@@ -19,7 +34,16 @@
|
|
| 19 |
"headDim": 256,
|
| 20 |
"vocabSize": 262144,
|
| 21 |
"maxSeqLen": 32768,
|
| 22 |
-
"ropeTheta": 1000000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
},
|
| 24 |
"moeConfig": null,
|
| 25 |
"inference": {
|
|
@@ -27,11 +51,12 @@
|
|
| 27 |
"attention": {
|
| 28 |
"queryPreAttnScalar": 256,
|
| 29 |
"attnLogitSoftcapping": null,
|
| 30 |
-
"slidingWindow":
|
| 31 |
"queryKeyNorm": true,
|
| 32 |
"causal": true,
|
| 33 |
"attentionBias": false,
|
| 34 |
-
"attentionOutputGate": false
|
|
|
|
| 35 |
},
|
| 36 |
"normalization": {
|
| 37 |
"rmsNormEps": 0.000001,
|
|
@@ -43,11 +68,13 @@
|
|
| 43 |
"ffn": {
|
| 44 |
"activation": "gelu",
|
| 45 |
"gatedActivation": true,
|
| 46 |
-
"
|
|
|
|
|
|
|
| 47 |
},
|
| 48 |
"rope": {
|
| 49 |
"ropeTheta": 1000000,
|
| 50 |
-
"ropeLocalTheta":
|
| 51 |
"mropeInterleaved": false,
|
| 52 |
"mropeSection": null,
|
| 53 |
"partialRotaryFactor": null,
|
|
@@ -60,7 +87,13 @@
|
|
| 60 |
"yarnOriginalMaxPos": null,
|
| 61 |
"ropeLocalYarnBetaFast": null,
|
| 62 |
"ropeLocalYarnBetaSlow": null,
|
| 63 |
-
"ropeLocalYarnOriginalMaxPos": null
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
},
|
| 65 |
"output": {
|
| 66 |
"finalLogitSoftcapping": null,
|
|
@@ -68,21 +101,30 @@
|
|
| 68 |
"scaleEmbeddings": true,
|
| 69 |
"embeddingTranspose": false,
|
| 70 |
"embeddingVocabSize": null,
|
| 71 |
-
"embeddingPostprocessor": null
|
|
|
|
|
|
|
| 72 |
},
|
| 73 |
"layerPattern": {
|
| 74 |
-
"type": "
|
| 75 |
"globalPattern": null,
|
| 76 |
-
"period":
|
| 77 |
-
"offset":
|
| 78 |
-
"layerTypes": null
|
|
|
|
| 79 |
},
|
| 80 |
"chatTemplate": {
|
| 81 |
-
"type": "
|
| 82 |
"enabled": true
|
| 83 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 84 |
"pipeline": null,
|
| 85 |
-
"
|
| 86 |
"compute": {
|
| 87 |
"defaults": {
|
| 88 |
"activationDtype": "f32",
|
|
@@ -92,46 +134,108 @@
|
|
| 92 |
}
|
| 93 |
},
|
| 94 |
"kvcache": {
|
| 95 |
-
"kvDtype": "f16"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 96 |
},
|
| 97 |
-
"
|
|
|
|
|
|
|
|
|
|
| 98 |
},
|
| 99 |
"execution": {
|
| 100 |
"kernels": {
|
| 101 |
"embed": {
|
| 102 |
"kernel": "gather_f16.wgsl",
|
| 103 |
"entry": "main",
|
| 104 |
-
"digest": "sha256:
|
| 105 |
},
|
| 106 |
"rmsnorm": {
|
| 107 |
"kernel": "rmsnorm.wgsl",
|
| 108 |
"entry": "main",
|
| 109 |
-
"digest": "sha256:
|
| 110 |
},
|
| 111 |
"gemv": {
|
| 112 |
"kernel": "matmul_gemv_subgroup.wgsl",
|
| 113 |
"entry": "main_vec4",
|
| 114 |
-
"digest": "sha256:
|
| 115 |
},
|
| 116 |
"rope": {
|
| 117 |
"kernel": "rope.wgsl",
|
| 118 |
"entry": "main",
|
| 119 |
-
"digest": "sha256:
|
| 120 |
},
|
| 121 |
"attn_decode": {
|
| 122 |
"kernel": "attention_decode_online_f16kv.wgsl",
|
| 123 |
"entry": "main",
|
| 124 |
-
"digest": "sha256:
|
|
|
|
|
|
|
|
|
|
| 125 |
},
|
| 126 |
"residual": {
|
| 127 |
"kernel": "residual.wgsl",
|
| 128 |
"entry": "main",
|
| 129 |
-
"digest": "sha256:
|
| 130 |
},
|
| 131 |
"gelu": {
|
| 132 |
"kernel": "gelu.wgsl",
|
| 133 |
"entry": "main",
|
| 134 |
-
"digest": "sha256:
|
| 135 |
"constants": {
|
| 136 |
"HAS_GATE": true
|
| 137 |
}
|
|
@@ -144,12 +248,15 @@
|
|
| 144 |
"attn_stream": {
|
| 145 |
"kernel": "attention_streaming_f16kv.wgsl",
|
| 146 |
"entry": "main",
|
| 147 |
-
"digest": "sha256:
|
|
|
|
|
|
|
|
|
|
| 148 |
},
|
| 149 |
"lm_head_gemv": {
|
| 150 |
"kernel": "matmul_gemv_subgroup.wgsl",
|
| 151 |
"entry": "main_multicol",
|
| 152 |
-
"digest": "sha256:
|
| 153 |
"constants": {
|
| 154 |
"MULTICOL_COLS_PER_WG": 64,
|
| 155 |
"MULTICOL_THREADS_PER_COL": 4
|
|
@@ -158,7 +265,7 @@
|
|
| 158 |
"sample": {
|
| 159 |
"kernel": "sample.wgsl",
|
| 160 |
"entry": "sample_single_pass",
|
| 161 |
-
"digest": "sha256:
|
| 162 |
}
|
| 163 |
},
|
| 164 |
"preLayer": [
|
|
@@ -338,128 +445,128 @@
|
|
| 338 |
"index": 0,
|
| 339 |
"filename": "shard_00000.bin",
|
| 340 |
"size": 67108864,
|
| 341 |
-
"hash": "
|
| 342 |
-
"blake3": "
|
| 343 |
"offset": 0
|
| 344 |
},
|
| 345 |
{
|
| 346 |
"index": 1,
|
| 347 |
"filename": "shard_00001.bin",
|
| 348 |
"size": 67108864,
|
| 349 |
-
"hash": "
|
| 350 |
-
"blake3": "
|
| 351 |
"offset": 67108864
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"index": 2,
|
| 355 |
"filename": "shard_00002.bin",
|
| 356 |
"size": 67108864,
|
| 357 |
-
"hash": "
|
| 358 |
-
"blake3": "
|
| 359 |
"offset": 134217728
|
| 360 |
},
|
| 361 |
{
|
| 362 |
"index": 3,
|
| 363 |
"filename": "shard_00003.bin",
|
| 364 |
"size": 67108864,
|
| 365 |
-
"hash": "
|
| 366 |
-
"blake3": "
|
| 367 |
"offset": 201326592
|
| 368 |
},
|
| 369 |
{
|
| 370 |
"index": 4,
|
| 371 |
"filename": "shard_00004.bin",
|
| 372 |
"size": 67108864,
|
| 373 |
-
"hash": "
|
| 374 |
-
"blake3": "
|
| 375 |
"offset": 268435456
|
| 376 |
},
|
| 377 |
{
|
| 378 |
"index": 5,
|
| 379 |
"filename": "shard_00005.bin",
|
| 380 |
"size": 67108864,
|
| 381 |
-
"hash": "
|
| 382 |
-
"blake3": "
|
| 383 |
"offset": 335544320
|
| 384 |
},
|
| 385 |
{
|
| 386 |
"index": 6,
|
| 387 |
"filename": "shard_00006.bin",
|
| 388 |
"size": 67108864,
|
| 389 |
-
"hash": "
|
| 390 |
-
"blake3": "
|
| 391 |
"offset": 402653184
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"index": 7,
|
| 395 |
"filename": "shard_00007.bin",
|
| 396 |
"size": 67108864,
|
| 397 |
-
"hash": "
|
| 398 |
-
"blake3": "
|
| 399 |
"offset": 469762048
|
| 400 |
},
|
| 401 |
{
|
| 402 |
"index": 8,
|
| 403 |
"filename": "shard_00008.bin",
|
| 404 |
"size": 67108864,
|
| 405 |
-
"hash": "
|
| 406 |
-
"blake3": "
|
| 407 |
"offset": 536870912
|
| 408 |
},
|
| 409 |
{
|
| 410 |
"index": 9,
|
| 411 |
"filename": "shard_00009.bin",
|
| 412 |
"size": 67108864,
|
| 413 |
-
"hash": "
|
| 414 |
-
"blake3": "
|
| 415 |
"offset": 603979776
|
| 416 |
},
|
| 417 |
{
|
| 418 |
"index": 10,
|
| 419 |
"filename": "shard_00010.bin",
|
| 420 |
"size": 67108864,
|
| 421 |
-
"hash": "
|
| 422 |
-
"blake3": "
|
| 423 |
"offset": 671088640
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"index": 11,
|
| 427 |
"filename": "shard_00011.bin",
|
| 428 |
"size": 67108864,
|
| 429 |
-
"hash": "
|
| 430 |
-
"blake3": "
|
| 431 |
"offset": 738197504
|
| 432 |
},
|
| 433 |
{
|
| 434 |
"index": 12,
|
| 435 |
"filename": "shard_00012.bin",
|
| 436 |
"size": 67108864,
|
| 437 |
-
"hash": "
|
| 438 |
-
"blake3": "
|
| 439 |
"offset": 805306368
|
| 440 |
},
|
| 441 |
{
|
| 442 |
"index": 13,
|
| 443 |
"filename": "shard_00013.bin",
|
| 444 |
"size": 67108864,
|
| 445 |
-
"hash": "
|
| 446 |
-
"blake3": "
|
| 447 |
"offset": 872415232
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"index": 14,
|
| 451 |
"filename": "shard_00014.bin",
|
| 452 |
"size": 67108864,
|
| 453 |
-
"hash": "
|
| 454 |
-
"blake3": "
|
| 455 |
"offset": 939524096
|
| 456 |
},
|
| 457 |
{
|
| 458 |
"index": 15,
|
| 459 |
"filename": "shard_00015.bin",
|
| 460 |
"size": 18860288,
|
| 461 |
-
"hash": "
|
| 462 |
-
"blake3": "
|
| 463 |
"offset": 1006632960
|
| 464 |
}
|
| 465 |
],
|
|
@@ -528,7 +635,7 @@
|
|
| 528 |
"shape": [
|
| 529 |
1152
|
| 530 |
],
|
| 531 |
-
"dtype": "
|
| 532 |
"role": "norm",
|
| 533 |
"group": "layer.0"
|
| 534 |
},
|
|
@@ -578,7 +685,7 @@
|
|
| 578 |
"shape": [
|
| 579 |
1152
|
| 580 |
],
|
| 581 |
-
"dtype": "
|
| 582 |
"role": "norm",
|
| 583 |
"group": "layer.0"
|
| 584 |
},
|
|
@@ -589,7 +696,7 @@
|
|
| 589 |
"shape": [
|
| 590 |
1152
|
| 591 |
],
|
| 592 |
-
"dtype": "
|
| 593 |
"role": "norm",
|
| 594 |
"group": "layer.0"
|
| 595 |
},
|
|
@@ -600,7 +707,7 @@
|
|
| 600 |
"shape": [
|
| 601 |
1152
|
| 602 |
],
|
| 603 |
-
"dtype": "
|
| 604 |
"role": "norm",
|
| 605 |
"group": "layer.0"
|
| 606 |
},
|
|
@@ -611,7 +718,7 @@
|
|
| 611 |
"shape": [
|
| 612 |
256
|
| 613 |
],
|
| 614 |
-
"dtype": "
|
| 615 |
"role": "norm",
|
| 616 |
"group": "layer.0"
|
| 617 |
},
|
|
@@ -648,7 +755,7 @@
|
|
| 648 |
"shape": [
|
| 649 |
256
|
| 650 |
],
|
| 651 |
-
"dtype": "
|
| 652 |
"role": "norm",
|
| 653 |
"group": "layer.0"
|
| 654 |
},
|
|
@@ -685,7 +792,7 @@
|
|
| 685 |
"shape": [
|
| 686 |
1152
|
| 687 |
],
|
| 688 |
-
"dtype": "
|
| 689 |
"role": "norm",
|
| 690 |
"group": "layer.1"
|
| 691 |
},
|
|
@@ -735,7 +842,7 @@
|
|
| 735 |
"shape": [
|
| 736 |
1152
|
| 737 |
],
|
| 738 |
-
"dtype": "
|
| 739 |
"role": "norm",
|
| 740 |
"group": "layer.1"
|
| 741 |
},
|
|
@@ -746,7 +853,7 @@
|
|
| 746 |
"shape": [
|
| 747 |
1152
|
| 748 |
],
|
| 749 |
-
"dtype": "
|
| 750 |
"role": "norm",
|
| 751 |
"group": "layer.1"
|
| 752 |
},
|
|
@@ -757,7 +864,7 @@
|
|
| 757 |
"shape": [
|
| 758 |
1152
|
| 759 |
],
|
| 760 |
-
"dtype": "
|
| 761 |
"role": "norm",
|
| 762 |
"group": "layer.1"
|
| 763 |
},
|
|
@@ -768,7 +875,7 @@
|
|
| 768 |
"shape": [
|
| 769 |
256
|
| 770 |
],
|
| 771 |
-
"dtype": "
|
| 772 |
"role": "norm",
|
| 773 |
"group": "layer.1"
|
| 774 |
},
|
|
@@ -805,7 +912,7 @@
|
|
| 805 |
"shape": [
|
| 806 |
256
|
| 807 |
],
|
| 808 |
-
"dtype": "
|
| 809 |
"role": "norm",
|
| 810 |
"group": "layer.1"
|
| 811 |
},
|
|
@@ -842,7 +949,7 @@
|
|
| 842 |
"shape": [
|
| 843 |
1152
|
| 844 |
],
|
| 845 |
-
"dtype": "
|
| 846 |
"role": "norm",
|
| 847 |
"group": "layer.10"
|
| 848 |
},
|
|
@@ -892,7 +999,7 @@
|
|
| 892 |
"shape": [
|
| 893 |
1152
|
| 894 |
],
|
| 895 |
-
"dtype": "
|
| 896 |
"role": "norm",
|
| 897 |
"group": "layer.10"
|
| 898 |
},
|
|
@@ -903,7 +1010,7 @@
|
|
| 903 |
"shape": [
|
| 904 |
1152
|
| 905 |
],
|
| 906 |
-
"dtype": "
|
| 907 |
"role": "norm",
|
| 908 |
"group": "layer.10"
|
| 909 |
},
|
|
@@ -914,7 +1021,7 @@
|
|
| 914 |
"shape": [
|
| 915 |
1152
|
| 916 |
],
|
| 917 |
-
"dtype": "
|
| 918 |
"role": "norm",
|
| 919 |
"group": "layer.10"
|
| 920 |
},
|
|
@@ -925,7 +1032,7 @@
|
|
| 925 |
"shape": [
|
| 926 |
256
|
| 927 |
],
|
| 928 |
-
"dtype": "
|
| 929 |
"role": "norm",
|
| 930 |
"group": "layer.10"
|
| 931 |
},
|
|
@@ -962,7 +1069,7 @@
|
|
| 962 |
"shape": [
|
| 963 |
256
|
| 964 |
],
|
| 965 |
-
"dtype": "
|
| 966 |
"role": "norm",
|
| 967 |
"group": "layer.10"
|
| 968 |
},
|
|
@@ -999,7 +1106,7 @@
|
|
| 999 |
"shape": [
|
| 1000 |
1152
|
| 1001 |
],
|
| 1002 |
-
"dtype": "
|
| 1003 |
"role": "norm",
|
| 1004 |
"group": "layer.11"
|
| 1005 |
},
|
|
@@ -1049,7 +1156,7 @@
|
|
| 1049 |
"shape": [
|
| 1050 |
1152
|
| 1051 |
],
|
| 1052 |
-
"dtype": "
|
| 1053 |
"role": "norm",
|
| 1054 |
"group": "layer.11"
|
| 1055 |
},
|
|
@@ -1060,7 +1167,7 @@
|
|
| 1060 |
"shape": [
|
| 1061 |
1152
|
| 1062 |
],
|
| 1063 |
-
"dtype": "
|
| 1064 |
"role": "norm",
|
| 1065 |
"group": "layer.11"
|
| 1066 |
},
|
|
@@ -1071,7 +1178,7 @@
|
|
| 1071 |
"shape": [
|
| 1072 |
1152
|
| 1073 |
],
|
| 1074 |
-
"dtype": "
|
| 1075 |
"role": "norm",
|
| 1076 |
"group": "layer.11"
|
| 1077 |
},
|
|
@@ -1082,7 +1189,7 @@
|
|
| 1082 |
"shape": [
|
| 1083 |
256
|
| 1084 |
],
|
| 1085 |
-
"dtype": "
|
| 1086 |
"role": "norm",
|
| 1087 |
"group": "layer.11"
|
| 1088 |
},
|
|
@@ -1119,7 +1226,7 @@
|
|
| 1119 |
"shape": [
|
| 1120 |
256
|
| 1121 |
],
|
| 1122 |
-
"dtype": "
|
| 1123 |
"role": "norm",
|
| 1124 |
"group": "layer.11"
|
| 1125 |
},
|
|
@@ -1156,7 +1263,7 @@
|
|
| 1156 |
"shape": [
|
| 1157 |
1152
|
| 1158 |
],
|
| 1159 |
-
"dtype": "
|
| 1160 |
"role": "norm",
|
| 1161 |
"group": "layer.12"
|
| 1162 |
},
|
|
@@ -1216,7 +1323,7 @@
|
|
| 1216 |
"shape": [
|
| 1217 |
1152
|
| 1218 |
],
|
| 1219 |
-
"dtype": "
|
| 1220 |
"role": "norm",
|
| 1221 |
"group": "layer.12"
|
| 1222 |
},
|
|
@@ -1227,7 +1334,7 @@
|
|
| 1227 |
"shape": [
|
| 1228 |
1152
|
| 1229 |
],
|
| 1230 |
-
"dtype": "
|
| 1231 |
"role": "norm",
|
| 1232 |
"group": "layer.12"
|
| 1233 |
},
|
|
@@ -1238,7 +1345,7 @@
|
|
| 1238 |
"shape": [
|
| 1239 |
1152
|
| 1240 |
],
|
| 1241 |
-
"dtype": "
|
| 1242 |
"role": "norm",
|
| 1243 |
"group": "layer.12"
|
| 1244 |
},
|
|
@@ -1249,7 +1356,7 @@
|
|
| 1249 |
"shape": [
|
| 1250 |
256
|
| 1251 |
],
|
| 1252 |
-
"dtype": "
|
| 1253 |
"role": "norm",
|
| 1254 |
"group": "layer.12"
|
| 1255 |
},
|
|
@@ -1286,7 +1393,7 @@
|
|
| 1286 |
"shape": [
|
| 1287 |
256
|
| 1288 |
],
|
| 1289 |
-
"dtype": "
|
| 1290 |
"role": "norm",
|
| 1291 |
"group": "layer.12"
|
| 1292 |
},
|
|
@@ -1323,7 +1430,7 @@
|
|
| 1323 |
"shape": [
|
| 1324 |
1152
|
| 1325 |
],
|
| 1326 |
-
"dtype": "
|
| 1327 |
"role": "norm",
|
| 1328 |
"group": "layer.13"
|
| 1329 |
},
|
|
@@ -1373,7 +1480,7 @@
|
|
| 1373 |
"shape": [
|
| 1374 |
1152
|
| 1375 |
],
|
| 1376 |
-
"dtype": "
|
| 1377 |
"role": "norm",
|
| 1378 |
"group": "layer.13"
|
| 1379 |
},
|
|
@@ -1384,7 +1491,7 @@
|
|
| 1384 |
"shape": [
|
| 1385 |
1152
|
| 1386 |
],
|
| 1387 |
-
"dtype": "
|
| 1388 |
"role": "norm",
|
| 1389 |
"group": "layer.13"
|
| 1390 |
},
|
|
@@ -1395,7 +1502,7 @@
|
|
| 1395 |
"shape": [
|
| 1396 |
1152
|
| 1397 |
],
|
| 1398 |
-
"dtype": "
|
| 1399 |
"role": "norm",
|
| 1400 |
"group": "layer.13"
|
| 1401 |
},
|
|
@@ -1406,7 +1513,7 @@
|
|
| 1406 |
"shape": [
|
| 1407 |
256
|
| 1408 |
],
|
| 1409 |
-
"dtype": "
|
| 1410 |
"role": "norm",
|
| 1411 |
"group": "layer.13"
|
| 1412 |
},
|
|
@@ -1443,7 +1550,7 @@
|
|
| 1443 |
"shape": [
|
| 1444 |
256
|
| 1445 |
],
|
| 1446 |
-
"dtype": "
|
| 1447 |
"role": "norm",
|
| 1448 |
"group": "layer.13"
|
| 1449 |
},
|
|
@@ -1480,7 +1587,7 @@
|
|
| 1480 |
"shape": [
|
| 1481 |
1152
|
| 1482 |
],
|
| 1483 |
-
"dtype": "
|
| 1484 |
"role": "norm",
|
| 1485 |
"group": "layer.14"
|
| 1486 |
},
|
|
@@ -1530,7 +1637,7 @@
|
|
| 1530 |
"shape": [
|
| 1531 |
1152
|
| 1532 |
],
|
| 1533 |
-
"dtype": "
|
| 1534 |
"role": "norm",
|
| 1535 |
"group": "layer.14"
|
| 1536 |
},
|
|
@@ -1541,7 +1648,7 @@
|
|
| 1541 |
"shape": [
|
| 1542 |
1152
|
| 1543 |
],
|
| 1544 |
-
"dtype": "
|
| 1545 |
"role": "norm",
|
| 1546 |
"group": "layer.14"
|
| 1547 |
},
|
|
@@ -1552,7 +1659,7 @@
|
|
| 1552 |
"shape": [
|
| 1553 |
1152
|
| 1554 |
],
|
| 1555 |
-
"dtype": "
|
| 1556 |
"role": "norm",
|
| 1557 |
"group": "layer.14"
|
| 1558 |
},
|
|
@@ -1563,7 +1670,7 @@
|
|
| 1563 |
"shape": [
|
| 1564 |
256
|
| 1565 |
],
|
| 1566 |
-
"dtype": "
|
| 1567 |
"role": "norm",
|
| 1568 |
"group": "layer.14"
|
| 1569 |
},
|
|
@@ -1600,7 +1707,7 @@
|
|
| 1600 |
"shape": [
|
| 1601 |
256
|
| 1602 |
],
|
| 1603 |
-
"dtype": "
|
| 1604 |
"role": "norm",
|
| 1605 |
"group": "layer.14"
|
| 1606 |
},
|
|
@@ -1637,7 +1744,7 @@
|
|
| 1637 |
"shape": [
|
| 1638 |
1152
|
| 1639 |
],
|
| 1640 |
-
"dtype": "
|
| 1641 |
"role": "norm",
|
| 1642 |
"group": "layer.15"
|
| 1643 |
},
|
|
@@ -1687,7 +1794,7 @@
|
|
| 1687 |
"shape": [
|
| 1688 |
1152
|
| 1689 |
],
|
| 1690 |
-
"dtype": "
|
| 1691 |
"role": "norm",
|
| 1692 |
"group": "layer.15"
|
| 1693 |
},
|
|
@@ -1698,7 +1805,7 @@
|
|
| 1698 |
"shape": [
|
| 1699 |
1152
|
| 1700 |
],
|
| 1701 |
-
"dtype": "
|
| 1702 |
"role": "norm",
|
| 1703 |
"group": "layer.15"
|
| 1704 |
},
|
|
@@ -1709,7 +1816,7 @@
|
|
| 1709 |
"shape": [
|
| 1710 |
1152
|
| 1711 |
],
|
| 1712 |
-
"dtype": "
|
| 1713 |
"role": "norm",
|
| 1714 |
"group": "layer.15"
|
| 1715 |
},
|
|
@@ -1720,7 +1827,7 @@
|
|
| 1720 |
"shape": [
|
| 1721 |
256
|
| 1722 |
],
|
| 1723 |
-
"dtype": "
|
| 1724 |
"role": "norm",
|
| 1725 |
"group": "layer.15"
|
| 1726 |
},
|
|
@@ -1757,7 +1864,7 @@
|
|
| 1757 |
"shape": [
|
| 1758 |
256
|
| 1759 |
],
|
| 1760 |
-
"dtype": "
|
| 1761 |
"role": "norm",
|
| 1762 |
"group": "layer.15"
|
| 1763 |
},
|
|
@@ -1794,7 +1901,7 @@
|
|
| 1794 |
"shape": [
|
| 1795 |
1152
|
| 1796 |
],
|
| 1797 |
-
"dtype": "
|
| 1798 |
"role": "norm",
|
| 1799 |
"group": "layer.16"
|
| 1800 |
},
|
|
@@ -1854,7 +1961,7 @@
|
|
| 1854 |
"shape": [
|
| 1855 |
1152
|
| 1856 |
],
|
| 1857 |
-
"dtype": "
|
| 1858 |
"role": "norm",
|
| 1859 |
"group": "layer.16"
|
| 1860 |
},
|
|
@@ -1865,7 +1972,7 @@
|
|
| 1865 |
"shape": [
|
| 1866 |
1152
|
| 1867 |
],
|
| 1868 |
-
"dtype": "
|
| 1869 |
"role": "norm",
|
| 1870 |
"group": "layer.16"
|
| 1871 |
},
|
|
@@ -1876,7 +1983,7 @@
|
|
| 1876 |
"shape": [
|
| 1877 |
1152
|
| 1878 |
],
|
| 1879 |
-
"dtype": "
|
| 1880 |
"role": "norm",
|
| 1881 |
"group": "layer.16"
|
| 1882 |
},
|
|
@@ -1887,7 +1994,7 @@
|
|
| 1887 |
"shape": [
|
| 1888 |
256
|
| 1889 |
],
|
| 1890 |
-
"dtype": "
|
| 1891 |
"role": "norm",
|
| 1892 |
"group": "layer.16"
|
| 1893 |
},
|
|
@@ -1924,7 +2031,7 @@
|
|
| 1924 |
"shape": [
|
| 1925 |
256
|
| 1926 |
],
|
| 1927 |
-
"dtype": "
|
| 1928 |
"role": "norm",
|
| 1929 |
"group": "layer.16"
|
| 1930 |
},
|
|
@@ -1961,7 +2068,7 @@
|
|
| 1961 |
"shape": [
|
| 1962 |
1152
|
| 1963 |
],
|
| 1964 |
-
"dtype": "
|
| 1965 |
"role": "norm",
|
| 1966 |
"group": "layer.17"
|
| 1967 |
},
|
|
@@ -2011,7 +2118,7 @@
|
|
| 2011 |
"shape": [
|
| 2012 |
1152
|
| 2013 |
],
|
| 2014 |
-
"dtype": "
|
| 2015 |
"role": "norm",
|
| 2016 |
"group": "layer.17"
|
| 2017 |
},
|
|
@@ -2022,7 +2129,7 @@
|
|
| 2022 |
"shape": [
|
| 2023 |
1152
|
| 2024 |
],
|
| 2025 |
-
"dtype": "
|
| 2026 |
"role": "norm",
|
| 2027 |
"group": "layer.17"
|
| 2028 |
},
|
|
@@ -2033,7 +2140,7 @@
|
|
| 2033 |
"shape": [
|
| 2034 |
1152
|
| 2035 |
],
|
| 2036 |
-
"dtype": "
|
| 2037 |
"role": "norm",
|
| 2038 |
"group": "layer.17"
|
| 2039 |
},
|
|
@@ -2044,7 +2151,7 @@
|
|
| 2044 |
"shape": [
|
| 2045 |
256
|
| 2046 |
],
|
| 2047 |
-
"dtype": "
|
| 2048 |
"role": "norm",
|
| 2049 |
"group": "layer.17"
|
| 2050 |
},
|
|
@@ -2081,7 +2188,7 @@
|
|
| 2081 |
"shape": [
|
| 2082 |
256
|
| 2083 |
],
|
| 2084 |
-
"dtype": "
|
| 2085 |
"role": "norm",
|
| 2086 |
"group": "layer.17"
|
| 2087 |
},
|
|
@@ -2118,7 +2225,7 @@
|
|
| 2118 |
"shape": [
|
| 2119 |
1152
|
| 2120 |
],
|
| 2121 |
-
"dtype": "
|
| 2122 |
"role": "norm",
|
| 2123 |
"group": "layer.18"
|
| 2124 |
},
|
|
@@ -2168,7 +2275,7 @@
|
|
| 2168 |
"shape": [
|
| 2169 |
1152
|
| 2170 |
],
|
| 2171 |
-
"dtype": "
|
| 2172 |
"role": "norm",
|
| 2173 |
"group": "layer.18"
|
| 2174 |
},
|
|
@@ -2179,7 +2286,7 @@
|
|
| 2179 |
"shape": [
|
| 2180 |
1152
|
| 2181 |
],
|
| 2182 |
-
"dtype": "
|
| 2183 |
"role": "norm",
|
| 2184 |
"group": "layer.18"
|
| 2185 |
},
|
|
@@ -2190,7 +2297,7 @@
|
|
| 2190 |
"shape": [
|
| 2191 |
1152
|
| 2192 |
],
|
| 2193 |
-
"dtype": "
|
| 2194 |
"role": "norm",
|
| 2195 |
"group": "layer.18"
|
| 2196 |
},
|
|
@@ -2201,7 +2308,7 @@
|
|
| 2201 |
"shape": [
|
| 2202 |
256
|
| 2203 |
],
|
| 2204 |
-
"dtype": "
|
| 2205 |
"role": "norm",
|
| 2206 |
"group": "layer.18"
|
| 2207 |
},
|
|
@@ -2238,7 +2345,7 @@
|
|
| 2238 |
"shape": [
|
| 2239 |
256
|
| 2240 |
],
|
| 2241 |
-
"dtype": "
|
| 2242 |
"role": "norm",
|
| 2243 |
"group": "layer.18"
|
| 2244 |
},
|
|
@@ -2275,7 +2382,7 @@
|
|
| 2275 |
"shape": [
|
| 2276 |
1152
|
| 2277 |
],
|
| 2278 |
-
"dtype": "
|
| 2279 |
"role": "norm",
|
| 2280 |
"group": "layer.19"
|
| 2281 |
},
|
|
@@ -2325,7 +2432,7 @@
|
|
| 2325 |
"shape": [
|
| 2326 |
1152
|
| 2327 |
],
|
| 2328 |
-
"dtype": "
|
| 2329 |
"role": "norm",
|
| 2330 |
"group": "layer.19"
|
| 2331 |
},
|
|
@@ -2336,7 +2443,7 @@
|
|
| 2336 |
"shape": [
|
| 2337 |
1152
|
| 2338 |
],
|
| 2339 |
-
"dtype": "
|
| 2340 |
"role": "norm",
|
| 2341 |
"group": "layer.19"
|
| 2342 |
},
|
|
@@ -2347,7 +2454,7 @@
|
|
| 2347 |
"shape": [
|
| 2348 |
1152
|
| 2349 |
],
|
| 2350 |
-
"dtype": "
|
| 2351 |
"role": "norm",
|
| 2352 |
"group": "layer.19"
|
| 2353 |
},
|
|
@@ -2358,7 +2465,7 @@
|
|
| 2358 |
"shape": [
|
| 2359 |
256
|
| 2360 |
],
|
| 2361 |
-
"dtype": "
|
| 2362 |
"role": "norm",
|
| 2363 |
"group": "layer.19"
|
| 2364 |
},
|
|
@@ -2395,7 +2502,7 @@
|
|
| 2395 |
"shape": [
|
| 2396 |
256
|
| 2397 |
],
|
| 2398 |
-
"dtype": "
|
| 2399 |
"role": "norm",
|
| 2400 |
"group": "layer.19"
|
| 2401 |
},
|
|
@@ -2432,7 +2539,7 @@
|
|
| 2432 |
"shape": [
|
| 2433 |
1152
|
| 2434 |
],
|
| 2435 |
-
"dtype": "
|
| 2436 |
"role": "norm",
|
| 2437 |
"group": "layer.2"
|
| 2438 |
},
|
|
@@ -2492,7 +2599,7 @@
|
|
| 2492 |
"shape": [
|
| 2493 |
1152
|
| 2494 |
],
|
| 2495 |
-
"dtype": "
|
| 2496 |
"role": "norm",
|
| 2497 |
"group": "layer.2"
|
| 2498 |
},
|
|
@@ -2503,7 +2610,7 @@
|
|
| 2503 |
"shape": [
|
| 2504 |
1152
|
| 2505 |
],
|
| 2506 |
-
"dtype": "
|
| 2507 |
"role": "norm",
|
| 2508 |
"group": "layer.2"
|
| 2509 |
},
|
|
@@ -2514,7 +2621,7 @@
|
|
| 2514 |
"shape": [
|
| 2515 |
1152
|
| 2516 |
],
|
| 2517 |
-
"dtype": "
|
| 2518 |
"role": "norm",
|
| 2519 |
"group": "layer.2"
|
| 2520 |
},
|
|
@@ -2525,7 +2632,7 @@
|
|
| 2525 |
"shape": [
|
| 2526 |
256
|
| 2527 |
],
|
| 2528 |
-
"dtype": "
|
| 2529 |
"role": "norm",
|
| 2530 |
"group": "layer.2"
|
| 2531 |
},
|
|
@@ -2562,7 +2669,7 @@
|
|
| 2562 |
"shape": [
|
| 2563 |
256
|
| 2564 |
],
|
| 2565 |
-
"dtype": "
|
| 2566 |
"role": "norm",
|
| 2567 |
"group": "layer.2"
|
| 2568 |
},
|
|
@@ -2599,7 +2706,7 @@
|
|
| 2599 |
"shape": [
|
| 2600 |
1152
|
| 2601 |
],
|
| 2602 |
-
"dtype": "
|
| 2603 |
"role": "norm",
|
| 2604 |
"group": "layer.20"
|
| 2605 |
},
|
|
@@ -2649,7 +2756,7 @@
|
|
| 2649 |
"shape": [
|
| 2650 |
1152
|
| 2651 |
],
|
| 2652 |
-
"dtype": "
|
| 2653 |
"role": "norm",
|
| 2654 |
"group": "layer.20"
|
| 2655 |
},
|
|
@@ -2660,7 +2767,7 @@
|
|
| 2660 |
"shape": [
|
| 2661 |
1152
|
| 2662 |
],
|
| 2663 |
-
"dtype": "
|
| 2664 |
"role": "norm",
|
| 2665 |
"group": "layer.20"
|
| 2666 |
},
|
|
@@ -2671,7 +2778,7 @@
|
|
| 2671 |
"shape": [
|
| 2672 |
1152
|
| 2673 |
],
|
| 2674 |
-
"dtype": "
|
| 2675 |
"role": "norm",
|
| 2676 |
"group": "layer.20"
|
| 2677 |
},
|
|
@@ -2682,7 +2789,7 @@
|
|
| 2682 |
"shape": [
|
| 2683 |
256
|
| 2684 |
],
|
| 2685 |
-
"dtype": "
|
| 2686 |
"role": "norm",
|
| 2687 |
"group": "layer.20"
|
| 2688 |
},
|
|
@@ -2719,7 +2826,7 @@
|
|
| 2719 |
"shape": [
|
| 2720 |
256
|
| 2721 |
],
|
| 2722 |
-
"dtype": "
|
| 2723 |
"role": "norm",
|
| 2724 |
"group": "layer.20"
|
| 2725 |
},
|
|
@@ -2756,7 +2863,7 @@
|
|
| 2756 |
"shape": [
|
| 2757 |
1152
|
| 2758 |
],
|
| 2759 |
-
"dtype": "
|
| 2760 |
"role": "norm",
|
| 2761 |
"group": "layer.21"
|
| 2762 |
},
|
|
@@ -2806,7 +2913,7 @@
|
|
| 2806 |
"shape": [
|
| 2807 |
1152
|
| 2808 |
],
|
| 2809 |
-
"dtype": "
|
| 2810 |
"role": "norm",
|
| 2811 |
"group": "layer.21"
|
| 2812 |
},
|
|
@@ -2817,7 +2924,7 @@
|
|
| 2817 |
"shape": [
|
| 2818 |
1152
|
| 2819 |
],
|
| 2820 |
-
"dtype": "
|
| 2821 |
"role": "norm",
|
| 2822 |
"group": "layer.21"
|
| 2823 |
},
|
|
@@ -2828,7 +2935,7 @@
|
|
| 2828 |
"shape": [
|
| 2829 |
1152
|
| 2830 |
],
|
| 2831 |
-
"dtype": "
|
| 2832 |
"role": "norm",
|
| 2833 |
"group": "layer.21"
|
| 2834 |
},
|
|
@@ -2839,7 +2946,7 @@
|
|
| 2839 |
"shape": [
|
| 2840 |
256
|
| 2841 |
],
|
| 2842 |
-
"dtype": "
|
| 2843 |
"role": "norm",
|
| 2844 |
"group": "layer.21"
|
| 2845 |
},
|
|
@@ -2876,7 +2983,7 @@
|
|
| 2876 |
"shape": [
|
| 2877 |
256
|
| 2878 |
],
|
| 2879 |
-
"dtype": "
|
| 2880 |
"role": "norm",
|
| 2881 |
"group": "layer.21"
|
| 2882 |
},
|
|
@@ -2913,7 +3020,7 @@
|
|
| 2913 |
"shape": [
|
| 2914 |
1152
|
| 2915 |
],
|
| 2916 |
-
"dtype": "
|
| 2917 |
"role": "norm",
|
| 2918 |
"group": "layer.22"
|
| 2919 |
},
|
|
@@ -2963,7 +3070,7 @@
|
|
| 2963 |
"shape": [
|
| 2964 |
1152
|
| 2965 |
],
|
| 2966 |
-
"dtype": "
|
| 2967 |
"role": "norm",
|
| 2968 |
"group": "layer.22"
|
| 2969 |
},
|
|
@@ -2974,7 +3081,7 @@
|
|
| 2974 |
"shape": [
|
| 2975 |
1152
|
| 2976 |
],
|
| 2977 |
-
"dtype": "
|
| 2978 |
"role": "norm",
|
| 2979 |
"group": "layer.22"
|
| 2980 |
},
|
|
@@ -2985,7 +3092,7 @@
|
|
| 2985 |
"shape": [
|
| 2986 |
1152
|
| 2987 |
],
|
| 2988 |
-
"dtype": "
|
| 2989 |
"role": "norm",
|
| 2990 |
"group": "layer.22"
|
| 2991 |
},
|
|
@@ -2996,7 +3103,7 @@
|
|
| 2996 |
"shape": [
|
| 2997 |
256
|
| 2998 |
],
|
| 2999 |
-
"dtype": "
|
| 3000 |
"role": "norm",
|
| 3001 |
"group": "layer.22"
|
| 3002 |
},
|
|
@@ -3033,7 +3140,7 @@
|
|
| 3033 |
"shape": [
|
| 3034 |
256
|
| 3035 |
],
|
| 3036 |
-
"dtype": "
|
| 3037 |
"role": "norm",
|
| 3038 |
"group": "layer.22"
|
| 3039 |
},
|
|
@@ -3070,7 +3177,7 @@
|
|
| 3070 |
"shape": [
|
| 3071 |
1152
|
| 3072 |
],
|
| 3073 |
-
"dtype": "
|
| 3074 |
"role": "norm",
|
| 3075 |
"group": "layer.23"
|
| 3076 |
},
|
|
@@ -3130,7 +3237,7 @@
|
|
| 3130 |
"shape": [
|
| 3131 |
1152
|
| 3132 |
],
|
| 3133 |
-
"dtype": "
|
| 3134 |
"role": "norm",
|
| 3135 |
"group": "layer.23"
|
| 3136 |
},
|
|
@@ -3141,7 +3248,7 @@
|
|
| 3141 |
"shape": [
|
| 3142 |
1152
|
| 3143 |
],
|
| 3144 |
-
"dtype": "
|
| 3145 |
"role": "norm",
|
| 3146 |
"group": "layer.23"
|
| 3147 |
},
|
|
@@ -3152,7 +3259,7 @@
|
|
| 3152 |
"shape": [
|
| 3153 |
1152
|
| 3154 |
],
|
| 3155 |
-
"dtype": "
|
| 3156 |
"role": "norm",
|
| 3157 |
"group": "layer.23"
|
| 3158 |
},
|
|
@@ -3163,7 +3270,7 @@
|
|
| 3163 |
"shape": [
|
| 3164 |
256
|
| 3165 |
],
|
| 3166 |
-
"dtype": "
|
| 3167 |
"role": "norm",
|
| 3168 |
"group": "layer.23"
|
| 3169 |
},
|
|
@@ -3200,7 +3307,7 @@
|
|
| 3200 |
"shape": [
|
| 3201 |
256
|
| 3202 |
],
|
| 3203 |
-
"dtype": "
|
| 3204 |
"role": "norm",
|
| 3205 |
"group": "layer.23"
|
| 3206 |
},
|
|
@@ -3237,7 +3344,7 @@
|
|
| 3237 |
"shape": [
|
| 3238 |
1152
|
| 3239 |
],
|
| 3240 |
-
"dtype": "
|
| 3241 |
"role": "norm",
|
| 3242 |
"group": "layer.24"
|
| 3243 |
},
|
|
@@ -3287,7 +3394,7 @@
|
|
| 3287 |
"shape": [
|
| 3288 |
1152
|
| 3289 |
],
|
| 3290 |
-
"dtype": "
|
| 3291 |
"role": "norm",
|
| 3292 |
"group": "layer.24"
|
| 3293 |
},
|
|
@@ -3298,7 +3405,7 @@
|
|
| 3298 |
"shape": [
|
| 3299 |
1152
|
| 3300 |
],
|
| 3301 |
-
"dtype": "
|
| 3302 |
"role": "norm",
|
| 3303 |
"group": "layer.24"
|
| 3304 |
},
|
|
@@ -3309,7 +3416,7 @@
|
|
| 3309 |
"shape": [
|
| 3310 |
1152
|
| 3311 |
],
|
| 3312 |
-
"dtype": "
|
| 3313 |
"role": "norm",
|
| 3314 |
"group": "layer.24"
|
| 3315 |
},
|
|
@@ -3320,7 +3427,7 @@
|
|
| 3320 |
"shape": [
|
| 3321 |
256
|
| 3322 |
],
|
| 3323 |
-
"dtype": "
|
| 3324 |
"role": "norm",
|
| 3325 |
"group": "layer.24"
|
| 3326 |
},
|
|
@@ -3357,7 +3464,7 @@
|
|
| 3357 |
"shape": [
|
| 3358 |
256
|
| 3359 |
],
|
| 3360 |
-
"dtype": "
|
| 3361 |
"role": "norm",
|
| 3362 |
"group": "layer.24"
|
| 3363 |
},
|
|
@@ -3394,7 +3501,7 @@
|
|
| 3394 |
"shape": [
|
| 3395 |
1152
|
| 3396 |
],
|
| 3397 |
-
"dtype": "
|
| 3398 |
"role": "norm",
|
| 3399 |
"group": "layer.25"
|
| 3400 |
},
|
|
@@ -3444,7 +3551,7 @@
|
|
| 3444 |
"shape": [
|
| 3445 |
1152
|
| 3446 |
],
|
| 3447 |
-
"dtype": "
|
| 3448 |
"role": "norm",
|
| 3449 |
"group": "layer.25"
|
| 3450 |
},
|
|
@@ -3455,7 +3562,7 @@
|
|
| 3455 |
"shape": [
|
| 3456 |
1152
|
| 3457 |
],
|
| 3458 |
-
"dtype": "
|
| 3459 |
"role": "norm",
|
| 3460 |
"group": "layer.25"
|
| 3461 |
},
|
|
@@ -3466,7 +3573,7 @@
|
|
| 3466 |
"shape": [
|
| 3467 |
1152
|
| 3468 |
],
|
| 3469 |
-
"dtype": "
|
| 3470 |
"role": "norm",
|
| 3471 |
"group": "layer.25"
|
| 3472 |
},
|
|
@@ -3477,7 +3584,7 @@
|
|
| 3477 |
"shape": [
|
| 3478 |
256
|
| 3479 |
],
|
| 3480 |
-
"dtype": "
|
| 3481 |
"role": "norm",
|
| 3482 |
"group": "layer.25"
|
| 3483 |
},
|
|
@@ -3514,7 +3621,7 @@
|
|
| 3514 |
"shape": [
|
| 3515 |
256
|
| 3516 |
],
|
| 3517 |
-
"dtype": "
|
| 3518 |
"role": "norm",
|
| 3519 |
"group": "layer.25"
|
| 3520 |
},
|
|
@@ -3551,7 +3658,7 @@
|
|
| 3551 |
"shape": [
|
| 3552 |
1152
|
| 3553 |
],
|
| 3554 |
-
"dtype": "
|
| 3555 |
"role": "norm",
|
| 3556 |
"group": "layer.3"
|
| 3557 |
},
|
|
@@ -3601,7 +3708,7 @@
|
|
| 3601 |
"shape": [
|
| 3602 |
1152
|
| 3603 |
],
|
| 3604 |
-
"dtype": "
|
| 3605 |
"role": "norm",
|
| 3606 |
"group": "layer.3"
|
| 3607 |
},
|
|
@@ -3612,7 +3719,7 @@
|
|
| 3612 |
"shape": [
|
| 3613 |
1152
|
| 3614 |
],
|
| 3615 |
-
"dtype": "
|
| 3616 |
"role": "norm",
|
| 3617 |
"group": "layer.3"
|
| 3618 |
},
|
|
@@ -3623,7 +3730,7 @@
|
|
| 3623 |
"shape": [
|
| 3624 |
1152
|
| 3625 |
],
|
| 3626 |
-
"dtype": "
|
| 3627 |
"role": "norm",
|
| 3628 |
"group": "layer.3"
|
| 3629 |
},
|
|
@@ -3634,7 +3741,7 @@
|
|
| 3634 |
"shape": [
|
| 3635 |
256
|
| 3636 |
],
|
| 3637 |
-
"dtype": "
|
| 3638 |
"role": "norm",
|
| 3639 |
"group": "layer.3"
|
| 3640 |
},
|
|
@@ -3671,7 +3778,7 @@
|
|
| 3671 |
"shape": [
|
| 3672 |
256
|
| 3673 |
],
|
| 3674 |
-
"dtype": "
|
| 3675 |
"role": "norm",
|
| 3676 |
"group": "layer.3"
|
| 3677 |
},
|
|
@@ -3708,7 +3815,7 @@
|
|
| 3708 |
"shape": [
|
| 3709 |
1152
|
| 3710 |
],
|
| 3711 |
-
"dtype": "
|
| 3712 |
"role": "norm",
|
| 3713 |
"group": "layer.4"
|
| 3714 |
},
|
|
@@ -3768,7 +3875,7 @@
|
|
| 3768 |
"shape": [
|
| 3769 |
1152
|
| 3770 |
],
|
| 3771 |
-
"dtype": "
|
| 3772 |
"role": "norm",
|
| 3773 |
"group": "layer.4"
|
| 3774 |
},
|
|
@@ -3779,7 +3886,7 @@
|
|
| 3779 |
"shape": [
|
| 3780 |
1152
|
| 3781 |
],
|
| 3782 |
-
"dtype": "
|
| 3783 |
"role": "norm",
|
| 3784 |
"group": "layer.4"
|
| 3785 |
},
|
|
@@ -3790,7 +3897,7 @@
|
|
| 3790 |
"shape": [
|
| 3791 |
1152
|
| 3792 |
],
|
| 3793 |
-
"dtype": "
|
| 3794 |
"role": "norm",
|
| 3795 |
"group": "layer.4"
|
| 3796 |
},
|
|
@@ -3801,7 +3908,7 @@
|
|
| 3801 |
"shape": [
|
| 3802 |
256
|
| 3803 |
],
|
| 3804 |
-
"dtype": "
|
| 3805 |
"role": "norm",
|
| 3806 |
"group": "layer.4"
|
| 3807 |
},
|
|
@@ -3838,7 +3945,7 @@
|
|
| 3838 |
"shape": [
|
| 3839 |
256
|
| 3840 |
],
|
| 3841 |
-
"dtype": "
|
| 3842 |
"role": "norm",
|
| 3843 |
"group": "layer.4"
|
| 3844 |
},
|
|
@@ -3875,7 +3982,7 @@
|
|
| 3875 |
"shape": [
|
| 3876 |
1152
|
| 3877 |
],
|
| 3878 |
-
"dtype": "
|
| 3879 |
"role": "norm",
|
| 3880 |
"group": "layer.5"
|
| 3881 |
},
|
|
@@ -3925,7 +4032,7 @@
|
|
| 3925 |
"shape": [
|
| 3926 |
1152
|
| 3927 |
],
|
| 3928 |
-
"dtype": "
|
| 3929 |
"role": "norm",
|
| 3930 |
"group": "layer.5"
|
| 3931 |
},
|
|
@@ -3936,7 +4043,7 @@
|
|
| 3936 |
"shape": [
|
| 3937 |
1152
|
| 3938 |
],
|
| 3939 |
-
"dtype": "
|
| 3940 |
"role": "norm",
|
| 3941 |
"group": "layer.5"
|
| 3942 |
},
|
|
@@ -3947,7 +4054,7 @@
|
|
| 3947 |
"shape": [
|
| 3948 |
1152
|
| 3949 |
],
|
| 3950 |
-
"dtype": "
|
| 3951 |
"role": "norm",
|
| 3952 |
"group": "layer.5"
|
| 3953 |
},
|
|
@@ -3958,7 +4065,7 @@
|
|
| 3958 |
"shape": [
|
| 3959 |
256
|
| 3960 |
],
|
| 3961 |
-
"dtype": "
|
| 3962 |
"role": "norm",
|
| 3963 |
"group": "layer.5"
|
| 3964 |
},
|
|
@@ -3995,7 +4102,7 @@
|
|
| 3995 |
"shape": [
|
| 3996 |
256
|
| 3997 |
],
|
| 3998 |
-
"dtype": "
|
| 3999 |
"role": "norm",
|
| 4000 |
"group": "layer.5"
|
| 4001 |
},
|
|
@@ -4032,7 +4139,7 @@
|
|
| 4032 |
"shape": [
|
| 4033 |
1152
|
| 4034 |
],
|
| 4035 |
-
"dtype": "
|
| 4036 |
"role": "norm",
|
| 4037 |
"group": "layer.6"
|
| 4038 |
},
|
|
@@ -4082,7 +4189,7 @@
|
|
| 4082 |
"shape": [
|
| 4083 |
1152
|
| 4084 |
],
|
| 4085 |
-
"dtype": "
|
| 4086 |
"role": "norm",
|
| 4087 |
"group": "layer.6"
|
| 4088 |
},
|
|
@@ -4093,7 +4200,7 @@
|
|
| 4093 |
"shape": [
|
| 4094 |
1152
|
| 4095 |
],
|
| 4096 |
-
"dtype": "
|
| 4097 |
"role": "norm",
|
| 4098 |
"group": "layer.6"
|
| 4099 |
},
|
|
@@ -4104,7 +4211,7 @@
|
|
| 4104 |
"shape": [
|
| 4105 |
1152
|
| 4106 |
],
|
| 4107 |
-
"dtype": "
|
| 4108 |
"role": "norm",
|
| 4109 |
"group": "layer.6"
|
| 4110 |
},
|
|
@@ -4115,7 +4222,7 @@
|
|
| 4115 |
"shape": [
|
| 4116 |
256
|
| 4117 |
],
|
| 4118 |
-
"dtype": "
|
| 4119 |
"role": "norm",
|
| 4120 |
"group": "layer.6"
|
| 4121 |
},
|
|
@@ -4152,7 +4259,7 @@
|
|
| 4152 |
"shape": [
|
| 4153 |
256
|
| 4154 |
],
|
| 4155 |
-
"dtype": "
|
| 4156 |
"role": "norm",
|
| 4157 |
"group": "layer.6"
|
| 4158 |
},
|
|
@@ -4189,7 +4296,7 @@
|
|
| 4189 |
"shape": [
|
| 4190 |
1152
|
| 4191 |
],
|
| 4192 |
-
"dtype": "
|
| 4193 |
"role": "norm",
|
| 4194 |
"group": "layer.7"
|
| 4195 |
},
|
|
@@ -4239,7 +4346,7 @@
|
|
| 4239 |
"shape": [
|
| 4240 |
1152
|
| 4241 |
],
|
| 4242 |
-
"dtype": "
|
| 4243 |
"role": "norm",
|
| 4244 |
"group": "layer.7"
|
| 4245 |
},
|
|
@@ -4250,7 +4357,7 @@
|
|
| 4250 |
"shape": [
|
| 4251 |
1152
|
| 4252 |
],
|
| 4253 |
-
"dtype": "
|
| 4254 |
"role": "norm",
|
| 4255 |
"group": "layer.7"
|
| 4256 |
},
|
|
@@ -4261,7 +4368,7 @@
|
|
| 4261 |
"shape": [
|
| 4262 |
1152
|
| 4263 |
],
|
| 4264 |
-
"dtype": "
|
| 4265 |
"role": "norm",
|
| 4266 |
"group": "layer.7"
|
| 4267 |
},
|
|
@@ -4272,7 +4379,7 @@
|
|
| 4272 |
"shape": [
|
| 4273 |
256
|
| 4274 |
],
|
| 4275 |
-
"dtype": "
|
| 4276 |
"role": "norm",
|
| 4277 |
"group": "layer.7"
|
| 4278 |
},
|
|
@@ -4309,7 +4416,7 @@
|
|
| 4309 |
"shape": [
|
| 4310 |
256
|
| 4311 |
],
|
| 4312 |
-
"dtype": "
|
| 4313 |
"role": "norm",
|
| 4314 |
"group": "layer.7"
|
| 4315 |
},
|
|
@@ -4346,7 +4453,7 @@
|
|
| 4346 |
"shape": [
|
| 4347 |
1152
|
| 4348 |
],
|
| 4349 |
-
"dtype": "
|
| 4350 |
"role": "norm",
|
| 4351 |
"group": "layer.8"
|
| 4352 |
},
|
|
@@ -4406,7 +4513,7 @@
|
|
| 4406 |
"shape": [
|
| 4407 |
1152
|
| 4408 |
],
|
| 4409 |
-
"dtype": "
|
| 4410 |
"role": "norm",
|
| 4411 |
"group": "layer.8"
|
| 4412 |
},
|
|
@@ -4417,7 +4524,7 @@
|
|
| 4417 |
"shape": [
|
| 4418 |
1152
|
| 4419 |
],
|
| 4420 |
-
"dtype": "
|
| 4421 |
"role": "norm",
|
| 4422 |
"group": "layer.8"
|
| 4423 |
},
|
|
@@ -4428,7 +4535,7 @@
|
|
| 4428 |
"shape": [
|
| 4429 |
1152
|
| 4430 |
],
|
| 4431 |
-
"dtype": "
|
| 4432 |
"role": "norm",
|
| 4433 |
"group": "layer.8"
|
| 4434 |
},
|
|
@@ -4439,7 +4546,7 @@
|
|
| 4439 |
"shape": [
|
| 4440 |
256
|
| 4441 |
],
|
| 4442 |
-
"dtype": "
|
| 4443 |
"role": "norm",
|
| 4444 |
"group": "layer.8"
|
| 4445 |
},
|
|
@@ -4476,7 +4583,7 @@
|
|
| 4476 |
"shape": [
|
| 4477 |
256
|
| 4478 |
],
|
| 4479 |
-
"dtype": "
|
| 4480 |
"role": "norm",
|
| 4481 |
"group": "layer.8"
|
| 4482 |
},
|
|
@@ -4513,7 +4620,7 @@
|
|
| 4513 |
"shape": [
|
| 4514 |
1152
|
| 4515 |
],
|
| 4516 |
-
"dtype": "
|
| 4517 |
"role": "norm",
|
| 4518 |
"group": "layer.9"
|
| 4519 |
},
|
|
@@ -4563,7 +4670,7 @@
|
|
| 4563 |
"shape": [
|
| 4564 |
1152
|
| 4565 |
],
|
| 4566 |
-
"dtype": "
|
| 4567 |
"role": "norm",
|
| 4568 |
"group": "layer.9"
|
| 4569 |
},
|
|
@@ -4574,7 +4681,7 @@
|
|
| 4574 |
"shape": [
|
| 4575 |
1152
|
| 4576 |
],
|
| 4577 |
-
"dtype": "
|
| 4578 |
"role": "norm",
|
| 4579 |
"group": "layer.9"
|
| 4580 |
},
|
|
@@ -4585,7 +4692,7 @@
|
|
| 4585 |
"shape": [
|
| 4586 |
1152
|
| 4587 |
],
|
| 4588 |
-
"dtype": "
|
| 4589 |
"role": "norm",
|
| 4590 |
"group": "layer.9"
|
| 4591 |
},
|
|
@@ -4596,7 +4703,7 @@
|
|
| 4596 |
"shape": [
|
| 4597 |
256
|
| 4598 |
],
|
| 4599 |
-
"dtype": "
|
| 4600 |
"role": "norm",
|
| 4601 |
"group": "layer.9"
|
| 4602 |
},
|
|
@@ -4633,7 +4740,7 @@
|
|
| 4633 |
"shape": [
|
| 4634 |
256
|
| 4635 |
],
|
| 4636 |
-
"dtype": "
|
| 4637 |
"role": "norm",
|
| 4638 |
"group": "layer.9"
|
| 4639 |
},
|
|
@@ -4670,7 +4777,7 @@
|
|
| 4670 |
"shape": [
|
| 4671 |
1152
|
| 4672 |
],
|
| 4673 |
-
"dtype": "
|
| 4674 |
"role": "norm",
|
| 4675 |
"group": "head"
|
| 4676 |
}
|
|
@@ -4681,18 +4788,369 @@
|
|
| 4681 |
1,
|
| 4682 |
106
|
| 4683 |
],
|
|
|
|
| 4684 |
"metadata": {
|
| 4685 |
-
"source": "
|
| 4686 |
-
"convertedAt": "2026-
|
| 4687 |
"hasTokenizer": true,
|
| 4688 |
"manifestRefresh": {
|
| 4689 |
-
"at": "2026-
|
| 4690 |
"config": "translategemma-4b-1b-enes-q4k-ehf16-af32.json"
|
| 4691 |
}
|
| 4692 |
},
|
| 4693 |
"tokenizer": {
|
| 4694 |
"type": "bundled",
|
| 4695 |
"vocabSize": 262144,
|
| 4696 |
-
"file": "tokenizer.json"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4697 |
}
|
| 4698 |
}
|
|
|
|
| 10 |
"layout": "row",
|
| 11 |
"variantTag": "q4k-ehf16-af32"
|
| 12 |
},
|
| 13 |
+
"artifactIdentity": {
|
| 14 |
+
"artifactCompleteness": "complete",
|
| 15 |
+
"conversionConfigDigest": "sha256:e1a07175c0b34d9a746c4c6613f5a8557249d5755a25ecbdda2004ba2fb2343d",
|
| 16 |
+
"conversionConfigPath": "src/config/conversion/gemma3/translategemma-4b-1b-enes-q4k-ehf16-af32.json",
|
| 17 |
+
"manifestVariantId": "translategemma-4b-1b-enes-q4k-ehf16-af32-mv-b3c719ee90e7",
|
| 18 |
+
"materializationProfile": "auto",
|
| 19 |
+
"modalitySet": [
|
| 20 |
+
"text"
|
| 21 |
+
],
|
| 22 |
+
"shardSetHash": "sha256:916693349fb4528e3a188db1dc484ac0c794cbb2d858c50a659ceb0df61e2001",
|
| 23 |
+
"sourceCheckpointId": "clocksmith/gamma-translategemma-4b-1b-enes-nativekd2@sha256:c567331d8eb9d3da65205b83f4e0af06568c47ba81a7927005c1c2e72444bc87",
|
| 24 |
+
"sourceFormat": "safetensors",
|
| 25 |
+
"weightPackHash": "sha256:16acf07340bdea908fc4096d03c21a473135739b292bae1a22ee641703e46fc4",
|
| 26 |
+
"weightPackId": "translategemma-4b-1b-enes-q4k-ehf16-af32-wp-16acf07340bd"
|
| 27 |
+
},
|
| 28 |
"architecture": {
|
| 29 |
"numLayers": 26,
|
| 30 |
"hiddenSize": 1152,
|
|
|
|
| 34 |
"headDim": 256,
|
| 35 |
"vocabSize": 262144,
|
| 36 |
"maxSeqLen": 32768,
|
| 37 |
+
"ropeTheta": 1000000,
|
| 38 |
+
"linearNumKeyHeads": null,
|
| 39 |
+
"linearNumValueHeads": null,
|
| 40 |
+
"linearKeyHeadDim": null,
|
| 41 |
+
"linearValueHeadDim": null,
|
| 42 |
+
"linearConvKernelDim": null,
|
| 43 |
+
"hiddenSizePerLayerInput": null,
|
| 44 |
+
"vocabSizePerLayerInput": null,
|
| 45 |
+
"globalHeadDim": null,
|
| 46 |
+
"numKvSharedLayers": null
|
| 47 |
},
|
| 48 |
"moeConfig": null,
|
| 49 |
"inference": {
|
|
|
|
| 51 |
"attention": {
|
| 52 |
"queryPreAttnScalar": 256,
|
| 53 |
"attnLogitSoftcapping": null,
|
| 54 |
+
"slidingWindow": 512,
|
| 55 |
"queryKeyNorm": true,
|
| 56 |
"causal": true,
|
| 57 |
"attentionBias": false,
|
| 58 |
+
"attentionOutputGate": false,
|
| 59 |
+
"valueNorm": false
|
| 60 |
},
|
| 61 |
"normalization": {
|
| 62 |
"rmsNormEps": 0.000001,
|
|
|
|
| 68 |
"ffn": {
|
| 69 |
"activation": "gelu",
|
| 70 |
"gatedActivation": true,
|
| 71 |
+
"branchMode": "auto",
|
| 72 |
+
"swigluLimit": null,
|
| 73 |
+
"useDoubleWideMlp": false
|
| 74 |
},
|
| 75 |
"rope": {
|
| 76 |
"ropeTheta": 1000000,
|
| 77 |
+
"ropeLocalTheta": 10000,
|
| 78 |
"mropeInterleaved": false,
|
| 79 |
"mropeSection": null,
|
| 80 |
"partialRotaryFactor": null,
|
|
|
|
| 87 |
"yarnOriginalMaxPos": null,
|
| 88 |
"ropeLocalYarnBetaFast": null,
|
| 89 |
"ropeLocalYarnBetaSlow": null,
|
| 90 |
+
"ropeLocalYarnOriginalMaxPos": null,
|
| 91 |
+
"ropeLocalPartialRotaryFactor": null,
|
| 92 |
+
"ropeFrequencyBaseDim": null,
|
| 93 |
+
"ropeLocalFrequencyBaseDim": null,
|
| 94 |
+
"longropeShortFactor": null,
|
| 95 |
+
"longropeLongFactor": null,
|
| 96 |
+
"longropeOriginalMaxPos": null
|
| 97 |
},
|
| 98 |
"output": {
|
| 99 |
"finalLogitSoftcapping": null,
|
|
|
|
| 101 |
"scaleEmbeddings": true,
|
| 102 |
"embeddingTranspose": false,
|
| 103 |
"embeddingVocabSize": null,
|
| 104 |
+
"embeddingPostprocessor": null,
|
| 105 |
+
"embeddingScale": null,
|
| 106 |
+
"logitInputScale": 1
|
| 107 |
},
|
| 108 |
"layerPattern": {
|
| 109 |
+
"type": "every_n",
|
| 110 |
"globalPattern": null,
|
| 111 |
+
"period": 6,
|
| 112 |
+
"offset": 5,
|
| 113 |
+
"layerTypes": null,
|
| 114 |
+
"residualBranchScale": 1
|
| 115 |
},
|
| 116 |
"chatTemplate": {
|
| 117 |
+
"type": "gemma",
|
| 118 |
"enabled": true
|
| 119 |
},
|
| 120 |
+
"supportsEmbedding": false,
|
| 121 |
+
"supportsRerank": false,
|
| 122 |
+
"supportsTranscription": false,
|
| 123 |
+
"supportsVision": false,
|
| 124 |
+
"rerank": null,
|
| 125 |
+
"diffusionGemma": null,
|
| 126 |
"pipeline": null,
|
| 127 |
+
"session": {
|
| 128 |
"compute": {
|
| 129 |
"defaults": {
|
| 130 |
"activationDtype": "f32",
|
|
|
|
| 134 |
}
|
| 135 |
},
|
| 136 |
"kvcache": {
|
| 137 |
+
"kvDtype": "f16",
|
| 138 |
+
"layout": "contiguous",
|
| 139 |
+
"pageSize": 256,
|
| 140 |
+
"tiering": {
|
| 141 |
+
"mode": "off",
|
| 142 |
+
"hotWindow": 1024,
|
| 143 |
+
"coldPageSize": 256,
|
| 144 |
+
"coldDtype": "f16",
|
| 145 |
+
"compression": {
|
| 146 |
+
"mode": "none",
|
| 147 |
+
"blockSize": 1,
|
| 148 |
+
"bitWidth": 4,
|
| 149 |
+
"prodMode": false
|
| 150 |
+
},
|
| 151 |
+
"gating": {
|
| 152 |
+
"mode": "auto",
|
| 153 |
+
"minAluBwRatio": 0
|
| 154 |
+
}
|
| 155 |
+
},
|
| 156 |
+
"quantization": {
|
| 157 |
+
"mode": "none",
|
| 158 |
+
"bitWidth": 4,
|
| 159 |
+
"prodMode": false
|
| 160 |
+
}
|
| 161 |
+
},
|
| 162 |
+
"decodeLoop": {
|
| 163 |
+
"batchSize": 4,
|
| 164 |
+
"stopCheckMode": "batch",
|
| 165 |
+
"readbackInterval": 1,
|
| 166 |
+
"readbackMode": "sequential",
|
| 167 |
+
"ringTokens": 1,
|
| 168 |
+
"ringStop": 1,
|
| 169 |
+
"ringStaging": 1,
|
| 170 |
+
"disableCommandBatching": false
|
| 171 |
+
},
|
| 172 |
+
"perLayerInputs": {
|
| 173 |
+
"materialization": "auto",
|
| 174 |
+
"rowCache": {
|
| 175 |
+
"mode": "lru",
|
| 176 |
+
"maxRows": 256,
|
| 177 |
+
"maxBytes": 134217728,
|
| 178 |
+
"decodedDtype": "f32"
|
| 179 |
+
},
|
| 180 |
+
"prefetch": {
|
| 181 |
+
"mode": "next_token",
|
| 182 |
+
"rowsAhead": 1
|
| 183 |
+
},
|
| 184 |
+
"gpuUpload": {
|
| 185 |
+
"mode": "per_step_slices",
|
| 186 |
+
"stagingRows": 2
|
| 187 |
+
},
|
| 188 |
+
"hotCache": {
|
| 189 |
+
"mode": "prepared_tokens",
|
| 190 |
+
"maxTokens": 1024,
|
| 191 |
+
"maxBytes": 134217728,
|
| 192 |
+
"outputDtype": "f32"
|
| 193 |
+
}
|
| 194 |
},
|
| 195 |
+
"prefillChunkSubmitMode": "sync",
|
| 196 |
+
"useFlashPrefillAttention": false,
|
| 197 |
+
"useWideTileQ4KPrefill": false,
|
| 198 |
+
"retainQ4KMaterialization": false
|
| 199 |
},
|
| 200 |
"execution": {
|
| 201 |
"kernels": {
|
| 202 |
"embed": {
|
| 203 |
"kernel": "gather_f16.wgsl",
|
| 204 |
"entry": "main",
|
| 205 |
+
"digest": "sha256:8995b4a790a1f3b89fbb801f89d595985eee46c9bfca4133f74396259083eda9"
|
| 206 |
},
|
| 207 |
"rmsnorm": {
|
| 208 |
"kernel": "rmsnorm.wgsl",
|
| 209 |
"entry": "main",
|
| 210 |
+
"digest": "sha256:284d3efb0ad0991fc57ece5f634cbc8a931fcab36f193b2b6832561d4cc79ef1"
|
| 211 |
},
|
| 212 |
"gemv": {
|
| 213 |
"kernel": "matmul_gemv_subgroup.wgsl",
|
| 214 |
"entry": "main_vec4",
|
| 215 |
+
"digest": "sha256:2ea9aea659367210fbf61d922c0d4ee17cdac68ffb506b3bc5516e498071e011"
|
| 216 |
},
|
| 217 |
"rope": {
|
| 218 |
"kernel": "rope.wgsl",
|
| 219 |
"entry": "main",
|
| 220 |
+
"digest": "sha256:b2da9d396668981dab9794c2973b668279f768994466b083d2105730555e1a5b"
|
| 221 |
},
|
| 222 |
"attn_decode": {
|
| 223 |
"kernel": "attention_decode_online_f16kv.wgsl",
|
| 224 |
"entry": "main",
|
| 225 |
+
"digest": "sha256:91808be35895e921c0fa43fc47bfe8cab69c437c388ab561f595d9dc983f66e1",
|
| 226 |
+
"precision": {
|
| 227 |
+
"kvDtype": "f16"
|
| 228 |
+
}
|
| 229 |
},
|
| 230 |
"residual": {
|
| 231 |
"kernel": "residual.wgsl",
|
| 232 |
"entry": "main",
|
| 233 |
+
"digest": "sha256:abd19bc08ad668a7cad562e2bc0a4be1aa8827ad4300d8d474b7fc2af4c27117"
|
| 234 |
},
|
| 235 |
"gelu": {
|
| 236 |
"kernel": "gelu.wgsl",
|
| 237 |
"entry": "main",
|
| 238 |
+
"digest": "sha256:7f8900b69de5107e4cf424cac0d4de1539591ece34e977ff30f6f7364460ab34",
|
| 239 |
"constants": {
|
| 240 |
"HAS_GATE": true
|
| 241 |
}
|
|
|
|
| 248 |
"attn_stream": {
|
| 249 |
"kernel": "attention_streaming_f16kv.wgsl",
|
| 250 |
"entry": "main",
|
| 251 |
+
"digest": "sha256:c3ec920699a81ee6df04a64eb0ea2477bec168ebb809af29f2d4b0924a4bdf8f",
|
| 252 |
+
"precision": {
|
| 253 |
+
"kvDtype": "f16"
|
| 254 |
+
}
|
| 255 |
},
|
| 256 |
"lm_head_gemv": {
|
| 257 |
"kernel": "matmul_gemv_subgroup.wgsl",
|
| 258 |
"entry": "main_multicol",
|
| 259 |
+
"digest": "sha256:e41f94574d5ac54dd2710036da5d5acc643a483b79b2d74b86825efdaaa7438f",
|
| 260 |
"constants": {
|
| 261 |
"MULTICOL_COLS_PER_WG": 64,
|
| 262 |
"MULTICOL_THREADS_PER_COL": 4
|
|
|
|
| 265 |
"sample": {
|
| 266 |
"kernel": "sample.wgsl",
|
| 267 |
"entry": "sample_single_pass",
|
| 268 |
+
"digest": "sha256:7ff3dd675b4737d920e0b3889e15c4fedde8410a353bbc6d4651db76ce69eb9b"
|
| 269 |
}
|
| 270 |
},
|
| 271 |
"preLayer": [
|
|
|
|
| 445 |
"index": 0,
|
| 446 |
"filename": "shard_00000.bin",
|
| 447 |
"size": 67108864,
|
| 448 |
+
"hash": "d131d7f6c16207e77a1d192e7064c7576c35d68add8bda7d25ab84ce91c8835e",
|
| 449 |
+
"blake3": "d131d7f6c16207e77a1d192e7064c7576c35d68add8bda7d25ab84ce91c8835e",
|
| 450 |
"offset": 0
|
| 451 |
},
|
| 452 |
{
|
| 453 |
"index": 1,
|
| 454 |
"filename": "shard_00001.bin",
|
| 455 |
"size": 67108864,
|
| 456 |
+
"hash": "29b3602ce153e3f0042b41c5ed95da88c30c5daea38d0a5315df2ed8d19e9277",
|
| 457 |
+
"blake3": "29b3602ce153e3f0042b41c5ed95da88c30c5daea38d0a5315df2ed8d19e9277",
|
| 458 |
"offset": 67108864
|
| 459 |
},
|
| 460 |
{
|
| 461 |
"index": 2,
|
| 462 |
"filename": "shard_00002.bin",
|
| 463 |
"size": 67108864,
|
| 464 |
+
"hash": "7550100a833d58db59f9b6d37751a2853b9ef0910680a2615e7ae6626ca7e52d",
|
| 465 |
+
"blake3": "7550100a833d58db59f9b6d37751a2853b9ef0910680a2615e7ae6626ca7e52d",
|
| 466 |
"offset": 134217728
|
| 467 |
},
|
| 468 |
{
|
| 469 |
"index": 3,
|
| 470 |
"filename": "shard_00003.bin",
|
| 471 |
"size": 67108864,
|
| 472 |
+
"hash": "93eada898b0833122e1f654eeefcf548f14b77f6542634d6cb28aba883b24ce5",
|
| 473 |
+
"blake3": "93eada898b0833122e1f654eeefcf548f14b77f6542634d6cb28aba883b24ce5",
|
| 474 |
"offset": 201326592
|
| 475 |
},
|
| 476 |
{
|
| 477 |
"index": 4,
|
| 478 |
"filename": "shard_00004.bin",
|
| 479 |
"size": 67108864,
|
| 480 |
+
"hash": "133c80ac9119302ca1f5fa0087ea8d8adcd0e27602bd362e23894ac88b88ca9e",
|
| 481 |
+
"blake3": "133c80ac9119302ca1f5fa0087ea8d8adcd0e27602bd362e23894ac88b88ca9e",
|
| 482 |
"offset": 268435456
|
| 483 |
},
|
| 484 |
{
|
| 485 |
"index": 5,
|
| 486 |
"filename": "shard_00005.bin",
|
| 487 |
"size": 67108864,
|
| 488 |
+
"hash": "dddbe9dac42493b004cb5c00fb1813106b1376d7eede45d5fd460e61c03e7e63",
|
| 489 |
+
"blake3": "dddbe9dac42493b004cb5c00fb1813106b1376d7eede45d5fd460e61c03e7e63",
|
| 490 |
"offset": 335544320
|
| 491 |
},
|
| 492 |
{
|
| 493 |
"index": 6,
|
| 494 |
"filename": "shard_00006.bin",
|
| 495 |
"size": 67108864,
|
| 496 |
+
"hash": "0518b0f45a4ee502d7ac7de55ff1d65fac94953adfb00f8f8adefc43cc736926",
|
| 497 |
+
"blake3": "0518b0f45a4ee502d7ac7de55ff1d65fac94953adfb00f8f8adefc43cc736926",
|
| 498 |
"offset": 402653184
|
| 499 |
},
|
| 500 |
{
|
| 501 |
"index": 7,
|
| 502 |
"filename": "shard_00007.bin",
|
| 503 |
"size": 67108864,
|
| 504 |
+
"hash": "fd8112f0840b225d009ac889df884df4e4e6f592e68f6af7fe8b8ed0b1d94529",
|
| 505 |
+
"blake3": "fd8112f0840b225d009ac889df884df4e4e6f592e68f6af7fe8b8ed0b1d94529",
|
| 506 |
"offset": 469762048
|
| 507 |
},
|
| 508 |
{
|
| 509 |
"index": 8,
|
| 510 |
"filename": "shard_00008.bin",
|
| 511 |
"size": 67108864,
|
| 512 |
+
"hash": "5671d65845227d36853e6778749cc021d78baef447d95b6c5fd2ff1bbdad10a9",
|
| 513 |
+
"blake3": "5671d65845227d36853e6778749cc021d78baef447d95b6c5fd2ff1bbdad10a9",
|
| 514 |
"offset": 536870912
|
| 515 |
},
|
| 516 |
{
|
| 517 |
"index": 9,
|
| 518 |
"filename": "shard_00009.bin",
|
| 519 |
"size": 67108864,
|
| 520 |
+
"hash": "9cdcbd75b78e6807414e4feb62de18d29b4c9fc96eba50de5950162b3f2e7558",
|
| 521 |
+
"blake3": "9cdcbd75b78e6807414e4feb62de18d29b4c9fc96eba50de5950162b3f2e7558",
|
| 522 |
"offset": 603979776
|
| 523 |
},
|
| 524 |
{
|
| 525 |
"index": 10,
|
| 526 |
"filename": "shard_00010.bin",
|
| 527 |
"size": 67108864,
|
| 528 |
+
"hash": "cb54da5bd1180b66f77c15c40d943ad88332abf0dd24e30e9eca61beeb4055d6",
|
| 529 |
+
"blake3": "cb54da5bd1180b66f77c15c40d943ad88332abf0dd24e30e9eca61beeb4055d6",
|
| 530 |
"offset": 671088640
|
| 531 |
},
|
| 532 |
{
|
| 533 |
"index": 11,
|
| 534 |
"filename": "shard_00011.bin",
|
| 535 |
"size": 67108864,
|
| 536 |
+
"hash": "3192759dad85e38c9cbfa84d67949d8efe0e3a2d9c1a180fa3cccbf92f415c4b",
|
| 537 |
+
"blake3": "3192759dad85e38c9cbfa84d67949d8efe0e3a2d9c1a180fa3cccbf92f415c4b",
|
| 538 |
"offset": 738197504
|
| 539 |
},
|
| 540 |
{
|
| 541 |
"index": 12,
|
| 542 |
"filename": "shard_00012.bin",
|
| 543 |
"size": 67108864,
|
| 544 |
+
"hash": "ca573de37d2ae350dff4cc2ca0d017ba27115b2858f463214eeaae7525039ce6",
|
| 545 |
+
"blake3": "ca573de37d2ae350dff4cc2ca0d017ba27115b2858f463214eeaae7525039ce6",
|
| 546 |
"offset": 805306368
|
| 547 |
},
|
| 548 |
{
|
| 549 |
"index": 13,
|
| 550 |
"filename": "shard_00013.bin",
|
| 551 |
"size": 67108864,
|
| 552 |
+
"hash": "4abeed2a2cac6d819bce6f3333602f97d639dd806d7b4ca93cf2956286487a4a",
|
| 553 |
+
"blake3": "4abeed2a2cac6d819bce6f3333602f97d639dd806d7b4ca93cf2956286487a4a",
|
| 554 |
"offset": 872415232
|
| 555 |
},
|
| 556 |
{
|
| 557 |
"index": 14,
|
| 558 |
"filename": "shard_00014.bin",
|
| 559 |
"size": 67108864,
|
| 560 |
+
"hash": "59ed5c76c9a7320182d16c80db8469186e5bcc696c17397df498af7a42f53fdb",
|
| 561 |
+
"blake3": "59ed5c76c9a7320182d16c80db8469186e5bcc696c17397df498af7a42f53fdb",
|
| 562 |
"offset": 939524096
|
| 563 |
},
|
| 564 |
{
|
| 565 |
"index": 15,
|
| 566 |
"filename": "shard_00015.bin",
|
| 567 |
"size": 18860288,
|
| 568 |
+
"hash": "671b5387c2ba7ab7fb3dce7f90ee8e808bb42a6f21b5d809f26d39c3a2801d91",
|
| 569 |
+
"blake3": "671b5387c2ba7ab7fb3dce7f90ee8e808bb42a6f21b5d809f26d39c3a2801d91",
|
| 570 |
"offset": 1006632960
|
| 571 |
}
|
| 572 |
],
|
|
|
|
| 635 |
"shape": [
|
| 636 |
1152
|
| 637 |
],
|
| 638 |
+
"dtype": "F16",
|
| 639 |
"role": "norm",
|
| 640 |
"group": "layer.0"
|
| 641 |
},
|
|
|
|
| 685 |
"shape": [
|
| 686 |
1152
|
| 687 |
],
|
| 688 |
+
"dtype": "F16",
|
| 689 |
"role": "norm",
|
| 690 |
"group": "layer.0"
|
| 691 |
},
|
|
|
|
| 696 |
"shape": [
|
| 697 |
1152
|
| 698 |
],
|
| 699 |
+
"dtype": "F16",
|
| 700 |
"role": "norm",
|
| 701 |
"group": "layer.0"
|
| 702 |
},
|
|
|
|
| 707 |
"shape": [
|
| 708 |
1152
|
| 709 |
],
|
| 710 |
+
"dtype": "F16",
|
| 711 |
"role": "norm",
|
| 712 |
"group": "layer.0"
|
| 713 |
},
|
|
|
|
| 718 |
"shape": [
|
| 719 |
256
|
| 720 |
],
|
| 721 |
+
"dtype": "F16",
|
| 722 |
"role": "norm",
|
| 723 |
"group": "layer.0"
|
| 724 |
},
|
|
|
|
| 755 |
"shape": [
|
| 756 |
256
|
| 757 |
],
|
| 758 |
+
"dtype": "F16",
|
| 759 |
"role": "norm",
|
| 760 |
"group": "layer.0"
|
| 761 |
},
|
|
|
|
| 792 |
"shape": [
|
| 793 |
1152
|
| 794 |
],
|
| 795 |
+
"dtype": "F16",
|
| 796 |
"role": "norm",
|
| 797 |
"group": "layer.1"
|
| 798 |
},
|
|
|
|
| 842 |
"shape": [
|
| 843 |
1152
|
| 844 |
],
|
| 845 |
+
"dtype": "F16",
|
| 846 |
"role": "norm",
|
| 847 |
"group": "layer.1"
|
| 848 |
},
|
|
|
|
| 853 |
"shape": [
|
| 854 |
1152
|
| 855 |
],
|
| 856 |
+
"dtype": "F16",
|
| 857 |
"role": "norm",
|
| 858 |
"group": "layer.1"
|
| 859 |
},
|
|
|
|
| 864 |
"shape": [
|
| 865 |
1152
|
| 866 |
],
|
| 867 |
+
"dtype": "F16",
|
| 868 |
"role": "norm",
|
| 869 |
"group": "layer.1"
|
| 870 |
},
|
|
|
|
| 875 |
"shape": [
|
| 876 |
256
|
| 877 |
],
|
| 878 |
+
"dtype": "F16",
|
| 879 |
"role": "norm",
|
| 880 |
"group": "layer.1"
|
| 881 |
},
|
|
|
|
| 912 |
"shape": [
|
| 913 |
256
|
| 914 |
],
|
| 915 |
+
"dtype": "F16",
|
| 916 |
"role": "norm",
|
| 917 |
"group": "layer.1"
|
| 918 |
},
|
|
|
|
| 949 |
"shape": [
|
| 950 |
1152
|
| 951 |
],
|
| 952 |
+
"dtype": "F16",
|
| 953 |
"role": "norm",
|
| 954 |
"group": "layer.10"
|
| 955 |
},
|
|
|
|
| 999 |
"shape": [
|
| 1000 |
1152
|
| 1001 |
],
|
| 1002 |
+
"dtype": "F16",
|
| 1003 |
"role": "norm",
|
| 1004 |
"group": "layer.10"
|
| 1005 |
},
|
|
|
|
| 1010 |
"shape": [
|
| 1011 |
1152
|
| 1012 |
],
|
| 1013 |
+
"dtype": "F16",
|
| 1014 |
"role": "norm",
|
| 1015 |
"group": "layer.10"
|
| 1016 |
},
|
|
|
|
| 1021 |
"shape": [
|
| 1022 |
1152
|
| 1023 |
],
|
| 1024 |
+
"dtype": "F16",
|
| 1025 |
"role": "norm",
|
| 1026 |
"group": "layer.10"
|
| 1027 |
},
|
|
|
|
| 1032 |
"shape": [
|
| 1033 |
256
|
| 1034 |
],
|
| 1035 |
+
"dtype": "F16",
|
| 1036 |
"role": "norm",
|
| 1037 |
"group": "layer.10"
|
| 1038 |
},
|
|
|
|
| 1069 |
"shape": [
|
| 1070 |
256
|
| 1071 |
],
|
| 1072 |
+
"dtype": "F16",
|
| 1073 |
"role": "norm",
|
| 1074 |
"group": "layer.10"
|
| 1075 |
},
|
|
|
|
| 1106 |
"shape": [
|
| 1107 |
1152
|
| 1108 |
],
|
| 1109 |
+
"dtype": "F16",
|
| 1110 |
"role": "norm",
|
| 1111 |
"group": "layer.11"
|
| 1112 |
},
|
|
|
|
| 1156 |
"shape": [
|
| 1157 |
1152
|
| 1158 |
],
|
| 1159 |
+
"dtype": "F16",
|
| 1160 |
"role": "norm",
|
| 1161 |
"group": "layer.11"
|
| 1162 |
},
|
|
|
|
| 1167 |
"shape": [
|
| 1168 |
1152
|
| 1169 |
],
|
| 1170 |
+
"dtype": "F16",
|
| 1171 |
"role": "norm",
|
| 1172 |
"group": "layer.11"
|
| 1173 |
},
|
|
|
|
| 1178 |
"shape": [
|
| 1179 |
1152
|
| 1180 |
],
|
| 1181 |
+
"dtype": "F16",
|
| 1182 |
"role": "norm",
|
| 1183 |
"group": "layer.11"
|
| 1184 |
},
|
|
|
|
| 1189 |
"shape": [
|
| 1190 |
256
|
| 1191 |
],
|
| 1192 |
+
"dtype": "F16",
|
| 1193 |
"role": "norm",
|
| 1194 |
"group": "layer.11"
|
| 1195 |
},
|
|
|
|
| 1226 |
"shape": [
|
| 1227 |
256
|
| 1228 |
],
|
| 1229 |
+
"dtype": "F16",
|
| 1230 |
"role": "norm",
|
| 1231 |
"group": "layer.11"
|
| 1232 |
},
|
|
|
|
| 1263 |
"shape": [
|
| 1264 |
1152
|
| 1265 |
],
|
| 1266 |
+
"dtype": "F16",
|
| 1267 |
"role": "norm",
|
| 1268 |
"group": "layer.12"
|
| 1269 |
},
|
|
|
|
| 1323 |
"shape": [
|
| 1324 |
1152
|
| 1325 |
],
|
| 1326 |
+
"dtype": "F16",
|
| 1327 |
"role": "norm",
|
| 1328 |
"group": "layer.12"
|
| 1329 |
},
|
|
|
|
| 1334 |
"shape": [
|
| 1335 |
1152
|
| 1336 |
],
|
| 1337 |
+
"dtype": "F16",
|
| 1338 |
"role": "norm",
|
| 1339 |
"group": "layer.12"
|
| 1340 |
},
|
|
|
|
| 1345 |
"shape": [
|
| 1346 |
1152
|
| 1347 |
],
|
| 1348 |
+
"dtype": "F16",
|
| 1349 |
"role": "norm",
|
| 1350 |
"group": "layer.12"
|
| 1351 |
},
|
|
|
|
| 1356 |
"shape": [
|
| 1357 |
256
|
| 1358 |
],
|
| 1359 |
+
"dtype": "F16",
|
| 1360 |
"role": "norm",
|
| 1361 |
"group": "layer.12"
|
| 1362 |
},
|
|
|
|
| 1393 |
"shape": [
|
| 1394 |
256
|
| 1395 |
],
|
| 1396 |
+
"dtype": "F16",
|
| 1397 |
"role": "norm",
|
| 1398 |
"group": "layer.12"
|
| 1399 |
},
|
|
|
|
| 1430 |
"shape": [
|
| 1431 |
1152
|
| 1432 |
],
|
| 1433 |
+
"dtype": "F16",
|
| 1434 |
"role": "norm",
|
| 1435 |
"group": "layer.13"
|
| 1436 |
},
|
|
|
|
| 1480 |
"shape": [
|
| 1481 |
1152
|
| 1482 |
],
|
| 1483 |
+
"dtype": "F16",
|
| 1484 |
"role": "norm",
|
| 1485 |
"group": "layer.13"
|
| 1486 |
},
|
|
|
|
| 1491 |
"shape": [
|
| 1492 |
1152
|
| 1493 |
],
|
| 1494 |
+
"dtype": "F16",
|
| 1495 |
"role": "norm",
|
| 1496 |
"group": "layer.13"
|
| 1497 |
},
|
|
|
|
| 1502 |
"shape": [
|
| 1503 |
1152
|
| 1504 |
],
|
| 1505 |
+
"dtype": "F16",
|
| 1506 |
"role": "norm",
|
| 1507 |
"group": "layer.13"
|
| 1508 |
},
|
|
|
|
| 1513 |
"shape": [
|
| 1514 |
256
|
| 1515 |
],
|
| 1516 |
+
"dtype": "F16",
|
| 1517 |
"role": "norm",
|
| 1518 |
"group": "layer.13"
|
| 1519 |
},
|
|
|
|
| 1550 |
"shape": [
|
| 1551 |
256
|
| 1552 |
],
|
| 1553 |
+
"dtype": "F16",
|
| 1554 |
"role": "norm",
|
| 1555 |
"group": "layer.13"
|
| 1556 |
},
|
|
|
|
| 1587 |
"shape": [
|
| 1588 |
1152
|
| 1589 |
],
|
| 1590 |
+
"dtype": "F16",
|
| 1591 |
"role": "norm",
|
| 1592 |
"group": "layer.14"
|
| 1593 |
},
|
|
|
|
| 1637 |
"shape": [
|
| 1638 |
1152
|
| 1639 |
],
|
| 1640 |
+
"dtype": "F16",
|
| 1641 |
"role": "norm",
|
| 1642 |
"group": "layer.14"
|
| 1643 |
},
|
|
|
|
| 1648 |
"shape": [
|
| 1649 |
1152
|
| 1650 |
],
|
| 1651 |
+
"dtype": "F16",
|
| 1652 |
"role": "norm",
|
| 1653 |
"group": "layer.14"
|
| 1654 |
},
|
|
|
|
| 1659 |
"shape": [
|
| 1660 |
1152
|
| 1661 |
],
|
| 1662 |
+
"dtype": "F16",
|
| 1663 |
"role": "norm",
|
| 1664 |
"group": "layer.14"
|
| 1665 |
},
|
|
|
|
| 1670 |
"shape": [
|
| 1671 |
256
|
| 1672 |
],
|
| 1673 |
+
"dtype": "F16",
|
| 1674 |
"role": "norm",
|
| 1675 |
"group": "layer.14"
|
| 1676 |
},
|
|
|
|
| 1707 |
"shape": [
|
| 1708 |
256
|
| 1709 |
],
|
| 1710 |
+
"dtype": "F16",
|
| 1711 |
"role": "norm",
|
| 1712 |
"group": "layer.14"
|
| 1713 |
},
|
|
|
|
| 1744 |
"shape": [
|
| 1745 |
1152
|
| 1746 |
],
|
| 1747 |
+
"dtype": "F16",
|
| 1748 |
"role": "norm",
|
| 1749 |
"group": "layer.15"
|
| 1750 |
},
|
|
|
|
| 1794 |
"shape": [
|
| 1795 |
1152
|
| 1796 |
],
|
| 1797 |
+
"dtype": "F16",
|
| 1798 |
"role": "norm",
|
| 1799 |
"group": "layer.15"
|
| 1800 |
},
|
|
|
|
| 1805 |
"shape": [
|
| 1806 |
1152
|
| 1807 |
],
|
| 1808 |
+
"dtype": "F16",
|
| 1809 |
"role": "norm",
|
| 1810 |
"group": "layer.15"
|
| 1811 |
},
|
|
|
|
| 1816 |
"shape": [
|
| 1817 |
1152
|
| 1818 |
],
|
| 1819 |
+
"dtype": "F16",
|
| 1820 |
"role": "norm",
|
| 1821 |
"group": "layer.15"
|
| 1822 |
},
|
|
|
|
| 1827 |
"shape": [
|
| 1828 |
256
|
| 1829 |
],
|
| 1830 |
+
"dtype": "F16",
|
| 1831 |
"role": "norm",
|
| 1832 |
"group": "layer.15"
|
| 1833 |
},
|
|
|
|
| 1864 |
"shape": [
|
| 1865 |
256
|
| 1866 |
],
|
| 1867 |
+
"dtype": "F16",
|
| 1868 |
"role": "norm",
|
| 1869 |
"group": "layer.15"
|
| 1870 |
},
|
|
|
|
| 1901 |
"shape": [
|
| 1902 |
1152
|
| 1903 |
],
|
| 1904 |
+
"dtype": "F16",
|
| 1905 |
"role": "norm",
|
| 1906 |
"group": "layer.16"
|
| 1907 |
},
|
|
|
|
| 1961 |
"shape": [
|
| 1962 |
1152
|
| 1963 |
],
|
| 1964 |
+
"dtype": "F16",
|
| 1965 |
"role": "norm",
|
| 1966 |
"group": "layer.16"
|
| 1967 |
},
|
|
|
|
| 1972 |
"shape": [
|
| 1973 |
1152
|
| 1974 |
],
|
| 1975 |
+
"dtype": "F16",
|
| 1976 |
"role": "norm",
|
| 1977 |
"group": "layer.16"
|
| 1978 |
},
|
|
|
|
| 1983 |
"shape": [
|
| 1984 |
1152
|
| 1985 |
],
|
| 1986 |
+
"dtype": "F16",
|
| 1987 |
"role": "norm",
|
| 1988 |
"group": "layer.16"
|
| 1989 |
},
|
|
|
|
| 1994 |
"shape": [
|
| 1995 |
256
|
| 1996 |
],
|
| 1997 |
+
"dtype": "F16",
|
| 1998 |
"role": "norm",
|
| 1999 |
"group": "layer.16"
|
| 2000 |
},
|
|
|
|
| 2031 |
"shape": [
|
| 2032 |
256
|
| 2033 |
],
|
| 2034 |
+
"dtype": "F16",
|
| 2035 |
"role": "norm",
|
| 2036 |
"group": "layer.16"
|
| 2037 |
},
|
|
|
|
| 2068 |
"shape": [
|
| 2069 |
1152
|
| 2070 |
],
|
| 2071 |
+
"dtype": "F16",
|
| 2072 |
"role": "norm",
|
| 2073 |
"group": "layer.17"
|
| 2074 |
},
|
|
|
|
| 2118 |
"shape": [
|
| 2119 |
1152
|
| 2120 |
],
|
| 2121 |
+
"dtype": "F16",
|
| 2122 |
"role": "norm",
|
| 2123 |
"group": "layer.17"
|
| 2124 |
},
|
|
|
|
| 2129 |
"shape": [
|
| 2130 |
1152
|
| 2131 |
],
|
| 2132 |
+
"dtype": "F16",
|
| 2133 |
"role": "norm",
|
| 2134 |
"group": "layer.17"
|
| 2135 |
},
|
|
|
|
| 2140 |
"shape": [
|
| 2141 |
1152
|
| 2142 |
],
|
| 2143 |
+
"dtype": "F16",
|
| 2144 |
"role": "norm",
|
| 2145 |
"group": "layer.17"
|
| 2146 |
},
|
|
|
|
| 2151 |
"shape": [
|
| 2152 |
256
|
| 2153 |
],
|
| 2154 |
+
"dtype": "F16",
|
| 2155 |
"role": "norm",
|
| 2156 |
"group": "layer.17"
|
| 2157 |
},
|
|
|
|
| 2188 |
"shape": [
|
| 2189 |
256
|
| 2190 |
],
|
| 2191 |
+
"dtype": "F16",
|
| 2192 |
"role": "norm",
|
| 2193 |
"group": "layer.17"
|
| 2194 |
},
|
|
|
|
| 2225 |
"shape": [
|
| 2226 |
1152
|
| 2227 |
],
|
| 2228 |
+
"dtype": "F16",
|
| 2229 |
"role": "norm",
|
| 2230 |
"group": "layer.18"
|
| 2231 |
},
|
|
|
|
| 2275 |
"shape": [
|
| 2276 |
1152
|
| 2277 |
],
|
| 2278 |
+
"dtype": "F16",
|
| 2279 |
"role": "norm",
|
| 2280 |
"group": "layer.18"
|
| 2281 |
},
|
|
|
|
| 2286 |
"shape": [
|
| 2287 |
1152
|
| 2288 |
],
|
| 2289 |
+
"dtype": "F16",
|
| 2290 |
"role": "norm",
|
| 2291 |
"group": "layer.18"
|
| 2292 |
},
|
|
|
|
| 2297 |
"shape": [
|
| 2298 |
1152
|
| 2299 |
],
|
| 2300 |
+
"dtype": "F16",
|
| 2301 |
"role": "norm",
|
| 2302 |
"group": "layer.18"
|
| 2303 |
},
|
|
|
|
| 2308 |
"shape": [
|
| 2309 |
256
|
| 2310 |
],
|
| 2311 |
+
"dtype": "F16",
|
| 2312 |
"role": "norm",
|
| 2313 |
"group": "layer.18"
|
| 2314 |
},
|
|
|
|
| 2345 |
"shape": [
|
| 2346 |
256
|
| 2347 |
],
|
| 2348 |
+
"dtype": "F16",
|
| 2349 |
"role": "norm",
|
| 2350 |
"group": "layer.18"
|
| 2351 |
},
|
|
|
|
| 2382 |
"shape": [
|
| 2383 |
1152
|
| 2384 |
],
|
| 2385 |
+
"dtype": "F16",
|
| 2386 |
"role": "norm",
|
| 2387 |
"group": "layer.19"
|
| 2388 |
},
|
|
|
|
| 2432 |
"shape": [
|
| 2433 |
1152
|
| 2434 |
],
|
| 2435 |
+
"dtype": "F16",
|
| 2436 |
"role": "norm",
|
| 2437 |
"group": "layer.19"
|
| 2438 |
},
|
|
|
|
| 2443 |
"shape": [
|
| 2444 |
1152
|
| 2445 |
],
|
| 2446 |
+
"dtype": "F16",
|
| 2447 |
"role": "norm",
|
| 2448 |
"group": "layer.19"
|
| 2449 |
},
|
|
|
|
| 2454 |
"shape": [
|
| 2455 |
1152
|
| 2456 |
],
|
| 2457 |
+
"dtype": "F16",
|
| 2458 |
"role": "norm",
|
| 2459 |
"group": "layer.19"
|
| 2460 |
},
|
|
|
|
| 2465 |
"shape": [
|
| 2466 |
256
|
| 2467 |
],
|
| 2468 |
+
"dtype": "F16",
|
| 2469 |
"role": "norm",
|
| 2470 |
"group": "layer.19"
|
| 2471 |
},
|
|
|
|
| 2502 |
"shape": [
|
| 2503 |
256
|
| 2504 |
],
|
| 2505 |
+
"dtype": "F16",
|
| 2506 |
"role": "norm",
|
| 2507 |
"group": "layer.19"
|
| 2508 |
},
|
|
|
|
| 2539 |
"shape": [
|
| 2540 |
1152
|
| 2541 |
],
|
| 2542 |
+
"dtype": "F16",
|
| 2543 |
"role": "norm",
|
| 2544 |
"group": "layer.2"
|
| 2545 |
},
|
|
|
|
| 2599 |
"shape": [
|
| 2600 |
1152
|
| 2601 |
],
|
| 2602 |
+
"dtype": "F16",
|
| 2603 |
"role": "norm",
|
| 2604 |
"group": "layer.2"
|
| 2605 |
},
|
|
|
|
| 2610 |
"shape": [
|
| 2611 |
1152
|
| 2612 |
],
|
| 2613 |
+
"dtype": "F16",
|
| 2614 |
"role": "norm",
|
| 2615 |
"group": "layer.2"
|
| 2616 |
},
|
|
|
|
| 2621 |
"shape": [
|
| 2622 |
1152
|
| 2623 |
],
|
| 2624 |
+
"dtype": "F16",
|
| 2625 |
"role": "norm",
|
| 2626 |
"group": "layer.2"
|
| 2627 |
},
|
|
|
|
| 2632 |
"shape": [
|
| 2633 |
256
|
| 2634 |
],
|
| 2635 |
+
"dtype": "F16",
|
| 2636 |
"role": "norm",
|
| 2637 |
"group": "layer.2"
|
| 2638 |
},
|
|
|
|
| 2669 |
"shape": [
|
| 2670 |
256
|
| 2671 |
],
|
| 2672 |
+
"dtype": "F16",
|
| 2673 |
"role": "norm",
|
| 2674 |
"group": "layer.2"
|
| 2675 |
},
|
|
|
|
| 2706 |
"shape": [
|
| 2707 |
1152
|
| 2708 |
],
|
| 2709 |
+
"dtype": "F16",
|
| 2710 |
"role": "norm",
|
| 2711 |
"group": "layer.20"
|
| 2712 |
},
|
|
|
|
| 2756 |
"shape": [
|
| 2757 |
1152
|
| 2758 |
],
|
| 2759 |
+
"dtype": "F16",
|
| 2760 |
"role": "norm",
|
| 2761 |
"group": "layer.20"
|
| 2762 |
},
|
|
|
|
| 2767 |
"shape": [
|
| 2768 |
1152
|
| 2769 |
],
|
| 2770 |
+
"dtype": "F16",
|
| 2771 |
"role": "norm",
|
| 2772 |
"group": "layer.20"
|
| 2773 |
},
|
|
|
|
| 2778 |
"shape": [
|
| 2779 |
1152
|
| 2780 |
],
|
| 2781 |
+
"dtype": "F16",
|
| 2782 |
"role": "norm",
|
| 2783 |
"group": "layer.20"
|
| 2784 |
},
|
|
|
|
| 2789 |
"shape": [
|
| 2790 |
256
|
| 2791 |
],
|
| 2792 |
+
"dtype": "F16",
|
| 2793 |
"role": "norm",
|
| 2794 |
"group": "layer.20"
|
| 2795 |
},
|
|
|
|
| 2826 |
"shape": [
|
| 2827 |
256
|
| 2828 |
],
|
| 2829 |
+
"dtype": "F16",
|
| 2830 |
"role": "norm",
|
| 2831 |
"group": "layer.20"
|
| 2832 |
},
|
|
|
|
| 2863 |
"shape": [
|
| 2864 |
1152
|
| 2865 |
],
|
| 2866 |
+
"dtype": "F16",
|
| 2867 |
"role": "norm",
|
| 2868 |
"group": "layer.21"
|
| 2869 |
},
|
|
|
|
| 2913 |
"shape": [
|
| 2914 |
1152
|
| 2915 |
],
|
| 2916 |
+
"dtype": "F16",
|
| 2917 |
"role": "norm",
|
| 2918 |
"group": "layer.21"
|
| 2919 |
},
|
|
|
|
| 2924 |
"shape": [
|
| 2925 |
1152
|
| 2926 |
],
|
| 2927 |
+
"dtype": "F16",
|
| 2928 |
"role": "norm",
|
| 2929 |
"group": "layer.21"
|
| 2930 |
},
|
|
|
|
| 2935 |
"shape": [
|
| 2936 |
1152
|
| 2937 |
],
|
| 2938 |
+
"dtype": "F16",
|
| 2939 |
"role": "norm",
|
| 2940 |
"group": "layer.21"
|
| 2941 |
},
|
|
|
|
| 2946 |
"shape": [
|
| 2947 |
256
|
| 2948 |
],
|
| 2949 |
+
"dtype": "F16",
|
| 2950 |
"role": "norm",
|
| 2951 |
"group": "layer.21"
|
| 2952 |
},
|
|
|
|
| 2983 |
"shape": [
|
| 2984 |
256
|
| 2985 |
],
|
| 2986 |
+
"dtype": "F16",
|
| 2987 |
"role": "norm",
|
| 2988 |
"group": "layer.21"
|
| 2989 |
},
|
|
|
|
| 3020 |
"shape": [
|
| 3021 |
1152
|
| 3022 |
],
|
| 3023 |
+
"dtype": "F16",
|
| 3024 |
"role": "norm",
|
| 3025 |
"group": "layer.22"
|
| 3026 |
},
|
|
|
|
| 3070 |
"shape": [
|
| 3071 |
1152
|
| 3072 |
],
|
| 3073 |
+
"dtype": "F16",
|
| 3074 |
"role": "norm",
|
| 3075 |
"group": "layer.22"
|
| 3076 |
},
|
|
|
|
| 3081 |
"shape": [
|
| 3082 |
1152
|
| 3083 |
],
|
| 3084 |
+
"dtype": "F16",
|
| 3085 |
"role": "norm",
|
| 3086 |
"group": "layer.22"
|
| 3087 |
},
|
|
|
|
| 3092 |
"shape": [
|
| 3093 |
1152
|
| 3094 |
],
|
| 3095 |
+
"dtype": "F16",
|
| 3096 |
"role": "norm",
|
| 3097 |
"group": "layer.22"
|
| 3098 |
},
|
|
|
|
| 3103 |
"shape": [
|
| 3104 |
256
|
| 3105 |
],
|
| 3106 |
+
"dtype": "F16",
|
| 3107 |
"role": "norm",
|
| 3108 |
"group": "layer.22"
|
| 3109 |
},
|
|
|
|
| 3140 |
"shape": [
|
| 3141 |
256
|
| 3142 |
],
|
| 3143 |
+
"dtype": "F16",
|
| 3144 |
"role": "norm",
|
| 3145 |
"group": "layer.22"
|
| 3146 |
},
|
|
|
|
| 3177 |
"shape": [
|
| 3178 |
1152
|
| 3179 |
],
|
| 3180 |
+
"dtype": "F16",
|
| 3181 |
"role": "norm",
|
| 3182 |
"group": "layer.23"
|
| 3183 |
},
|
|
|
|
| 3237 |
"shape": [
|
| 3238 |
1152
|
| 3239 |
],
|
| 3240 |
+
"dtype": "F16",
|
| 3241 |
"role": "norm",
|
| 3242 |
"group": "layer.23"
|
| 3243 |
},
|
|
|
|
| 3248 |
"shape": [
|
| 3249 |
1152
|
| 3250 |
],
|
| 3251 |
+
"dtype": "F16",
|
| 3252 |
"role": "norm",
|
| 3253 |
"group": "layer.23"
|
| 3254 |
},
|
|
|
|
| 3259 |
"shape": [
|
| 3260 |
1152
|
| 3261 |
],
|
| 3262 |
+
"dtype": "F16",
|
| 3263 |
"role": "norm",
|
| 3264 |
"group": "layer.23"
|
| 3265 |
},
|
|
|
|
| 3270 |
"shape": [
|
| 3271 |
256
|
| 3272 |
],
|
| 3273 |
+
"dtype": "F16",
|
| 3274 |
"role": "norm",
|
| 3275 |
"group": "layer.23"
|
| 3276 |
},
|
|
|
|
| 3307 |
"shape": [
|
| 3308 |
256
|
| 3309 |
],
|
| 3310 |
+
"dtype": "F16",
|
| 3311 |
"role": "norm",
|
| 3312 |
"group": "layer.23"
|
| 3313 |
},
|
|
|
|
| 3344 |
"shape": [
|
| 3345 |
1152
|
| 3346 |
],
|
| 3347 |
+
"dtype": "F16",
|
| 3348 |
"role": "norm",
|
| 3349 |
"group": "layer.24"
|
| 3350 |
},
|
|
|
|
| 3394 |
"shape": [
|
| 3395 |
1152
|
| 3396 |
],
|
| 3397 |
+
"dtype": "F16",
|
| 3398 |
"role": "norm",
|
| 3399 |
"group": "layer.24"
|
| 3400 |
},
|
|
|
|
| 3405 |
"shape": [
|
| 3406 |
1152
|
| 3407 |
],
|
| 3408 |
+
"dtype": "F16",
|
| 3409 |
"role": "norm",
|
| 3410 |
"group": "layer.24"
|
| 3411 |
},
|
|
|
|
| 3416 |
"shape": [
|
| 3417 |
1152
|
| 3418 |
],
|
| 3419 |
+
"dtype": "F16",
|
| 3420 |
"role": "norm",
|
| 3421 |
"group": "layer.24"
|
| 3422 |
},
|
|
|
|
| 3427 |
"shape": [
|
| 3428 |
256
|
| 3429 |
],
|
| 3430 |
+
"dtype": "F16",
|
| 3431 |
"role": "norm",
|
| 3432 |
"group": "layer.24"
|
| 3433 |
},
|
|
|
|
| 3464 |
"shape": [
|
| 3465 |
256
|
| 3466 |
],
|
| 3467 |
+
"dtype": "F16",
|
| 3468 |
"role": "norm",
|
| 3469 |
"group": "layer.24"
|
| 3470 |
},
|
|
|
|
| 3501 |
"shape": [
|
| 3502 |
1152
|
| 3503 |
],
|
| 3504 |
+
"dtype": "F16",
|
| 3505 |
"role": "norm",
|
| 3506 |
"group": "layer.25"
|
| 3507 |
},
|
|
|
|
| 3551 |
"shape": [
|
| 3552 |
1152
|
| 3553 |
],
|
| 3554 |
+
"dtype": "F16",
|
| 3555 |
"role": "norm",
|
| 3556 |
"group": "layer.25"
|
| 3557 |
},
|
|
|
|
| 3562 |
"shape": [
|
| 3563 |
1152
|
| 3564 |
],
|
| 3565 |
+
"dtype": "F16",
|
| 3566 |
"role": "norm",
|
| 3567 |
"group": "layer.25"
|
| 3568 |
},
|
|
|
|
| 3573 |
"shape": [
|
| 3574 |
1152
|
| 3575 |
],
|
| 3576 |
+
"dtype": "F16",
|
| 3577 |
"role": "norm",
|
| 3578 |
"group": "layer.25"
|
| 3579 |
},
|
|
|
|
| 3584 |
"shape": [
|
| 3585 |
256
|
| 3586 |
],
|
| 3587 |
+
"dtype": "F16",
|
| 3588 |
"role": "norm",
|
| 3589 |
"group": "layer.25"
|
| 3590 |
},
|
|
|
|
| 3621 |
"shape": [
|
| 3622 |
256
|
| 3623 |
],
|
| 3624 |
+
"dtype": "F16",
|
| 3625 |
"role": "norm",
|
| 3626 |
"group": "layer.25"
|
| 3627 |
},
|
|
|
|
| 3658 |
"shape": [
|
| 3659 |
1152
|
| 3660 |
],
|
| 3661 |
+
"dtype": "F16",
|
| 3662 |
"role": "norm",
|
| 3663 |
"group": "layer.3"
|
| 3664 |
},
|
|
|
|
| 3708 |
"shape": [
|
| 3709 |
1152
|
| 3710 |
],
|
| 3711 |
+
"dtype": "F16",
|
| 3712 |
"role": "norm",
|
| 3713 |
"group": "layer.3"
|
| 3714 |
},
|
|
|
|
| 3719 |
"shape": [
|
| 3720 |
1152
|
| 3721 |
],
|
| 3722 |
+
"dtype": "F16",
|
| 3723 |
"role": "norm",
|
| 3724 |
"group": "layer.3"
|
| 3725 |
},
|
|
|
|
| 3730 |
"shape": [
|
| 3731 |
1152
|
| 3732 |
],
|
| 3733 |
+
"dtype": "F16",
|
| 3734 |
"role": "norm",
|
| 3735 |
"group": "layer.3"
|
| 3736 |
},
|
|
|
|
| 3741 |
"shape": [
|
| 3742 |
256
|
| 3743 |
],
|
| 3744 |
+
"dtype": "F16",
|
| 3745 |
"role": "norm",
|
| 3746 |
"group": "layer.3"
|
| 3747 |
},
|
|
|
|
| 3778 |
"shape": [
|
| 3779 |
256
|
| 3780 |
],
|
| 3781 |
+
"dtype": "F16",
|
| 3782 |
"role": "norm",
|
| 3783 |
"group": "layer.3"
|
| 3784 |
},
|
|
|
|
| 3815 |
"shape": [
|
| 3816 |
1152
|
| 3817 |
],
|
| 3818 |
+
"dtype": "F16",
|
| 3819 |
"role": "norm",
|
| 3820 |
"group": "layer.4"
|
| 3821 |
},
|
|
|
|
| 3875 |
"shape": [
|
| 3876 |
1152
|
| 3877 |
],
|
| 3878 |
+
"dtype": "F16",
|
| 3879 |
"role": "norm",
|
| 3880 |
"group": "layer.4"
|
| 3881 |
},
|
|
|
|
| 3886 |
"shape": [
|
| 3887 |
1152
|
| 3888 |
],
|
| 3889 |
+
"dtype": "F16",
|
| 3890 |
"role": "norm",
|
| 3891 |
"group": "layer.4"
|
| 3892 |
},
|
|
|
|
| 3897 |
"shape": [
|
| 3898 |
1152
|
| 3899 |
],
|
| 3900 |
+
"dtype": "F16",
|
| 3901 |
"role": "norm",
|
| 3902 |
"group": "layer.4"
|
| 3903 |
},
|
|
|
|
| 3908 |
"shape": [
|
| 3909 |
256
|
| 3910 |
],
|
| 3911 |
+
"dtype": "F16",
|
| 3912 |
"role": "norm",
|
| 3913 |
"group": "layer.4"
|
| 3914 |
},
|
|
|
|
| 3945 |
"shape": [
|
| 3946 |
256
|
| 3947 |
],
|
| 3948 |
+
"dtype": "F16",
|
| 3949 |
"role": "norm",
|
| 3950 |
"group": "layer.4"
|
| 3951 |
},
|
|
|
|
| 3982 |
"shape": [
|
| 3983 |
1152
|
| 3984 |
],
|
| 3985 |
+
"dtype": "F16",
|
| 3986 |
"role": "norm",
|
| 3987 |
"group": "layer.5"
|
| 3988 |
},
|
|
|
|
| 4032 |
"shape": [
|
| 4033 |
1152
|
| 4034 |
],
|
| 4035 |
+
"dtype": "F16",
|
| 4036 |
"role": "norm",
|
| 4037 |
"group": "layer.5"
|
| 4038 |
},
|
|
|
|
| 4043 |
"shape": [
|
| 4044 |
1152
|
| 4045 |
],
|
| 4046 |
+
"dtype": "F16",
|
| 4047 |
"role": "norm",
|
| 4048 |
"group": "layer.5"
|
| 4049 |
},
|
|
|
|
| 4054 |
"shape": [
|
| 4055 |
1152
|
| 4056 |
],
|
| 4057 |
+
"dtype": "F16",
|
| 4058 |
"role": "norm",
|
| 4059 |
"group": "layer.5"
|
| 4060 |
},
|
|
|
|
| 4065 |
"shape": [
|
| 4066 |
256
|
| 4067 |
],
|
| 4068 |
+
"dtype": "F16",
|
| 4069 |
"role": "norm",
|
| 4070 |
"group": "layer.5"
|
| 4071 |
},
|
|
|
|
| 4102 |
"shape": [
|
| 4103 |
256
|
| 4104 |
],
|
| 4105 |
+
"dtype": "F16",
|
| 4106 |
"role": "norm",
|
| 4107 |
"group": "layer.5"
|
| 4108 |
},
|
|
|
|
| 4139 |
"shape": [
|
| 4140 |
1152
|
| 4141 |
],
|
| 4142 |
+
"dtype": "F16",
|
| 4143 |
"role": "norm",
|
| 4144 |
"group": "layer.6"
|
| 4145 |
},
|
|
|
|
| 4189 |
"shape": [
|
| 4190 |
1152
|
| 4191 |
],
|
| 4192 |
+
"dtype": "F16",
|
| 4193 |
"role": "norm",
|
| 4194 |
"group": "layer.6"
|
| 4195 |
},
|
|
|
|
| 4200 |
"shape": [
|
| 4201 |
1152
|
| 4202 |
],
|
| 4203 |
+
"dtype": "F16",
|
| 4204 |
"role": "norm",
|
| 4205 |
"group": "layer.6"
|
| 4206 |
},
|
|
|
|
| 4211 |
"shape": [
|
| 4212 |
1152
|
| 4213 |
],
|
| 4214 |
+
"dtype": "F16",
|
| 4215 |
"role": "norm",
|
| 4216 |
"group": "layer.6"
|
| 4217 |
},
|
|
|
|
| 4222 |
"shape": [
|
| 4223 |
256
|
| 4224 |
],
|
| 4225 |
+
"dtype": "F16",
|
| 4226 |
"role": "norm",
|
| 4227 |
"group": "layer.6"
|
| 4228 |
},
|
|
|
|
| 4259 |
"shape": [
|
| 4260 |
256
|
| 4261 |
],
|
| 4262 |
+
"dtype": "F16",
|
| 4263 |
"role": "norm",
|
| 4264 |
"group": "layer.6"
|
| 4265 |
},
|
|
|
|
| 4296 |
"shape": [
|
| 4297 |
1152
|
| 4298 |
],
|
| 4299 |
+
"dtype": "F16",
|
| 4300 |
"role": "norm",
|
| 4301 |
"group": "layer.7"
|
| 4302 |
},
|
|
|
|
| 4346 |
"shape": [
|
| 4347 |
1152
|
| 4348 |
],
|
| 4349 |
+
"dtype": "F16",
|
| 4350 |
"role": "norm",
|
| 4351 |
"group": "layer.7"
|
| 4352 |
},
|
|
|
|
| 4357 |
"shape": [
|
| 4358 |
1152
|
| 4359 |
],
|
| 4360 |
+
"dtype": "F16",
|
| 4361 |
"role": "norm",
|
| 4362 |
"group": "layer.7"
|
| 4363 |
},
|
|
|
|
| 4368 |
"shape": [
|
| 4369 |
1152
|
| 4370 |
],
|
| 4371 |
+
"dtype": "F16",
|
| 4372 |
"role": "norm",
|
| 4373 |
"group": "layer.7"
|
| 4374 |
},
|
|
|
|
| 4379 |
"shape": [
|
| 4380 |
256
|
| 4381 |
],
|
| 4382 |
+
"dtype": "F16",
|
| 4383 |
"role": "norm",
|
| 4384 |
"group": "layer.7"
|
| 4385 |
},
|
|
|
|
| 4416 |
"shape": [
|
| 4417 |
256
|
| 4418 |
],
|
| 4419 |
+
"dtype": "F16",
|
| 4420 |
"role": "norm",
|
| 4421 |
"group": "layer.7"
|
| 4422 |
},
|
|
|
|
| 4453 |
"shape": [
|
| 4454 |
1152
|
| 4455 |
],
|
| 4456 |
+
"dtype": "F16",
|
| 4457 |
"role": "norm",
|
| 4458 |
"group": "layer.8"
|
| 4459 |
},
|
|
|
|
| 4513 |
"shape": [
|
| 4514 |
1152
|
| 4515 |
],
|
| 4516 |
+
"dtype": "F16",
|
| 4517 |
"role": "norm",
|
| 4518 |
"group": "layer.8"
|
| 4519 |
},
|
|
|
|
| 4524 |
"shape": [
|
| 4525 |
1152
|
| 4526 |
],
|
| 4527 |
+
"dtype": "F16",
|
| 4528 |
"role": "norm",
|
| 4529 |
"group": "layer.8"
|
| 4530 |
},
|
|
|
|
| 4535 |
"shape": [
|
| 4536 |
1152
|
| 4537 |
],
|
| 4538 |
+
"dtype": "F16",
|
| 4539 |
"role": "norm",
|
| 4540 |
"group": "layer.8"
|
| 4541 |
},
|
|
|
|
| 4546 |
"shape": [
|
| 4547 |
256
|
| 4548 |
],
|
| 4549 |
+
"dtype": "F16",
|
| 4550 |
"role": "norm",
|
| 4551 |
"group": "layer.8"
|
| 4552 |
},
|
|
|
|
| 4583 |
"shape": [
|
| 4584 |
256
|
| 4585 |
],
|
| 4586 |
+
"dtype": "F16",
|
| 4587 |
"role": "norm",
|
| 4588 |
"group": "layer.8"
|
| 4589 |
},
|
|
|
|
| 4620 |
"shape": [
|
| 4621 |
1152
|
| 4622 |
],
|
| 4623 |
+
"dtype": "F16",
|
| 4624 |
"role": "norm",
|
| 4625 |
"group": "layer.9"
|
| 4626 |
},
|
|
|
|
| 4670 |
"shape": [
|
| 4671 |
1152
|
| 4672 |
],
|
| 4673 |
+
"dtype": "F16",
|
| 4674 |
"role": "norm",
|
| 4675 |
"group": "layer.9"
|
| 4676 |
},
|
|
|
|
| 4681 |
"shape": [
|
| 4682 |
1152
|
| 4683 |
],
|
| 4684 |
+
"dtype": "F16",
|
| 4685 |
"role": "norm",
|
| 4686 |
"group": "layer.9"
|
| 4687 |
},
|
|
|
|
| 4692 |
"shape": [
|
| 4693 |
1152
|
| 4694 |
],
|
| 4695 |
+
"dtype": "F16",
|
| 4696 |
"role": "norm",
|
| 4697 |
"group": "layer.9"
|
| 4698 |
},
|
|
|
|
| 4703 |
"shape": [
|
| 4704 |
256
|
| 4705 |
],
|
| 4706 |
+
"dtype": "F16",
|
| 4707 |
"role": "norm",
|
| 4708 |
"group": "layer.9"
|
| 4709 |
},
|
|
|
|
| 4740 |
"shape": [
|
| 4741 |
256
|
| 4742 |
],
|
| 4743 |
+
"dtype": "F16",
|
| 4744 |
"role": "norm",
|
| 4745 |
"group": "layer.9"
|
| 4746 |
},
|
|
|
|
| 4777 |
"shape": [
|
| 4778 |
1152
|
| 4779 |
],
|
| 4780 |
+
"dtype": "F16",
|
| 4781 |
"role": "norm",
|
| 4782 |
"group": "head"
|
| 4783 |
}
|
|
|
|
| 4788 |
1,
|
| 4789 |
106
|
| 4790 |
],
|
| 4791 |
+
"conversion": null,
|
| 4792 |
"metadata": {
|
| 4793 |
+
"source": "clocksmith/gamma-translategemma-4b-1b-enes-nativekd2@sha256:c567331d8eb9d3da65205b83f4e0af06568c47ba81a7927005c1c2e72444bc87",
|
| 4794 |
+
"convertedAt": "2026-07-11T00:54:07.571Z",
|
| 4795 |
"hasTokenizer": true,
|
| 4796 |
"manifestRefresh": {
|
| 4797 |
+
"at": "2026-07-11T11:41:37.184Z",
|
| 4798 |
"config": "translategemma-4b-1b-enes-q4k-ehf16-af32.json"
|
| 4799 |
}
|
| 4800 |
},
|
| 4801 |
"tokenizer": {
|
| 4802 |
"type": "bundled",
|
| 4803 |
"vocabSize": 262144,
|
| 4804 |
+
"file": "tokenizer.json",
|
| 4805 |
+
"addBosToken": true,
|
| 4806 |
+
"addEosToken": false
|
| 4807 |
+
},
|
| 4808 |
+
"integrityExtensions": {
|
| 4809 |
+
"contractVersion": 1,
|
| 4810 |
+
"blockMerkle": {
|
| 4811 |
+
"blockSize": 1048576,
|
| 4812 |
+
"roots": {
|
| 4813 |
+
"model.embed_tokens.weight": "sha256:a7a3f6eedcb5a10dc20b341e4bc5c1dc30aceeaf078fafced56c0cd7365a0334",
|
| 4814 |
+
"model.layers.0.input_layernorm.weight": "sha256:af48f1517372a26b9d6325f0a7aea1ae05dd27f3957eda247a18bec5c8822e42",
|
| 4815 |
+
"model.layers.0.mlp.down_proj.weight": "sha256:bd7ec01eac8befe4952e82c093c3de27c77b53b88b5af04bed0eeebe3d009254",
|
| 4816 |
+
"model.layers.0.mlp.gate_proj.weight": "sha256:0826bac62bc030d5b8c7bdbe2702ed5c3859385a0e4b401ba83fc9d48fd7c6f9",
|
| 4817 |
+
"model.layers.0.mlp.up_proj.weight": "sha256:a42f36601a2b4f4c3e789682e39c748a4091399eb83ee1e6215c30e9d48146fd",
|
| 4818 |
+
"model.layers.0.post_attention_layernorm.weight": "sha256:ca47820fa2f346c8b04f19e898c663caaa2ba888dd7faf8dac70fc0a87defde7",
|
| 4819 |
+
"model.layers.0.post_feedforward_layernorm.weight": "sha256:4f58f4c268707c279d4c3b8c1d036dcf719ad87334ee1ba222bc013fa60fec98",
|
| 4820 |
+
"model.layers.0.pre_feedforward_layernorm.weight": "sha256:0e2755b97f53c4dae279c241a1a4b16e6aa281c6e8de6deaa529c5eeddf0bc7b",
|
| 4821 |
+
"model.layers.0.self_attn.k_norm.weight": "sha256:902cb606124614af6542f916daf9b4231df26c8e4b38ce284d7ff99d675a10c0",
|
| 4822 |
+
"model.layers.0.self_attn.k_proj.weight": "sha256:d565d5e7c48f9563ecad51e0af8acf5ba2bc61aad1fd2c3f96df12cd1856a47b",
|
| 4823 |
+
"model.layers.0.self_attn.o_proj.weight": "sha256:66508e9a97bebf2d9900d5ebfedf18890c2925f0abd35873233bf42adabadab6",
|
| 4824 |
+
"model.layers.0.self_attn.q_norm.weight": "sha256:70a57a2678585da22ef62da13902d0d61f7c6ed78434325dce2883a50d05c92b",
|
| 4825 |
+
"model.layers.0.self_attn.q_proj.weight": "sha256:740ae3ab0c77df9fab43fcd58bc7f97240c2ef78361c1afd33889d6794d544b1",
|
| 4826 |
+
"model.layers.0.self_attn.v_proj.weight": "sha256:da2cecf767b0ced3c293838346f400d713b713d5e3dbb1184afcc11cfeed6c11",
|
| 4827 |
+
"model.layers.1.input_layernorm.weight": "sha256:bb1691c924027763d2f7bafce250e5e08b5a4ad0eb4e58b09cd13c7c2eea2106",
|
| 4828 |
+
"model.layers.1.mlp.down_proj.weight": "sha256:00c6d23607af82be5c46f546469f6ee59d74897e1e1918d2bfc9deb4264bf271",
|
| 4829 |
+
"model.layers.1.mlp.gate_proj.weight": "sha256:d9e276bb3851076f35d388a957ce77f52eedfe684489ee14ac7d7abd1b2734c4",
|
| 4830 |
+
"model.layers.1.mlp.up_proj.weight": "sha256:112c03312616a725a48962e918c90158f3422be2a650ff8ff3a69a3d0d9f3ff3",
|
| 4831 |
+
"model.layers.1.post_attention_layernorm.weight": "sha256:1f2b5b993da30b442100a1bdb130f5c00e165f8f8282b47b93d5ee6348cdd321",
|
| 4832 |
+
"model.layers.1.post_feedforward_layernorm.weight": "sha256:bb623c94ac6f8577c105b613ad9177c84dd8067e6b64c0f5e0826c497975eede",
|
| 4833 |
+
"model.layers.1.pre_feedforward_layernorm.weight": "sha256:8de386419e6b9865039667499e8b349fd4124a35ef14e774fbcc39fb8f1f5064",
|
| 4834 |
+
"model.layers.1.self_attn.k_norm.weight": "sha256:548f1ed3d52555c00c0a8468e4bf81d993d32fa9efc056df5fa1fe98c2893cea",
|
| 4835 |
+
"model.layers.1.self_attn.k_proj.weight": "sha256:6c45483624ea96d681573e58ebfc302543abe2c2895a41573c32deb4679be25b",
|
| 4836 |
+
"model.layers.1.self_attn.o_proj.weight": "sha256:c5bbdb1389a2a1268f8e0272e45bd12239de474f77b08f60e2e70ac37aa6509c",
|
| 4837 |
+
"model.layers.1.self_attn.q_norm.weight": "sha256:a4a6e0e620159c7e7014c723b3f95078eabb1b256be22a339b65f4a0ad634942",
|
| 4838 |
+
"model.layers.1.self_attn.q_proj.weight": "sha256:ce820d201d9dfd691336a58aae76248413e47ec30c87a61e6a0d326d610e45ce",
|
| 4839 |
+
"model.layers.1.self_attn.v_proj.weight": "sha256:9729c399361480cd3ed35d105eee659730e593c70743c306591d007f6a5beb1c",
|
| 4840 |
+
"model.layers.10.input_layernorm.weight": "sha256:e3c706f3e3dc80e5e0054f8ba30f34d53bf07a4f369b6d11b53c848389c3a120",
|
| 4841 |
+
"model.layers.10.mlp.down_proj.weight": "sha256:082ff34dd073bd239effc547a8f752c74744893060ffa8be0128013d2ecfd566",
|
| 4842 |
+
"model.layers.10.mlp.gate_proj.weight": "sha256:ffff115c546399a4ffed8a352d1cc70d7c06633207ac2b3ad47e71abaded7e8e",
|
| 4843 |
+
"model.layers.10.mlp.up_proj.weight": "sha256:088d089d38c53a4f9a14ddc8a4c4a2f249a977519f7e86fcc05c0e328f04e29a",
|
| 4844 |
+
"model.layers.10.post_attention_layernorm.weight": "sha256:d93c9d3442ce8a3273c15f3e24191d5f45217e0b6ebde07eb524a0ed156f9a85",
|
| 4845 |
+
"model.layers.10.post_feedforward_layernorm.weight": "sha256:cdc64f81b158c68d71169a5e830bdf519e0af3fe543fc6eae965fe35734d7209",
|
| 4846 |
+
"model.layers.10.pre_feedforward_layernorm.weight": "sha256:befc18033c9ed2656ba9f0abdf393df30332aca649d9a670d2296d59510d13e8",
|
| 4847 |
+
"model.layers.10.self_attn.k_norm.weight": "sha256:74ab819761d51beb226a1e37d1e341f9c3504a5e03d9806e2c4f47a698f9608c",
|
| 4848 |
+
"model.layers.10.self_attn.k_proj.weight": "sha256:dd5931ee1b94bb01d213823fc36f81c6a37481cc3b59e99a72992ac24d75dc0b",
|
| 4849 |
+
"model.layers.10.self_attn.o_proj.weight": "sha256:285ec14326882266ed88689b7356c34fb5a987bf100373b3239dbca95a6c9f2b",
|
| 4850 |
+
"model.layers.10.self_attn.q_norm.weight": "sha256:fc1b1e230dc474074d3d89828aa6745c14c8f40a0947bf74570762b12f8babf3",
|
| 4851 |
+
"model.layers.10.self_attn.q_proj.weight": "sha256:80ed3bed0f367c05219a18dcb8f26033372c895d0ba546a11fb771f18f45ca3f",
|
| 4852 |
+
"model.layers.10.self_attn.v_proj.weight": "sha256:6a58313e6a40fef7ee99a9b37d44bb946cb6799b2fb93afa09bf44f7d7114cf6",
|
| 4853 |
+
"model.layers.11.input_layernorm.weight": "sha256:0a9c1f662d1596b5459685338cd533ed81b7bfecbaf82d7df41897a52e84847a",
|
| 4854 |
+
"model.layers.11.mlp.down_proj.weight": "sha256:55205d7b8e2ca835b4b002935da7dded8d332d6fefaa5938f39e1b5a66e537ea",
|
| 4855 |
+
"model.layers.11.mlp.gate_proj.weight": "sha256:657eb5e40dd5e64bccdb21026665a82b445fa99eacc048ba9fadf05c53ef23f3",
|
| 4856 |
+
"model.layers.11.mlp.up_proj.weight": "sha256:71069c6db86a3eb1d3d39350f8196dbb6ff927aaa3bd53082e0b44bfd302fd50",
|
| 4857 |
+
"model.layers.11.post_attention_layernorm.weight": "sha256:80a36754e66cdac05b7b282f3c732ee4979007033884af4ce2a5bd244550be3f",
|
| 4858 |
+
"model.layers.11.post_feedforward_layernorm.weight": "sha256:e6889c18b2c9284d37852c4271194e785f1b5c8c1791d50e8208f8cd715fc346",
|
| 4859 |
+
"model.layers.11.pre_feedforward_layernorm.weight": "sha256:8605f4a090e024e2d82e2dac7fc27a313404567b3fac9a043cebe5c9fcfe4c66",
|
| 4860 |
+
"model.layers.11.self_attn.k_norm.weight": "sha256:9e520ebc4d2cb3c5e117fc276e4681efd39be1ba9614f9493a3daf39b8c4bfdc",
|
| 4861 |
+
"model.layers.11.self_attn.k_proj.weight": "sha256:647ea829193167ea720dd8c88826f8ef8827e1ab2e7c88f00c7fa98c4f1e3c40",
|
| 4862 |
+
"model.layers.11.self_attn.o_proj.weight": "sha256:cf5b55172eb4e4538e6ddb0a39417a6a6830afc9de12b8e05e1ebccd97c5741c",
|
| 4863 |
+
"model.layers.11.self_attn.q_norm.weight": "sha256:89290f54da1696f045daa3d5354967a4eb855fb06e0012dbcbe283ba2eb17389",
|
| 4864 |
+
"model.layers.11.self_attn.q_proj.weight": "sha256:35569cc7ab8423cb2b6809b2474b7273cf9c4979f7f949bf8cdbe709442b3c2b",
|
| 4865 |
+
"model.layers.11.self_attn.v_proj.weight": "sha256:b8babd57f2dc2a9e79b9863664d0d73da97bd4028ceed9988fb49060d18144cb",
|
| 4866 |
+
"model.layers.12.input_layernorm.weight": "sha256:732ec2f513d8db3f2b5c7fdf5feab5b2317a3ac4e85bfdeb2388f19165fd7190",
|
| 4867 |
+
"model.layers.12.mlp.down_proj.weight": "sha256:5e84927eb49ad98e6f2d0f36e7cf50b745928325deb5ef68978444a3ce3d4c4b",
|
| 4868 |
+
"model.layers.12.mlp.gate_proj.weight": "sha256:dea602eea67b841dee1cab35f50d554d60610556a7148eec9f45e7c43c88fcc1",
|
| 4869 |
+
"model.layers.12.mlp.up_proj.weight": "sha256:48177e849caa8375b6ef26c24357f0c5385a22d364538516fa568199b70f12a5",
|
| 4870 |
+
"model.layers.12.post_attention_layernorm.weight": "sha256:29226fae70afee8c4f275382b3dd841bcc5e0337aaa9cca1b426c402706a8299",
|
| 4871 |
+
"model.layers.12.post_feedforward_layernorm.weight": "sha256:ba0f7b615b199a0b1a36c83e6d04ff629ff450b5671ac3556a0ef8d6ac80af06",
|
| 4872 |
+
"model.layers.12.pre_feedforward_layernorm.weight": "sha256:f4d23c5a0ab7143b7bd253aed85d3d03de66e72e6df2e6400c3d0af6df5dfb29",
|
| 4873 |
+
"model.layers.12.self_attn.k_norm.weight": "sha256:e52356a4c83f2798f3e200e69f1f86961e36fdfdff893492bd8cb5b4ffaf0df2",
|
| 4874 |
+
"model.layers.12.self_attn.k_proj.weight": "sha256:879a1882c9b9e43290eaa8fee7579fa7dd2d4705e607f5bbdb7bfad80dfae5ea",
|
| 4875 |
+
"model.layers.12.self_attn.o_proj.weight": "sha256:1cafcef398b68102db2316a22d7ccc2670003c4f4a5df426dc302e051061677a",
|
| 4876 |
+
"model.layers.12.self_attn.q_norm.weight": "sha256:be748f9c66c4caae2767f366a12b75bfd7bc562d200395700f8c7c4ba386d7fb",
|
| 4877 |
+
"model.layers.12.self_attn.q_proj.weight": "sha256:9f47e580952d578125ad47711eee32e53e27fa39b731694746585d1edefa4681",
|
| 4878 |
+
"model.layers.12.self_attn.v_proj.weight": "sha256:80f24f1a708c76d73b315773c1831f19bc0203ff360ea0d83c78e306030a1c9e",
|
| 4879 |
+
"model.layers.13.input_layernorm.weight": "sha256:e1de24573119bc4e371cc71e8913861fc3f8096965129d8c7b097c2d13ef178e",
|
| 4880 |
+
"model.layers.13.mlp.down_proj.weight": "sha256:97338e95ccf73742ce8d8c9f23f461896ea1c638a2f09f1c8a92e569ee07b010",
|
| 4881 |
+
"model.layers.13.mlp.gate_proj.weight": "sha256:f05b88a53b31979065b9335ae96762c127dd1d60b417047389ce46d1a70ddfe6",
|
| 4882 |
+
"model.layers.13.mlp.up_proj.weight": "sha256:979b0d958458baee896dc8c6c48d486940da546c04beff0b3e1e52548fc8c8b3",
|
| 4883 |
+
"model.layers.13.post_attention_layernorm.weight": "sha256:65f152f444262e306403a34dbf43b47ead43807a799029359af7f9e2820be7d0",
|
| 4884 |
+
"model.layers.13.post_feedforward_layernorm.weight": "sha256:6a9b1dc42e9efc26a50f833dac53552ed43a964f1ed2e84331e056c6945f9dba",
|
| 4885 |
+
"model.layers.13.pre_feedforward_layernorm.weight": "sha256:993f10a97d84727c7cf703f1aa3c383742b5de9a608bf4381fc88b9bec67101e",
|
| 4886 |
+
"model.layers.13.self_attn.k_norm.weight": "sha256:3f4ddb2d53265d25bd3640bb568ecacc17d984f99294fc607974897ee1652518",
|
| 4887 |
+
"model.layers.13.self_attn.k_proj.weight": "sha256:8a48fbd7e9f7cbebc1a1a53e924e6704f6784ed2f61d5218042154c8f3efcca0",
|
| 4888 |
+
"model.layers.13.self_attn.o_proj.weight": "sha256:445d05bb8c56f6884ff24fa3e49301ec8fdf04ba313bc8849cc14ee92157d8b0",
|
| 4889 |
+
"model.layers.13.self_attn.q_norm.weight": "sha256:aae4200c58708b814662bca5223797b7d21f02ecdd4da146043ab4b06b1f80f8",
|
| 4890 |
+
"model.layers.13.self_attn.q_proj.weight": "sha256:0d61a5ffba1d55b5f52f9c2857c0a3477b464ba5084b069b66f44ca2aa9368ff",
|
| 4891 |
+
"model.layers.13.self_attn.v_proj.weight": "sha256:dd389357c6e76fea116c349fe338fe370367420d7e52fc548eab362562dc832d",
|
| 4892 |
+
"model.layers.14.input_layernorm.weight": "sha256:f6f37c200c87811c22ad4fa9baf90cc7b9792984ae76bc76b659a2cfee745e0e",
|
| 4893 |
+
"model.layers.14.mlp.down_proj.weight": "sha256:dc34e27df9cb7d76e9ed9399c85713e3e837d8b3eea76c9731e507c52be40ac1",
|
| 4894 |
+
"model.layers.14.mlp.gate_proj.weight": "sha256:a939d945be98a0c89ec861454bc2125cc814efdc08cf4fa557fb5cac6ce40239",
|
| 4895 |
+
"model.layers.14.mlp.up_proj.weight": "sha256:7dd3e336f4700e1ba1566e881b063e5ecb6db54d178287f39a937b6bc75fdd2a",
|
| 4896 |
+
"model.layers.14.post_attention_layernorm.weight": "sha256:d10f7a82f00f5f618b6054266d0797834ad7ad3651f9e92af9b70ca04e625bcf",
|
| 4897 |
+
"model.layers.14.post_feedforward_layernorm.weight": "sha256:b1f175a89a34062466f164a0273e5aca1a1a6913f461582a0c1aaffb1522e77c",
|
| 4898 |
+
"model.layers.14.pre_feedforward_layernorm.weight": "sha256:b7baf7ba8369da25c46aef1ccda755b39285be93f5cfa1d84a72e89c0a6a0638",
|
| 4899 |
+
"model.layers.14.self_attn.k_norm.weight": "sha256:454004b1ae4a328e34b5cee1efcca985a3f2cf8a5664d2647dd1a7f63b74e926",
|
| 4900 |
+
"model.layers.14.self_attn.k_proj.weight": "sha256:1dcd0fe0783bd590c52eddb90edb8f94dd9a34948bce8674b1e721a748fc2c70",
|
| 4901 |
+
"model.layers.14.self_attn.o_proj.weight": "sha256:b0960902c6b1c2a7fe93fb7680136457f0cf756702c378e6ab681a64a799fea9",
|
| 4902 |
+
"model.layers.14.self_attn.q_norm.weight": "sha256:ed11b4d38b86b8951fbc45adf26ce551283fee9d2eaa5b4c8448ea207baa4bec",
|
| 4903 |
+
"model.layers.14.self_attn.q_proj.weight": "sha256:b20e0baa40fd0df8fb3664fe069941bfd62f539345015cef5eaa70b34da95286",
|
| 4904 |
+
"model.layers.14.self_attn.v_proj.weight": "sha256:e836d841cf6439c69a9f833604cba9a9b0593a20460923983d1cfe0ff4b4c7c9",
|
| 4905 |
+
"model.layers.15.input_layernorm.weight": "sha256:8aa4943e89f5f99885e26b7a5b48d8c17785c2b557ab0d41aef33f8135a03b30",
|
| 4906 |
+
"model.layers.15.mlp.down_proj.weight": "sha256:9364d7058a10b73ef0d30dfbc396dff56470ad061e5b319fc6383837f07e89d5",
|
| 4907 |
+
"model.layers.15.mlp.gate_proj.weight": "sha256:26a2a60f4dcecd52b1670aaeba42dbeaf7f607de187a49b7a486d900586b42d2",
|
| 4908 |
+
"model.layers.15.mlp.up_proj.weight": "sha256:42d3ebc82f4c41025ba1124d7ad21b6c567ba7f586c6b1864a2cfb8f3b12eb2b",
|
| 4909 |
+
"model.layers.15.post_attention_layernorm.weight": "sha256:3ee02ff9cea9b4439cc2148c41b3f9c823b997c4b462bc88b434a2049c98f5e9",
|
| 4910 |
+
"model.layers.15.post_feedforward_layernorm.weight": "sha256:1d14f6f4bea9f6b036a1efbc974273b90a65487524d21f015762c196b74de069",
|
| 4911 |
+
"model.layers.15.pre_feedforward_layernorm.weight": "sha256:28fdaa8903259974f2aacf504d7482c7aff076d3c4498e26c1c41728265c8d0d",
|
| 4912 |
+
"model.layers.15.self_attn.k_norm.weight": "sha256:0f048b98f3916e09734bd22bae349cc7c243f941a7d19e7b471e35ae24c30e30",
|
| 4913 |
+
"model.layers.15.self_attn.k_proj.weight": "sha256:e042dad51314681e203f210ed702c2b751ba367118b9ff0d2293be5322236333",
|
| 4914 |
+
"model.layers.15.self_attn.o_proj.weight": "sha256:f9ba0d02aaff4d9917b05e6aff827717baf8073c9e9fecce20d182ffa4e7c111",
|
| 4915 |
+
"model.layers.15.self_attn.q_norm.weight": "sha256:86edc7f3d2e017c464a8f11eb0a89d2adde04e52ed8cd29808d3160956d8ab49",
|
| 4916 |
+
"model.layers.15.self_attn.q_proj.weight": "sha256:9b1de76485f4d3615f11a7d43bdd611fa4902ca14eb62f16a41065addbcd10b0",
|
| 4917 |
+
"model.layers.15.self_attn.v_proj.weight": "sha256:277622b5c351f6219026b70f78459945ec23aae5365bd6d0c63ce9501bd17e30",
|
| 4918 |
+
"model.layers.16.input_layernorm.weight": "sha256:a21735061cbc731d324981e56f068fae9a540793c04d2d5a9c7e6c95ba64ddbf",
|
| 4919 |
+
"model.layers.16.mlp.down_proj.weight": "sha256:696c01560bb1ebf5ef17e96916f01667175b1e27408bb64fa38181e5d646ffeb",
|
| 4920 |
+
"model.layers.16.mlp.gate_proj.weight": "sha256:ec526941afd3b72b70a509a158e66ee2906fe8e612fa91a89333e4bbd3dd8245",
|
| 4921 |
+
"model.layers.16.mlp.up_proj.weight": "sha256:b67cb08a5733a6a0c8cfaacb9dfab611adcdf03d62d4bd007ff29c64297fcee6",
|
| 4922 |
+
"model.layers.16.post_attention_layernorm.weight": "sha256:1310df6bf9531b1933d88bb9c34a0f9d516b7eb72a9c567d17f1e23f0d126b61",
|
| 4923 |
+
"model.layers.16.post_feedforward_layernorm.weight": "sha256:ad5c8e54e513bdee044933780240d9c4d60e066d592e390ead1cf051b4752483",
|
| 4924 |
+
"model.layers.16.pre_feedforward_layernorm.weight": "sha256:070a9bfd71f96eef233f9d6634f0654fd771fc182bb53db42e867deb098c7e44",
|
| 4925 |
+
"model.layers.16.self_attn.k_norm.weight": "sha256:cfa8f914345540a8c588a3582ac5af91edef20141b8ee15dcc7670df1b3ebd85",
|
| 4926 |
+
"model.layers.16.self_attn.k_proj.weight": "sha256:d2cabd5e862267f16c7f0ce1c7dd421e8ae513ca84abee516afb34a046ecc4d9",
|
| 4927 |
+
"model.layers.16.self_attn.o_proj.weight": "sha256:1ddcae16ce25077632b7cab742f0465c0012954bfdd7e9585ae4fac81d602e1f",
|
| 4928 |
+
"model.layers.16.self_attn.q_norm.weight": "sha256:c313c4754ecb996eeff6568529420107431c23a859948ffcb13ba0134d114820",
|
| 4929 |
+
"model.layers.16.self_attn.q_proj.weight": "sha256:2e8becf70170708fa522d5e991ff9e4c280ffb651cd18dfe72397842ee5614e0",
|
| 4930 |
+
"model.layers.16.self_attn.v_proj.weight": "sha256:89a0ec33c50f8390ca9b81834f157efaa0f2b40816aee52ac9a9c1998a9836dd",
|
| 4931 |
+
"model.layers.17.input_layernorm.weight": "sha256:23d457c5152aee21346b43bf9c5f8ab388e04da5afdee3518a10bfc19754f808",
|
| 4932 |
+
"model.layers.17.mlp.down_proj.weight": "sha256:57f84e8090555009b208a7874e6ffe113f6b608d7ae397889b396b03f9f6be7c",
|
| 4933 |
+
"model.layers.17.mlp.gate_proj.weight": "sha256:4c17cfe71a101303fff28af4318a961163481f12b438c3a138b7077cecc19cd0",
|
| 4934 |
+
"model.layers.17.mlp.up_proj.weight": "sha256:cae1b53a5c4e4695b9f3a5d30fc1e8a806c4258d871d212706450dbf5f33cdb1",
|
| 4935 |
+
"model.layers.17.post_attention_layernorm.weight": "sha256:847c8d400708b1b2c0986980725401140abe0dd6b6ba24873b58a517e7162771",
|
| 4936 |
+
"model.layers.17.post_feedforward_layernorm.weight": "sha256:f05a1c78cbf066a0af87d6b49defaf7825727a675da103a05c70525e0c45334e",
|
| 4937 |
+
"model.layers.17.pre_feedforward_layernorm.weight": "sha256:5e6fb47473f2b60b628ce8ee964062b42d66d198e2165331326489d33b7b95e4",
|
| 4938 |
+
"model.layers.17.self_attn.k_norm.weight": "sha256:f2e2347a54cb1f43bfc7c33dce3cb3e88e487434d4f983f490690a26e0516802",
|
| 4939 |
+
"model.layers.17.self_attn.k_proj.weight": "sha256:4136876a97f3cef97122253b2c4dc7ebcf0d3c7ad1051c8a84b1cdc9ba16f644",
|
| 4940 |
+
"model.layers.17.self_attn.o_proj.weight": "sha256:fc2c4dcfe43aef97079e06d172816c47211ad4b43533283522ead415c97faf0f",
|
| 4941 |
+
"model.layers.17.self_attn.q_norm.weight": "sha256:0d124924c74aa4152cfed5dc06bdf6adf9f3a3bebc8a572ad47ed092118f29bc",
|
| 4942 |
+
"model.layers.17.self_attn.q_proj.weight": "sha256:ffc1a6b15b66fee765383727d7f8c5064e887db1347093b6ee4f959cc9e03778",
|
| 4943 |
+
"model.layers.17.self_attn.v_proj.weight": "sha256:1f62e4e709bc088a7dc700874a2ff8b80a53ad59cbf50a6a02621b5f6c27e868",
|
| 4944 |
+
"model.layers.18.input_layernorm.weight": "sha256:7d12d072967b9d25d83503d71de771705a4a93fe4ab975351d3fa161e60cdb63",
|
| 4945 |
+
"model.layers.18.mlp.down_proj.weight": "sha256:06d1d5af6a3bf995d95ddd1708806be61c99f4273f3b720a2512dba8819dd99f",
|
| 4946 |
+
"model.layers.18.mlp.gate_proj.weight": "sha256:2c1fcf8ad905f72d95754889899460b35e3be208e6ef3d1ffdb3608af2e8f178",
|
| 4947 |
+
"model.layers.18.mlp.up_proj.weight": "sha256:db89fd1a06c8f16ef4bf377f220b1ff5aee1c879bdb6f9b5d1672b50b521f218",
|
| 4948 |
+
"model.layers.18.post_attention_layernorm.weight": "sha256:eab78fbde08ea9de13f27cc4fa1150ae6d47908d2cb9b296bfbc1c57ea28d142",
|
| 4949 |
+
"model.layers.18.post_feedforward_layernorm.weight": "sha256:2d152957839ff26935235313053d5880de02eb5ff0c5ac4746011a437c69709e",
|
| 4950 |
+
"model.layers.18.pre_feedforward_layernorm.weight": "sha256:525851dd7c9c4e85598df8c9c6afea8cc6f448badf39461f94cd2a14c1e72e65",
|
| 4951 |
+
"model.layers.18.self_attn.k_norm.weight": "sha256:96da7023e758456b941c49f34769e0f6509759511d4894941c018000a7f44577",
|
| 4952 |
+
"model.layers.18.self_attn.k_proj.weight": "sha256:96102e3e4894c784768b791c2911349d05457a52324accd34e5dda1d922229fd",
|
| 4953 |
+
"model.layers.18.self_attn.o_proj.weight": "sha256:717780f43388431af851f20e2553e284bd76338896cd9538cd337b986bf1a484",
|
| 4954 |
+
"model.layers.18.self_attn.q_norm.weight": "sha256:22850f7cad43013c91674addf662e6fa08e5f929c4643ce65d53330134d4999b",
|
| 4955 |
+
"model.layers.18.self_attn.q_proj.weight": "sha256:6387e07dc27fa080bd6e754206917eea2288b8e583e94796215fa8ce2068f787",
|
| 4956 |
+
"model.layers.18.self_attn.v_proj.weight": "sha256:2d97a20e30eeff739b85c278ddc3a91778ac7edc25272237d4f72d679eed1717",
|
| 4957 |
+
"model.layers.19.input_layernorm.weight": "sha256:ce44d7f64ca7f3f4c92a51311fa167805f9d636ca015b8cc5a12b2f92c7eea5c",
|
| 4958 |
+
"model.layers.19.mlp.down_proj.weight": "sha256:a8cf3ee167be6502a57641db41f5f2e5bae7ab333cafcb6d00febd50e5a4fbb6",
|
| 4959 |
+
"model.layers.19.mlp.gate_proj.weight": "sha256:eddfeaf39355f677807da9259e58e7de364cc97cc57c78961f328aa09fbfb08e",
|
| 4960 |
+
"model.layers.19.mlp.up_proj.weight": "sha256:2cc90dbdb380f02b9cf05df55f83a82c1aa3bf11c7ffd54f2afccb29f867f0d3",
|
| 4961 |
+
"model.layers.19.post_attention_layernorm.weight": "sha256:3784085ec20a312019befb1594acb5139beeb080f2bd03ab150baabf50392a72",
|
| 4962 |
+
"model.layers.19.post_feedforward_layernorm.weight": "sha256:34346f45be644e2a3673fdc05e1bb6104ee097aa6af7a6c562ba2be281a546c0",
|
| 4963 |
+
"model.layers.19.pre_feedforward_layernorm.weight": "sha256:64645ab26c6c381b84d4b62de90726d6afec2360940f545a18fbefc6e621a797",
|
| 4964 |
+
"model.layers.19.self_attn.k_norm.weight": "sha256:194fc9c55a07ce36019a55764d1b20b1d1d17c6ea5c836af0438a17601b3c093",
|
| 4965 |
+
"model.layers.19.self_attn.k_proj.weight": "sha256:b7331096f28f112de4a36061b51209468d0e8cebca9b62d005d7a00179d9cfa9",
|
| 4966 |
+
"model.layers.19.self_attn.o_proj.weight": "sha256:9f9fe7e822aff324ae09fa31eeeb9c4ece9fe4e531b6f8fe5494a2afe5c1a50b",
|
| 4967 |
+
"model.layers.19.self_attn.q_norm.weight": "sha256:878903b5bbce011c556e774b2569a5671adb35fdf44a12c1c9b1be44851d2f4b",
|
| 4968 |
+
"model.layers.19.self_attn.q_proj.weight": "sha256:7604dc554cf84e006b71e41d2096008ee158b2637dfb849440032115b771ffcf",
|
| 4969 |
+
"model.layers.19.self_attn.v_proj.weight": "sha256:d933226f2284c30b4f233a839b3f771d502459a3f8c3a81c1839a4842ba41029",
|
| 4970 |
+
"model.layers.2.input_layernorm.weight": "sha256:764598d9eb6dd9824be81078445418097a0689c5ada4b863fee493acb23eb493",
|
| 4971 |
+
"model.layers.2.mlp.down_proj.weight": "sha256:93141d6aaf131f0aac3a25ac08e746449a961323060b675e372b36ceddfdf451",
|
| 4972 |
+
"model.layers.2.mlp.gate_proj.weight": "sha256:2e5cbad40a440ea7891660924959b3490296c214d6ceb3b0efd6cf17914e6291",
|
| 4973 |
+
"model.layers.2.mlp.up_proj.weight": "sha256:52e18584124822933dd90acd9ee610a1c6fe72c42ef6931534e58aaa4dea9dc3",
|
| 4974 |
+
"model.layers.2.post_attention_layernorm.weight": "sha256:162041cc65ab63ba49961367fe876a132fca87d00b0d092330da25007a0ae180",
|
| 4975 |
+
"model.layers.2.post_feedforward_layernorm.weight": "sha256:2139903d92f3ed052bfb79c53d1c06a4cade0f7e6e309da2863cdb731363916e",
|
| 4976 |
+
"model.layers.2.pre_feedforward_layernorm.weight": "sha256:d3c6b676096ff8551597a4e0ef9204de64f0fa13e5bd3e3469d7da987ce893eb",
|
| 4977 |
+
"model.layers.2.self_attn.k_norm.weight": "sha256:e8a6d14782284f2b9ec3ca5846388ed61b8a61861e0a48c0564a5654ccba779b",
|
| 4978 |
+
"model.layers.2.self_attn.k_proj.weight": "sha256:d5c1e64dd225fea71dc414dc7326149a15b7334b85d570272373f1f642c3df8e",
|
| 4979 |
+
"model.layers.2.self_attn.o_proj.weight": "sha256:f219a9d88fb40acfab143a45f135f67f50d3bc41c88957286a30aca9aa054079",
|
| 4980 |
+
"model.layers.2.self_attn.q_norm.weight": "sha256:8358825c1f879d5d02b8a3b48d66ecfe5fe76cec1d0572b4c091d021c898648d",
|
| 4981 |
+
"model.layers.2.self_attn.q_proj.weight": "sha256:3408c1fb9087b3eaace669d819ec3921794f74e4f8aad3e7135a6f7a1382deca",
|
| 4982 |
+
"model.layers.2.self_attn.v_proj.weight": "sha256:7b0422b1c9a63f4efeeff6054c4b24a51555691d30705b134111ee8d66ba22d1",
|
| 4983 |
+
"model.layers.20.input_layernorm.weight": "sha256:27a6f4a0a821fd4bdd1a43f9e49b1cb643526729e7c895f2f950b3b3c5901e9c",
|
| 4984 |
+
"model.layers.20.mlp.down_proj.weight": "sha256:de1a3efa34bc0527876dbb7b2a0930b85530dcb7b2c82d91316388d4dafdb8bc",
|
| 4985 |
+
"model.layers.20.mlp.gate_proj.weight": "sha256:38f6e71b9e101d67acfab870e9325c69ec6fefc241798cac054d51e34435f4ef",
|
| 4986 |
+
"model.layers.20.mlp.up_proj.weight": "sha256:7d029c6d778023b53ce99846acb9d69baca38809d0a405159981790bde3137b6",
|
| 4987 |
+
"model.layers.20.post_attention_layernorm.weight": "sha256:04659e1733d47a0df9280c61c7d253060d9b10073eb0f3156a9d74f510c52a69",
|
| 4988 |
+
"model.layers.20.post_feedforward_layernorm.weight": "sha256:c2cab54443529ce8356676b00bf490ac0013e8e1df5213acd5c3d399306184ae",
|
| 4989 |
+
"model.layers.20.pre_feedforward_layernorm.weight": "sha256:b770181bc1d2d98bb230b34009f24c752f56488b767a76eb58a65d50ac170b9a",
|
| 4990 |
+
"model.layers.20.self_attn.k_norm.weight": "sha256:d47ba1d00be0609bbef07ac249e2f26aaec93d2eb38e3005fe03388604f8a9f1",
|
| 4991 |
+
"model.layers.20.self_attn.k_proj.weight": "sha256:138b781bcac6ce6b73d1af64b568ad1d77b531c9137de6b1b80fb06799ddd0e4",
|
| 4992 |
+
"model.layers.20.self_attn.o_proj.weight": "sha256:2586cb8a9e082fafe542981f1a6fd378f9b231a6d4c71895092bbcdc881a4451",
|
| 4993 |
+
"model.layers.20.self_attn.q_norm.weight": "sha256:e9905b181e9eb9896586b086c8343d2f04dd375b5ef7a9b18aa3cb6f3cadc60f",
|
| 4994 |
+
"model.layers.20.self_attn.q_proj.weight": "sha256:f7e07e48c9c0fc7c1d95c27a8441b4857fe93faaff7feba60d49b82105ea1e45",
|
| 4995 |
+
"model.layers.20.self_attn.v_proj.weight": "sha256:186f311683161fcd54f3a3ff2cc43abc65fd7083b3b80e18ac617f4174edd435",
|
| 4996 |
+
"model.layers.21.input_layernorm.weight": "sha256:c73d9a202b0de574db2fa9cbb3340e1cb325ded75b492e24f0f1a7304ef37a41",
|
| 4997 |
+
"model.layers.21.mlp.down_proj.weight": "sha256:28739c89b59e16a72b8789e0cd1ce147cb3bbcea461e3f49e4098130bec426c4",
|
| 4998 |
+
"model.layers.21.mlp.gate_proj.weight": "sha256:31673b848f396c973f43c760f7de19d7aa06ce626a0c5ac66c7dc525838fbcc7",
|
| 4999 |
+
"model.layers.21.mlp.up_proj.weight": "sha256:adaab9c8521ff6a3a310a905a8cb0e3435b2c43e24aec12f1fec6e13fb1a9445",
|
| 5000 |
+
"model.layers.21.post_attention_layernorm.weight": "sha256:ffb5aecd6aac46cf8b0a2dcbe42c81e4ccf4bd5360235d2df1d15266f871f244",
|
| 5001 |
+
"model.layers.21.post_feedforward_layernorm.weight": "sha256:92c0613d7cf801268cf3d1d31198f164b89e12aadcbe9f771547039f6e06e935",
|
| 5002 |
+
"model.layers.21.pre_feedforward_layernorm.weight": "sha256:aec729126c4d96a4e5d0b46be41cc3b6e554aa78e1b89db12006417e4b5c7435",
|
| 5003 |
+
"model.layers.21.self_attn.k_norm.weight": "sha256:ece6b8543d59c3401b3e17342c72a7b6800c86747ee10ae2a998237a14fa77df",
|
| 5004 |
+
"model.layers.21.self_attn.k_proj.weight": "sha256:1f1a0ead5879f6b56a6613d7ed3801f945ec3712a0fcebf6dd1c2b9af1a70665",
|
| 5005 |
+
"model.layers.21.self_attn.o_proj.weight": "sha256:6a1ebd39dd5bcb19eccc5ba64def9d09b9815db9062959ebf957e84eeb50c1c4",
|
| 5006 |
+
"model.layers.21.self_attn.q_norm.weight": "sha256:bad521c1a82cfc68686acf191bded97a316711d385aab4a7a121b6857a2a6ae6",
|
| 5007 |
+
"model.layers.21.self_attn.q_proj.weight": "sha256:0b4e0654e86a4fd7ab3357eab5b411f2c42187068965d0f3c90a274846a34e8d",
|
| 5008 |
+
"model.layers.21.self_attn.v_proj.weight": "sha256:23d31e7f7e75820b05d7f1c9698486b956de6930f035ab484319e67b5ffdd187",
|
| 5009 |
+
"model.layers.22.input_layernorm.weight": "sha256:a37e06dc56da127506f74e819c567b005f2bf158cd7db48d585496625f044c9a",
|
| 5010 |
+
"model.layers.22.mlp.down_proj.weight": "sha256:1fe07154e544fe193ed41c23ea5e750766877c94fe6501d7d678a83d9f5e9630",
|
| 5011 |
+
"model.layers.22.mlp.gate_proj.weight": "sha256:38f2b0867f9f1f563df63681b14559b9ebc934c2eca06ddd1cb452c37fb5ec25",
|
| 5012 |
+
"model.layers.22.mlp.up_proj.weight": "sha256:d51cb55288ab23f3a0dd4dccd9957083ee29f00355a43113ff7d5b81102ebe72",
|
| 5013 |
+
"model.layers.22.post_attention_layernorm.weight": "sha256:f0955a4eb6eff00bc40e2f23d2145eafeea9801ba365fd2da5cae94557b7652f",
|
| 5014 |
+
"model.layers.22.post_feedforward_layernorm.weight": "sha256:719be46dfe3c3add2e40649736cee7add55296297fcab93b0bc6f86aba4d62ef",
|
| 5015 |
+
"model.layers.22.pre_feedforward_layernorm.weight": "sha256:4ffeaf6e5da145d78c002ad2a9c0b6818d4203207bb7a7e347c0cb8b932261e4",
|
| 5016 |
+
"model.layers.22.self_attn.k_norm.weight": "sha256:3f1139f20404f4921faff4ff033960a1af0dbb0fee23228d27fea83d0be46b9b",
|
| 5017 |
+
"model.layers.22.self_attn.k_proj.weight": "sha256:de3861021bc46ff3d162c135dcb2b43902941c28bd374265e3267ce13cde44a1",
|
| 5018 |
+
"model.layers.22.self_attn.o_proj.weight": "sha256:02c1e0afd1f6fd1ec3a9314a38736da09ca4f34f866b164711324c9b188c0a42",
|
| 5019 |
+
"model.layers.22.self_attn.q_norm.weight": "sha256:2ddf72b0a3075abbbc0420b76d285c630e703c9a3b43e291fe2997a8b139e588",
|
| 5020 |
+
"model.layers.22.self_attn.q_proj.weight": "sha256:538d209c804e754c6148918c420713c5e4cda962ed9b14fa40738acc7c0ba88b",
|
| 5021 |
+
"model.layers.22.self_attn.v_proj.weight": "sha256:e1a96f3a6d40abbdcf911fefbda51e74ba69b53a3f0508171caf6415554aa130",
|
| 5022 |
+
"model.layers.23.input_layernorm.weight": "sha256:2e71fb7fa6173e092deae375107c072f5ce376791da5aaab3690f5bb19300acd",
|
| 5023 |
+
"model.layers.23.mlp.down_proj.weight": "sha256:1b44807e23dbacd900cafd6b6ada2b3626f19ed79e3e2f1f83fe436a8ff94590",
|
| 5024 |
+
"model.layers.23.mlp.gate_proj.weight": "sha256:5a8724c65bcf9c80d6ec27dccfdf5fe7680320723b0f8107b6785581f8fdd730",
|
| 5025 |
+
"model.layers.23.mlp.up_proj.weight": "sha256:137a8252acba5e6fbcfd16692cce0603dafde12d46e0e32ba15c7e6a54e75594",
|
| 5026 |
+
"model.layers.23.post_attention_layernorm.weight": "sha256:e61b33a7f48d528b2afcadc50f6adf626102b194f5493757ca1d7fee4171cc3e",
|
| 5027 |
+
"model.layers.23.post_feedforward_layernorm.weight": "sha256:611a7ca2fe54cf2c8e73ae5d915489476ae3457387cd3ff8f7a1cee54d9cddc2",
|
| 5028 |
+
"model.layers.23.pre_feedforward_layernorm.weight": "sha256:5d85bd4172a939634f014b63dcec00a82ac36ba99a663c786c1b40c49b102953",
|
| 5029 |
+
"model.layers.23.self_attn.k_norm.weight": "sha256:6789ea0bb5fff8ddff936c1ddfe5b00231a888dbdcdf1efcdb94ede5a1ba8de0",
|
| 5030 |
+
"model.layers.23.self_attn.k_proj.weight": "sha256:c4903be12f50296c8f9449723616e14ea131b62a427605f11b08bbac602c8d46",
|
| 5031 |
+
"model.layers.23.self_attn.o_proj.weight": "sha256:ddee2dc9cf485f63da756f6787071c39e8f263b35b0c96df8536015127a4cc74",
|
| 5032 |
+
"model.layers.23.self_attn.q_norm.weight": "sha256:4203294c84c8e83413febe0346d8a109eb0147a15289d1c62d460bc3ac094839",
|
| 5033 |
+
"model.layers.23.self_attn.q_proj.weight": "sha256:b712d2bed0e423328edee8cc04904478261832b35b93f204c302b17b94154575",
|
| 5034 |
+
"model.layers.23.self_attn.v_proj.weight": "sha256:3305e0782f3336a2c5afdf73804332c1bbf34dd4a9dee9530084855dfcaed162",
|
| 5035 |
+
"model.layers.24.input_layernorm.weight": "sha256:170785b38d390999037dea8cd901bfc1fc65a2e72ba17f4cd6ef2ece81789f63",
|
| 5036 |
+
"model.layers.24.mlp.down_proj.weight": "sha256:ce6ed6e5521d5925d293826a9563c4cb36d584101a99f86d0bf125bce84e654a",
|
| 5037 |
+
"model.layers.24.mlp.gate_proj.weight": "sha256:46c682013d4220d6514f655c93836ece34034fa9899112c13e1539614147db5b",
|
| 5038 |
+
"model.layers.24.mlp.up_proj.weight": "sha256:dba14dba4f6416bebacc25d71cc218a9c86ba0e301428cbbf0fa1fc547b06742",
|
| 5039 |
+
"model.layers.24.post_attention_layernorm.weight": "sha256:2436cc02e47e84676c6963994c3fc18c04a3da2aea6fdd428eafb71094d2cf45",
|
| 5040 |
+
"model.layers.24.post_feedforward_layernorm.weight": "sha256:dd58023f60f836863128551cdf64aacdd4144d73cf6f9b6633ea78774f13f434",
|
| 5041 |
+
"model.layers.24.pre_feedforward_layernorm.weight": "sha256:bc0ad195f2ba98f9e98063a5dfb04f0f449ba375d104c0002be99d29212599b4",
|
| 5042 |
+
"model.layers.24.self_attn.k_norm.weight": "sha256:5113fd62cba7c7da17bd68d4306d595597b3f1eacd73844f00a80a718f55018d",
|
| 5043 |
+
"model.layers.24.self_attn.k_proj.weight": "sha256:0614b138ab544fd90027e878d602e7a9ded6de092735c25185f661219ba23ab4",
|
| 5044 |
+
"model.layers.24.self_attn.o_proj.weight": "sha256:0f62103cff20d70210b2970ea7ee6912b64ae70a296846d0dfe3c78d67d4da07",
|
| 5045 |
+
"model.layers.24.self_attn.q_norm.weight": "sha256:57300e25f76ecd3cd06a4cdd27090bd2bd071c0deddd06cff28f84bc037cc98e",
|
| 5046 |
+
"model.layers.24.self_attn.q_proj.weight": "sha256:bff818b77f9447ba5f12bbc1ea80bff9c0ba8a927b24422cd57532d6001894a6",
|
| 5047 |
+
"model.layers.24.self_attn.v_proj.weight": "sha256:caf9cd137af0d1a18dc791889a66544309ab3bf3de45f73c2bf6261bbc4cee49",
|
| 5048 |
+
"model.layers.25.input_layernorm.weight": "sha256:34bda399211ca26355fabffef0f151338bb6a3597007f4a59ae30c7dfeb75058",
|
| 5049 |
+
"model.layers.25.mlp.down_proj.weight": "sha256:20f8c6f477e400114f9e50089996a360d00eef5b01704178fc56e7c39941bd66",
|
| 5050 |
+
"model.layers.25.mlp.gate_proj.weight": "sha256:b9123e8deda232bae00c854a52a5c5d63265a146cd2e3716543ffd7edfcf9bb2",
|
| 5051 |
+
"model.layers.25.mlp.up_proj.weight": "sha256:43afe9476ddcf987fb78cce4b5fe848877bc364fef811e38fbb355c1bce5e3a7",
|
| 5052 |
+
"model.layers.25.post_attention_layernorm.weight": "sha256:b5dfed170852c619059198bd0dd3aeb0404be8114acce09b639fe14c9e155962",
|
| 5053 |
+
"model.layers.25.post_feedforward_layernorm.weight": "sha256:7794a974694fa51815b27f02d707750e94627384060213fd7b018a7446766618",
|
| 5054 |
+
"model.layers.25.pre_feedforward_layernorm.weight": "sha256:2f52bc101716db4fe8cad8ab2c6f04c5a8134797f1e088519024f095d6d70985",
|
| 5055 |
+
"model.layers.25.self_attn.k_norm.weight": "sha256:59e1e17c49b4e033536d0cc1f9fd7690c514a38afce7e6b72520b09cfbc6a903",
|
| 5056 |
+
"model.layers.25.self_attn.k_proj.weight": "sha256:3e8c1bd9c52af0cd372fede6ada8fe084a541b470af2deeb0a5059624eb6166a",
|
| 5057 |
+
"model.layers.25.self_attn.o_proj.weight": "sha256:ecfc6eb19d611b7e5cbbcd599fc9efc82e3d5bb0b2991e720dde8ec8b5109d84",
|
| 5058 |
+
"model.layers.25.self_attn.q_norm.weight": "sha256:9094ccd61064e7ead878acb1f991b8b4fd11b975bb4728e91bea9d0e31da5214",
|
| 5059 |
+
"model.layers.25.self_attn.q_proj.weight": "sha256:5fb7abed4433e841c89346fdc112000d419717b54de4d1b7c66d0c3b4811af09",
|
| 5060 |
+
"model.layers.25.self_attn.v_proj.weight": "sha256:2ff4e5203f02147d3b832860a533a442dc3f2252cf42666a0cd45194636d4675",
|
| 5061 |
+
"model.layers.3.input_layernorm.weight": "sha256:8e5aac0622cb26aee5e3be0ace6b84108123d025380b3ef33e2f5e12fb0a0451",
|
| 5062 |
+
"model.layers.3.mlp.down_proj.weight": "sha256:fc174f6dec3aa7d36c89a1bc50e83297e3d3bc775eeb5cd70a2c6eefd95d7d4e",
|
| 5063 |
+
"model.layers.3.mlp.gate_proj.weight": "sha256:1c5f75275ff32fbf0b7042e493917a097d37406efa6961d5a7b9af5795afdd67",
|
| 5064 |
+
"model.layers.3.mlp.up_proj.weight": "sha256:3772111cd660777e0bcbcae1c8829f26333b9c3371747b9d1629b88ed6c835a9",
|
| 5065 |
+
"model.layers.3.post_attention_layernorm.weight": "sha256:11ee00a394f7d36a1a9931f42e39df1e5666fd4ec35b91e498826ab34b9c8649",
|
| 5066 |
+
"model.layers.3.post_feedforward_layernorm.weight": "sha256:d82d78994a71fed403dee938fe288a2d81eecbf68ff5f397187e6e342b8febd4",
|
| 5067 |
+
"model.layers.3.pre_feedforward_layernorm.weight": "sha256:33b2dde99a5669ba2bf06501ea713d1d2485239f54446224e477322e26972e4f",
|
| 5068 |
+
"model.layers.3.self_attn.k_norm.weight": "sha256:e24c2b4f0f0fe67d707eef4b6826554b7a0129e2f2daf9758c611824b555538e",
|
| 5069 |
+
"model.layers.3.self_attn.k_proj.weight": "sha256:d7885e1846cdc17d701501d221bf116f4ca6b84cdf78360f8062a65a40bbb542",
|
| 5070 |
+
"model.layers.3.self_attn.o_proj.weight": "sha256:0fc8180d4a749583fdd5dfd4dd44a70e1f4e121106bfc26258073fecc7a043dd",
|
| 5071 |
+
"model.layers.3.self_attn.q_norm.weight": "sha256:f27008480bdea2cfd87dce388b687a0f7d9a6f30923e58bfaaa05505f86fce1b",
|
| 5072 |
+
"model.layers.3.self_attn.q_proj.weight": "sha256:73831542edaf7a232852f40971724c571ab65e71c8f419179b0c5fd586ed1faf",
|
| 5073 |
+
"model.layers.3.self_attn.v_proj.weight": "sha256:f1a1abf53acb8b8a386b1940f3718888feef84ef1d6f1b45d4d49508d7186616",
|
| 5074 |
+
"model.layers.4.input_layernorm.weight": "sha256:c2a4dec1bf0340d3c5773da3be3aacc00a727767ece369f3750794c65f3d2184",
|
| 5075 |
+
"model.layers.4.mlp.down_proj.weight": "sha256:7c2d0e87d7ba37aa957943d1f3176395645cb14fffad4347d2dd0ffa1d8fb6c0",
|
| 5076 |
+
"model.layers.4.mlp.gate_proj.weight": "sha256:751c8cc1cb8dd3b7ec318286f0c4d4db6023ca1c213103372870a0d6ce66780a",
|
| 5077 |
+
"model.layers.4.mlp.up_proj.weight": "sha256:724d4d19cf330c750b3b27da204d7121ac575692e9834f8f4238399b81c2aea1",
|
| 5078 |
+
"model.layers.4.post_attention_layernorm.weight": "sha256:9057473e5096e72ae5c412ef161fb2f3a29534e99ab1f42afb45a2e02b89b72b",
|
| 5079 |
+
"model.layers.4.post_feedforward_layernorm.weight": "sha256:d29d9f1fcef3787589dcd77cb45f4c5854708f57604af195d15ce8dffca013eb",
|
| 5080 |
+
"model.layers.4.pre_feedforward_layernorm.weight": "sha256:44ad48f034bf06678fbe71fd72870064d673af2e509be1eb720f1e8e745dd45c",
|
| 5081 |
+
"model.layers.4.self_attn.k_norm.weight": "sha256:9ccec7221841883c4ddc1a9e5e286a9acaaef183a13ddb8c060c886f956ba7de",
|
| 5082 |
+
"model.layers.4.self_attn.k_proj.weight": "sha256:631226628f1fe23e64b2119deb1f2b25eda0f4b6f185a458c9081637b8f2aaa5",
|
| 5083 |
+
"model.layers.4.self_attn.o_proj.weight": "sha256:a2f181d06ecb7e9a38b455f2262707ae47232e76d8667f6c2aedb23b6e4092b7",
|
| 5084 |
+
"model.layers.4.self_attn.q_norm.weight": "sha256:a526b08a8d53a8b89e89f09f8523641d6ea5115e870cd96a1101504db44aa8dc",
|
| 5085 |
+
"model.layers.4.self_attn.q_proj.weight": "sha256:473de54537646c8d2b3ad96df6d97f5e037b1826c4d1ca33c84be60b6f03a541",
|
| 5086 |
+
"model.layers.4.self_attn.v_proj.weight": "sha256:9658e3b9e5664c4f5bc3b5f746f4b9e1822aa765dd3f82af882ef40a3472665a",
|
| 5087 |
+
"model.layers.5.input_layernorm.weight": "sha256:4f2a4a289d2ce0cd6d0f3db2e9b5dc67df0f150ee13968d18ea6fa28fe50736a",
|
| 5088 |
+
"model.layers.5.mlp.down_proj.weight": "sha256:8966b3589acc51f00a9247bc07b1a88480e6da4fa2395d181838d50543147bf3",
|
| 5089 |
+
"model.layers.5.mlp.gate_proj.weight": "sha256:a6325888e4d5f893fbf2a0807f5ab05cd878b525210e70b752bb7a3e4c72a51a",
|
| 5090 |
+
"model.layers.5.mlp.up_proj.weight": "sha256:fddfce3f9e44fd4172570648445c13047f2a587c386be6d24f6bcc697be40eb6",
|
| 5091 |
+
"model.layers.5.post_attention_layernorm.weight": "sha256:12b4c1b5f71b90bc31484bd522d7d8c51fa07b9b05fc1467bccb7bdaf06310dc",
|
| 5092 |
+
"model.layers.5.post_feedforward_layernorm.weight": "sha256:b9aa5e4e3874c90980e39b95cd20b92c25bdac654ee9168c494d2929a4906097",
|
| 5093 |
+
"model.layers.5.pre_feedforward_layernorm.weight": "sha256:dec40835217deaa81f7d676de767cf098827e9761357e783475782f9ade565fe",
|
| 5094 |
+
"model.layers.5.self_attn.k_norm.weight": "sha256:d0cea3044a0b784626db26704ad29205048846f5c5d5e46116d5ceceae60bbf1",
|
| 5095 |
+
"model.layers.5.self_attn.k_proj.weight": "sha256:d70fe0d5094897b817aaf7c8c417edfa50ff57db4a5ef85b169503497697a649",
|
| 5096 |
+
"model.layers.5.self_attn.o_proj.weight": "sha256:8756035da843d6535cd5316971a5e92bcfc75d50f3162d03e5289f9b2bafdf2e",
|
| 5097 |
+
"model.layers.5.self_attn.q_norm.weight": "sha256:ffcc62d9bce53424c312223c865595312053fe91c278a48a8ad7705454980484",
|
| 5098 |
+
"model.layers.5.self_attn.q_proj.weight": "sha256:ee1dcc8b251ca9fb553918f8ff867e61ba0d5590d7b07a9840651960c3e2f1d1",
|
| 5099 |
+
"model.layers.5.self_attn.v_proj.weight": "sha256:eb733fc4ceb19960622c079502b6bd1055e06146d0c1c0ad9fec6f3a61f39e04",
|
| 5100 |
+
"model.layers.6.input_layernorm.weight": "sha256:40c545dd43e53cb16894902868f4a182093eab38e7af88432181a2d662ca6d23",
|
| 5101 |
+
"model.layers.6.mlp.down_proj.weight": "sha256:bb66e65047748c688b5ff6dfa8c4f3e7023f4c98427799181db19a0ebfcf54d3",
|
| 5102 |
+
"model.layers.6.mlp.gate_proj.weight": "sha256:1ee3327ca3d186da706304c01d5977c6df1f934bff835c2136694d002d3d7c50",
|
| 5103 |
+
"model.layers.6.mlp.up_proj.weight": "sha256:1f79b35668182047d48401c903d2de8d67f6e1bcacdee8a8143356588365520d",
|
| 5104 |
+
"model.layers.6.post_attention_layernorm.weight": "sha256:6df4447db7a378584885829d047d7ca4aadc84c5832251e57e25fcf342e86001",
|
| 5105 |
+
"model.layers.6.post_feedforward_layernorm.weight": "sha256:702bd0cdcf9c2362b76ff40cffc0f8a450a8c5b625f07dc4650b1ceef5b4560d",
|
| 5106 |
+
"model.layers.6.pre_feedforward_layernorm.weight": "sha256:2fb91e313c30178292e359eaa60d76afa0d9b4562d3914f103f2156d0f0d9cf0",
|
| 5107 |
+
"model.layers.6.self_attn.k_norm.weight": "sha256:bf8299f20b3973f08b09b9ba22708fe693bf62035b18a4025215be95e45f5f28",
|
| 5108 |
+
"model.layers.6.self_attn.k_proj.weight": "sha256:c646e3dccc2c8beebcf9020e4744b15066a71de4884c5e6f3f1cc3091106eabc",
|
| 5109 |
+
"model.layers.6.self_attn.o_proj.weight": "sha256:18d14748e325b5e6aa9574885c217522c53bf685b6aad3513c40bf8641a6fc92",
|
| 5110 |
+
"model.layers.6.self_attn.q_norm.weight": "sha256:53a991a44d9ec8f0ca7c73a99f84ce1a6799812ab6af99efcb8a245c4f67249e",
|
| 5111 |
+
"model.layers.6.self_attn.q_proj.weight": "sha256:cfdd6dc00c94a00580a2f0e24ad6a8f98ca1a5188be5ef3e79feedf965472f78",
|
| 5112 |
+
"model.layers.6.self_attn.v_proj.weight": "sha256:129a2bcc404b147b356b5fce6c1dd3bf0e4dc50f98a48774b4fa807cf10a1e45",
|
| 5113 |
+
"model.layers.7.input_layernorm.weight": "sha256:6aa94562174baf0233e72c1b60d5ad85c4780386f091e46b883e978f9f3dd00b",
|
| 5114 |
+
"model.layers.7.mlp.down_proj.weight": "sha256:120b6cc8b49221c8ebe9747586c3d5dcd7419bd35fcf91b7b1cb6a800390ea38",
|
| 5115 |
+
"model.layers.7.mlp.gate_proj.weight": "sha256:756f417cb81cc86706efa88f4a4cfcc43ef3c3861de6a697036903b29a3c74b8",
|
| 5116 |
+
"model.layers.7.mlp.up_proj.weight": "sha256:ff9aa82476f4ffa324efc896e1b9c1aecf4fa85dc836eb16bdef05eb5052ac1c",
|
| 5117 |
+
"model.layers.7.post_attention_layernorm.weight": "sha256:62dcbb20e28337f5d4cdc41aadd88bbf2ae0553911dab83bf4c52eaef12d92a2",
|
| 5118 |
+
"model.layers.7.post_feedforward_layernorm.weight": "sha256:cf5c9563aa77a1cf693eae6e2cc12982ae89101ff21666338cf667df5f40eff9",
|
| 5119 |
+
"model.layers.7.pre_feedforward_layernorm.weight": "sha256:4b6673dbd67158b8ae02e96e9ac75c456a32f9d608b973bc7db606d1b2776ce2",
|
| 5120 |
+
"model.layers.7.self_attn.k_norm.weight": "sha256:ccd85fa0360fd18de3cce849f766cb9a839df3b05afd3f7f26bb480fa618f0bc",
|
| 5121 |
+
"model.layers.7.self_attn.k_proj.weight": "sha256:d493cfc0db626fb6464b52e1419d262eaeebc69c5832d91288164d1cbdb1791e",
|
| 5122 |
+
"model.layers.7.self_attn.o_proj.weight": "sha256:2ffab84929a93016e5612b26bcd5b2749a332265cc20976e9f45fb1570d49918",
|
| 5123 |
+
"model.layers.7.self_attn.q_norm.weight": "sha256:577f638e5c70600f76ecb5a52728823b19b373b2954ff73d6046c3331748fcb8",
|
| 5124 |
+
"model.layers.7.self_attn.q_proj.weight": "sha256:733e6ba4ce62207dd80524eae04c8d268ebd3cf8a5092b7b69066c3e2f87d220",
|
| 5125 |
+
"model.layers.7.self_attn.v_proj.weight": "sha256:0e2815e611de472cd7967f846419bd42aae7ebe59a218680fffc00290acb171c",
|
| 5126 |
+
"model.layers.8.input_layernorm.weight": "sha256:05c11c138de73c210d13944e3c0cf1f6c376e8ee6bd01aa221db31e542a8a398",
|
| 5127 |
+
"model.layers.8.mlp.down_proj.weight": "sha256:c58bb3fae25a077a14784fd14e7cdf267340d0d4f02a5608964465e7e355e704",
|
| 5128 |
+
"model.layers.8.mlp.gate_proj.weight": "sha256:a1f51b3b1d1b68906696dd2a758146ceb1bd1f7c587c80367419b414200a92d0",
|
| 5129 |
+
"model.layers.8.mlp.up_proj.weight": "sha256:41b0069e633da31b8c7999d4bdf55f8010b390db618edd3b8d9ce7d02f95d1b7",
|
| 5130 |
+
"model.layers.8.post_attention_layernorm.weight": "sha256:3765272c62c16033446ecaa19226d0a8990a70d326fce5b1e6d5c72b34fb6ffd",
|
| 5131 |
+
"model.layers.8.post_feedforward_layernorm.weight": "sha256:c72c9143c09ce959230426699848c172e5f36ca37f0ea22fa10e9a0d0993bd52",
|
| 5132 |
+
"model.layers.8.pre_feedforward_layernorm.weight": "sha256:1e6be0ce554ffa5392f06d7ede6037e0957a88edcb2acd38ed87ac7d24864edb",
|
| 5133 |
+
"model.layers.8.self_attn.k_norm.weight": "sha256:606071a110d547f771693b0e8dd7f4c40677209cb9a9a796ab09432f1516c633",
|
| 5134 |
+
"model.layers.8.self_attn.k_proj.weight": "sha256:50e07cba4571c4758428fcde37f4831dbb86a667f0cd97b4576081564d56af7d",
|
| 5135 |
+
"model.layers.8.self_attn.o_proj.weight": "sha256:1f641127c6e4c8935eaa52046afa550318f1c9540c8ac115f932521fb3f2a7d6",
|
| 5136 |
+
"model.layers.8.self_attn.q_norm.weight": "sha256:36480890a80da9f6865ac5cf23d382d44931773bec8e5a5baf737c131493ddc4",
|
| 5137 |
+
"model.layers.8.self_attn.q_proj.weight": "sha256:a970e198acbc454373dc634596927ff78fb604dced5b24111df3720c895c21cc",
|
| 5138 |
+
"model.layers.8.self_attn.v_proj.weight": "sha256:578ea1d2e31deb099449fa720affb683bf6af18956d007f0f668603b3bffa1fb",
|
| 5139 |
+
"model.layers.9.input_layernorm.weight": "sha256:e36b4a0fa3f046ab678948ecec4be36318cc09cf1fc3277ec04f31fddc30fdaf",
|
| 5140 |
+
"model.layers.9.mlp.down_proj.weight": "sha256:c64b0ec9963fdebfc914c9c845ddde0a9e63568755ec4ec9e84c313fcff524d6",
|
| 5141 |
+
"model.layers.9.mlp.gate_proj.weight": "sha256:4a78ff33a59767731a122194b7d6225fc710ec3e5fce9547702c6969955e4b07",
|
| 5142 |
+
"model.layers.9.mlp.up_proj.weight": "sha256:dc586a2a40d5d0abbfedf119d3d387c19d5dc6ec7aeac84e4c2a3994e20398ca",
|
| 5143 |
+
"model.layers.9.post_attention_layernorm.weight": "sha256:925c720a31d559dad545944a57ac31b755985cfcceaa9ef43300221cdb4d8a42",
|
| 5144 |
+
"model.layers.9.post_feedforward_layernorm.weight": "sha256:bc267a9a12b15298321b5dabdb44bb37dd006d450039bba4b676f6d970f69c9b",
|
| 5145 |
+
"model.layers.9.pre_feedforward_layernorm.weight": "sha256:8c8851ae5e14dd6c9281b932ef8f45674d86e7ae490c842eaea45b90002a4510",
|
| 5146 |
+
"model.layers.9.self_attn.k_norm.weight": "sha256:9b59960251c7ba411dd2ca4895dd1c8293ea4460359c81ac1b4e14eee307821e",
|
| 5147 |
+
"model.layers.9.self_attn.k_proj.weight": "sha256:a353230f04df6fdf56a42fe5f425bd705fd15bc399c4d9d9620b77082af151b7",
|
| 5148 |
+
"model.layers.9.self_attn.o_proj.weight": "sha256:05b9d42d9eac2e672e4c39528c279a80d363cd0af25bf3cee7fa9f5aeef6fec1",
|
| 5149 |
+
"model.layers.9.self_attn.q_norm.weight": "sha256:6a1465702a974985bc79639443fe0280e7b95bc72a44b8934b98150ff53ef294",
|
| 5150 |
+
"model.layers.9.self_attn.q_proj.weight": "sha256:099cee016ede79462680738ea8be77f4bad3d6497db2ac857d460e6b0f3de359",
|
| 5151 |
+
"model.layers.9.self_attn.v_proj.weight": "sha256:34773f18e15d475ebf45b2f193a02cd259862bbc61289e7861f0a3781cbaea6a",
|
| 5152 |
+
"model.norm.weight": "sha256:1d5b835f0f654bed32aa4f9724f79434d405d40ae3222b3924fac5cc1220d92f"
|
| 5153 |
+
}
|
| 5154 |
+
}
|
| 5155 |
}
|
| 5156 |
}
|
models/translategemma-4b-1b-enes-q4k-ehf16-af32/origin.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"sourceModel": "
|
| 3 |
-
"sourceRepo": "
|
| 4 |
"sourceFormat": "safetensors",
|
| 5 |
-
"sourceRevision": "
|
| 6 |
-
"
|
| 7 |
-
"variant": "q4k-ehf16-af32",
|
| 8 |
-
"convertedAt": "2026-
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"sourceModel": "TranslateGemma 4B to Gemma 3 1B EN/ES NativeKD2 checkpoint 25",
|
| 3 |
+
"sourceRepo": "clocksmith/gamma",
|
| 4 |
"sourceFormat": "safetensors",
|
| 5 |
+
"sourceRevision": "sha256:c567331d8eb9d3da65205b83f4e0af06568c47ba81a7927005c1c2e72444bc87",
|
| 6 |
+
"sourceCheckpointId": "clocksmith/gamma-translategemma-4b-1b-enes-nativekd2@sha256:c567331d8eb9d3da65205b83f4e0af06568c47ba81a7927005c1c2e72444bc87",
|
| 7 |
+
"variant": "nativekd2-enes-q4k-ehf16-af32",
|
| 8 |
+
"convertedAt": "2026-07-11T00:54:07.571Z"
|
| 9 |
}
|
models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00000.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 67108864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d131d7f6c16207e77a1d192e7064c7576c35d68add8bda7d25ab84ce91c8835e
|
| 3 |
size 67108864
|
models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00001.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 67108864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29b3602ce153e3f0042b41c5ed95da88c30c5daea38d0a5315df2ed8d19e9277
|
| 3 |
size 67108864
|
models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00002.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 67108864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7550100a833d58db59f9b6d37751a2853b9ef0910680a2615e7ae6626ca7e52d
|
| 3 |
size 67108864
|
models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00003.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 67108864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93eada898b0833122e1f654eeefcf548f14b77f6542634d6cb28aba883b24ce5
|
| 3 |
size 67108864
|
models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00004.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 67108864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:133c80ac9119302ca1f5fa0087ea8d8adcd0e27602bd362e23894ac88b88ca9e
|
| 3 |
size 67108864
|
models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00005.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 67108864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dddbe9dac42493b004cb5c00fb1813106b1376d7eede45d5fd460e61c03e7e63
|
| 3 |
size 67108864
|
models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00006.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 67108864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0518b0f45a4ee502d7ac7de55ff1d65fac94953adfb00f8f8adefc43cc736926
|
| 3 |
size 67108864
|
models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00007.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 67108864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd8112f0840b225d009ac889df884df4e4e6f592e68f6af7fe8b8ed0b1d94529
|
| 3 |
size 67108864
|
models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00008.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 67108864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5671d65845227d36853e6778749cc021d78baef447d95b6c5fd2ff1bbdad10a9
|
| 3 |
size 67108864
|
models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00009.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 67108864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9cdcbd75b78e6807414e4feb62de18d29b4c9fc96eba50de5950162b3f2e7558
|
| 3 |
size 67108864
|
models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00010.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 67108864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb54da5bd1180b66f77c15c40d943ad88332abf0dd24e30e9eca61beeb4055d6
|
| 3 |
size 67108864
|
models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00011.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 67108864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3192759dad85e38c9cbfa84d67949d8efe0e3a2d9c1a180fa3cccbf92f415c4b
|
| 3 |
size 67108864
|
models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00012.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 67108864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca573de37d2ae350dff4cc2ca0d017ba27115b2858f463214eeaae7525039ce6
|
| 3 |
size 67108864
|
models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00013.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 67108864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4abeed2a2cac6d819bce6f3333602f97d639dd806d7b4ca93cf2956286487a4a
|
| 3 |
size 67108864
|
models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00014.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 67108864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59ed5c76c9a7320182d16c80db8469186e5bcc696c17397df498af7a42f53fdb
|
| 3 |
size 67108864
|
models/translategemma-4b-1b-enes-q4k-ehf16-af32/shard_00015.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 18860288
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:671b5387c2ba7ab7fb3dce7f90ee8e808bb42a6f21b5d809f26d39c3a2801d91
|
| 3 |
size 18860288
|
models/translategemma-4b-1b-enes-q4k-ehf16-af32/tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:064a2dec7b49ca382d305994e953c6054356c8056538e114081d44604e1934f1
|
| 3 |
+
size 14386431
|