bdellabe commited on
Commit
c3bccf8
·
verified ·
1 Parent(s): 714fc3d

Add files using upload-large-folder tool

Browse files
config.json CHANGED
@@ -94,7 +94,7 @@
94
  },
95
  "output_activations": null,
96
  "targets": [
97
- "re:.*mlp\\..*"
98
  ],
99
  "weights": {
100
  "actorder": null,
@@ -110,6 +110,44 @@
110
  "type": "float",
111
  "zp_dtype": null
112
  }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
113
  }
114
  },
115
  "format": "mixed-precision",
@@ -463,4 +501,4 @@
463
  "use_vision_norm": true,
464
  "vision_encoder_type": "hmlp"
465
  }
466
- }
 
94
  },
95
  "output_activations": null,
96
  "targets": [
97
+ "re:.*mlp\\.(?!shared_experts).*"
98
  ],
99
  "weights": {
100
  "actorder": null,
 
110
  "type": "float",
111
  "zp_dtype": null
112
  }
113
+ },
114
+ "group_2": {
115
+ "format": "float-quantized",
116
+ "input_activations": {
117
+ "actorder": null,
118
+ "block_structure": null,
119
+ "dynamic": true,
120
+ "group_size": 128,
121
+ "num_bits": 8,
122
+ "observer": null,
123
+ "observer_kwargs": {},
124
+ "scale_dtype": null,
125
+ "strategy": "group",
126
+ "symmetric": true,
127
+ "type": "float",
128
+ "zp_dtype": null
129
+ },
130
+ "output_activations": null,
131
+ "targets": [
132
+ "re:.*shared_experts.*"
133
+ ],
134
+ "weights": {
135
+ "actorder": null,
136
+ "block_structure": [
137
+ 128,
138
+ 128
139
+ ],
140
+ "dynamic": false,
141
+ "group_size": null,
142
+ "num_bits": 8,
143
+ "observer": "memoryless_minmax",
144
+ "observer_kwargs": {},
145
+ "scale_dtype": null,
146
+ "strategy": "block",
147
+ "symmetric": true,
148
+ "type": "float",
149
+ "zp_dtype": null
150
+ }
151
  }
152
  },
153
  "format": "mixed-precision",
 
501
  "use_vision_norm": true,
502
  "vision_encoder_type": "hmlp"
503
  }
504
+ }
model-00033-of-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f09547eecf7b6944dec2a2ec4bd2d56953fdd80c7f0ee492ef0282ea82120f20
3
+ size 7248678304
model.safetensors.index.json CHANGED
@@ -91,8 +91,6 @@
91
  "model.llm.layers.10.mlp.gate.bias": "model-00001-of-00032.safetensors",
92
  "model.llm.layers.10.mlp.gate.global_scale": "model-00001-of-00032.safetensors",
93
  "model.llm.layers.10.mlp.gate.weight": "model-00001-of-00032.safetensors",
94
- "model.llm.layers.10.mlp.shared_experts.shared_w13_weight": "model-00001-of-00032.safetensors",
95
- "model.llm.layers.10.mlp.shared_experts.shared_w2_weight": "model-00001-of-00032.safetensors",
96
  "model.llm.layers.10.mlp_norm.weight": "model-00001-of-00032.safetensors",
97
  "model.llm.layers.10.mlp_sconv.weight": "model-00001-of-00032.safetensors",
98
  "model.llm.layers.11.attn.k_norm.weight": "model-00001-of-00032.safetensors",
@@ -123,8 +121,6 @@
123
  "model.llm.layers.11.mlp.gate.bias": "model-00001-of-00032.safetensors",
124
  "model.llm.layers.11.mlp.gate.global_scale": "model-00001-of-00032.safetensors",
125
  "model.llm.layers.11.mlp.gate.weight": "model-00001-of-00032.safetensors",
126
- "model.llm.layers.11.mlp.shared_experts.shared_w13_weight": "model-00001-of-00032.safetensors",
127
- "model.llm.layers.11.mlp.shared_experts.shared_w2_weight": "model-00001-of-00032.safetensors",
128
  "model.llm.layers.11.mlp_norm.weight": "model-00001-of-00032.safetensors",
129
  "model.llm.layers.11.mlp_sconv.weight": "model-00001-of-00032.safetensors",
130
  "model.llm.layers.12.attn.k_norm.weight": "model-00001-of-00032.safetensors",
@@ -155,8 +151,6 @@
155
  "model.llm.layers.12.mlp.gate.bias": "model-00002-of-00032.safetensors",
156
  "model.llm.layers.12.mlp.gate.global_scale": "model-00002-of-00032.safetensors",
157
  "model.llm.layers.12.mlp.gate.weight": "model-00002-of-00032.safetensors",
158
- "model.llm.layers.12.mlp.shared_experts.shared_w13_weight": "model-00002-of-00032.safetensors",
159
- "model.llm.layers.12.mlp.shared_experts.shared_w2_weight": "model-00002-of-00032.safetensors",
160
  "model.llm.layers.12.mlp_norm.weight": "model-00002-of-00032.safetensors",
161
  "model.llm.layers.12.mlp_sconv.weight": "model-00002-of-00032.safetensors",
162
  "model.llm.layers.13.attn.k_norm.weight": "model-00002-of-00032.safetensors",
@@ -187,8 +181,6 @@
187
  "model.llm.layers.13.mlp.gate.bias": "model-00002-of-00032.safetensors",
188
  "model.llm.layers.13.mlp.gate.global_scale": "model-00002-of-00032.safetensors",
189
  "model.llm.layers.13.mlp.gate.weight": "model-00002-of-00032.safetensors",
190
- "model.llm.layers.13.mlp.shared_experts.shared_w13_weight": "model-00002-of-00032.safetensors",
191
- "model.llm.layers.13.mlp.shared_experts.shared_w2_weight": "model-00002-of-00032.safetensors",
192
  "model.llm.layers.13.mlp_norm.weight": "model-00002-of-00032.safetensors",
193
  "model.llm.layers.13.mlp_sconv.weight": "model-00002-of-00032.safetensors",
194
  "model.llm.layers.14.attn.k_norm.weight": "model-00002-of-00032.safetensors",
@@ -219,8 +211,6 @@
219
  "model.llm.layers.14.mlp.gate.bias": "model-00003-of-00032.safetensors",
220
  "model.llm.layers.14.mlp.gate.global_scale": "model-00003-of-00032.safetensors",
221
  "model.llm.layers.14.mlp.gate.weight": "model-00003-of-00032.safetensors",
222
- "model.llm.layers.14.mlp.shared_experts.shared_w13_weight": "model-00003-of-00032.safetensors",
223
- "model.llm.layers.14.mlp.shared_experts.shared_w2_weight": "model-00003-of-00032.safetensors",
224
  "model.llm.layers.14.mlp_norm.weight": "model-00003-of-00032.safetensors",
225
  "model.llm.layers.14.mlp_sconv.weight": "model-00003-of-00032.safetensors",
226
  "model.llm.layers.15.attn.k_norm.weight": "model-00003-of-00032.safetensors",
@@ -251,8 +241,6 @@
251
  "model.llm.layers.15.mlp.gate.bias": "model-00003-of-00032.safetensors",
252
  "model.llm.layers.15.mlp.gate.global_scale": "model-00003-of-00032.safetensors",
253
  "model.llm.layers.15.mlp.gate.weight": "model-00003-of-00032.safetensors",
254
- "model.llm.layers.15.mlp.shared_experts.shared_w13_weight": "model-00003-of-00032.safetensors",
255
- "model.llm.layers.15.mlp.shared_experts.shared_w2_weight": "model-00003-of-00032.safetensors",
256
  "model.llm.layers.15.mlp_norm.weight": "model-00003-of-00032.safetensors",
257
  "model.llm.layers.15.mlp_sconv.weight": "model-00003-of-00032.safetensors",
258
  "model.llm.layers.16.attn.k_norm.weight": "model-00003-of-00032.safetensors",
@@ -283,8 +271,6 @@
283
  "model.llm.layers.16.mlp.gate.bias": "model-00004-of-00032.safetensors",
284
  "model.llm.layers.16.mlp.gate.global_scale": "model-00004-of-00032.safetensors",
285
  "model.llm.layers.16.mlp.gate.weight": "model-00004-of-00032.safetensors",
286
- "model.llm.layers.16.mlp.shared_experts.shared_w13_weight": "model-00004-of-00032.safetensors",
287
- "model.llm.layers.16.mlp.shared_experts.shared_w2_weight": "model-00004-of-00032.safetensors",
288
  "model.llm.layers.16.mlp_norm.weight": "model-00004-of-00032.safetensors",
289
  "model.llm.layers.16.mlp_sconv.weight": "model-00004-of-00032.safetensors",
290
  "model.llm.layers.17.attn.k_norm.weight": "model-00004-of-00032.safetensors",
@@ -315,8 +301,6 @@
315
  "model.llm.layers.17.mlp.gate.bias": "model-00004-of-00032.safetensors",
316
  "model.llm.layers.17.mlp.gate.global_scale": "model-00004-of-00032.safetensors",
317
  "model.llm.layers.17.mlp.gate.weight": "model-00004-of-00032.safetensors",
318
- "model.llm.layers.17.mlp.shared_experts.shared_w13_weight": "model-00004-of-00032.safetensors",
319
- "model.llm.layers.17.mlp.shared_experts.shared_w2_weight": "model-00004-of-00032.safetensors",
320
  "model.llm.layers.17.mlp_norm.weight": "model-00004-of-00032.safetensors",
321
  "model.llm.layers.17.mlp_sconv.weight": "model-00004-of-00032.safetensors",
322
  "model.llm.layers.18.attn.k_norm.weight": "model-00004-of-00032.safetensors",
@@ -347,8 +331,6 @@
347
  "model.llm.layers.18.mlp.gate.bias": "model-00005-of-00032.safetensors",
348
  "model.llm.layers.18.mlp.gate.global_scale": "model-00005-of-00032.safetensors",
349
  "model.llm.layers.18.mlp.gate.weight": "model-00005-of-00032.safetensors",
350
- "model.llm.layers.18.mlp.shared_experts.shared_w13_weight": "model-00005-of-00032.safetensors",
351
- "model.llm.layers.18.mlp.shared_experts.shared_w2_weight": "model-00005-of-00032.safetensors",
352
  "model.llm.layers.18.mlp_norm.weight": "model-00005-of-00032.safetensors",
353
  "model.llm.layers.18.mlp_sconv.weight": "model-00005-of-00032.safetensors",
354
  "model.llm.layers.19.attn.k_norm.weight": "model-00005-of-00032.safetensors",
@@ -379,8 +361,6 @@
379
  "model.llm.layers.19.mlp.gate.bias": "model-00005-of-00032.safetensors",
380
  "model.llm.layers.19.mlp.gate.global_scale": "model-00005-of-00032.safetensors",
381
  "model.llm.layers.19.mlp.gate.weight": "model-00005-of-00032.safetensors",
382
- "model.llm.layers.19.mlp.shared_experts.shared_w13_weight": "model-00005-of-00032.safetensors",
383
- "model.llm.layers.19.mlp.shared_experts.shared_w2_weight": "model-00005-of-00032.safetensors",
384
  "model.llm.layers.19.mlp_norm.weight": "model-00005-of-00032.safetensors",
385
  "model.llm.layers.19.mlp_sconv.weight": "model-00005-of-00032.safetensors",
386
  "model.llm.layers.2.attn.k_norm.weight": "model-00005-of-00032.safetensors",
@@ -411,8 +391,6 @@
411
  "model.llm.layers.2.mlp.gate.bias": "model-00006-of-00032.safetensors",
412
  "model.llm.layers.2.mlp.gate.global_scale": "model-00006-of-00032.safetensors",
413
  "model.llm.layers.2.mlp.gate.weight": "model-00006-of-00032.safetensors",
414
- "model.llm.layers.2.mlp.shared_experts.shared_w13_weight": "model-00006-of-00032.safetensors",
415
- "model.llm.layers.2.mlp.shared_experts.shared_w2_weight": "model-00006-of-00032.safetensors",
416
  "model.llm.layers.2.mlp_norm.weight": "model-00006-of-00032.safetensors",
417
  "model.llm.layers.2.mlp_sconv.weight": "model-00006-of-00032.safetensors",
418
  "model.llm.layers.20.attn.k_norm.weight": "model-00006-of-00032.safetensors",
@@ -443,8 +421,6 @@
443
  "model.llm.layers.20.mlp.gate.bias": "model-00006-of-00032.safetensors",
444
  "model.llm.layers.20.mlp.gate.global_scale": "model-00006-of-00032.safetensors",
445
  "model.llm.layers.20.mlp.gate.weight": "model-00006-of-00032.safetensors",
446
- "model.llm.layers.20.mlp.shared_experts.shared_w13_weight": "model-00006-of-00032.safetensors",
447
- "model.llm.layers.20.mlp.shared_experts.shared_w2_weight": "model-00006-of-00032.safetensors",
448
  "model.llm.layers.20.mlp_norm.weight": "model-00006-of-00032.safetensors",
449
  "model.llm.layers.20.mlp_sconv.weight": "model-00006-of-00032.safetensors",
450
  "model.llm.layers.21.attn.k_norm.weight": "model-00006-of-00032.safetensors",
@@ -475,8 +451,6 @@
475
  "model.llm.layers.21.mlp.gate.bias": "model-00007-of-00032.safetensors",
476
  "model.llm.layers.21.mlp.gate.global_scale": "model-00007-of-00032.safetensors",
477
  "model.llm.layers.21.mlp.gate.weight": "model-00007-of-00032.safetensors",
478
- "model.llm.layers.21.mlp.shared_experts.shared_w13_weight": "model-00007-of-00032.safetensors",
479
- "model.llm.layers.21.mlp.shared_experts.shared_w2_weight": "model-00007-of-00032.safetensors",
480
  "model.llm.layers.21.mlp_norm.weight": "model-00007-of-00032.safetensors",
481
  "model.llm.layers.21.mlp_sconv.weight": "model-00007-of-00032.safetensors",
482
  "model.llm.layers.22.attn.k_norm.weight": "model-00007-of-00032.safetensors",
@@ -507,8 +481,6 @@
507
  "model.llm.layers.22.mlp.gate.bias": "model-00007-of-00032.safetensors",
508
  "model.llm.layers.22.mlp.gate.global_scale": "model-00007-of-00032.safetensors",
509
  "model.llm.layers.22.mlp.gate.weight": "model-00007-of-00032.safetensors",
510
- "model.llm.layers.22.mlp.shared_experts.shared_w13_weight": "model-00007-of-00032.safetensors",
511
- "model.llm.layers.22.mlp.shared_experts.shared_w2_weight": "model-00007-of-00032.safetensors",
512
  "model.llm.layers.22.mlp_norm.weight": "model-00007-of-00032.safetensors",
513
  "model.llm.layers.22.mlp_sconv.weight": "model-00007-of-00032.safetensors",
514
  "model.llm.layers.23.attn.k_norm.weight": "model-00007-of-00032.safetensors",
@@ -539,8 +511,6 @@
539
  "model.llm.layers.23.mlp.gate.bias": "model-00008-of-00032.safetensors",
540
  "model.llm.layers.23.mlp.gate.global_scale": "model-00008-of-00032.safetensors",
541
  "model.llm.layers.23.mlp.gate.weight": "model-00008-of-00032.safetensors",
542
- "model.llm.layers.23.mlp.shared_experts.shared_w13_weight": "model-00008-of-00032.safetensors",
543
- "model.llm.layers.23.mlp.shared_experts.shared_w2_weight": "model-00008-of-00032.safetensors",
544
  "model.llm.layers.23.mlp_norm.weight": "model-00008-of-00032.safetensors",
545
  "model.llm.layers.23.mlp_sconv.weight": "model-00008-of-00032.safetensors",
546
  "model.llm.layers.24.attn.k_norm.weight": "model-00008-of-00032.safetensors",
@@ -571,8 +541,6 @@
571
  "model.llm.layers.24.mlp.gate.bias": "model-00008-of-00032.safetensors",
572
  "model.llm.layers.24.mlp.gate.global_scale": "model-00008-of-00032.safetensors",
573
  "model.llm.layers.24.mlp.gate.weight": "model-00008-of-00032.safetensors",
574
- "model.llm.layers.24.mlp.shared_experts.shared_w13_weight": "model-00008-of-00032.safetensors",
575
- "model.llm.layers.24.mlp.shared_experts.shared_w2_weight": "model-00008-of-00032.safetensors",
576
  "model.llm.layers.24.mlp_norm.weight": "model-00008-of-00032.safetensors",
577
  "model.llm.layers.24.mlp_sconv.weight": "model-00008-of-00032.safetensors",
578
  "model.llm.layers.25.attn.k_norm.weight": "model-00008-of-00032.safetensors",
@@ -603,8 +571,6 @@
603
  "model.llm.layers.25.mlp.gate.bias": "model-00009-of-00032.safetensors",
604
  "model.llm.layers.25.mlp.gate.global_scale": "model-00009-of-00032.safetensors",
605
  "model.llm.layers.25.mlp.gate.weight": "model-00009-of-00032.safetensors",
606
- "model.llm.layers.25.mlp.shared_experts.shared_w13_weight": "model-00009-of-00032.safetensors",
607
- "model.llm.layers.25.mlp.shared_experts.shared_w2_weight": "model-00009-of-00032.safetensors",
608
  "model.llm.layers.25.mlp_norm.weight": "model-00009-of-00032.safetensors",
609
  "model.llm.layers.25.mlp_sconv.weight": "model-00009-of-00032.safetensors",
610
  "model.llm.layers.26.attn.k_norm.weight": "model-00009-of-00032.safetensors",
@@ -635,8 +601,6 @@
635
  "model.llm.layers.26.mlp.gate.bias": "model-00009-of-00032.safetensors",
636
  "model.llm.layers.26.mlp.gate.global_scale": "model-00009-of-00032.safetensors",
637
  "model.llm.layers.26.mlp.gate.weight": "model-00009-of-00032.safetensors",
638
- "model.llm.layers.26.mlp.shared_experts.shared_w13_weight": "model-00009-of-00032.safetensors",
639
- "model.llm.layers.26.mlp.shared_experts.shared_w2_weight": "model-00009-of-00032.safetensors",
640
  "model.llm.layers.26.mlp_norm.weight": "model-00009-of-00032.safetensors",
641
  "model.llm.layers.26.mlp_sconv.weight": "model-00009-of-00032.safetensors",
642
  "model.llm.layers.27.attn.k_norm.weight": "model-00009-of-00032.safetensors",
@@ -667,8 +631,6 @@
667
  "model.llm.layers.27.mlp.gate.bias": "model-00010-of-00032.safetensors",
668
  "model.llm.layers.27.mlp.gate.global_scale": "model-00010-of-00032.safetensors",
669
  "model.llm.layers.27.mlp.gate.weight": "model-00010-of-00032.safetensors",
670
- "model.llm.layers.27.mlp.shared_experts.shared_w13_weight": "model-00010-of-00032.safetensors",
671
- "model.llm.layers.27.mlp.shared_experts.shared_w2_weight": "model-00010-of-00032.safetensors",
672
  "model.llm.layers.27.mlp_norm.weight": "model-00010-of-00032.safetensors",
673
  "model.llm.layers.27.mlp_sconv.weight": "model-00010-of-00032.safetensors",
674
  "model.llm.layers.28.attn.k_norm.weight": "model-00010-of-00032.safetensors",
@@ -699,8 +661,6 @@
699
  "model.llm.layers.28.mlp.gate.bias": "model-00010-of-00032.safetensors",
700
  "model.llm.layers.28.mlp.gate.global_scale": "model-00010-of-00032.safetensors",
701
  "model.llm.layers.28.mlp.gate.weight": "model-00010-of-00032.safetensors",
702
- "model.llm.layers.28.mlp.shared_experts.shared_w13_weight": "model-00010-of-00032.safetensors",
703
- "model.llm.layers.28.mlp.shared_experts.shared_w2_weight": "model-00010-of-00032.safetensors",
704
  "model.llm.layers.28.mlp_norm.weight": "model-00010-of-00032.safetensors",
705
  "model.llm.layers.28.mlp_sconv.weight": "model-00010-of-00032.safetensors",
706
  "model.llm.layers.29.attn.k_norm.weight": "model-00010-of-00032.safetensors",
@@ -731,8 +691,6 @@
731
  "model.llm.layers.29.mlp.gate.bias": "model-00011-of-00032.safetensors",
732
  "model.llm.layers.29.mlp.gate.global_scale": "model-00011-of-00032.safetensors",
733
  "model.llm.layers.29.mlp.gate.weight": "model-00011-of-00032.safetensors",
734
- "model.llm.layers.29.mlp.shared_experts.shared_w13_weight": "model-00011-of-00032.safetensors",
735
- "model.llm.layers.29.mlp.shared_experts.shared_w2_weight": "model-00011-of-00032.safetensors",
736
  "model.llm.layers.29.mlp_norm.weight": "model-00011-of-00032.safetensors",
737
  "model.llm.layers.29.mlp_sconv.weight": "model-00011-of-00032.safetensors",
738
  "model.llm.layers.3.attn.k_norm.weight": "model-00011-of-00032.safetensors",
@@ -763,8 +721,6 @@
763
  "model.llm.layers.3.mlp.gate.bias": "model-00011-of-00032.safetensors",
764
  "model.llm.layers.3.mlp.gate.global_scale": "model-00011-of-00032.safetensors",
765
  "model.llm.layers.3.mlp.gate.weight": "model-00011-of-00032.safetensors",
766
- "model.llm.layers.3.mlp.shared_experts.shared_w13_weight": "model-00011-of-00032.safetensors",
767
- "model.llm.layers.3.mlp.shared_experts.shared_w2_weight": "model-00011-of-00032.safetensors",
768
  "model.llm.layers.3.mlp_norm.weight": "model-00011-of-00032.safetensors",
769
  "model.llm.layers.3.mlp_sconv.weight": "model-00011-of-00032.safetensors",
770
  "model.llm.layers.30.attn.k_norm.weight": "model-00011-of-00032.safetensors",
@@ -795,8 +751,6 @@
795
  "model.llm.layers.30.mlp.gate.bias": "model-00012-of-00032.safetensors",
796
  "model.llm.layers.30.mlp.gate.global_scale": "model-00012-of-00032.safetensors",
797
  "model.llm.layers.30.mlp.gate.weight": "model-00012-of-00032.safetensors",
798
- "model.llm.layers.30.mlp.shared_experts.shared_w13_weight": "model-00012-of-00032.safetensors",
799
- "model.llm.layers.30.mlp.shared_experts.shared_w2_weight": "model-00012-of-00032.safetensors",
800
  "model.llm.layers.30.mlp_norm.weight": "model-00012-of-00032.safetensors",
801
  "model.llm.layers.30.mlp_sconv.weight": "model-00012-of-00032.safetensors",
802
  "model.llm.layers.31.attn.k_norm.weight": "model-00012-of-00032.safetensors",
@@ -827,8 +781,6 @@
827
  "model.llm.layers.31.mlp.gate.bias": "model-00012-of-00032.safetensors",
828
  "model.llm.layers.31.mlp.gate.global_scale": "model-00012-of-00032.safetensors",
829
  "model.llm.layers.31.mlp.gate.weight": "model-00012-of-00032.safetensors",
830
- "model.llm.layers.31.mlp.shared_experts.shared_w13_weight": "model-00012-of-00032.safetensors",
831
- "model.llm.layers.31.mlp.shared_experts.shared_w2_weight": "model-00012-of-00032.safetensors",
832
  "model.llm.layers.31.mlp_norm.weight": "model-00012-of-00032.safetensors",
833
  "model.llm.layers.31.mlp_sconv.weight": "model-00012-of-00032.safetensors",
834
  "model.llm.layers.32.attn.k_norm.weight": "model-00012-of-00032.safetensors",
@@ -859,8 +811,6 @@
859
  "model.llm.layers.32.mlp.gate.bias": "model-00013-of-00032.safetensors",
860
  "model.llm.layers.32.mlp.gate.global_scale": "model-00013-of-00032.safetensors",
861
  "model.llm.layers.32.mlp.gate.weight": "model-00013-of-00032.safetensors",
862
- "model.llm.layers.32.mlp.shared_experts.shared_w13_weight": "model-00013-of-00032.safetensors",
863
- "model.llm.layers.32.mlp.shared_experts.shared_w2_weight": "model-00013-of-00032.safetensors",
864
  "model.llm.layers.32.mlp_norm.weight": "model-00013-of-00032.safetensors",
865
  "model.llm.layers.32.mlp_sconv.weight": "model-00013-of-00032.safetensors",
866
  "model.llm.layers.33.attn.k_norm.weight": "model-00013-of-00032.safetensors",
@@ -891,8 +841,6 @@
891
  "model.llm.layers.33.mlp.gate.bias": "model-00013-of-00032.safetensors",
892
  "model.llm.layers.33.mlp.gate.global_scale": "model-00013-of-00032.safetensors",
893
  "model.llm.layers.33.mlp.gate.weight": "model-00013-of-00032.safetensors",
894
- "model.llm.layers.33.mlp.shared_experts.shared_w13_weight": "model-00013-of-00032.safetensors",
895
- "model.llm.layers.33.mlp.shared_experts.shared_w2_weight": "model-00013-of-00032.safetensors",
896
  "model.llm.layers.33.mlp_norm.weight": "model-00013-of-00032.safetensors",
897
  "model.llm.layers.33.mlp_sconv.weight": "model-00013-of-00032.safetensors",
898
  "model.llm.layers.34.attn.k_norm.weight": "model-00013-of-00032.safetensors",
@@ -923,8 +871,6 @@
923
  "model.llm.layers.34.mlp.gate.bias": "model-00014-of-00032.safetensors",
924
  "model.llm.layers.34.mlp.gate.global_scale": "model-00014-of-00032.safetensors",
925
  "model.llm.layers.34.mlp.gate.weight": "model-00014-of-00032.safetensors",
926
- "model.llm.layers.34.mlp.shared_experts.shared_w13_weight": "model-00014-of-00032.safetensors",
927
- "model.llm.layers.34.mlp.shared_experts.shared_w2_weight": "model-00014-of-00032.safetensors",
928
  "model.llm.layers.34.mlp_norm.weight": "model-00014-of-00032.safetensors",
929
  "model.llm.layers.34.mlp_sconv.weight": "model-00014-of-00032.safetensors",
930
  "model.llm.layers.35.attn.k_norm.weight": "model-00014-of-00032.safetensors",
@@ -955,8 +901,6 @@
955
  "model.llm.layers.35.mlp.gate.bias": "model-00014-of-00032.safetensors",
956
  "model.llm.layers.35.mlp.gate.global_scale": "model-00014-of-00032.safetensors",
957
  "model.llm.layers.35.mlp.gate.weight": "model-00014-of-00032.safetensors",
958
- "model.llm.layers.35.mlp.shared_experts.shared_w13_weight": "model-00014-of-00032.safetensors",
959
- "model.llm.layers.35.mlp.shared_experts.shared_w2_weight": "model-00014-of-00032.safetensors",
960
  "model.llm.layers.35.mlp_norm.weight": "model-00014-of-00032.safetensors",
961
  "model.llm.layers.35.mlp_sconv.weight": "model-00014-of-00032.safetensors",
962
  "model.llm.layers.36.attn.k_norm.weight": "model-00014-of-00032.safetensors",
@@ -987,8 +931,6 @@
987
  "model.llm.layers.36.mlp.gate.bias": "model-00015-of-00032.safetensors",
988
  "model.llm.layers.36.mlp.gate.global_scale": "model-00015-of-00032.safetensors",
989
  "model.llm.layers.36.mlp.gate.weight": "model-00015-of-00032.safetensors",
990
- "model.llm.layers.36.mlp.shared_experts.shared_w13_weight": "model-00015-of-00032.safetensors",
991
- "model.llm.layers.36.mlp.shared_experts.shared_w2_weight": "model-00015-of-00032.safetensors",
992
  "model.llm.layers.36.mlp_norm.weight": "model-00015-of-00032.safetensors",
993
  "model.llm.layers.36.mlp_sconv.weight": "model-00015-of-00032.safetensors",
994
  "model.llm.layers.37.attn.k_norm.weight": "model-00015-of-00032.safetensors",
@@ -1019,8 +961,6 @@
1019
  "model.llm.layers.37.mlp.gate.bias": "model-00015-of-00032.safetensors",
1020
  "model.llm.layers.37.mlp.gate.global_scale": "model-00015-of-00032.safetensors",
1021
  "model.llm.layers.37.mlp.gate.weight": "model-00015-of-00032.safetensors",
1022
- "model.llm.layers.37.mlp.shared_experts.shared_w13_weight": "model-00015-of-00032.safetensors",
1023
- "model.llm.layers.37.mlp.shared_experts.shared_w2_weight": "model-00015-of-00032.safetensors",
1024
  "model.llm.layers.37.mlp_norm.weight": "model-00015-of-00032.safetensors",
1025
  "model.llm.layers.37.mlp_sconv.weight": "model-00015-of-00032.safetensors",
1026
  "model.llm.layers.38.attn.k_norm.weight": "model-00015-of-00032.safetensors",
@@ -1051,8 +991,6 @@
1051
  "model.llm.layers.38.mlp.gate.bias": "model-00016-of-00032.safetensors",
1052
  "model.llm.layers.38.mlp.gate.global_scale": "model-00016-of-00032.safetensors",
1053
  "model.llm.layers.38.mlp.gate.weight": "model-00016-of-00032.safetensors",
1054
- "model.llm.layers.38.mlp.shared_experts.shared_w13_weight": "model-00016-of-00032.safetensors",
1055
- "model.llm.layers.38.mlp.shared_experts.shared_w2_weight": "model-00016-of-00032.safetensors",
1056
  "model.llm.layers.38.mlp_norm.weight": "model-00016-of-00032.safetensors",
1057
  "model.llm.layers.38.mlp_sconv.weight": "model-00016-of-00032.safetensors",
1058
  "model.llm.layers.39.attn.k_norm.weight": "model-00016-of-00032.safetensors",
@@ -1083,8 +1021,6 @@
1083
  "model.llm.layers.39.mlp.gate.bias": "model-00016-of-00032.safetensors",
1084
  "model.llm.layers.39.mlp.gate.global_scale": "model-00016-of-00032.safetensors",
1085
  "model.llm.layers.39.mlp.gate.weight": "model-00016-of-00032.safetensors",
1086
- "model.llm.layers.39.mlp.shared_experts.shared_w13_weight": "model-00016-of-00032.safetensors",
1087
- "model.llm.layers.39.mlp.shared_experts.shared_w2_weight": "model-00016-of-00032.safetensors",
1088
  "model.llm.layers.39.mlp_norm.weight": "model-00016-of-00032.safetensors",
1089
  "model.llm.layers.39.mlp_sconv.weight": "model-00016-of-00032.safetensors",
1090
  "model.llm.layers.4.attn.k_norm.weight": "model-00016-of-00032.safetensors",
@@ -1115,8 +1051,6 @@
1115
  "model.llm.layers.4.mlp.gate.bias": "model-00017-of-00032.safetensors",
1116
  "model.llm.layers.4.mlp.gate.global_scale": "model-00017-of-00032.safetensors",
1117
  "model.llm.layers.4.mlp.gate.weight": "model-00017-of-00032.safetensors",
1118
- "model.llm.layers.4.mlp.shared_experts.shared_w13_weight": "model-00017-of-00032.safetensors",
1119
- "model.llm.layers.4.mlp.shared_experts.shared_w2_weight": "model-00017-of-00032.safetensors",
1120
  "model.llm.layers.4.mlp_norm.weight": "model-00017-of-00032.safetensors",
1121
  "model.llm.layers.4.mlp_sconv.weight": "model-00017-of-00032.safetensors",
1122
  "model.llm.layers.40.attn.k_norm.weight": "model-00017-of-00032.safetensors",
@@ -1147,8 +1081,6 @@
1147
  "model.llm.layers.40.mlp.gate.bias": "model-00017-of-00032.safetensors",
1148
  "model.llm.layers.40.mlp.gate.global_scale": "model-00017-of-00032.safetensors",
1149
  "model.llm.layers.40.mlp.gate.weight": "model-00017-of-00032.safetensors",
1150
- "model.llm.layers.40.mlp.shared_experts.shared_w13_weight": "model-00017-of-00032.safetensors",
1151
- "model.llm.layers.40.mlp.shared_experts.shared_w2_weight": "model-00017-of-00032.safetensors",
1152
  "model.llm.layers.40.mlp_norm.weight": "model-00017-of-00032.safetensors",
1153
  "model.llm.layers.40.mlp_sconv.weight": "model-00017-of-00032.safetensors",
1154
  "model.llm.layers.41.attn.k_norm.weight": "model-00017-of-00032.safetensors",
@@ -1179,8 +1111,6 @@
1179
  "model.llm.layers.41.mlp.gate.bias": "model-00018-of-00032.safetensors",
1180
  "model.llm.layers.41.mlp.gate.global_scale": "model-00018-of-00032.safetensors",
1181
  "model.llm.layers.41.mlp.gate.weight": "model-00018-of-00032.safetensors",
1182
- "model.llm.layers.41.mlp.shared_experts.shared_w13_weight": "model-00018-of-00032.safetensors",
1183
- "model.llm.layers.41.mlp.shared_experts.shared_w2_weight": "model-00018-of-00032.safetensors",
1184
  "model.llm.layers.41.mlp_norm.weight": "model-00018-of-00032.safetensors",
1185
  "model.llm.layers.41.mlp_sconv.weight": "model-00018-of-00032.safetensors",
1186
  "model.llm.layers.42.attn.k_norm.weight": "model-00018-of-00032.safetensors",
@@ -1211,8 +1141,6 @@
1211
  "model.llm.layers.42.mlp.gate.bias": "model-00018-of-00032.safetensors",
1212
  "model.llm.layers.42.mlp.gate.global_scale": "model-00018-of-00032.safetensors",
1213
  "model.llm.layers.42.mlp.gate.weight": "model-00018-of-00032.safetensors",
1214
- "model.llm.layers.42.mlp.shared_experts.shared_w13_weight": "model-00018-of-00032.safetensors",
1215
- "model.llm.layers.42.mlp.shared_experts.shared_w2_weight": "model-00018-of-00032.safetensors",
1216
  "model.llm.layers.42.mlp_norm.weight": "model-00018-of-00032.safetensors",
1217
  "model.llm.layers.42.mlp_sconv.weight": "model-00018-of-00032.safetensors",
1218
  "model.llm.layers.43.attn.k_norm.weight": "model-00018-of-00032.safetensors",
@@ -1243,8 +1171,6 @@
1243
  "model.llm.layers.43.mlp.gate.bias": "model-00019-of-00032.safetensors",
1244
  "model.llm.layers.43.mlp.gate.global_scale": "model-00019-of-00032.safetensors",
1245
  "model.llm.layers.43.mlp.gate.weight": "model-00019-of-00032.safetensors",
1246
- "model.llm.layers.43.mlp.shared_experts.shared_w13_weight": "model-00019-of-00032.safetensors",
1247
- "model.llm.layers.43.mlp.shared_experts.shared_w2_weight": "model-00019-of-00032.safetensors",
1248
  "model.llm.layers.43.mlp_norm.weight": "model-00019-of-00032.safetensors",
1249
  "model.llm.layers.43.mlp_sconv.weight": "model-00019-of-00032.safetensors",
1250
  "model.llm.layers.44.attn.k_norm.weight": "model-00019-of-00032.safetensors",
@@ -1275,8 +1201,6 @@
1275
  "model.llm.layers.44.mlp.gate.bias": "model-00019-of-00032.safetensors",
1276
  "model.llm.layers.44.mlp.gate.global_scale": "model-00019-of-00032.safetensors",
1277
  "model.llm.layers.44.mlp.gate.weight": "model-00019-of-00032.safetensors",
1278
- "model.llm.layers.44.mlp.shared_experts.shared_w13_weight": "model-00019-of-00032.safetensors",
1279
- "model.llm.layers.44.mlp.shared_experts.shared_w2_weight": "model-00019-of-00032.safetensors",
1280
  "model.llm.layers.44.mlp_norm.weight": "model-00019-of-00032.safetensors",
1281
  "model.llm.layers.44.mlp_sconv.weight": "model-00019-of-00032.safetensors",
1282
  "model.llm.layers.45.attn.k_norm.weight": "model-00019-of-00032.safetensors",
@@ -1307,8 +1231,6 @@
1307
  "model.llm.layers.45.mlp.gate.bias": "model-00020-of-00032.safetensors",
1308
  "model.llm.layers.45.mlp.gate.global_scale": "model-00020-of-00032.safetensors",
1309
  "model.llm.layers.45.mlp.gate.weight": "model-00020-of-00032.safetensors",
1310
- "model.llm.layers.45.mlp.shared_experts.shared_w13_weight": "model-00020-of-00032.safetensors",
1311
- "model.llm.layers.45.mlp.shared_experts.shared_w2_weight": "model-00020-of-00032.safetensors",
1312
  "model.llm.layers.45.mlp_norm.weight": "model-00020-of-00032.safetensors",
1313
  "model.llm.layers.45.mlp_sconv.weight": "model-00020-of-00032.safetensors",
1314
  "model.llm.layers.46.attn.k_norm.weight": "model-00020-of-00032.safetensors",
@@ -1339,8 +1261,6 @@
1339
  "model.llm.layers.46.mlp.gate.bias": "model-00020-of-00032.safetensors",
1340
  "model.llm.layers.46.mlp.gate.global_scale": "model-00020-of-00032.safetensors",
1341
  "model.llm.layers.46.mlp.gate.weight": "model-00020-of-00032.safetensors",
1342
- "model.llm.layers.46.mlp.shared_experts.shared_w13_weight": "model-00020-of-00032.safetensors",
1343
- "model.llm.layers.46.mlp.shared_experts.shared_w2_weight": "model-00020-of-00032.safetensors",
1344
  "model.llm.layers.46.mlp_norm.weight": "model-00020-of-00032.safetensors",
1345
  "model.llm.layers.46.mlp_sconv.weight": "model-00020-of-00032.safetensors",
1346
  "model.llm.layers.47.attn.k_norm.weight": "model-00020-of-00032.safetensors",
@@ -1371,8 +1291,6 @@
1371
  "model.llm.layers.47.mlp.gate.bias": "model-00021-of-00032.safetensors",
1372
  "model.llm.layers.47.mlp.gate.global_scale": "model-00021-of-00032.safetensors",
1373
  "model.llm.layers.47.mlp.gate.weight": "model-00021-of-00032.safetensors",
1374
- "model.llm.layers.47.mlp.shared_experts.shared_w13_weight": "model-00021-of-00032.safetensors",
1375
- "model.llm.layers.47.mlp.shared_experts.shared_w2_weight": "model-00021-of-00032.safetensors",
1376
  "model.llm.layers.47.mlp_norm.weight": "model-00021-of-00032.safetensors",
1377
  "model.llm.layers.47.mlp_sconv.weight": "model-00021-of-00032.safetensors",
1378
  "model.llm.layers.48.attn.k_norm.weight": "model-00021-of-00032.safetensors",
@@ -1403,8 +1321,6 @@
1403
  "model.llm.layers.48.mlp.gate.bias": "model-00021-of-00032.safetensors",
1404
  "model.llm.layers.48.mlp.gate.global_scale": "model-00021-of-00032.safetensors",
1405
  "model.llm.layers.48.mlp.gate.weight": "model-00021-of-00032.safetensors",
1406
- "model.llm.layers.48.mlp.shared_experts.shared_w13_weight": "model-00021-of-00032.safetensors",
1407
- "model.llm.layers.48.mlp.shared_experts.shared_w2_weight": "model-00021-of-00032.safetensors",
1408
  "model.llm.layers.48.mlp_norm.weight": "model-00021-of-00032.safetensors",
1409
  "model.llm.layers.48.mlp_sconv.weight": "model-00021-of-00032.safetensors",
1410
  "model.llm.layers.49.attn.k_norm.weight": "model-00021-of-00032.safetensors",
@@ -1435,8 +1351,6 @@
1435
  "model.llm.layers.49.mlp.gate.bias": "model-00022-of-00032.safetensors",
1436
  "model.llm.layers.49.mlp.gate.global_scale": "model-00022-of-00032.safetensors",
1437
  "model.llm.layers.49.mlp.gate.weight": "model-00022-of-00032.safetensors",
1438
- "model.llm.layers.49.mlp.shared_experts.shared_w13_weight": "model-00022-of-00032.safetensors",
1439
- "model.llm.layers.49.mlp.shared_experts.shared_w2_weight": "model-00022-of-00032.safetensors",
1440
  "model.llm.layers.49.mlp_norm.weight": "model-00022-of-00032.safetensors",
1441
  "model.llm.layers.49.mlp_sconv.weight": "model-00022-of-00032.safetensors",
1442
  "model.llm.layers.5.attn.k_norm.weight": "model-00022-of-00032.safetensors",
@@ -1467,8 +1381,6 @@
1467
  "model.llm.layers.5.mlp.gate.bias": "model-00022-of-00032.safetensors",
1468
  "model.llm.layers.5.mlp.gate.global_scale": "model-00022-of-00032.safetensors",
1469
  "model.llm.layers.5.mlp.gate.weight": "model-00022-of-00032.safetensors",
1470
- "model.llm.layers.5.mlp.shared_experts.shared_w13_weight": "model-00022-of-00032.safetensors",
1471
- "model.llm.layers.5.mlp.shared_experts.shared_w2_weight": "model-00022-of-00032.safetensors",
1472
  "model.llm.layers.5.mlp_norm.weight": "model-00022-of-00032.safetensors",
1473
  "model.llm.layers.5.mlp_sconv.weight": "model-00022-of-00032.safetensors",
1474
  "model.llm.layers.50.attn.k_norm.weight": "model-00022-of-00032.safetensors",
@@ -1499,8 +1411,6 @@
1499
  "model.llm.layers.50.mlp.gate.bias": "model-00023-of-00032.safetensors",
1500
  "model.llm.layers.50.mlp.gate.global_scale": "model-00023-of-00032.safetensors",
1501
  "model.llm.layers.50.mlp.gate.weight": "model-00023-of-00032.safetensors",
1502
- "model.llm.layers.50.mlp.shared_experts.shared_w13_weight": "model-00023-of-00032.safetensors",
1503
- "model.llm.layers.50.mlp.shared_experts.shared_w2_weight": "model-00023-of-00032.safetensors",
1504
  "model.llm.layers.50.mlp_norm.weight": "model-00023-of-00032.safetensors",
1505
  "model.llm.layers.50.mlp_sconv.weight": "model-00023-of-00032.safetensors",
1506
  "model.llm.layers.51.attn.k_norm.weight": "model-00023-of-00032.safetensors",
@@ -1531,8 +1441,6 @@
1531
  "model.llm.layers.51.mlp.gate.bias": "model-00023-of-00032.safetensors",
1532
  "model.llm.layers.51.mlp.gate.global_scale": "model-00023-of-00032.safetensors",
1533
  "model.llm.layers.51.mlp.gate.weight": "model-00023-of-00032.safetensors",
1534
- "model.llm.layers.51.mlp.shared_experts.shared_w13_weight": "model-00023-of-00032.safetensors",
1535
- "model.llm.layers.51.mlp.shared_experts.shared_w2_weight": "model-00023-of-00032.safetensors",
1536
  "model.llm.layers.51.mlp_norm.weight": "model-00023-of-00032.safetensors",
1537
  "model.llm.layers.51.mlp_sconv.weight": "model-00023-of-00032.safetensors",
1538
  "model.llm.layers.52.attn.k_norm.weight": "model-00023-of-00032.safetensors",
@@ -1563,8 +1471,6 @@
1563
  "model.llm.layers.52.mlp.gate.bias": "model-00024-of-00032.safetensors",
1564
  "model.llm.layers.52.mlp.gate.global_scale": "model-00024-of-00032.safetensors",
1565
  "model.llm.layers.52.mlp.gate.weight": "model-00024-of-00032.safetensors",
1566
- "model.llm.layers.52.mlp.shared_experts.shared_w13_weight": "model-00024-of-00032.safetensors",
1567
- "model.llm.layers.52.mlp.shared_experts.shared_w2_weight": "model-00024-of-00032.safetensors",
1568
  "model.llm.layers.52.mlp_norm.weight": "model-00024-of-00032.safetensors",
1569
  "model.llm.layers.52.mlp_sconv.weight": "model-00024-of-00032.safetensors",
1570
  "model.llm.layers.53.attn.k_norm.weight": "model-00024-of-00032.safetensors",
@@ -1595,8 +1501,6 @@
1595
  "model.llm.layers.53.mlp.gate.bias": "model-00024-of-00032.safetensors",
1596
  "model.llm.layers.53.mlp.gate.global_scale": "model-00024-of-00032.safetensors",
1597
  "model.llm.layers.53.mlp.gate.weight": "model-00024-of-00032.safetensors",
1598
- "model.llm.layers.53.mlp.shared_experts.shared_w13_weight": "model-00024-of-00032.safetensors",
1599
- "model.llm.layers.53.mlp.shared_experts.shared_w2_weight": "model-00024-of-00032.safetensors",
1600
  "model.llm.layers.53.mlp_norm.weight": "model-00024-of-00032.safetensors",
1601
  "model.llm.layers.53.mlp_sconv.weight": "model-00024-of-00032.safetensors",
1602
  "model.llm.layers.54.attn.k_norm.weight": "model-00024-of-00032.safetensors",
@@ -1627,8 +1531,6 @@
1627
  "model.llm.layers.54.mlp.gate.bias": "model-00025-of-00032.safetensors",
1628
  "model.llm.layers.54.mlp.gate.global_scale": "model-00025-of-00032.safetensors",
1629
  "model.llm.layers.54.mlp.gate.weight": "model-00025-of-00032.safetensors",
1630
- "model.llm.layers.54.mlp.shared_experts.shared_w13_weight": "model-00025-of-00032.safetensors",
1631
- "model.llm.layers.54.mlp.shared_experts.shared_w2_weight": "model-00025-of-00032.safetensors",
1632
  "model.llm.layers.54.mlp_norm.weight": "model-00025-of-00032.safetensors",
1633
  "model.llm.layers.54.mlp_sconv.weight": "model-00025-of-00032.safetensors",
1634
  "model.llm.layers.55.attn.k_norm.weight": "model-00025-of-00032.safetensors",
@@ -1659,8 +1561,6 @@
1659
  "model.llm.layers.55.mlp.gate.bias": "model-00025-of-00032.safetensors",
1660
  "model.llm.layers.55.mlp.gate.global_scale": "model-00025-of-00032.safetensors",
1661
  "model.llm.layers.55.mlp.gate.weight": "model-00025-of-00032.safetensors",
1662
- "model.llm.layers.55.mlp.shared_experts.shared_w13_weight": "model-00025-of-00032.safetensors",
1663
- "model.llm.layers.55.mlp.shared_experts.shared_w2_weight": "model-00025-of-00032.safetensors",
1664
  "model.llm.layers.55.mlp_norm.weight": "model-00025-of-00032.safetensors",
1665
  "model.llm.layers.55.mlp_sconv.weight": "model-00025-of-00032.safetensors",
1666
  "model.llm.layers.56.attn.k_norm.weight": "model-00025-of-00032.safetensors",
@@ -1691,8 +1591,6 @@
1691
  "model.llm.layers.56.mlp.gate.bias": "model-00026-of-00032.safetensors",
1692
  "model.llm.layers.56.mlp.gate.global_scale": "model-00026-of-00032.safetensors",
1693
  "model.llm.layers.56.mlp.gate.weight": "model-00026-of-00032.safetensors",
1694
- "model.llm.layers.56.mlp.shared_experts.shared_w13_weight": "model-00026-of-00032.safetensors",
1695
- "model.llm.layers.56.mlp.shared_experts.shared_w2_weight": "model-00026-of-00032.safetensors",
1696
  "model.llm.layers.56.mlp_norm.weight": "model-00026-of-00032.safetensors",
1697
  "model.llm.layers.56.mlp_sconv.weight": "model-00026-of-00032.safetensors",
1698
  "model.llm.layers.57.attn.k_norm.weight": "model-00026-of-00032.safetensors",
@@ -1723,8 +1621,6 @@
1723
  "model.llm.layers.57.mlp.gate.bias": "model-00026-of-00032.safetensors",
1724
  "model.llm.layers.57.mlp.gate.global_scale": "model-00026-of-00032.safetensors",
1725
  "model.llm.layers.57.mlp.gate.weight": "model-00026-of-00032.safetensors",
1726
- "model.llm.layers.57.mlp.shared_experts.shared_w13_weight": "model-00026-of-00032.safetensors",
1727
- "model.llm.layers.57.mlp.shared_experts.shared_w2_weight": "model-00026-of-00032.safetensors",
1728
  "model.llm.layers.57.mlp_norm.weight": "model-00026-of-00032.safetensors",
1729
  "model.llm.layers.57.mlp_sconv.weight": "model-00026-of-00032.safetensors",
1730
  "model.llm.layers.58.attn.k_norm.weight": "model-00026-of-00032.safetensors",
@@ -1755,8 +1651,6 @@
1755
  "model.llm.layers.58.mlp.gate.bias": "model-00027-of-00032.safetensors",
1756
  "model.llm.layers.58.mlp.gate.global_scale": "model-00027-of-00032.safetensors",
1757
  "model.llm.layers.58.mlp.gate.weight": "model-00027-of-00032.safetensors",
1758
- "model.llm.layers.58.mlp.shared_experts.shared_w13_weight": "model-00027-of-00032.safetensors",
1759
- "model.llm.layers.58.mlp.shared_experts.shared_w2_weight": "model-00027-of-00032.safetensors",
1760
  "model.llm.layers.58.mlp_norm.weight": "model-00027-of-00032.safetensors",
1761
  "model.llm.layers.58.mlp_sconv.weight": "model-00027-of-00032.safetensors",
1762
  "model.llm.layers.59.attn.k_norm.weight": "model-00027-of-00032.safetensors",
@@ -1787,8 +1681,6 @@
1787
  "model.llm.layers.59.mlp.gate.bias": "model-00027-of-00032.safetensors",
1788
  "model.llm.layers.59.mlp.gate.global_scale": "model-00027-of-00032.safetensors",
1789
  "model.llm.layers.59.mlp.gate.weight": "model-00027-of-00032.safetensors",
1790
- "model.llm.layers.59.mlp.shared_experts.shared_w13_weight": "model-00027-of-00032.safetensors",
1791
- "model.llm.layers.59.mlp.shared_experts.shared_w2_weight": "model-00027-of-00032.safetensors",
1792
  "model.llm.layers.59.mlp_norm.weight": "model-00027-of-00032.safetensors",
1793
  "model.llm.layers.59.mlp_sconv.weight": "model-00027-of-00032.safetensors",
1794
  "model.llm.layers.6.attn.k_norm.weight": "model-00027-of-00032.safetensors",
@@ -1819,8 +1711,6 @@
1819
  "model.llm.layers.6.mlp.gate.bias": "model-00028-of-00032.safetensors",
1820
  "model.llm.layers.6.mlp.gate.global_scale": "model-00028-of-00032.safetensors",
1821
  "model.llm.layers.6.mlp.gate.weight": "model-00028-of-00032.safetensors",
1822
- "model.llm.layers.6.mlp.shared_experts.shared_w13_weight": "model-00028-of-00032.safetensors",
1823
- "model.llm.layers.6.mlp.shared_experts.shared_w2_weight": "model-00028-of-00032.safetensors",
1824
  "model.llm.layers.6.mlp_norm.weight": "model-00028-of-00032.safetensors",
1825
  "model.llm.layers.6.mlp_sconv.weight": "model-00028-of-00032.safetensors",
1826
  "model.llm.layers.60.attn.k_norm.weight": "model-00028-of-00032.safetensors",
@@ -1851,8 +1741,6 @@
1851
  "model.llm.layers.60.mlp.gate.bias": "model-00028-of-00032.safetensors",
1852
  "model.llm.layers.60.mlp.gate.global_scale": "model-00028-of-00032.safetensors",
1853
  "model.llm.layers.60.mlp.gate.weight": "model-00028-of-00032.safetensors",
1854
- "model.llm.layers.60.mlp.shared_experts.shared_w13_weight": "model-00028-of-00032.safetensors",
1855
- "model.llm.layers.60.mlp.shared_experts.shared_w2_weight": "model-00028-of-00032.safetensors",
1856
  "model.llm.layers.60.mlp_norm.weight": "model-00028-of-00032.safetensors",
1857
  "model.llm.layers.60.mlp_sconv.weight": "model-00028-of-00032.safetensors",
1858
  "model.llm.layers.61.attn.k_norm.weight": "model-00028-of-00032.safetensors",
@@ -1883,8 +1771,6 @@
1883
  "model.llm.layers.61.mlp.gate.bias": "model-00029-of-00032.safetensors",
1884
  "model.llm.layers.61.mlp.gate.global_scale": "model-00029-of-00032.safetensors",
1885
  "model.llm.layers.61.mlp.gate.weight": "model-00029-of-00032.safetensors",
1886
- "model.llm.layers.61.mlp.shared_experts.shared_w13_weight": "model-00029-of-00032.safetensors",
1887
- "model.llm.layers.61.mlp.shared_experts.shared_w2_weight": "model-00029-of-00032.safetensors",
1888
  "model.llm.layers.61.mlp_norm.weight": "model-00029-of-00032.safetensors",
1889
  "model.llm.layers.61.mlp_sconv.weight": "model-00029-of-00032.safetensors",
1890
  "model.llm.layers.62.attn.k_norm.weight": "model-00029-of-00032.safetensors",
@@ -1915,8 +1801,6 @@
1915
  "model.llm.layers.62.mlp.gate.bias": "model-00029-of-00032.safetensors",
1916
  "model.llm.layers.62.mlp.gate.global_scale": "model-00029-of-00032.safetensors",
1917
  "model.llm.layers.62.mlp.gate.weight": "model-00029-of-00032.safetensors",
1918
- "model.llm.layers.62.mlp.shared_experts.shared_w13_weight": "model-00029-of-00032.safetensors",
1919
- "model.llm.layers.62.mlp.shared_experts.shared_w2_weight": "model-00029-of-00032.safetensors",
1920
  "model.llm.layers.62.mlp_norm.weight": "model-00029-of-00032.safetensors",
1921
  "model.llm.layers.62.mlp_sconv.weight": "model-00029-of-00032.safetensors",
1922
  "model.llm.layers.63.attn.k_norm.weight": "model-00029-of-00032.safetensors",
@@ -1947,8 +1831,6 @@
1947
  "model.llm.layers.63.mlp.gate.bias": "model-00030-of-00032.safetensors",
1948
  "model.llm.layers.63.mlp.gate.global_scale": "model-00030-of-00032.safetensors",
1949
  "model.llm.layers.63.mlp.gate.weight": "model-00030-of-00032.safetensors",
1950
- "model.llm.layers.63.mlp.shared_experts.shared_w13_weight": "model-00030-of-00032.safetensors",
1951
- "model.llm.layers.63.mlp.shared_experts.shared_w2_weight": "model-00030-of-00032.safetensors",
1952
  "model.llm.layers.63.mlp_norm.weight": "model-00030-of-00032.safetensors",
1953
  "model.llm.layers.63.mlp_sconv.weight": "model-00030-of-00032.safetensors",
1954
  "model.llm.layers.64.attn.k_norm.weight": "model-00030-of-00032.safetensors",
@@ -1979,8 +1861,6 @@
1979
  "model.llm.layers.64.mlp.gate.bias": "model-00030-of-00032.safetensors",
1980
  "model.llm.layers.64.mlp.gate.global_scale": "model-00030-of-00032.safetensors",
1981
  "model.llm.layers.64.mlp.gate.weight": "model-00030-of-00032.safetensors",
1982
- "model.llm.layers.64.mlp.shared_experts.shared_w13_weight": "model-00030-of-00032.safetensors",
1983
- "model.llm.layers.64.mlp.shared_experts.shared_w2_weight": "model-00030-of-00032.safetensors",
1984
  "model.llm.layers.64.mlp_norm.weight": "model-00030-of-00032.safetensors",
1985
  "model.llm.layers.64.mlp_sconv.weight": "model-00030-of-00032.safetensors",
1986
  "model.llm.layers.65.attn.k_norm.weight": "model-00030-of-00032.safetensors",
@@ -2011,8 +1891,6 @@
2011
  "model.llm.layers.65.mlp.gate.bias": "model-00031-of-00032.safetensors",
2012
  "model.llm.layers.65.mlp.gate.global_scale": "model-00031-of-00032.safetensors",
2013
  "model.llm.layers.65.mlp.gate.weight": "model-00031-of-00032.safetensors",
2014
- "model.llm.layers.65.mlp.shared_experts.shared_w13_weight": "model-00031-of-00032.safetensors",
2015
- "model.llm.layers.65.mlp.shared_experts.shared_w2_weight": "model-00031-of-00032.safetensors",
2016
  "model.llm.layers.65.mlp_norm.weight": "model-00031-of-00032.safetensors",
2017
  "model.llm.layers.65.mlp_sconv.weight": "model-00031-of-00032.safetensors",
2018
  "model.llm.layers.7.attn.k_norm.weight": "model-00031-of-00032.safetensors",
@@ -2043,8 +1921,6 @@
2043
  "model.llm.layers.7.mlp.gate.bias": "model-00031-of-00032.safetensors",
2044
  "model.llm.layers.7.mlp.gate.global_scale": "model-00031-of-00032.safetensors",
2045
  "model.llm.layers.7.mlp.gate.weight": "model-00031-of-00032.safetensors",
2046
- "model.llm.layers.7.mlp.shared_experts.shared_w13_weight": "model-00031-of-00032.safetensors",
2047
- "model.llm.layers.7.mlp.shared_experts.shared_w2_weight": "model-00031-of-00032.safetensors",
2048
  "model.llm.layers.7.mlp_norm.weight": "model-00031-of-00032.safetensors",
2049
  "model.llm.layers.7.mlp_sconv.weight": "model-00031-of-00032.safetensors",
2050
  "model.llm.layers.8.attn.k_norm.weight": "model-00031-of-00032.safetensors",
@@ -2075,8 +1951,6 @@
2075
  "model.llm.layers.8.mlp.gate.bias": "model-00032-of-00032.safetensors",
2076
  "model.llm.layers.8.mlp.gate.global_scale": "model-00032-of-00032.safetensors",
2077
  "model.llm.layers.8.mlp.gate.weight": "model-00032-of-00032.safetensors",
2078
- "model.llm.layers.8.mlp.shared_experts.shared_w13_weight": "model-00032-of-00032.safetensors",
2079
- "model.llm.layers.8.mlp.shared_experts.shared_w2_weight": "model-00032-of-00032.safetensors",
2080
  "model.llm.layers.8.mlp_norm.weight": "model-00032-of-00032.safetensors",
2081
  "model.llm.layers.8.mlp_sconv.weight": "model-00032-of-00032.safetensors",
2082
  "model.llm.layers.9.attn.k_norm.weight": "model-00032-of-00032.safetensors",
@@ -2107,8 +1981,6 @@
2107
  "model.llm.layers.9.mlp.gate.bias": "model-00032-of-00032.safetensors",
2108
  "model.llm.layers.9.mlp.gate.global_scale": "model-00032-of-00032.safetensors",
2109
  "model.llm.layers.9.mlp.gate.weight": "model-00032-of-00032.safetensors",
2110
- "model.llm.layers.9.mlp.shared_experts.shared_w13_weight": "model-00032-of-00032.safetensors",
2111
- "model.llm.layers.9.mlp.shared_experts.shared_w2_weight": "model-00032-of-00032.safetensors",
2112
  "model.llm.layers.9.mlp_norm.weight": "model-00032-of-00032.safetensors",
2113
  "model.llm.layers.9.mlp_sconv.weight": "model-00032-of-00032.safetensors",
2114
  "model.llm.norm.weight": "model-00032-of-00032.safetensors",
@@ -2280,6 +2152,262 @@
2280
  "model.visual.layers.linear_3.weight": "model-00032-of-00032.safetensors",
2281
  "model.visual.layers.norm_0.weight": "model-00032-of-00032.safetensors",
2282
  "model.visual.layers.norm_1.weight": "model-00032-of-00032.safetensors",
2283
- "model.visual.layers.norm_2.weight": "model-00032-of-00032.safetensors"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2284
  }
2285
- }
 
91
  "model.llm.layers.10.mlp.gate.bias": "model-00001-of-00032.safetensors",
92
  "model.llm.layers.10.mlp.gate.global_scale": "model-00001-of-00032.safetensors",
93
  "model.llm.layers.10.mlp.gate.weight": "model-00001-of-00032.safetensors",
 
 
94
  "model.llm.layers.10.mlp_norm.weight": "model-00001-of-00032.safetensors",
95
  "model.llm.layers.10.mlp_sconv.weight": "model-00001-of-00032.safetensors",
96
  "model.llm.layers.11.attn.k_norm.weight": "model-00001-of-00032.safetensors",
 
121
  "model.llm.layers.11.mlp.gate.bias": "model-00001-of-00032.safetensors",
122
  "model.llm.layers.11.mlp.gate.global_scale": "model-00001-of-00032.safetensors",
123
  "model.llm.layers.11.mlp.gate.weight": "model-00001-of-00032.safetensors",
 
 
124
  "model.llm.layers.11.mlp_norm.weight": "model-00001-of-00032.safetensors",
125
  "model.llm.layers.11.mlp_sconv.weight": "model-00001-of-00032.safetensors",
126
  "model.llm.layers.12.attn.k_norm.weight": "model-00001-of-00032.safetensors",
 
151
  "model.llm.layers.12.mlp.gate.bias": "model-00002-of-00032.safetensors",
152
  "model.llm.layers.12.mlp.gate.global_scale": "model-00002-of-00032.safetensors",
153
  "model.llm.layers.12.mlp.gate.weight": "model-00002-of-00032.safetensors",
 
 
154
  "model.llm.layers.12.mlp_norm.weight": "model-00002-of-00032.safetensors",
155
  "model.llm.layers.12.mlp_sconv.weight": "model-00002-of-00032.safetensors",
156
  "model.llm.layers.13.attn.k_norm.weight": "model-00002-of-00032.safetensors",
 
181
  "model.llm.layers.13.mlp.gate.bias": "model-00002-of-00032.safetensors",
182
  "model.llm.layers.13.mlp.gate.global_scale": "model-00002-of-00032.safetensors",
183
  "model.llm.layers.13.mlp.gate.weight": "model-00002-of-00032.safetensors",
 
 
184
  "model.llm.layers.13.mlp_norm.weight": "model-00002-of-00032.safetensors",
185
  "model.llm.layers.13.mlp_sconv.weight": "model-00002-of-00032.safetensors",
186
  "model.llm.layers.14.attn.k_norm.weight": "model-00002-of-00032.safetensors",
 
211
  "model.llm.layers.14.mlp.gate.bias": "model-00003-of-00032.safetensors",
212
  "model.llm.layers.14.mlp.gate.global_scale": "model-00003-of-00032.safetensors",
213
  "model.llm.layers.14.mlp.gate.weight": "model-00003-of-00032.safetensors",
 
 
214
  "model.llm.layers.14.mlp_norm.weight": "model-00003-of-00032.safetensors",
215
  "model.llm.layers.14.mlp_sconv.weight": "model-00003-of-00032.safetensors",
216
  "model.llm.layers.15.attn.k_norm.weight": "model-00003-of-00032.safetensors",
 
241
  "model.llm.layers.15.mlp.gate.bias": "model-00003-of-00032.safetensors",
242
  "model.llm.layers.15.mlp.gate.global_scale": "model-00003-of-00032.safetensors",
243
  "model.llm.layers.15.mlp.gate.weight": "model-00003-of-00032.safetensors",
 
 
244
  "model.llm.layers.15.mlp_norm.weight": "model-00003-of-00032.safetensors",
245
  "model.llm.layers.15.mlp_sconv.weight": "model-00003-of-00032.safetensors",
246
  "model.llm.layers.16.attn.k_norm.weight": "model-00003-of-00032.safetensors",
 
271
  "model.llm.layers.16.mlp.gate.bias": "model-00004-of-00032.safetensors",
272
  "model.llm.layers.16.mlp.gate.global_scale": "model-00004-of-00032.safetensors",
273
  "model.llm.layers.16.mlp.gate.weight": "model-00004-of-00032.safetensors",
 
 
274
  "model.llm.layers.16.mlp_norm.weight": "model-00004-of-00032.safetensors",
275
  "model.llm.layers.16.mlp_sconv.weight": "model-00004-of-00032.safetensors",
276
  "model.llm.layers.17.attn.k_norm.weight": "model-00004-of-00032.safetensors",
 
301
  "model.llm.layers.17.mlp.gate.bias": "model-00004-of-00032.safetensors",
302
  "model.llm.layers.17.mlp.gate.global_scale": "model-00004-of-00032.safetensors",
303
  "model.llm.layers.17.mlp.gate.weight": "model-00004-of-00032.safetensors",
 
 
304
  "model.llm.layers.17.mlp_norm.weight": "model-00004-of-00032.safetensors",
305
  "model.llm.layers.17.mlp_sconv.weight": "model-00004-of-00032.safetensors",
306
  "model.llm.layers.18.attn.k_norm.weight": "model-00004-of-00032.safetensors",
 
331
  "model.llm.layers.18.mlp.gate.bias": "model-00005-of-00032.safetensors",
332
  "model.llm.layers.18.mlp.gate.global_scale": "model-00005-of-00032.safetensors",
333
  "model.llm.layers.18.mlp.gate.weight": "model-00005-of-00032.safetensors",
 
 
334
  "model.llm.layers.18.mlp_norm.weight": "model-00005-of-00032.safetensors",
335
  "model.llm.layers.18.mlp_sconv.weight": "model-00005-of-00032.safetensors",
336
  "model.llm.layers.19.attn.k_norm.weight": "model-00005-of-00032.safetensors",
 
361
  "model.llm.layers.19.mlp.gate.bias": "model-00005-of-00032.safetensors",
362
  "model.llm.layers.19.mlp.gate.global_scale": "model-00005-of-00032.safetensors",
363
  "model.llm.layers.19.mlp.gate.weight": "model-00005-of-00032.safetensors",
 
 
364
  "model.llm.layers.19.mlp_norm.weight": "model-00005-of-00032.safetensors",
365
  "model.llm.layers.19.mlp_sconv.weight": "model-00005-of-00032.safetensors",
366
  "model.llm.layers.2.attn.k_norm.weight": "model-00005-of-00032.safetensors",
 
391
  "model.llm.layers.2.mlp.gate.bias": "model-00006-of-00032.safetensors",
392
  "model.llm.layers.2.mlp.gate.global_scale": "model-00006-of-00032.safetensors",
393
  "model.llm.layers.2.mlp.gate.weight": "model-00006-of-00032.safetensors",
 
 
394
  "model.llm.layers.2.mlp_norm.weight": "model-00006-of-00032.safetensors",
395
  "model.llm.layers.2.mlp_sconv.weight": "model-00006-of-00032.safetensors",
396
  "model.llm.layers.20.attn.k_norm.weight": "model-00006-of-00032.safetensors",
 
421
  "model.llm.layers.20.mlp.gate.bias": "model-00006-of-00032.safetensors",
422
  "model.llm.layers.20.mlp.gate.global_scale": "model-00006-of-00032.safetensors",
423
  "model.llm.layers.20.mlp.gate.weight": "model-00006-of-00032.safetensors",
 
 
424
  "model.llm.layers.20.mlp_norm.weight": "model-00006-of-00032.safetensors",
425
  "model.llm.layers.20.mlp_sconv.weight": "model-00006-of-00032.safetensors",
426
  "model.llm.layers.21.attn.k_norm.weight": "model-00006-of-00032.safetensors",
 
451
  "model.llm.layers.21.mlp.gate.bias": "model-00007-of-00032.safetensors",
452
  "model.llm.layers.21.mlp.gate.global_scale": "model-00007-of-00032.safetensors",
453
  "model.llm.layers.21.mlp.gate.weight": "model-00007-of-00032.safetensors",
 
 
454
  "model.llm.layers.21.mlp_norm.weight": "model-00007-of-00032.safetensors",
455
  "model.llm.layers.21.mlp_sconv.weight": "model-00007-of-00032.safetensors",
456
  "model.llm.layers.22.attn.k_norm.weight": "model-00007-of-00032.safetensors",
 
481
  "model.llm.layers.22.mlp.gate.bias": "model-00007-of-00032.safetensors",
482
  "model.llm.layers.22.mlp.gate.global_scale": "model-00007-of-00032.safetensors",
483
  "model.llm.layers.22.mlp.gate.weight": "model-00007-of-00032.safetensors",
 
 
484
  "model.llm.layers.22.mlp_norm.weight": "model-00007-of-00032.safetensors",
485
  "model.llm.layers.22.mlp_sconv.weight": "model-00007-of-00032.safetensors",
486
  "model.llm.layers.23.attn.k_norm.weight": "model-00007-of-00032.safetensors",
 
511
  "model.llm.layers.23.mlp.gate.bias": "model-00008-of-00032.safetensors",
512
  "model.llm.layers.23.mlp.gate.global_scale": "model-00008-of-00032.safetensors",
513
  "model.llm.layers.23.mlp.gate.weight": "model-00008-of-00032.safetensors",
 
 
514
  "model.llm.layers.23.mlp_norm.weight": "model-00008-of-00032.safetensors",
515
  "model.llm.layers.23.mlp_sconv.weight": "model-00008-of-00032.safetensors",
516
  "model.llm.layers.24.attn.k_norm.weight": "model-00008-of-00032.safetensors",
 
541
  "model.llm.layers.24.mlp.gate.bias": "model-00008-of-00032.safetensors",
542
  "model.llm.layers.24.mlp.gate.global_scale": "model-00008-of-00032.safetensors",
543
  "model.llm.layers.24.mlp.gate.weight": "model-00008-of-00032.safetensors",
 
 
544
  "model.llm.layers.24.mlp_norm.weight": "model-00008-of-00032.safetensors",
545
  "model.llm.layers.24.mlp_sconv.weight": "model-00008-of-00032.safetensors",
546
  "model.llm.layers.25.attn.k_norm.weight": "model-00008-of-00032.safetensors",
 
571
  "model.llm.layers.25.mlp.gate.bias": "model-00009-of-00032.safetensors",
572
  "model.llm.layers.25.mlp.gate.global_scale": "model-00009-of-00032.safetensors",
573
  "model.llm.layers.25.mlp.gate.weight": "model-00009-of-00032.safetensors",
 
 
574
  "model.llm.layers.25.mlp_norm.weight": "model-00009-of-00032.safetensors",
575
  "model.llm.layers.25.mlp_sconv.weight": "model-00009-of-00032.safetensors",
576
  "model.llm.layers.26.attn.k_norm.weight": "model-00009-of-00032.safetensors",
 
601
  "model.llm.layers.26.mlp.gate.bias": "model-00009-of-00032.safetensors",
602
  "model.llm.layers.26.mlp.gate.global_scale": "model-00009-of-00032.safetensors",
603
  "model.llm.layers.26.mlp.gate.weight": "model-00009-of-00032.safetensors",
 
 
604
  "model.llm.layers.26.mlp_norm.weight": "model-00009-of-00032.safetensors",
605
  "model.llm.layers.26.mlp_sconv.weight": "model-00009-of-00032.safetensors",
606
  "model.llm.layers.27.attn.k_norm.weight": "model-00009-of-00032.safetensors",
 
631
  "model.llm.layers.27.mlp.gate.bias": "model-00010-of-00032.safetensors",
632
  "model.llm.layers.27.mlp.gate.global_scale": "model-00010-of-00032.safetensors",
633
  "model.llm.layers.27.mlp.gate.weight": "model-00010-of-00032.safetensors",
 
 
634
  "model.llm.layers.27.mlp_norm.weight": "model-00010-of-00032.safetensors",
635
  "model.llm.layers.27.mlp_sconv.weight": "model-00010-of-00032.safetensors",
636
  "model.llm.layers.28.attn.k_norm.weight": "model-00010-of-00032.safetensors",
 
661
  "model.llm.layers.28.mlp.gate.bias": "model-00010-of-00032.safetensors",
662
  "model.llm.layers.28.mlp.gate.global_scale": "model-00010-of-00032.safetensors",
663
  "model.llm.layers.28.mlp.gate.weight": "model-00010-of-00032.safetensors",
 
 
664
  "model.llm.layers.28.mlp_norm.weight": "model-00010-of-00032.safetensors",
665
  "model.llm.layers.28.mlp_sconv.weight": "model-00010-of-00032.safetensors",
666
  "model.llm.layers.29.attn.k_norm.weight": "model-00010-of-00032.safetensors",
 
691
  "model.llm.layers.29.mlp.gate.bias": "model-00011-of-00032.safetensors",
692
  "model.llm.layers.29.mlp.gate.global_scale": "model-00011-of-00032.safetensors",
693
  "model.llm.layers.29.mlp.gate.weight": "model-00011-of-00032.safetensors",
 
 
694
  "model.llm.layers.29.mlp_norm.weight": "model-00011-of-00032.safetensors",
695
  "model.llm.layers.29.mlp_sconv.weight": "model-00011-of-00032.safetensors",
696
  "model.llm.layers.3.attn.k_norm.weight": "model-00011-of-00032.safetensors",
 
721
  "model.llm.layers.3.mlp.gate.bias": "model-00011-of-00032.safetensors",
722
  "model.llm.layers.3.mlp.gate.global_scale": "model-00011-of-00032.safetensors",
723
  "model.llm.layers.3.mlp.gate.weight": "model-00011-of-00032.safetensors",
 
 
724
  "model.llm.layers.3.mlp_norm.weight": "model-00011-of-00032.safetensors",
725
  "model.llm.layers.3.mlp_sconv.weight": "model-00011-of-00032.safetensors",
726
  "model.llm.layers.30.attn.k_norm.weight": "model-00011-of-00032.safetensors",
 
751
  "model.llm.layers.30.mlp.gate.bias": "model-00012-of-00032.safetensors",
752
  "model.llm.layers.30.mlp.gate.global_scale": "model-00012-of-00032.safetensors",
753
  "model.llm.layers.30.mlp.gate.weight": "model-00012-of-00032.safetensors",
 
 
754
  "model.llm.layers.30.mlp_norm.weight": "model-00012-of-00032.safetensors",
755
  "model.llm.layers.30.mlp_sconv.weight": "model-00012-of-00032.safetensors",
756
  "model.llm.layers.31.attn.k_norm.weight": "model-00012-of-00032.safetensors",
 
781
  "model.llm.layers.31.mlp.gate.bias": "model-00012-of-00032.safetensors",
782
  "model.llm.layers.31.mlp.gate.global_scale": "model-00012-of-00032.safetensors",
783
  "model.llm.layers.31.mlp.gate.weight": "model-00012-of-00032.safetensors",
 
 
784
  "model.llm.layers.31.mlp_norm.weight": "model-00012-of-00032.safetensors",
785
  "model.llm.layers.31.mlp_sconv.weight": "model-00012-of-00032.safetensors",
786
  "model.llm.layers.32.attn.k_norm.weight": "model-00012-of-00032.safetensors",
 
811
  "model.llm.layers.32.mlp.gate.bias": "model-00013-of-00032.safetensors",
812
  "model.llm.layers.32.mlp.gate.global_scale": "model-00013-of-00032.safetensors",
813
  "model.llm.layers.32.mlp.gate.weight": "model-00013-of-00032.safetensors",
 
 
814
  "model.llm.layers.32.mlp_norm.weight": "model-00013-of-00032.safetensors",
815
  "model.llm.layers.32.mlp_sconv.weight": "model-00013-of-00032.safetensors",
816
  "model.llm.layers.33.attn.k_norm.weight": "model-00013-of-00032.safetensors",
 
841
  "model.llm.layers.33.mlp.gate.bias": "model-00013-of-00032.safetensors",
842
  "model.llm.layers.33.mlp.gate.global_scale": "model-00013-of-00032.safetensors",
843
  "model.llm.layers.33.mlp.gate.weight": "model-00013-of-00032.safetensors",
 
 
844
  "model.llm.layers.33.mlp_norm.weight": "model-00013-of-00032.safetensors",
845
  "model.llm.layers.33.mlp_sconv.weight": "model-00013-of-00032.safetensors",
846
  "model.llm.layers.34.attn.k_norm.weight": "model-00013-of-00032.safetensors",
 
871
  "model.llm.layers.34.mlp.gate.bias": "model-00014-of-00032.safetensors",
872
  "model.llm.layers.34.mlp.gate.global_scale": "model-00014-of-00032.safetensors",
873
  "model.llm.layers.34.mlp.gate.weight": "model-00014-of-00032.safetensors",
 
 
874
  "model.llm.layers.34.mlp_norm.weight": "model-00014-of-00032.safetensors",
875
  "model.llm.layers.34.mlp_sconv.weight": "model-00014-of-00032.safetensors",
876
  "model.llm.layers.35.attn.k_norm.weight": "model-00014-of-00032.safetensors",
 
901
  "model.llm.layers.35.mlp.gate.bias": "model-00014-of-00032.safetensors",
902
  "model.llm.layers.35.mlp.gate.global_scale": "model-00014-of-00032.safetensors",
903
  "model.llm.layers.35.mlp.gate.weight": "model-00014-of-00032.safetensors",
 
 
904
  "model.llm.layers.35.mlp_norm.weight": "model-00014-of-00032.safetensors",
905
  "model.llm.layers.35.mlp_sconv.weight": "model-00014-of-00032.safetensors",
906
  "model.llm.layers.36.attn.k_norm.weight": "model-00014-of-00032.safetensors",
 
931
  "model.llm.layers.36.mlp.gate.bias": "model-00015-of-00032.safetensors",
932
  "model.llm.layers.36.mlp.gate.global_scale": "model-00015-of-00032.safetensors",
933
  "model.llm.layers.36.mlp.gate.weight": "model-00015-of-00032.safetensors",
 
 
934
  "model.llm.layers.36.mlp_norm.weight": "model-00015-of-00032.safetensors",
935
  "model.llm.layers.36.mlp_sconv.weight": "model-00015-of-00032.safetensors",
936
  "model.llm.layers.37.attn.k_norm.weight": "model-00015-of-00032.safetensors",
 
961
  "model.llm.layers.37.mlp.gate.bias": "model-00015-of-00032.safetensors",
962
  "model.llm.layers.37.mlp.gate.global_scale": "model-00015-of-00032.safetensors",
963
  "model.llm.layers.37.mlp.gate.weight": "model-00015-of-00032.safetensors",
 
 
964
  "model.llm.layers.37.mlp_norm.weight": "model-00015-of-00032.safetensors",
965
  "model.llm.layers.37.mlp_sconv.weight": "model-00015-of-00032.safetensors",
966
  "model.llm.layers.38.attn.k_norm.weight": "model-00015-of-00032.safetensors",
 
991
  "model.llm.layers.38.mlp.gate.bias": "model-00016-of-00032.safetensors",
992
  "model.llm.layers.38.mlp.gate.global_scale": "model-00016-of-00032.safetensors",
993
  "model.llm.layers.38.mlp.gate.weight": "model-00016-of-00032.safetensors",
 
 
994
  "model.llm.layers.38.mlp_norm.weight": "model-00016-of-00032.safetensors",
995
  "model.llm.layers.38.mlp_sconv.weight": "model-00016-of-00032.safetensors",
996
  "model.llm.layers.39.attn.k_norm.weight": "model-00016-of-00032.safetensors",
 
1021
  "model.llm.layers.39.mlp.gate.bias": "model-00016-of-00032.safetensors",
1022
  "model.llm.layers.39.mlp.gate.global_scale": "model-00016-of-00032.safetensors",
1023
  "model.llm.layers.39.mlp.gate.weight": "model-00016-of-00032.safetensors",
 
 
1024
  "model.llm.layers.39.mlp_norm.weight": "model-00016-of-00032.safetensors",
1025
  "model.llm.layers.39.mlp_sconv.weight": "model-00016-of-00032.safetensors",
1026
  "model.llm.layers.4.attn.k_norm.weight": "model-00016-of-00032.safetensors",
 
1051
  "model.llm.layers.4.mlp.gate.bias": "model-00017-of-00032.safetensors",
1052
  "model.llm.layers.4.mlp.gate.global_scale": "model-00017-of-00032.safetensors",
1053
  "model.llm.layers.4.mlp.gate.weight": "model-00017-of-00032.safetensors",
 
 
1054
  "model.llm.layers.4.mlp_norm.weight": "model-00017-of-00032.safetensors",
1055
  "model.llm.layers.4.mlp_sconv.weight": "model-00017-of-00032.safetensors",
1056
  "model.llm.layers.40.attn.k_norm.weight": "model-00017-of-00032.safetensors",
 
1081
  "model.llm.layers.40.mlp.gate.bias": "model-00017-of-00032.safetensors",
1082
  "model.llm.layers.40.mlp.gate.global_scale": "model-00017-of-00032.safetensors",
1083
  "model.llm.layers.40.mlp.gate.weight": "model-00017-of-00032.safetensors",
 
 
1084
  "model.llm.layers.40.mlp_norm.weight": "model-00017-of-00032.safetensors",
1085
  "model.llm.layers.40.mlp_sconv.weight": "model-00017-of-00032.safetensors",
1086
  "model.llm.layers.41.attn.k_norm.weight": "model-00017-of-00032.safetensors",
 
1111
  "model.llm.layers.41.mlp.gate.bias": "model-00018-of-00032.safetensors",
1112
  "model.llm.layers.41.mlp.gate.global_scale": "model-00018-of-00032.safetensors",
1113
  "model.llm.layers.41.mlp.gate.weight": "model-00018-of-00032.safetensors",
 
 
1114
  "model.llm.layers.41.mlp_norm.weight": "model-00018-of-00032.safetensors",
1115
  "model.llm.layers.41.mlp_sconv.weight": "model-00018-of-00032.safetensors",
1116
  "model.llm.layers.42.attn.k_norm.weight": "model-00018-of-00032.safetensors",
 
1141
  "model.llm.layers.42.mlp.gate.bias": "model-00018-of-00032.safetensors",
1142
  "model.llm.layers.42.mlp.gate.global_scale": "model-00018-of-00032.safetensors",
1143
  "model.llm.layers.42.mlp.gate.weight": "model-00018-of-00032.safetensors",
 
 
1144
  "model.llm.layers.42.mlp_norm.weight": "model-00018-of-00032.safetensors",
1145
  "model.llm.layers.42.mlp_sconv.weight": "model-00018-of-00032.safetensors",
1146
  "model.llm.layers.43.attn.k_norm.weight": "model-00018-of-00032.safetensors",
 
1171
  "model.llm.layers.43.mlp.gate.bias": "model-00019-of-00032.safetensors",
1172
  "model.llm.layers.43.mlp.gate.global_scale": "model-00019-of-00032.safetensors",
1173
  "model.llm.layers.43.mlp.gate.weight": "model-00019-of-00032.safetensors",
 
 
1174
  "model.llm.layers.43.mlp_norm.weight": "model-00019-of-00032.safetensors",
1175
  "model.llm.layers.43.mlp_sconv.weight": "model-00019-of-00032.safetensors",
1176
  "model.llm.layers.44.attn.k_norm.weight": "model-00019-of-00032.safetensors",
 
1201
  "model.llm.layers.44.mlp.gate.bias": "model-00019-of-00032.safetensors",
1202
  "model.llm.layers.44.mlp.gate.global_scale": "model-00019-of-00032.safetensors",
1203
  "model.llm.layers.44.mlp.gate.weight": "model-00019-of-00032.safetensors",
 
 
1204
  "model.llm.layers.44.mlp_norm.weight": "model-00019-of-00032.safetensors",
1205
  "model.llm.layers.44.mlp_sconv.weight": "model-00019-of-00032.safetensors",
1206
  "model.llm.layers.45.attn.k_norm.weight": "model-00019-of-00032.safetensors",
 
1231
  "model.llm.layers.45.mlp.gate.bias": "model-00020-of-00032.safetensors",
1232
  "model.llm.layers.45.mlp.gate.global_scale": "model-00020-of-00032.safetensors",
1233
  "model.llm.layers.45.mlp.gate.weight": "model-00020-of-00032.safetensors",
 
 
1234
  "model.llm.layers.45.mlp_norm.weight": "model-00020-of-00032.safetensors",
1235
  "model.llm.layers.45.mlp_sconv.weight": "model-00020-of-00032.safetensors",
1236
  "model.llm.layers.46.attn.k_norm.weight": "model-00020-of-00032.safetensors",
 
1261
  "model.llm.layers.46.mlp.gate.bias": "model-00020-of-00032.safetensors",
1262
  "model.llm.layers.46.mlp.gate.global_scale": "model-00020-of-00032.safetensors",
1263
  "model.llm.layers.46.mlp.gate.weight": "model-00020-of-00032.safetensors",
 
 
1264
  "model.llm.layers.46.mlp_norm.weight": "model-00020-of-00032.safetensors",
1265
  "model.llm.layers.46.mlp_sconv.weight": "model-00020-of-00032.safetensors",
1266
  "model.llm.layers.47.attn.k_norm.weight": "model-00020-of-00032.safetensors",
 
1291
  "model.llm.layers.47.mlp.gate.bias": "model-00021-of-00032.safetensors",
1292
  "model.llm.layers.47.mlp.gate.global_scale": "model-00021-of-00032.safetensors",
1293
  "model.llm.layers.47.mlp.gate.weight": "model-00021-of-00032.safetensors",
 
 
1294
  "model.llm.layers.47.mlp_norm.weight": "model-00021-of-00032.safetensors",
1295
  "model.llm.layers.47.mlp_sconv.weight": "model-00021-of-00032.safetensors",
1296
  "model.llm.layers.48.attn.k_norm.weight": "model-00021-of-00032.safetensors",
 
1321
  "model.llm.layers.48.mlp.gate.bias": "model-00021-of-00032.safetensors",
1322
  "model.llm.layers.48.mlp.gate.global_scale": "model-00021-of-00032.safetensors",
1323
  "model.llm.layers.48.mlp.gate.weight": "model-00021-of-00032.safetensors",
 
 
1324
  "model.llm.layers.48.mlp_norm.weight": "model-00021-of-00032.safetensors",
1325
  "model.llm.layers.48.mlp_sconv.weight": "model-00021-of-00032.safetensors",
1326
  "model.llm.layers.49.attn.k_norm.weight": "model-00021-of-00032.safetensors",
 
1351
  "model.llm.layers.49.mlp.gate.bias": "model-00022-of-00032.safetensors",
1352
  "model.llm.layers.49.mlp.gate.global_scale": "model-00022-of-00032.safetensors",
1353
  "model.llm.layers.49.mlp.gate.weight": "model-00022-of-00032.safetensors",
 
 
1354
  "model.llm.layers.49.mlp_norm.weight": "model-00022-of-00032.safetensors",
1355
  "model.llm.layers.49.mlp_sconv.weight": "model-00022-of-00032.safetensors",
1356
  "model.llm.layers.5.attn.k_norm.weight": "model-00022-of-00032.safetensors",
 
1381
  "model.llm.layers.5.mlp.gate.bias": "model-00022-of-00032.safetensors",
1382
  "model.llm.layers.5.mlp.gate.global_scale": "model-00022-of-00032.safetensors",
1383
  "model.llm.layers.5.mlp.gate.weight": "model-00022-of-00032.safetensors",
 
 
1384
  "model.llm.layers.5.mlp_norm.weight": "model-00022-of-00032.safetensors",
1385
  "model.llm.layers.5.mlp_sconv.weight": "model-00022-of-00032.safetensors",
1386
  "model.llm.layers.50.attn.k_norm.weight": "model-00022-of-00032.safetensors",
 
1411
  "model.llm.layers.50.mlp.gate.bias": "model-00023-of-00032.safetensors",
1412
  "model.llm.layers.50.mlp.gate.global_scale": "model-00023-of-00032.safetensors",
1413
  "model.llm.layers.50.mlp.gate.weight": "model-00023-of-00032.safetensors",
 
 
1414
  "model.llm.layers.50.mlp_norm.weight": "model-00023-of-00032.safetensors",
1415
  "model.llm.layers.50.mlp_sconv.weight": "model-00023-of-00032.safetensors",
1416
  "model.llm.layers.51.attn.k_norm.weight": "model-00023-of-00032.safetensors",
 
1441
  "model.llm.layers.51.mlp.gate.bias": "model-00023-of-00032.safetensors",
1442
  "model.llm.layers.51.mlp.gate.global_scale": "model-00023-of-00032.safetensors",
1443
  "model.llm.layers.51.mlp.gate.weight": "model-00023-of-00032.safetensors",
 
 
1444
  "model.llm.layers.51.mlp_norm.weight": "model-00023-of-00032.safetensors",
1445
  "model.llm.layers.51.mlp_sconv.weight": "model-00023-of-00032.safetensors",
1446
  "model.llm.layers.52.attn.k_norm.weight": "model-00023-of-00032.safetensors",
 
1471
  "model.llm.layers.52.mlp.gate.bias": "model-00024-of-00032.safetensors",
1472
  "model.llm.layers.52.mlp.gate.global_scale": "model-00024-of-00032.safetensors",
1473
  "model.llm.layers.52.mlp.gate.weight": "model-00024-of-00032.safetensors",
 
 
1474
  "model.llm.layers.52.mlp_norm.weight": "model-00024-of-00032.safetensors",
1475
  "model.llm.layers.52.mlp_sconv.weight": "model-00024-of-00032.safetensors",
1476
  "model.llm.layers.53.attn.k_norm.weight": "model-00024-of-00032.safetensors",
 
1501
  "model.llm.layers.53.mlp.gate.bias": "model-00024-of-00032.safetensors",
1502
  "model.llm.layers.53.mlp.gate.global_scale": "model-00024-of-00032.safetensors",
1503
  "model.llm.layers.53.mlp.gate.weight": "model-00024-of-00032.safetensors",
 
 
1504
  "model.llm.layers.53.mlp_norm.weight": "model-00024-of-00032.safetensors",
1505
  "model.llm.layers.53.mlp_sconv.weight": "model-00024-of-00032.safetensors",
1506
  "model.llm.layers.54.attn.k_norm.weight": "model-00024-of-00032.safetensors",
 
1531
  "model.llm.layers.54.mlp.gate.bias": "model-00025-of-00032.safetensors",
1532
  "model.llm.layers.54.mlp.gate.global_scale": "model-00025-of-00032.safetensors",
1533
  "model.llm.layers.54.mlp.gate.weight": "model-00025-of-00032.safetensors",
 
 
1534
  "model.llm.layers.54.mlp_norm.weight": "model-00025-of-00032.safetensors",
1535
  "model.llm.layers.54.mlp_sconv.weight": "model-00025-of-00032.safetensors",
1536
  "model.llm.layers.55.attn.k_norm.weight": "model-00025-of-00032.safetensors",
 
1561
  "model.llm.layers.55.mlp.gate.bias": "model-00025-of-00032.safetensors",
1562
  "model.llm.layers.55.mlp.gate.global_scale": "model-00025-of-00032.safetensors",
1563
  "model.llm.layers.55.mlp.gate.weight": "model-00025-of-00032.safetensors",
 
 
1564
  "model.llm.layers.55.mlp_norm.weight": "model-00025-of-00032.safetensors",
1565
  "model.llm.layers.55.mlp_sconv.weight": "model-00025-of-00032.safetensors",
1566
  "model.llm.layers.56.attn.k_norm.weight": "model-00025-of-00032.safetensors",
 
1591
  "model.llm.layers.56.mlp.gate.bias": "model-00026-of-00032.safetensors",
1592
  "model.llm.layers.56.mlp.gate.global_scale": "model-00026-of-00032.safetensors",
1593
  "model.llm.layers.56.mlp.gate.weight": "model-00026-of-00032.safetensors",
 
 
1594
  "model.llm.layers.56.mlp_norm.weight": "model-00026-of-00032.safetensors",
1595
  "model.llm.layers.56.mlp_sconv.weight": "model-00026-of-00032.safetensors",
1596
  "model.llm.layers.57.attn.k_norm.weight": "model-00026-of-00032.safetensors",
 
1621
  "model.llm.layers.57.mlp.gate.bias": "model-00026-of-00032.safetensors",
1622
  "model.llm.layers.57.mlp.gate.global_scale": "model-00026-of-00032.safetensors",
1623
  "model.llm.layers.57.mlp.gate.weight": "model-00026-of-00032.safetensors",
 
 
1624
  "model.llm.layers.57.mlp_norm.weight": "model-00026-of-00032.safetensors",
1625
  "model.llm.layers.57.mlp_sconv.weight": "model-00026-of-00032.safetensors",
1626
  "model.llm.layers.58.attn.k_norm.weight": "model-00026-of-00032.safetensors",
 
1651
  "model.llm.layers.58.mlp.gate.bias": "model-00027-of-00032.safetensors",
1652
  "model.llm.layers.58.mlp.gate.global_scale": "model-00027-of-00032.safetensors",
1653
  "model.llm.layers.58.mlp.gate.weight": "model-00027-of-00032.safetensors",
 
 
1654
  "model.llm.layers.58.mlp_norm.weight": "model-00027-of-00032.safetensors",
1655
  "model.llm.layers.58.mlp_sconv.weight": "model-00027-of-00032.safetensors",
1656
  "model.llm.layers.59.attn.k_norm.weight": "model-00027-of-00032.safetensors",
 
1681
  "model.llm.layers.59.mlp.gate.bias": "model-00027-of-00032.safetensors",
1682
  "model.llm.layers.59.mlp.gate.global_scale": "model-00027-of-00032.safetensors",
1683
  "model.llm.layers.59.mlp.gate.weight": "model-00027-of-00032.safetensors",
 
 
1684
  "model.llm.layers.59.mlp_norm.weight": "model-00027-of-00032.safetensors",
1685
  "model.llm.layers.59.mlp_sconv.weight": "model-00027-of-00032.safetensors",
1686
  "model.llm.layers.6.attn.k_norm.weight": "model-00027-of-00032.safetensors",
 
1711
  "model.llm.layers.6.mlp.gate.bias": "model-00028-of-00032.safetensors",
1712
  "model.llm.layers.6.mlp.gate.global_scale": "model-00028-of-00032.safetensors",
1713
  "model.llm.layers.6.mlp.gate.weight": "model-00028-of-00032.safetensors",
 
 
1714
  "model.llm.layers.6.mlp_norm.weight": "model-00028-of-00032.safetensors",
1715
  "model.llm.layers.6.mlp_sconv.weight": "model-00028-of-00032.safetensors",
1716
  "model.llm.layers.60.attn.k_norm.weight": "model-00028-of-00032.safetensors",
 
1741
  "model.llm.layers.60.mlp.gate.bias": "model-00028-of-00032.safetensors",
1742
  "model.llm.layers.60.mlp.gate.global_scale": "model-00028-of-00032.safetensors",
1743
  "model.llm.layers.60.mlp.gate.weight": "model-00028-of-00032.safetensors",
 
 
1744
  "model.llm.layers.60.mlp_norm.weight": "model-00028-of-00032.safetensors",
1745
  "model.llm.layers.60.mlp_sconv.weight": "model-00028-of-00032.safetensors",
1746
  "model.llm.layers.61.attn.k_norm.weight": "model-00028-of-00032.safetensors",
 
1771
  "model.llm.layers.61.mlp.gate.bias": "model-00029-of-00032.safetensors",
1772
  "model.llm.layers.61.mlp.gate.global_scale": "model-00029-of-00032.safetensors",
1773
  "model.llm.layers.61.mlp.gate.weight": "model-00029-of-00032.safetensors",
 
 
1774
  "model.llm.layers.61.mlp_norm.weight": "model-00029-of-00032.safetensors",
1775
  "model.llm.layers.61.mlp_sconv.weight": "model-00029-of-00032.safetensors",
1776
  "model.llm.layers.62.attn.k_norm.weight": "model-00029-of-00032.safetensors",
 
1801
  "model.llm.layers.62.mlp.gate.bias": "model-00029-of-00032.safetensors",
1802
  "model.llm.layers.62.mlp.gate.global_scale": "model-00029-of-00032.safetensors",
1803
  "model.llm.layers.62.mlp.gate.weight": "model-00029-of-00032.safetensors",
 
 
1804
  "model.llm.layers.62.mlp_norm.weight": "model-00029-of-00032.safetensors",
1805
  "model.llm.layers.62.mlp_sconv.weight": "model-00029-of-00032.safetensors",
1806
  "model.llm.layers.63.attn.k_norm.weight": "model-00029-of-00032.safetensors",
 
1831
  "model.llm.layers.63.mlp.gate.bias": "model-00030-of-00032.safetensors",
1832
  "model.llm.layers.63.mlp.gate.global_scale": "model-00030-of-00032.safetensors",
1833
  "model.llm.layers.63.mlp.gate.weight": "model-00030-of-00032.safetensors",
 
 
1834
  "model.llm.layers.63.mlp_norm.weight": "model-00030-of-00032.safetensors",
1835
  "model.llm.layers.63.mlp_sconv.weight": "model-00030-of-00032.safetensors",
1836
  "model.llm.layers.64.attn.k_norm.weight": "model-00030-of-00032.safetensors",
 
1861
  "model.llm.layers.64.mlp.gate.bias": "model-00030-of-00032.safetensors",
1862
  "model.llm.layers.64.mlp.gate.global_scale": "model-00030-of-00032.safetensors",
1863
  "model.llm.layers.64.mlp.gate.weight": "model-00030-of-00032.safetensors",
 
 
1864
  "model.llm.layers.64.mlp_norm.weight": "model-00030-of-00032.safetensors",
1865
  "model.llm.layers.64.mlp_sconv.weight": "model-00030-of-00032.safetensors",
1866
  "model.llm.layers.65.attn.k_norm.weight": "model-00030-of-00032.safetensors",
 
1891
  "model.llm.layers.65.mlp.gate.bias": "model-00031-of-00032.safetensors",
1892
  "model.llm.layers.65.mlp.gate.global_scale": "model-00031-of-00032.safetensors",
1893
  "model.llm.layers.65.mlp.gate.weight": "model-00031-of-00032.safetensors",
 
 
1894
  "model.llm.layers.65.mlp_norm.weight": "model-00031-of-00032.safetensors",
1895
  "model.llm.layers.65.mlp_sconv.weight": "model-00031-of-00032.safetensors",
1896
  "model.llm.layers.7.attn.k_norm.weight": "model-00031-of-00032.safetensors",
 
1921
  "model.llm.layers.7.mlp.gate.bias": "model-00031-of-00032.safetensors",
1922
  "model.llm.layers.7.mlp.gate.global_scale": "model-00031-of-00032.safetensors",
1923
  "model.llm.layers.7.mlp.gate.weight": "model-00031-of-00032.safetensors",
 
 
1924
  "model.llm.layers.7.mlp_norm.weight": "model-00031-of-00032.safetensors",
1925
  "model.llm.layers.7.mlp_sconv.weight": "model-00031-of-00032.safetensors",
1926
  "model.llm.layers.8.attn.k_norm.weight": "model-00031-of-00032.safetensors",
 
1951
  "model.llm.layers.8.mlp.gate.bias": "model-00032-of-00032.safetensors",
1952
  "model.llm.layers.8.mlp.gate.global_scale": "model-00032-of-00032.safetensors",
1953
  "model.llm.layers.8.mlp.gate.weight": "model-00032-of-00032.safetensors",
 
 
1954
  "model.llm.layers.8.mlp_norm.weight": "model-00032-of-00032.safetensors",
1955
  "model.llm.layers.8.mlp_sconv.weight": "model-00032-of-00032.safetensors",
1956
  "model.llm.layers.9.attn.k_norm.weight": "model-00032-of-00032.safetensors",
 
1981
  "model.llm.layers.9.mlp.gate.bias": "model-00032-of-00032.safetensors",
1982
  "model.llm.layers.9.mlp.gate.global_scale": "model-00032-of-00032.safetensors",
1983
  "model.llm.layers.9.mlp.gate.weight": "model-00032-of-00032.safetensors",
 
 
1984
  "model.llm.layers.9.mlp_norm.weight": "model-00032-of-00032.safetensors",
1985
  "model.llm.layers.9.mlp_sconv.weight": "model-00032-of-00032.safetensors",
1986
  "model.llm.norm.weight": "model-00032-of-00032.safetensors",
 
2152
  "model.visual.layers.linear_3.weight": "model-00032-of-00032.safetensors",
2153
  "model.visual.layers.norm_0.weight": "model-00032-of-00032.safetensors",
2154
  "model.visual.layers.norm_1.weight": "model-00032-of-00032.safetensors",
2155
+ "model.visual.layers.norm_2.weight": "model-00032-of-00032.safetensors",
2156
+ "model.llm.layers.10.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2157
+ "model.llm.layers.10.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2158
+ "model.llm.layers.10.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2159
+ "model.llm.layers.10.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2160
+ "model.llm.layers.11.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2161
+ "model.llm.layers.11.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2162
+ "model.llm.layers.11.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2163
+ "model.llm.layers.11.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2164
+ "model.llm.layers.12.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2165
+ "model.llm.layers.12.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2166
+ "model.llm.layers.12.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2167
+ "model.llm.layers.12.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2168
+ "model.llm.layers.13.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2169
+ "model.llm.layers.13.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2170
+ "model.llm.layers.13.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2171
+ "model.llm.layers.13.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2172
+ "model.llm.layers.14.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2173
+ "model.llm.layers.14.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2174
+ "model.llm.layers.14.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2175
+ "model.llm.layers.14.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2176
+ "model.llm.layers.15.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2177
+ "model.llm.layers.15.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2178
+ "model.llm.layers.15.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2179
+ "model.llm.layers.15.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2180
+ "model.llm.layers.16.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2181
+ "model.llm.layers.16.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2182
+ "model.llm.layers.16.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2183
+ "model.llm.layers.16.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2184
+ "model.llm.layers.17.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2185
+ "model.llm.layers.17.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2186
+ "model.llm.layers.17.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2187
+ "model.llm.layers.17.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2188
+ "model.llm.layers.18.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2189
+ "model.llm.layers.18.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2190
+ "model.llm.layers.18.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2191
+ "model.llm.layers.18.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2192
+ "model.llm.layers.19.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2193
+ "model.llm.layers.19.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2194
+ "model.llm.layers.19.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2195
+ "model.llm.layers.19.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2196
+ "model.llm.layers.2.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2197
+ "model.llm.layers.2.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2198
+ "model.llm.layers.2.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2199
+ "model.llm.layers.2.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2200
+ "model.llm.layers.20.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2201
+ "model.llm.layers.20.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2202
+ "model.llm.layers.20.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2203
+ "model.llm.layers.20.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2204
+ "model.llm.layers.21.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2205
+ "model.llm.layers.21.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2206
+ "model.llm.layers.21.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2207
+ "model.llm.layers.21.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2208
+ "model.llm.layers.22.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2209
+ "model.llm.layers.22.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2210
+ "model.llm.layers.22.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2211
+ "model.llm.layers.22.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2212
+ "model.llm.layers.23.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2213
+ "model.llm.layers.23.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2214
+ "model.llm.layers.23.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2215
+ "model.llm.layers.23.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2216
+ "model.llm.layers.24.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2217
+ "model.llm.layers.24.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2218
+ "model.llm.layers.24.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2219
+ "model.llm.layers.24.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2220
+ "model.llm.layers.25.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2221
+ "model.llm.layers.25.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2222
+ "model.llm.layers.25.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2223
+ "model.llm.layers.25.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2224
+ "model.llm.layers.26.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2225
+ "model.llm.layers.26.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2226
+ "model.llm.layers.26.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2227
+ "model.llm.layers.26.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2228
+ "model.llm.layers.27.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2229
+ "model.llm.layers.27.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2230
+ "model.llm.layers.27.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2231
+ "model.llm.layers.27.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2232
+ "model.llm.layers.28.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2233
+ "model.llm.layers.28.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2234
+ "model.llm.layers.28.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2235
+ "model.llm.layers.28.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2236
+ "model.llm.layers.29.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2237
+ "model.llm.layers.29.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2238
+ "model.llm.layers.29.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2239
+ "model.llm.layers.29.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2240
+ "model.llm.layers.3.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2241
+ "model.llm.layers.3.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2242
+ "model.llm.layers.3.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2243
+ "model.llm.layers.3.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2244
+ "model.llm.layers.30.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2245
+ "model.llm.layers.30.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2246
+ "model.llm.layers.30.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2247
+ "model.llm.layers.30.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2248
+ "model.llm.layers.31.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2249
+ "model.llm.layers.31.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2250
+ "model.llm.layers.31.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2251
+ "model.llm.layers.31.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2252
+ "model.llm.layers.32.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2253
+ "model.llm.layers.32.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2254
+ "model.llm.layers.32.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2255
+ "model.llm.layers.32.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2256
+ "model.llm.layers.33.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2257
+ "model.llm.layers.33.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2258
+ "model.llm.layers.33.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2259
+ "model.llm.layers.33.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2260
+ "model.llm.layers.34.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2261
+ "model.llm.layers.34.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2262
+ "model.llm.layers.34.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2263
+ "model.llm.layers.34.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2264
+ "model.llm.layers.35.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2265
+ "model.llm.layers.35.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2266
+ "model.llm.layers.35.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2267
+ "model.llm.layers.35.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2268
+ "model.llm.layers.36.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2269
+ "model.llm.layers.36.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2270
+ "model.llm.layers.36.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2271
+ "model.llm.layers.36.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2272
+ "model.llm.layers.37.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2273
+ "model.llm.layers.37.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2274
+ "model.llm.layers.37.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2275
+ "model.llm.layers.37.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2276
+ "model.llm.layers.38.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2277
+ "model.llm.layers.38.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2278
+ "model.llm.layers.38.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2279
+ "model.llm.layers.38.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2280
+ "model.llm.layers.39.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2281
+ "model.llm.layers.39.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2282
+ "model.llm.layers.39.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2283
+ "model.llm.layers.39.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2284
+ "model.llm.layers.4.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2285
+ "model.llm.layers.4.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2286
+ "model.llm.layers.4.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2287
+ "model.llm.layers.4.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2288
+ "model.llm.layers.40.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2289
+ "model.llm.layers.40.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2290
+ "model.llm.layers.40.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2291
+ "model.llm.layers.40.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2292
+ "model.llm.layers.41.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2293
+ "model.llm.layers.41.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2294
+ "model.llm.layers.41.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2295
+ "model.llm.layers.41.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2296
+ "model.llm.layers.42.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2297
+ "model.llm.layers.42.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2298
+ "model.llm.layers.42.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2299
+ "model.llm.layers.42.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2300
+ "model.llm.layers.43.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2301
+ "model.llm.layers.43.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2302
+ "model.llm.layers.43.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2303
+ "model.llm.layers.43.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2304
+ "model.llm.layers.44.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2305
+ "model.llm.layers.44.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2306
+ "model.llm.layers.44.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2307
+ "model.llm.layers.44.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2308
+ "model.llm.layers.45.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2309
+ "model.llm.layers.45.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2310
+ "model.llm.layers.45.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2311
+ "model.llm.layers.45.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2312
+ "model.llm.layers.46.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2313
+ "model.llm.layers.46.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2314
+ "model.llm.layers.46.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2315
+ "model.llm.layers.46.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2316
+ "model.llm.layers.47.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2317
+ "model.llm.layers.47.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2318
+ "model.llm.layers.47.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2319
+ "model.llm.layers.47.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2320
+ "model.llm.layers.48.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2321
+ "model.llm.layers.48.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2322
+ "model.llm.layers.48.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2323
+ "model.llm.layers.48.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2324
+ "model.llm.layers.49.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2325
+ "model.llm.layers.49.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2326
+ "model.llm.layers.49.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2327
+ "model.llm.layers.49.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2328
+ "model.llm.layers.5.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2329
+ "model.llm.layers.5.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2330
+ "model.llm.layers.5.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2331
+ "model.llm.layers.5.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2332
+ "model.llm.layers.50.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2333
+ "model.llm.layers.50.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2334
+ "model.llm.layers.50.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2335
+ "model.llm.layers.50.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2336
+ "model.llm.layers.51.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2337
+ "model.llm.layers.51.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2338
+ "model.llm.layers.51.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2339
+ "model.llm.layers.51.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2340
+ "model.llm.layers.52.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2341
+ "model.llm.layers.52.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2342
+ "model.llm.layers.52.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2343
+ "model.llm.layers.52.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2344
+ "model.llm.layers.53.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2345
+ "model.llm.layers.53.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2346
+ "model.llm.layers.53.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2347
+ "model.llm.layers.53.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2348
+ "model.llm.layers.54.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2349
+ "model.llm.layers.54.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2350
+ "model.llm.layers.54.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2351
+ "model.llm.layers.54.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2352
+ "model.llm.layers.55.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2353
+ "model.llm.layers.55.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2354
+ "model.llm.layers.55.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2355
+ "model.llm.layers.55.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2356
+ "model.llm.layers.56.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2357
+ "model.llm.layers.56.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2358
+ "model.llm.layers.56.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2359
+ "model.llm.layers.56.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2360
+ "model.llm.layers.57.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2361
+ "model.llm.layers.57.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2362
+ "model.llm.layers.57.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2363
+ "model.llm.layers.57.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2364
+ "model.llm.layers.58.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2365
+ "model.llm.layers.58.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2366
+ "model.llm.layers.58.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2367
+ "model.llm.layers.58.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2368
+ "model.llm.layers.59.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2369
+ "model.llm.layers.59.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2370
+ "model.llm.layers.59.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2371
+ "model.llm.layers.59.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2372
+ "model.llm.layers.6.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2373
+ "model.llm.layers.6.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2374
+ "model.llm.layers.6.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2375
+ "model.llm.layers.6.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2376
+ "model.llm.layers.60.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2377
+ "model.llm.layers.60.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2378
+ "model.llm.layers.60.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2379
+ "model.llm.layers.60.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2380
+ "model.llm.layers.61.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2381
+ "model.llm.layers.61.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2382
+ "model.llm.layers.61.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2383
+ "model.llm.layers.61.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2384
+ "model.llm.layers.62.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2385
+ "model.llm.layers.62.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2386
+ "model.llm.layers.62.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2387
+ "model.llm.layers.62.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2388
+ "model.llm.layers.63.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2389
+ "model.llm.layers.63.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2390
+ "model.llm.layers.63.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2391
+ "model.llm.layers.63.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2392
+ "model.llm.layers.64.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2393
+ "model.llm.layers.64.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2394
+ "model.llm.layers.64.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2395
+ "model.llm.layers.64.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2396
+ "model.llm.layers.65.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2397
+ "model.llm.layers.65.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2398
+ "model.llm.layers.65.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2399
+ "model.llm.layers.65.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2400
+ "model.llm.layers.7.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2401
+ "model.llm.layers.7.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2402
+ "model.llm.layers.7.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2403
+ "model.llm.layers.7.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2404
+ "model.llm.layers.8.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2405
+ "model.llm.layers.8.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2406
+ "model.llm.layers.8.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2407
+ "model.llm.layers.8.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors",
2408
+ "model.llm.layers.9.mlp.shared_experts.shared_w13_weight.weight": "model-00033-of-00033.safetensors",
2409
+ "model.llm.layers.9.mlp.shared_experts.shared_w13_weight.weight_scale": "model-00033-of-00033.safetensors",
2410
+ "model.llm.layers.9.mlp.shared_experts.shared_w2_weight.weight": "model-00033-of-00033.safetensors",
2411
+ "model.llm.layers.9.mlp.shared_experts.shared_w2_weight.weight_scale": "model-00033-of-00033.safetensors"
2412
  }
2413
+ }