Hugging Face's logo

mlx-community
/
LFM2-8B-A1B-3bit-MLX

Text Generation
MLX
Safetensors
English
lfm2_moe
apple-silicon
liquidai
lfm2
Mixture of Experts
transformer
long-context
instruct
quantized
3bit
coding
conversational
custom_code
3-bit
Model card Files
xet
Community
LFM2-8B-A1B-3bit-MLX
File size: 43,344 Bytes 
1c78497
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
 
{
    "metadata": {
        "total_size": 4171609856,
        "total_parameters": 8339929856
    },
    "weight_map": {
        "model.embed_tokens.biases": "model.safetensors",
        "model.embed_tokens.scales": "model.safetensors",
        "model.embed_tokens.weight": "model.safetensors",
        "model.embedding_norm.weight": "model.safetensors",
        "model.layers.0.conv.conv.weight": "model.safetensors",
        "model.layers.0.conv.in_proj.biases": "model.safetensors",
        "model.layers.0.conv.in_proj.scales": "model.safetensors",
        "model.layers.0.conv.in_proj.weight": "model.safetensors",
        "model.layers.0.conv.out_proj.biases": "model.safetensors",
        "model.layers.0.conv.out_proj.scales": "model.safetensors",
        "model.layers.0.conv.out_proj.weight": "model.safetensors",
        "model.layers.0.feed_forward.down_proj.biases": "model.safetensors",
        "model.layers.0.feed_forward.down_proj.scales": "model.safetensors",
        "model.layers.0.feed_forward.down_proj.weight": "model.safetensors",
        "model.layers.0.feed_forward.gate_proj.biases": "model.safetensors",
        "model.layers.0.feed_forward.gate_proj.scales": "model.safetensors",
        "model.layers.0.feed_forward.gate_proj.weight": "model.safetensors",
        "model.layers.0.feed_forward.up_proj.biases": "model.safetensors",
        "model.layers.0.feed_forward.up_proj.scales": "model.safetensors",
        "model.layers.0.feed_forward.up_proj.weight": "model.safetensors",
        "model.layers.0.ffn_norm.weight": "model.safetensors",
        "model.layers.0.operator_norm.weight": "model.safetensors",
        "model.layers.1.conv.conv.weight": "model.safetensors",
        "model.layers.1.conv.in_proj.biases": "model.safetensors",
        "model.layers.1.conv.in_proj.scales": "model.safetensors",
        "model.layers.1.conv.in_proj.weight": "model.safetensors",
        "model.layers.1.conv.out_proj.biases": "model.safetensors",
        "model.layers.1.conv.out_proj.scales": "model.safetensors",
        "model.layers.1.conv.out_proj.weight": "model.safetensors",
        "model.layers.1.feed_forward.down_proj.biases": "model.safetensors",
        "model.layers.1.feed_forward.down_proj.scales": "model.safetensors",
        "model.layers.1.feed_forward.down_proj.weight": "model.safetensors",
        "model.layers.1.feed_forward.gate_proj.biases": "model.safetensors",
        "model.layers.1.feed_forward.gate_proj.scales": "model.safetensors",
        "model.layers.1.feed_forward.gate_proj.weight": "model.safetensors",
        "model.layers.1.feed_forward.up_proj.biases": "model.safetensors",
        "model.layers.1.feed_forward.up_proj.scales": "model.safetensors",
        "model.layers.1.feed_forward.up_proj.weight": "model.safetensors",
        "model.layers.1.ffn_norm.weight": "model.safetensors",
        "model.layers.1.operator_norm.weight": "model.safetensors",
        "model.layers.10.feed_forward.expert_bias": "model.safetensors",
        "model.layers.10.feed_forward.gate.biases": "model.safetensors",
        "model.layers.10.feed_forward.gate.scales": "model.safetensors",
        "model.layers.10.feed_forward.gate.weight": "model.safetensors",
        "model.layers.10.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
        "model.layers.10.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
        "model.layers.10.feed_forward.switch_mlp.down_proj.weight": "model.safetensors",
        "model.layers.10.feed_forward.switch_mlp.gate_proj.biases": "model.safetensors",
        "model.layers.10.feed_forward.switch_mlp.gate_proj.scales": "model.safetensors",
        "model.layers.10.feed_forward.switch_mlp.gate_proj.weight": "model.safetensors",
        "model.layers.10.feed_forward.switch_mlp.up_proj.biases": "model.safetensors",
        "model.layers.10.feed_forward.switch_mlp.up_proj.scales": "model.safetensors",
        "model.layers.10.feed_forward.switch_mlp.up_proj.weight": "model.safetensors",
        "model.layers.10.ffn_norm.weight": "model.safetensors",
        "model.layers.10.operator_norm.weight": "model.safetensors",
        "model.layers.10.self_attn.k_layernorm.weight": "model.safetensors",
        "model.layers.10.self_attn.k_proj.biases": "model.safetensors",
        "model.layers.10.self_attn.k_proj.scales": "model.safetensors",
        "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
        "model.layers.10.self_attn.out_proj.biases": "model.safetensors",
        "model.layers.10.self_attn.out_proj.scales": "model.safetensors",
        "model.layers.10.self_attn.out_proj.weight": "model.safetensors",
        "model.layers.10.self_attn.q_layernorm.weight": "model.safetensors",
        "model.layers.10.self_attn.q_proj.biases": "model.safetensors",
        "model.layers.10.self_attn.q_proj.scales": "model.safetensors",
        "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
        "model.layers.10.self_attn.v_proj.biases": "model.safetensors",
        "model.layers.10.self_attn.v_proj.scales": "model.safetensors",
        "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
        "model.layers.11.conv.conv.weight": "model.safetensors",
        "model.layers.11.conv.in_proj.biases": "model.safetensors",
        "model.layers.11.conv.in_proj.scales": "model.safetensors",
        "model.layers.11.conv.in_proj.weight": "model.safetensors",
        "model.layers.11.conv.out_proj.biases": "model.safetensors",
        "model.layers.11.conv.out_proj.scales": "model.safetensors",
        "model.layers.11.conv.out_proj.weight": "model.safetensors",
        "model.layers.11.feed_forward.expert_bias": "model.safetensors",
        "model.layers.11.feed_forward.gate.biases": "model.safetensors",
        "model.layers.11.feed_forward.gate.scales": "model.safetensors",
        "model.layers.11.feed_forward.gate.weight": "model.safetensors",
        "model.layers.11.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
        "model.layers.11.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
        "model.layers.11.feed_forward.switch_mlp.down_proj.weight": "model.safetensors",
        "model.layers.11.feed_forward.switch_mlp.gate_proj.biases": "model.safetensors",
        "model.layers.11.feed_forward.switch_mlp.gate_proj.scales": "model.safetensors",
        "model.layers.11.feed_forward.switch_mlp.gate_proj.weight": "model.safetensors",
        "model.layers.11.feed_forward.switch_mlp.up_proj.biases": "model.safetensors",
        "model.layers.11.feed_forward.switch_mlp.up_proj.scales": "model.safetensors",
        "model.layers.11.feed_forward.switch_mlp.up_proj.weight": "model.safetensors",
        "model.layers.11.ffn_norm.weight": "model.safetensors",
        "model.layers.11.operator_norm.weight": "model.safetensors",
        "model.layers.12.conv.conv.weight": "model.safetensors",
        "model.layers.12.conv.in_proj.biases": "model.safetensors",
        "model.layers.12.conv.in_proj.scales": "model.safetensors",
        "model.layers.12.conv.in_proj.weight": "model.safetensors",
        "model.layers.12.conv.out_proj.biases": "model.safetensors",
        "model.layers.12.conv.out_proj.scales": "model.safetensors",
        "model.layers.12.conv.out_proj.weight": "model.safetensors",
        "model.layers.12.feed_forward.expert_bias": "model.safetensors",
        "model.layers.12.feed_forward.gate.biases": "model.safetensors",
        "model.layers.12.feed_forward.gate.scales": "model.safetensors",
        "model.layers.12.feed_forward.gate.weight": "model.safetensors",
        "model.layers.12.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
        "model.layers.12.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
        "model.layers.12.feed_forward.switch_mlp.down_proj.weight": "model.safetensors",
        "model.layers.12.feed_forward.switch_mlp.gate_proj.biases": "model.safetensors",
        "model.layers.12.feed_forward.switch_mlp.gate_proj.scales": "model.safetensors",
        "model.layers.12.feed_forward.switch_mlp.gate_proj.weight": "model.safetensors",
        "model.layers.12.feed_forward.switch_mlp.up_proj.biases": "model.safetensors",
        "model.layers.12.feed_forward.switch_mlp.up_proj.scales": "model.safetensors",
        "model.layers.12.feed_forward.switch_mlp.up_proj.weight": "model.safetensors",
        "model.layers.12.ffn_norm.weight": "model.safetensors",
        "model.layers.12.operator_norm.weight": "model.safetensors",
        "model.layers.13.conv.conv.weight": "model.safetensors",
        "model.layers.13.conv.in_proj.biases": "model.safetensors",
        "model.layers.13.conv.in_proj.scales": "model.safetensors",
        "model.layers.13.conv.in_proj.weight": "model.safetensors",
        "model.layers.13.conv.out_proj.biases": "model.safetensors",
        "model.layers.13.conv.out_proj.scales": "model.safetensors",
        "model.layers.13.conv.out_proj.weight": "model.safetensors",
        "model.layers.13.feed_forward.expert_bias": "model.safetensors",
        "model.layers.13.feed_forward.gate.biases": "model.safetensors",
        "model.layers.13.feed_forward.gate.scales": "model.safetensors",
        "model.layers.13.feed_forward.gate.weight": "model.safetensors",
        "model.layers.13.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
        "model.layers.13.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
        "model.layers.13.feed_forward.switch_mlp.down_proj.weight": "model.safetensors",
        "model.layers.13.feed_forward.switch_mlp.gate_proj.biases": "model.safetensors",
        "model.layers.13.feed_forward.switch_mlp.gate_proj.scales": "model.safetensors",
        "model.layers.13.feed_forward.switch_mlp.gate_proj.weight": "model.safetensors",
        "model.layers.13.feed_forward.switch_mlp.up_proj.biases": "model.safetensors",
        "model.layers.13.feed_forward.switch_mlp.up_proj.scales": "model.safetensors",
        "model.layers.13.feed_forward.switch_mlp.up_proj.weight": "model.safetensors",
        "model.layers.13.ffn_norm.weight": "model.safetensors",
        "model.layers.13.operator_norm.weight": "model.safetensors",
        "model.layers.14.feed_forward.expert_bias": "model.safetensors",
        "model.layers.14.feed_forward.gate.biases": "model.safetensors",
        "model.layers.14.feed_forward.gate.scales": "model.safetensors",
        "model.layers.14.feed_forward.gate.weight": "model.safetensors",
        "model.layers.14.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
        "model.layers.14.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
        "model.layers.14.feed_forward.switch_mlp.down_proj.weight": "model.safetensors",
        "model.layers.14.feed_forward.switch_mlp.gate_proj.biases": "model.safetensors",
        "model.layers.14.feed_forward.switch_mlp.gate_proj.scales": "model.safetensors",
        "model.layers.14.feed_forward.switch_mlp.gate_proj.weight": "model.safetensors",
        "model.layers.14.feed_forward.switch_mlp.up_proj.biases": "model.safetensors",
        "model.layers.14.feed_forward.switch_mlp.up_proj.scales": "model.safetensors",
        "model.layers.14.feed_forward.switch_mlp.up_proj.weight": "model.safetensors",
        "model.layers.14.ffn_norm.weight": "model.safetensors",
        "model.layers.14.operator_norm.weight": "model.safetensors",
        "model.layers.14.self_attn.k_layernorm.weight": "model.safetensors",
        "model.layers.14.self_attn.k_proj.biases": "model.safetensors",
        "model.layers.14.self_attn.k_proj.scales": "model.safetensors",
        "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
        "model.layers.14.self_attn.out_proj.biases": "model.safetensors",
        "model.layers.14.self_attn.out_proj.scales": "model.safetensors",
        "model.layers.14.self_attn.out_proj.weight": "model.safetensors",
        "model.layers.14.self_attn.q_layernorm.weight": "model.safetensors",
        "model.layers.14.self_attn.q_proj.biases": "model.safetensors",
        "model.layers.14.self_attn.q_proj.scales": "model.safetensors",
        "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
        "model.layers.14.self_attn.v_proj.biases": "model.safetensors",
        "model.layers.14.self_attn.v_proj.scales": "model.safetensors",
        "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
        "model.layers.15.conv.conv.weight": "model.safetensors",
        "model.layers.15.conv.in_proj.biases": "model.safetensors",
        "model.layers.15.conv.in_proj.scales": "model.safetensors",
        "model.layers.15.conv.in_proj.weight": "model.safetensors",
        "model.layers.15.conv.out_proj.biases": "model.safetensors",
        "model.layers.15.conv.out_proj.scales": "model.safetensors",
        "model.layers.15.conv.out_proj.weight": "model.safetensors",
        "model.layers.15.feed_forward.expert_bias": "model.safetensors",
        "model.layers.15.feed_forward.gate.biases": "model.safetensors",
        "model.layers.15.feed_forward.gate.scales": "model.safetensors",
        "model.layers.15.feed_forward.gate.weight": "model.safetensors",
        "model.layers.15.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
        "model.layers.15.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
        "model.layers.15.feed_forward.switch_mlp.down_proj.weight": "model.safetensors",
        "model.layers.15.feed_forward.switch_mlp.gate_proj.biases": "model.safetensors",
        "model.layers.15.feed_forward.switch_mlp.gate_proj.scales": "model.safetensors",
        "model.layers.15.feed_forward.switch_mlp.gate_proj.weight": "model.safetensors",
        "model.layers.15.feed_forward.switch_mlp.up_proj.biases": "model.safetensors",
        "model.layers.15.feed_forward.switch_mlp.up_proj.scales": "model.safetensors",
        "model.layers.15.feed_forward.switch_mlp.up_proj.weight": "model.safetensors",
        "model.layers.15.ffn_norm.weight": "model.safetensors",
        "model.layers.15.operator_norm.weight": "model.safetensors",
        "model.layers.16.conv.conv.weight": "model.safetensors",
        "model.layers.16.conv.in_proj.biases": "model.safetensors",
        "model.layers.16.conv.in_proj.scales": "model.safetensors",
        "model.layers.16.conv.in_proj.weight": "model.safetensors",
        "model.layers.16.conv.out_proj.biases": "model.safetensors",
        "model.layers.16.conv.out_proj.scales": "model.safetensors",
        "model.layers.16.conv.out_proj.weight": "model.safetensors",
        "model.layers.16.feed_forward.expert_bias": "model.safetensors",
        "model.layers.16.feed_forward.gate.biases": "model.safetensors",
        "model.layers.16.feed_forward.gate.scales": "model.safetensors",
        "model.layers.16.feed_forward.gate.weight": "model.safetensors",
        "model.layers.16.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
        "model.layers.16.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
        "model.layers.16.feed_forward.switch_mlp.down_proj.weight": "model.safetensors",
        "model.layers.16.feed_forward.switch_mlp.gate_proj.biases": "model.safetensors",
        "model.layers.16.feed_forward.switch_mlp.gate_proj.scales": "model.safetensors",
        "model.layers.16.feed_forward.switch_mlp.gate_proj.weight": "model.safetensors",
        "model.layers.16.feed_forward.switch_mlp.up_proj.biases": "model.safetensors",
        "model.layers.16.feed_forward.switch_mlp.up_proj.scales": "model.safetensors",
        "model.layers.16.feed_forward.switch_mlp.up_proj.weight": "model.safetensors",
        "model.layers.16.ffn_norm.weight": "model.safetensors",
        "model.layers.16.operator_norm.weight": "model.safetensors",
        "model.layers.17.conv.conv.weight": "model.safetensors",
        "model.layers.17.conv.in_proj.biases": "model.safetensors",
        "model.layers.17.conv.in_proj.scales": "model.safetensors",
        "model.layers.17.conv.in_proj.weight": "model.safetensors",
        "model.layers.17.conv.out_proj.biases": "model.safetensors",
        "model.layers.17.conv.out_proj.scales": "model.safetensors",
        "model.layers.17.conv.out_proj.weight": "model.safetensors",
        "model.layers.17.feed_forward.expert_bias": "model.safetensors",
        "model.layers.17.feed_forward.gate.biases": "model.safetensors",
        "model.layers.17.feed_forward.gate.scales": "model.safetensors",
        "model.layers.17.feed_forward.gate.weight": "model.safetensors",
        "model.layers.17.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
        "model.layers.17.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
        "model.layers.17.feed_forward.switch_mlp.down_proj.weight": "model.safetensors",
        "model.layers.17.feed_forward.switch_mlp.gate_proj.biases": "model.safetensors",
        "model.layers.17.feed_forward.switch_mlp.gate_proj.scales": "model.safetensors",
        "model.layers.17.feed_forward.switch_mlp.gate_proj.weight": "model.safetensors",
        "model.layers.17.feed_forward.switch_mlp.up_proj.biases": "model.safetensors",
        "model.layers.17.feed_forward.switch_mlp.up_proj.scales": "model.safetensors",
        "model.layers.17.feed_forward.switch_mlp.up_proj.weight": "model.safetensors",
        "model.layers.17.ffn_norm.weight": "model.safetensors",
        "model.layers.17.operator_norm.weight": "model.safetensors",
        "model.layers.18.feed_forward.expert_bias": "model.safetensors",
        "model.layers.18.feed_forward.gate.biases": "model.safetensors",
        "model.layers.18.feed_forward.gate.scales": "model.safetensors",
        "model.layers.18.feed_forward.gate.weight": "model.safetensors",
        "model.layers.18.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
        "model.layers.18.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
        "model.layers.18.feed_forward.switch_mlp.down_proj.weight": "model.safetensors",
        "model.layers.18.feed_forward.switch_mlp.gate_proj.biases": "model.safetensors",
        "model.layers.18.feed_forward.switch_mlp.gate_proj.scales": "model.safetensors",
        "model.layers.18.feed_forward.switch_mlp.gate_proj.weight": "model.safetensors",
        "model.layers.18.feed_forward.switch_mlp.up_proj.biases": "model.safetensors",
        "model.layers.18.feed_forward.switch_mlp.up_proj.scales": "model.safetensors",
        "model.layers.18.feed_forward.switch_mlp.up_proj.weight": "model.safetensors",
        "model.layers.18.ffn_norm.weight": "model.safetensors",
        "model.layers.18.operator_norm.weight": "model.safetensors",
        "model.layers.18.self_attn.k_layernorm.weight": "model.safetensors",
        "model.layers.18.self_attn.k_proj.biases": "model.safetensors",
        "model.layers.18.self_attn.k_proj.scales": "model.safetensors",
        "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
        "model.layers.18.self_attn.out_proj.biases": "model.safetensors",
        "model.layers.18.self_attn.out_proj.scales": "model.safetensors",
        "model.layers.18.self_attn.out_proj.weight": "model.safetensors",
        "model.layers.18.self_attn.q_layernorm.weight": "model.safetensors",
        "model.layers.18.self_attn.q_proj.biases": "model.safetensors",
        "model.layers.18.self_attn.q_proj.scales": "model.safetensors",
        "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
        "model.layers.18.self_attn.v_proj.biases": "model.safetensors",
        "model.layers.18.self_attn.v_proj.scales": "model.safetensors",
        "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
        "model.layers.19.conv.conv.weight": "model.safetensors",
        "model.layers.19.conv.in_proj.biases": "model.safetensors",
        "model.layers.19.conv.in_proj.scales": "model.safetensors",
        "model.layers.19.conv.in_proj.weight": "model.safetensors",
        "model.layers.19.conv.out_proj.biases": "model.safetensors",
        "model.layers.19.conv.out_proj.scales": "model.safetensors",
        "model.layers.19.conv.out_proj.weight": "model.safetensors",
        "model.layers.19.feed_forward.expert_bias": "model.safetensors",
        "model.layers.19.feed_forward.gate.biases": "model.safetensors",
        "model.layers.19.feed_forward.gate.scales": "model.safetensors",
        "model.layers.19.feed_forward.gate.weight": "model.safetensors",
        "model.layers.19.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
        "model.layers.19.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
        "model.layers.19.feed_forward.switch_mlp.down_proj.weight": "model.safetensors",
        "model.layers.19.feed_forward.switch_mlp.gate_proj.biases": "model.safetensors",
        "model.layers.19.feed_forward.switch_mlp.gate_proj.scales": "model.safetensors",
        "model.layers.19.feed_forward.switch_mlp.gate_proj.weight": "model.safetensors",
        "model.layers.19.feed_forward.switch_mlp.up_proj.biases": "model.safetensors",
        "model.layers.19.feed_forward.switch_mlp.up_proj.scales": "model.safetensors",
        "model.layers.19.feed_forward.switch_mlp.up_proj.weight": "model.safetensors",
        "model.layers.19.ffn_norm.weight": "model.safetensors",
        "model.layers.19.operator_norm.weight": "model.safetensors",
        "model.layers.2.feed_forward.expert_bias": "model.safetensors",
        "model.layers.2.feed_forward.gate.biases": "model.safetensors",
        "model.layers.2.feed_forward.gate.scales": "model.safetensors",
        "model.layers.2.feed_forward.gate.weight": "model.safetensors",
        "model.layers.2.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
        "model.layers.2.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
        "model.layers.2.feed_forward.switch_mlp.down_proj.weight": "model.safetensors",
        "model.layers.2.feed_forward.switch_mlp.gate_proj.biases": "model.safetensors",
        "model.layers.2.feed_forward.switch_mlp.gate_proj.scales": "model.safetensors",
        "model.layers.2.feed_forward.switch_mlp.gate_proj.weight": "model.safetensors",
        "model.layers.2.feed_forward.switch_mlp.up_proj.biases": "model.safetensors",
        "model.layers.2.feed_forward.switch_mlp.up_proj.scales": "model.safetensors",
        "model.layers.2.feed_forward.switch_mlp.up_proj.weight": "model.safetensors",
        "model.layers.2.ffn_norm.weight": "model.safetensors",
        "model.layers.2.operator_norm.weight": "model.safetensors",
        "model.layers.2.self_attn.k_layernorm.weight": "model.safetensors",
        "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
        "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
        "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
        "model.layers.2.self_attn.out_proj.biases": "model.safetensors",
        "model.layers.2.self_attn.out_proj.scales": "model.safetensors",
        "model.layers.2.self_attn.out_proj.weight": "model.safetensors",
        "model.layers.2.self_attn.q_layernorm.weight": "model.safetensors",
        "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
        "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
        "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
        "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
        "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
        "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
        "model.layers.20.conv.conv.weight": "model.safetensors",
        "model.layers.20.conv.in_proj.biases": "model.safetensors",
        "model.layers.20.conv.in_proj.scales": "model.safetensors",
        "model.layers.20.conv.in_proj.weight": "model.safetensors",
        "model.layers.20.conv.out_proj.biases": "model.safetensors",
        "model.layers.20.conv.out_proj.scales": "model.safetensors",
        "model.layers.20.conv.out_proj.weight": "model.safetensors",
        "model.layers.20.feed_forward.expert_bias": "model.safetensors",
        "model.layers.20.feed_forward.gate.biases": "model.safetensors",
        "model.layers.20.feed_forward.gate.scales": "model.safetensors",
        "model.layers.20.feed_forward.gate.weight": "model.safetensors",
        "model.layers.20.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
        "model.layers.20.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
        "model.layers.20.feed_forward.switch_mlp.down_proj.weight": "model.safetensors",
        "model.layers.20.feed_forward.switch_mlp.gate_proj.biases": "model.safetensors",
        "model.layers.20.feed_forward.switch_mlp.gate_proj.scales": "model.safetensors",
        "model.layers.20.feed_forward.switch_mlp.gate_proj.weight": "model.safetensors",
        "model.layers.20.feed_forward.switch_mlp.up_proj.biases": "model.safetensors",
        "model.layers.20.feed_forward.switch_mlp.up_proj.scales": "model.safetensors",
        "model.layers.20.feed_forward.switch_mlp.up_proj.weight": "model.safetensors",
        "model.layers.20.ffn_norm.weight": "model.safetensors",
        "model.layers.20.operator_norm.weight": "model.safetensors",
        "model.layers.21.feed_forward.expert_bias": "model.safetensors",
        "model.layers.21.feed_forward.gate.biases": "model.safetensors",
        "model.layers.21.feed_forward.gate.scales": "model.safetensors",
        "model.layers.21.feed_forward.gate.weight": "model.safetensors",
        "model.layers.21.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
        "model.layers.21.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
        "model.layers.21.feed_forward.switch_mlp.down_proj.weight": "model.safetensors",
        "model.layers.21.feed_forward.switch_mlp.gate_proj.biases": "model.safetensors",
        "model.layers.21.feed_forward.switch_mlp.gate_proj.scales": "model.safetensors",
        "model.layers.21.feed_forward.switch_mlp.gate_proj.weight": "model.safetensors",
        "model.layers.21.feed_forward.switch_mlp.up_proj.biases": "model.safetensors",
        "model.layers.21.feed_forward.switch_mlp.up_proj.scales": "model.safetensors",
        "model.layers.21.feed_forward.switch_mlp.up_proj.weight": "model.safetensors",
        "model.layers.21.ffn_norm.weight": "model.safetensors",
        "model.layers.21.operator_norm.weight": "model.safetensors",
        "model.layers.21.self_attn.k_layernorm.weight": "model.safetensors",
        "model.layers.21.self_attn.k_proj.biases": "model.safetensors",
        "model.layers.21.self_attn.k_proj.scales": "model.safetensors",
        "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
        "model.layers.21.self_attn.out_proj.biases": "model.safetensors",
        "model.layers.21.self_attn.out_proj.scales": "model.safetensors",
        "model.layers.21.self_attn.out_proj.weight": "model.safetensors",
        "model.layers.21.self_attn.q_layernorm.weight": "model.safetensors",
        "model.layers.21.self_attn.q_proj.biases": "model.safetensors",
        "model.layers.21.self_attn.q_proj.scales": "model.safetensors",
        "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
        "model.layers.21.self_attn.v_proj.biases": "model.safetensors",
        "model.layers.21.self_attn.v_proj.scales": "model.safetensors",
        "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
        "model.layers.22.conv.conv.weight": "model.safetensors",
        "model.layers.22.conv.in_proj.biases": "model.safetensors",
        "model.layers.22.conv.in_proj.scales": "model.safetensors",
        "model.layers.22.conv.in_proj.weight": "model.safetensors",
        "model.layers.22.conv.out_proj.biases": "model.safetensors",
        "model.layers.22.conv.out_proj.scales": "model.safetensors",
        "model.layers.22.conv.out_proj.weight": "model.safetensors",
        "model.layers.22.feed_forward.expert_bias": "model.safetensors",
        "model.layers.22.feed_forward.gate.biases": "model.safetensors",
        "model.layers.22.feed_forward.gate.scales": "model.safetensors",
        "model.layers.22.feed_forward.gate.weight": "model.safetensors",
        "model.layers.22.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
        "model.layers.22.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
        "model.layers.22.feed_forward.switch_mlp.down_proj.weight": "model.safetensors",
        "model.layers.22.feed_forward.switch_mlp.gate_proj.biases": "model.safetensors",
        "model.layers.22.feed_forward.switch_mlp.gate_proj.scales": "model.safetensors",
        "model.layers.22.feed_forward.switch_mlp.gate_proj.weight": "model.safetensors",
        "model.layers.22.feed_forward.switch_mlp.up_proj.biases": "model.safetensors",
        "model.layers.22.feed_forward.switch_mlp.up_proj.scales": "model.safetensors",
        "model.layers.22.feed_forward.switch_mlp.up_proj.weight": "model.safetensors",
        "model.layers.22.ffn_norm.weight": "model.safetensors",
        "model.layers.22.operator_norm.weight": "model.safetensors",
        "model.layers.23.conv.conv.weight": "model.safetensors",
        "model.layers.23.conv.in_proj.biases": "model.safetensors",
        "model.layers.23.conv.in_proj.scales": "model.safetensors",
        "model.layers.23.conv.in_proj.weight": "model.safetensors",
        "model.layers.23.conv.out_proj.biases": "model.safetensors",
        "model.layers.23.conv.out_proj.scales": "model.safetensors",
        "model.layers.23.conv.out_proj.weight": "model.safetensors",
        "model.layers.23.feed_forward.expert_bias": "model.safetensors",
        "model.layers.23.feed_forward.gate.biases": "model.safetensors",
        "model.layers.23.feed_forward.gate.scales": "model.safetensors",
        "model.layers.23.feed_forward.gate.weight": "model.safetensors",
        "model.layers.23.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
        "model.layers.23.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
        "model.layers.23.feed_forward.switch_mlp.down_proj.weight": "model.safetensors",
        "model.layers.23.feed_forward.switch_mlp.gate_proj.biases": "model.safetensors",
        "model.layers.23.feed_forward.switch_mlp.gate_proj.scales": "model.safetensors",
        "model.layers.23.feed_forward.switch_mlp.gate_proj.weight": "model.safetensors",
        "model.layers.23.feed_forward.switch_mlp.up_proj.biases": "model.safetensors",
        "model.layers.23.feed_forward.switch_mlp.up_proj.scales": "model.safetensors",
        "model.layers.23.feed_forward.switch_mlp.up_proj.weight": "model.safetensors",
        "model.layers.23.ffn_norm.weight": "model.safetensors",
        "model.layers.23.operator_norm.weight": "model.safetensors",
        "model.layers.3.conv.conv.weight": "model.safetensors",
        "model.layers.3.conv.in_proj.biases": "model.safetensors",
        "model.layers.3.conv.in_proj.scales": "model.safetensors",
        "model.layers.3.conv.in_proj.weight": "model.safetensors",
        "model.layers.3.conv.out_proj.biases": "model.safetensors",
        "model.layers.3.conv.out_proj.scales": "model.safetensors",
        "model.layers.3.conv.out_proj.weight": "model.safetensors",
        "model.layers.3.feed_forward.expert_bias": "model.safetensors",
        "model.layers.3.feed_forward.gate.biases": "model.safetensors",
        "model.layers.3.feed_forward.gate.scales": "model.safetensors",
        "model.layers.3.feed_forward.gate.weight": "model.safetensors",
        "model.layers.3.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
        "model.layers.3.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
        "model.layers.3.feed_forward.switch_mlp.down_proj.weight": "model.safetensors",
        "model.layers.3.feed_forward.switch_mlp.gate_proj.biases": "model.safetensors",
        "model.layers.3.feed_forward.switch_mlp.gate_proj.scales": "model.safetensors",
        "model.layers.3.feed_forward.switch_mlp.gate_proj.weight": "model.safetensors",
        "model.layers.3.feed_forward.switch_mlp.up_proj.biases": "model.safetensors",
        "model.layers.3.feed_forward.switch_mlp.up_proj.scales": "model.safetensors",
        "model.layers.3.feed_forward.switch_mlp.up_proj.weight": "model.safetensors",
        "model.layers.3.ffn_norm.weight": "model.safetensors",
        "model.layers.3.operator_norm.weight": "model.safetensors",
        "model.layers.4.conv.conv.weight": "model.safetensors",
        "model.layers.4.conv.in_proj.biases": "model.safetensors",
        "model.layers.4.conv.in_proj.scales": "model.safetensors",
        "model.layers.4.conv.in_proj.weight": "model.safetensors",
        "model.layers.4.conv.out_proj.biases": "model.safetensors",
        "model.layers.4.conv.out_proj.scales": "model.safetensors",
        "model.layers.4.conv.out_proj.weight": "model.safetensors",
        "model.layers.4.feed_forward.expert_bias": "model.safetensors",
        "model.layers.4.feed_forward.gate.biases": "model.safetensors",
        "model.layers.4.feed_forward.gate.scales": "model.safetensors",
        "model.layers.4.feed_forward.gate.weight": "model.safetensors",
        "model.layers.4.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
        "model.layers.4.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
        "model.layers.4.feed_forward.switch_mlp.down_proj.weight": "model.safetensors",
        "model.layers.4.feed_forward.switch_mlp.gate_proj.biases": "model.safetensors",
        "model.layers.4.feed_forward.switch_mlp.gate_proj.scales": "model.safetensors",
        "model.layers.4.feed_forward.switch_mlp.gate_proj.weight": "model.safetensors",
        "model.layers.4.feed_forward.switch_mlp.up_proj.biases": "model.safetensors",
        "model.layers.4.feed_forward.switch_mlp.up_proj.scales": "model.safetensors",
        "model.layers.4.feed_forward.switch_mlp.up_proj.weight": "model.safetensors",
        "model.layers.4.ffn_norm.weight": "model.safetensors",
        "model.layers.4.operator_norm.weight": "model.safetensors",
        "model.layers.5.conv.conv.weight": "model.safetensors",
        "model.layers.5.conv.in_proj.biases": "model.safetensors",
        "model.layers.5.conv.in_proj.scales": "model.safetensors",
        "model.layers.5.conv.in_proj.weight": "model.safetensors",
        "model.layers.5.conv.out_proj.biases": "model.safetensors",
        "model.layers.5.conv.out_proj.scales": "model.safetensors",
        "model.layers.5.conv.out_proj.weight": "model.safetensors",
        "model.layers.5.feed_forward.expert_bias": "model.safetensors",
        "model.layers.5.feed_forward.gate.biases": "model.safetensors",
        "model.layers.5.feed_forward.gate.scales": "model.safetensors",
        "model.layers.5.feed_forward.gate.weight": "model.safetensors",
        "model.layers.5.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
        "model.layers.5.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
        "model.layers.5.feed_forward.switch_mlp.down_proj.weight": "model.safetensors",
        "model.layers.5.feed_forward.switch_mlp.gate_proj.biases": "model.safetensors",
        "model.layers.5.feed_forward.switch_mlp.gate_proj.scales": "model.safetensors",
        "model.layers.5.feed_forward.switch_mlp.gate_proj.weight": "model.safetensors",
        "model.layers.5.feed_forward.switch_mlp.up_proj.biases": "model.safetensors",
        "model.layers.5.feed_forward.switch_mlp.up_proj.scales": "model.safetensors",
        "model.layers.5.feed_forward.switch_mlp.up_proj.weight": "model.safetensors",
        "model.layers.5.ffn_norm.weight": "model.safetensors",
        "model.layers.5.operator_norm.weight": "model.safetensors",
        "model.layers.6.feed_forward.expert_bias": "model.safetensors",
        "model.layers.6.feed_forward.gate.biases": "model.safetensors",
        "model.layers.6.feed_forward.gate.scales": "model.safetensors",
        "model.layers.6.feed_forward.gate.weight": "model.safetensors",
        "model.layers.6.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
        "model.layers.6.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
        "model.layers.6.feed_forward.switch_mlp.down_proj.weight": "model.safetensors",
        "model.layers.6.feed_forward.switch_mlp.gate_proj.biases": "model.safetensors",
        "model.layers.6.feed_forward.switch_mlp.gate_proj.scales": "model.safetensors",
        "model.layers.6.feed_forward.switch_mlp.gate_proj.weight": "model.safetensors",
        "model.layers.6.feed_forward.switch_mlp.up_proj.biases": "model.safetensors",
        "model.layers.6.feed_forward.switch_mlp.up_proj.scales": "model.safetensors",
        "model.layers.6.feed_forward.switch_mlp.up_proj.weight": "model.safetensors",
        "model.layers.6.ffn_norm.weight": "model.safetensors",
        "model.layers.6.operator_norm.weight": "model.safetensors",
        "model.layers.6.self_attn.k_layernorm.weight": "model.safetensors",
        "model.layers.6.self_attn.k_proj.biases": "model.safetensors",
        "model.layers.6.self_attn.k_proj.scales": "model.safetensors",
        "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
        "model.layers.6.self_attn.out_proj.biases": "model.safetensors",
        "model.layers.6.self_attn.out_proj.scales": "model.safetensors",
        "model.layers.6.self_attn.out_proj.weight": "model.safetensors",
        "model.layers.6.self_attn.q_layernorm.weight": "model.safetensors",
        "model.layers.6.self_attn.q_proj.biases": "model.safetensors",
        "model.layers.6.self_attn.q_proj.scales": "model.safetensors",
        "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
        "model.layers.6.self_attn.v_proj.biases": "model.safetensors",
        "model.layers.6.self_attn.v_proj.scales": "model.safetensors",
        "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
        "model.layers.7.conv.conv.weight": "model.safetensors",
        "model.layers.7.conv.in_proj.biases": "model.safetensors",
        "model.layers.7.conv.in_proj.scales": "model.safetensors",
        "model.layers.7.conv.in_proj.weight": "model.safetensors",
        "model.layers.7.conv.out_proj.biases": "model.safetensors",
        "model.layers.7.conv.out_proj.scales": "model.safetensors",
        "model.layers.7.conv.out_proj.weight": "model.safetensors",
        "model.layers.7.feed_forward.expert_bias": "model.safetensors",
        "model.layers.7.feed_forward.gate.biases": "model.safetensors",
        "model.layers.7.feed_forward.gate.scales": "model.safetensors",
        "model.layers.7.feed_forward.gate.weight": "model.safetensors",
        "model.layers.7.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
        "model.layers.7.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
        "model.layers.7.feed_forward.switch_mlp.down_proj.weight": "model.safetensors",
        "model.layers.7.feed_forward.switch_mlp.gate_proj.biases": "model.safetensors",
        "model.layers.7.feed_forward.switch_mlp.gate_proj.scales": "model.safetensors",
        "model.layers.7.feed_forward.switch_mlp.gate_proj.weight": "model.safetensors",
        "model.layers.7.feed_forward.switch_mlp.up_proj.biases": "model.safetensors",
        "model.layers.7.feed_forward.switch_mlp.up_proj.scales": "model.safetensors",
        "model.layers.7.feed_forward.switch_mlp.up_proj.weight": "model.safetensors",
        "model.layers.7.ffn_norm.weight": "model.safetensors",
        "model.layers.7.operator_norm.weight": "model.safetensors",
        "model.layers.8.conv.conv.weight": "model.safetensors",
        "model.layers.8.conv.in_proj.biases": "model.safetensors",
        "model.layers.8.conv.in_proj.scales": "model.safetensors",
        "model.layers.8.conv.in_proj.weight": "model.safetensors",
        "model.layers.8.conv.out_proj.biases": "model.safetensors",
        "model.layers.8.conv.out_proj.scales": "model.safetensors",
        "model.layers.8.conv.out_proj.weight": "model.safetensors",
        "model.layers.8.feed_forward.expert_bias": "model.safetensors",
        "model.layers.8.feed_forward.gate.biases": "model.safetensors",
        "model.layers.8.feed_forward.gate.scales": "model.safetensors",
        "model.layers.8.feed_forward.gate.weight": "model.safetensors",
        "model.layers.8.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
        "model.layers.8.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
        "model.layers.8.feed_forward.switch_mlp.down_proj.weight": "model.safetensors",
        "model.layers.8.feed_forward.switch_mlp.gate_proj.biases": "model.safetensors",
        "model.layers.8.feed_forward.switch_mlp.gate_proj.scales": "model.safetensors",
        "model.layers.8.feed_forward.switch_mlp.gate_proj.weight": "model.safetensors",
        "model.layers.8.feed_forward.switch_mlp.up_proj.biases": "model.safetensors",
        "model.layers.8.feed_forward.switch_mlp.up_proj.scales": "model.safetensors",
        "model.layers.8.feed_forward.switch_mlp.up_proj.weight": "model.safetensors",
        "model.layers.8.ffn_norm.weight": "model.safetensors",
        "model.layers.8.operator_norm.weight": "model.safetensors",
        "model.layers.9.conv.conv.weight": "model.safetensors",
        "model.layers.9.conv.in_proj.biases": "model.safetensors",
        "model.layers.9.conv.in_proj.scales": "model.safetensors",
        "model.layers.9.conv.in_proj.weight": "model.safetensors",
        "model.layers.9.conv.out_proj.biases": "model.safetensors",
        "model.layers.9.conv.out_proj.scales": "model.safetensors",
        "model.layers.9.conv.out_proj.weight": "model.safetensors",
        "model.layers.9.feed_forward.expert_bias": "model.safetensors",
        "model.layers.9.feed_forward.gate.biases": "model.safetensors",
        "model.layers.9.feed_forward.gate.scales": "model.safetensors",
        "model.layers.9.feed_forward.gate.weight": "model.safetensors",
        "model.layers.9.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
        "model.layers.9.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
        "model.layers.9.feed_forward.switch_mlp.down_proj.weight": "model.safetensors",
        "model.layers.9.feed_forward.switch_mlp.gate_proj.biases": "model.safetensors",
        "model.layers.9.feed_forward.switch_mlp.gate_proj.scales": "model.safetensors",
        "model.layers.9.feed_forward.switch_mlp.gate_proj.weight": "model.safetensors",
        "model.layers.9.feed_forward.switch_mlp.up_proj.biases": "model.safetensors",
        "model.layers.9.feed_forward.switch_mlp.up_proj.scales": "model.safetensors",
        "model.layers.9.feed_forward.switch_mlp.up_proj.weight": "model.safetensors",
        "model.layers.9.ffn_norm.weight": "model.safetensors",
        "model.layers.9.operator_norm.weight": "model.safetensors"
    }
}