Hugging Face's logo

LiquidAI
/
LFM2.5-8B-A1B-MLX-4bit

Text Generation
MLX
Safetensors
lfm2_moe
liquid
lfm2.5
edge
Mixture of Experts
conversational
4-bit precision
Model card Files
xet
 Community
1
ykhrustalev commited on
Commit
760bf10
·
verified ·
1 Parent(s): d16665c

Re-quantize: 6-bit tied embeddings/output, fp32 MoE router gate

Browse files
Files changed (3) hide show
  1. config.json +6 -172
  2. model.safetensors +2 -2
  3. model.safetensors.index.json +1 -45
config.json CHANGED
@@ -52,186 +52,20 @@
52
  "group_size": 64,
53
  "bits": 4,
54
  "mode": "affine",
55
- "model.layers.2.feed_forward.gate": {
56
  "group_size": 64,
57
- "bits": 8
58
- },
59
- "model.layers.3.feed_forward.gate": {
60
- "group_size": 64,
61
- "bits": 8
62
- },
63
- "model.layers.4.feed_forward.gate": {
64
- "group_size": 64,
65
- "bits": 8
66
- },
67
- "model.layers.5.feed_forward.gate": {
68
- "group_size": 64,
69
- "bits": 8
70
- },
71
- "model.layers.6.feed_forward.gate": {
72
- "group_size": 64,
73
- "bits": 8
74
- },
75
- "model.layers.7.feed_forward.gate": {
76
- "group_size": 64,
77
- "bits": 8
78
- },
79
- "model.layers.8.feed_forward.gate": {
80
- "group_size": 64,
81
- "bits": 8
82
- },
83
- "model.layers.9.feed_forward.gate": {
84
- "group_size": 64,
85
- "bits": 8
86
- },
87
- "model.layers.10.feed_forward.gate": {
88
- "group_size": 64,
89
- "bits": 8
90
- },
91
- "model.layers.11.feed_forward.gate": {
92
- "group_size": 64,
93
- "bits": 8
94
- },
95
- "model.layers.12.feed_forward.gate": {
96
- "group_size": 64,
97
- "bits": 8
98
- },
99
- "model.layers.13.feed_forward.gate": {
100
- "group_size": 64,
101
- "bits": 8
102
- },
103
- "model.layers.14.feed_forward.gate": {
104
- "group_size": 64,
105
- "bits": 8
106
- },
107
- "model.layers.15.feed_forward.gate": {
108
- "group_size": 64,
109
- "bits": 8
110
- },
111
- "model.layers.16.feed_forward.gate": {
112
- "group_size": 64,
113
- "bits": 8
114
- },
115
- "model.layers.17.feed_forward.gate": {
116
- "group_size": 64,
117
- "bits": 8
118
- },
119
- "model.layers.18.feed_forward.gate": {
120
- "group_size": 64,
121
- "bits": 8
122
- },
123
- "model.layers.19.feed_forward.gate": {
124
- "group_size": 64,
125
- "bits": 8
126
- },
127
- "model.layers.20.feed_forward.gate": {
128
- "group_size": 64,
129
- "bits": 8
130
- },
131
- "model.layers.21.feed_forward.gate": {
132
- "group_size": 64,
133
- "bits": 8
134
- },
135
- "model.layers.22.feed_forward.gate": {
136
- "group_size": 64,
137
- "bits": 8
138
- },
139
- "model.layers.23.feed_forward.gate": {
140
- "group_size": 64,
141
- "bits": 8
142
  }
143
  },
144
  "quantization_config": {
145
  "group_size": 64,
146
  "bits": 4,
147
  "mode": "affine",
148
- "model.layers.2.feed_forward.gate": {
149
- "group_size": 64,
150
- "bits": 8
151
- },
152
- "model.layers.3.feed_forward.gate": {
153
- "group_size": 64,
154
- "bits": 8
155
- },
156
- "model.layers.4.feed_forward.gate": {
157
- "group_size": 64,
158
- "bits": 8
159
- },
160
- "model.layers.5.feed_forward.gate": {
161
- "group_size": 64,
162
- "bits": 8
163
- },
164
- "model.layers.6.feed_forward.gate": {
165
- "group_size": 64,
166
- "bits": 8
167
- },
168
- "model.layers.7.feed_forward.gate": {
169
- "group_size": 64,
170
- "bits": 8
171
- },
172
- "model.layers.8.feed_forward.gate": {
173
- "group_size": 64,
174
- "bits": 8
175
- },
176
- "model.layers.9.feed_forward.gate": {
177
- "group_size": 64,
178
- "bits": 8
179
- },
180
- "model.layers.10.feed_forward.gate": {
181
- "group_size": 64,
182
- "bits": 8
183
- },
184
- "model.layers.11.feed_forward.gate": {
185
- "group_size": 64,
186
- "bits": 8
187
- },
188
- "model.layers.12.feed_forward.gate": {
189
- "group_size": 64,
190
- "bits": 8
191
- },
192
- "model.layers.13.feed_forward.gate": {
193
- "group_size": 64,
194
- "bits": 8
195
- },
196
- "model.layers.14.feed_forward.gate": {
197
- "group_size": 64,
198
- "bits": 8
199
- },
200
- "model.layers.15.feed_forward.gate": {
201
- "group_size": 64,
202
- "bits": 8
203
- },
204
- "model.layers.16.feed_forward.gate": {
205
- "group_size": 64,
206
- "bits": 8
207
- },
208
- "model.layers.17.feed_forward.gate": {
209
- "group_size": 64,
210
- "bits": 8
211
- },
212
- "model.layers.18.feed_forward.gate": {
213
- "group_size": 64,
214
- "bits": 8
215
- },
216
- "model.layers.19.feed_forward.gate": {
217
- "group_size": 64,
218
- "bits": 8
219
- },
220
- "model.layers.20.feed_forward.gate": {
221
- "group_size": 64,
222
- "bits": 8
223
- },
224
- "model.layers.21.feed_forward.gate": {
225
- "group_size": 64,
226
- "bits": 8
227
- },
228
- "model.layers.22.feed_forward.gate": {
229
- "group_size": 64,
230
- "bits": 8
231
- },
232
- "model.layers.23.feed_forward.gate": {
233
  "group_size": 64,
234
- "bits": 8
 
235
  }
236
  },
237
  "rope_parameters": {
 
52
  "group_size": 64,
53
  "bits": 4,
54
  "mode": "affine",
55
+ "model.embed_tokens": {
56
  "group_size": 64,
57
+ "bits": 6,
58
+ "mode": "affine"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59
  }
60
  },
61
  "quantization_config": {
62
  "group_size": 64,
63
  "bits": 4,
64
  "mode": "affine",
65
+ "model.embed_tokens": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
66
  "group_size": 64,
67
+ "bits": 6,
68
+ "mode": "affine"
69
  }
70
  },
71
  "rope_parameters": {
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eaebca378d92dc46b5dc8bfbf5a93e3f83d3b63c0531adeeed8456c18a2dfcc0
3
- size 4764263779
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cc15631acc1894b3584ac11fb4122beee50b604e1a0be575da686cee87aa3a4
3
+ size 4834029941
model.safetensors.index.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "metadata": {
3
- "total_size": 4764195712,
4
  "total_parameters": 8467856128
5
  },
6
  "weight_map": {
@@ -45,8 +45,6 @@
45
  "model.layers.1.ffn_norm.weight": "model.safetensors",
46
  "model.layers.1.operator_norm.weight": "model.safetensors",
47
  "model.layers.10.feed_forward.expert_bias": "model.safetensors",
48
- "model.layers.10.feed_forward.gate.biases": "model.safetensors",
49
- "model.layers.10.feed_forward.gate.scales": "model.safetensors",
50
  "model.layers.10.feed_forward.gate.weight": "model.safetensors",
51
  "model.layers.10.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
52
  "model.layers.10.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
@@ -81,8 +79,6 @@
81
  "model.layers.11.conv.out_proj.scales": "model.safetensors",
82
  "model.layers.11.conv.out_proj.weight": "model.safetensors",
83
  "model.layers.11.feed_forward.expert_bias": "model.safetensors",
84
- "model.layers.11.feed_forward.gate.biases": "model.safetensors",
85
- "model.layers.11.feed_forward.gate.scales": "model.safetensors",
86
  "model.layers.11.feed_forward.gate.weight": "model.safetensors",
87
  "model.layers.11.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
88
  "model.layers.11.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
@@ -103,8 +99,6 @@
103
  "model.layers.12.conv.out_proj.scales": "model.safetensors",
104
  "model.layers.12.conv.out_proj.weight": "model.safetensors",
105
  "model.layers.12.feed_forward.expert_bias": "model.safetensors",
106
- "model.layers.12.feed_forward.gate.biases": "model.safetensors",
107
- "model.layers.12.feed_forward.gate.scales": "model.safetensors",
108
  "model.layers.12.feed_forward.gate.weight": "model.safetensors",
109
  "model.layers.12.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
110
  "model.layers.12.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
@@ -125,8 +119,6 @@
125
  "model.layers.13.conv.out_proj.scales": "model.safetensors",
126
  "model.layers.13.conv.out_proj.weight": "model.safetensors",
127
  "model.layers.13.feed_forward.expert_bias": "model.safetensors",
128
- "model.layers.13.feed_forward.gate.biases": "model.safetensors",
129
- "model.layers.13.feed_forward.gate.scales": "model.safetensors",
130
  "model.layers.13.feed_forward.gate.weight": "model.safetensors",
131
  "model.layers.13.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
132
  "model.layers.13.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
@@ -140,8 +132,6 @@
140
  "model.layers.13.ffn_norm.weight": "model.safetensors",
141
  "model.layers.13.operator_norm.weight": "model.safetensors",
142
  "model.layers.14.feed_forward.expert_bias": "model.safetensors",
143
- "model.layers.14.feed_forward.gate.biases": "model.safetensors",
144
- "model.layers.14.feed_forward.gate.scales": "model.safetensors",
145
  "model.layers.14.feed_forward.gate.weight": "model.safetensors",
146
  "model.layers.14.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
147
  "model.layers.14.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
@@ -176,8 +166,6 @@
176
  "model.layers.15.conv.out_proj.scales": "model.safetensors",
177
  "model.layers.15.conv.out_proj.weight": "model.safetensors",
178
  "model.layers.15.feed_forward.expert_bias": "model.safetensors",
179
- "model.layers.15.feed_forward.gate.biases": "model.safetensors",
180
- "model.layers.15.feed_forward.gate.scales": "model.safetensors",
181
  "model.layers.15.feed_forward.gate.weight": "model.safetensors",
182
  "model.layers.15.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
183
  "model.layers.15.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
@@ -198,8 +186,6 @@
198
  "model.layers.16.conv.out_proj.scales": "model.safetensors",
199
  "model.layers.16.conv.out_proj.weight": "model.safetensors",
200
  "model.layers.16.feed_forward.expert_bias": "model.safetensors",
201
- "model.layers.16.feed_forward.gate.biases": "model.safetensors",
202
- "model.layers.16.feed_forward.gate.scales": "model.safetensors",
203
  "model.layers.16.feed_forward.gate.weight": "model.safetensors",
204
  "model.layers.16.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
205
  "model.layers.16.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
@@ -220,8 +206,6 @@
220
  "model.layers.17.conv.out_proj.scales": "model.safetensors",
221
  "model.layers.17.conv.out_proj.weight": "model.safetensors",
222
  "model.layers.17.feed_forward.expert_bias": "model.safetensors",
223
- "model.layers.17.feed_forward.gate.biases": "model.safetensors",
224
- "model.layers.17.feed_forward.gate.scales": "model.safetensors",
225
  "model.layers.17.feed_forward.gate.weight": "model.safetensors",
226
  "model.layers.17.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
227
  "model.layers.17.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
@@ -235,8 +219,6 @@
235
  "model.layers.17.ffn_norm.weight": "model.safetensors",
236
  "model.layers.17.operator_norm.weight": "model.safetensors",
237
  "model.layers.18.feed_forward.expert_bias": "model.safetensors",
238
- "model.layers.18.feed_forward.gate.biases": "model.safetensors",
239
- "model.layers.18.feed_forward.gate.scales": "model.safetensors",
240
  "model.layers.18.feed_forward.gate.weight": "model.safetensors",
241
  "model.layers.18.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
242
  "model.layers.18.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
@@ -271,8 +253,6 @@
271
  "model.layers.19.conv.out_proj.scales": "model.safetensors",
272
  "model.layers.19.conv.out_proj.weight": "model.safetensors",
273
  "model.layers.19.feed_forward.expert_bias": "model.safetensors",
274
- "model.layers.19.feed_forward.gate.biases": "model.safetensors",
275
- "model.layers.19.feed_forward.gate.scales": "model.safetensors",
276
  "model.layers.19.feed_forward.gate.weight": "model.safetensors",
277
  "model.layers.19.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
278
  "model.layers.19.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
@@ -286,8 +266,6 @@
286
  "model.layers.19.ffn_norm.weight": "model.safetensors",
287
  "model.layers.19.operator_norm.weight": "model.safetensors",
288
  "model.layers.2.feed_forward.expert_bias": "model.safetensors",
289
- "model.layers.2.feed_forward.gate.biases": "model.safetensors",
290
- "model.layers.2.feed_forward.gate.scales": "model.safetensors",
291
  "model.layers.2.feed_forward.gate.weight": "model.safetensors",
292
  "model.layers.2.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
293
  "model.layers.2.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
@@ -322,8 +300,6 @@
322
  "model.layers.20.conv.out_proj.scales": "model.safetensors",
323
  "model.layers.20.conv.out_proj.weight": "model.safetensors",
324
  "model.layers.20.feed_forward.expert_bias": "model.safetensors",
325
- "model.layers.20.feed_forward.gate.biases": "model.safetensors",
326
- "model.layers.20.feed_forward.gate.scales": "model.safetensors",
327
  "model.layers.20.feed_forward.gate.weight": "model.safetensors",
328
  "model.layers.20.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
329
  "model.layers.20.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
@@ -337,8 +313,6 @@
337
  "model.layers.20.ffn_norm.weight": "model.safetensors",
338
  "model.layers.20.operator_norm.weight": "model.safetensors",
339
  "model.layers.21.feed_forward.expert_bias": "model.safetensors",
340
- "model.layers.21.feed_forward.gate.biases": "model.safetensors",
341
- "model.layers.21.feed_forward.gate.scales": "model.safetensors",
342
  "model.layers.21.feed_forward.gate.weight": "model.safetensors",
343
  "model.layers.21.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
344
  "model.layers.21.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
@@ -373,8 +347,6 @@
373
  "model.layers.22.conv.out_proj.scales": "model.safetensors",
374
  "model.layers.22.conv.out_proj.weight": "model.safetensors",
375
  "model.layers.22.feed_forward.expert_bias": "model.safetensors",
376
- "model.layers.22.feed_forward.gate.biases": "model.safetensors",
377
- "model.layers.22.feed_forward.gate.scales": "model.safetensors",
378
  "model.layers.22.feed_forward.gate.weight": "model.safetensors",
379
  "model.layers.22.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
380
  "model.layers.22.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
@@ -395,8 +367,6 @@
395
  "model.layers.23.conv.out_proj.scales": "model.safetensors",
396
  "model.layers.23.conv.out_proj.weight": "model.safetensors",
397
  "model.layers.23.feed_forward.expert_bias": "model.safetensors",
398
- "model.layers.23.feed_forward.gate.biases": "model.safetensors",
399
- "model.layers.23.feed_forward.gate.scales": "model.safetensors",
400
  "model.layers.23.feed_forward.gate.weight": "model.safetensors",
401
  "model.layers.23.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
402
  "model.layers.23.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
@@ -417,8 +387,6 @@
417
  "model.layers.3.conv.out_proj.scales": "model.safetensors",
418
  "model.layers.3.conv.out_proj.weight": "model.safetensors",
419
  "model.layers.3.feed_forward.expert_bias": "model.safetensors",
420
- "model.layers.3.feed_forward.gate.biases": "model.safetensors",
421
- "model.layers.3.feed_forward.gate.scales": "model.safetensors",
422
  "model.layers.3.feed_forward.gate.weight": "model.safetensors",
423
  "model.layers.3.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
424
  "model.layers.3.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
@@ -439,8 +407,6 @@
439
  "model.layers.4.conv.out_proj.scales": "model.safetensors",
440
  "model.layers.4.conv.out_proj.weight": "model.safetensors",
441
  "model.layers.4.feed_forward.expert_bias": "model.safetensors",
442
- "model.layers.4.feed_forward.gate.biases": "model.safetensors",
443
- "model.layers.4.feed_forward.gate.scales": "model.safetensors",
444
  "model.layers.4.feed_forward.gate.weight": "model.safetensors",
445
  "model.layers.4.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
446
  "model.layers.4.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
@@ -461,8 +427,6 @@
461
  "model.layers.5.conv.out_proj.scales": "model.safetensors",
462
  "model.layers.5.conv.out_proj.weight": "model.safetensors",
463
  "model.layers.5.feed_forward.expert_bias": "model.safetensors",
464
- "model.layers.5.feed_forward.gate.biases": "model.safetensors",
465
- "model.layers.5.feed_forward.gate.scales": "model.safetensors",
466
  "model.layers.5.feed_forward.gate.weight": "model.safetensors",
467
  "model.layers.5.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
468
  "model.layers.5.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
@@ -476,8 +440,6 @@
476
  "model.layers.5.ffn_norm.weight": "model.safetensors",
477
  "model.layers.5.operator_norm.weight": "model.safetensors",
478
  "model.layers.6.feed_forward.expert_bias": "model.safetensors",
479
- "model.layers.6.feed_forward.gate.biases": "model.safetensors",
480
- "model.layers.6.feed_forward.gate.scales": "model.safetensors",
481
  "model.layers.6.feed_forward.gate.weight": "model.safetensors",
482
  "model.layers.6.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
483
  "model.layers.6.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
@@ -512,8 +474,6 @@
512
  "model.layers.7.conv.out_proj.scales": "model.safetensors",
513
  "model.layers.7.conv.out_proj.weight": "model.safetensors",
514
  "model.layers.7.feed_forward.expert_bias": "model.safetensors",
515
- "model.layers.7.feed_forward.gate.biases": "model.safetensors",
516
- "model.layers.7.feed_forward.gate.scales": "model.safetensors",
517
  "model.layers.7.feed_forward.gate.weight": "model.safetensors",
518
  "model.layers.7.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
519
  "model.layers.7.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
@@ -534,8 +494,6 @@
534
  "model.layers.8.conv.out_proj.scales": "model.safetensors",
535
  "model.layers.8.conv.out_proj.weight": "model.safetensors",
536
  "model.layers.8.feed_forward.expert_bias": "model.safetensors",
537
- "model.layers.8.feed_forward.gate.biases": "model.safetensors",
538
- "model.layers.8.feed_forward.gate.scales": "model.safetensors",
539
  "model.layers.8.feed_forward.gate.weight": "model.safetensors",
540
  "model.layers.8.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
541
  "model.layers.8.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
@@ -556,8 +514,6 @@
556
  "model.layers.9.conv.out_proj.scales": "model.safetensors",
557
  "model.layers.9.conv.out_proj.weight": "model.safetensors",
558
  "model.layers.9.feed_forward.expert_bias": "model.safetensors",
559
- "model.layers.9.feed_forward.gate.biases": "model.safetensors",
560
- "model.layers.9.feed_forward.gate.scales": "model.safetensors",
561
  "model.layers.9.feed_forward.gate.weight": "model.safetensors",
562
  "model.layers.9.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
563
  "model.layers.9.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
 
1
  {
2
  "metadata": {
3
+ "total_size": 4831083392,
4
  "total_parameters": 8467856128
5
  },
6
  "weight_map": {
 
45
  "model.layers.1.ffn_norm.weight": "model.safetensors",
46
  "model.layers.1.operator_norm.weight": "model.safetensors",
47
  "model.layers.10.feed_forward.expert_bias": "model.safetensors",
 
 
48
  "model.layers.10.feed_forward.gate.weight": "model.safetensors",
49
  "model.layers.10.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
50
  "model.layers.10.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
 
79
  "model.layers.11.conv.out_proj.scales": "model.safetensors",
80
  "model.layers.11.conv.out_proj.weight": "model.safetensors",
81
  "model.layers.11.feed_forward.expert_bias": "model.safetensors",
 
 
82
  "model.layers.11.feed_forward.gate.weight": "model.safetensors",
83
  "model.layers.11.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
84
  "model.layers.11.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
 
99
  "model.layers.12.conv.out_proj.scales": "model.safetensors",
100
  "model.layers.12.conv.out_proj.weight": "model.safetensors",
101
  "model.layers.12.feed_forward.expert_bias": "model.safetensors",
 
 
102
  "model.layers.12.feed_forward.gate.weight": "model.safetensors",
103
  "model.layers.12.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
104
  "model.layers.12.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
 
119
  "model.layers.13.conv.out_proj.scales": "model.safetensors",
120
  "model.layers.13.conv.out_proj.weight": "model.safetensors",
121
  "model.layers.13.feed_forward.expert_bias": "model.safetensors",
 
 
122
  "model.layers.13.feed_forward.gate.weight": "model.safetensors",
123
  "model.layers.13.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
124
  "model.layers.13.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
 
132
  "model.layers.13.ffn_norm.weight": "model.safetensors",
133
  "model.layers.13.operator_norm.weight": "model.safetensors",
134
  "model.layers.14.feed_forward.expert_bias": "model.safetensors",
 
 
135
  "model.layers.14.feed_forward.gate.weight": "model.safetensors",
136
  "model.layers.14.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
137
  "model.layers.14.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
 
166
  "model.layers.15.conv.out_proj.scales": "model.safetensors",
167
  "model.layers.15.conv.out_proj.weight": "model.safetensors",
168
  "model.layers.15.feed_forward.expert_bias": "model.safetensors",
 
 
169
  "model.layers.15.feed_forward.gate.weight": "model.safetensors",
170
  "model.layers.15.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
171
  "model.layers.15.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
 
186
  "model.layers.16.conv.out_proj.scales": "model.safetensors",
187
  "model.layers.16.conv.out_proj.weight": "model.safetensors",
188
  "model.layers.16.feed_forward.expert_bias": "model.safetensors",
 
 
189
  "model.layers.16.feed_forward.gate.weight": "model.safetensors",
190
  "model.layers.16.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
191
  "model.layers.16.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
 
206
  "model.layers.17.conv.out_proj.scales": "model.safetensors",
207
  "model.layers.17.conv.out_proj.weight": "model.safetensors",
208
  "model.layers.17.feed_forward.expert_bias": "model.safetensors",
 
 
209
  "model.layers.17.feed_forward.gate.weight": "model.safetensors",
210
  "model.layers.17.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
211
  "model.layers.17.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
 
219
  "model.layers.17.ffn_norm.weight": "model.safetensors",
220
  "model.layers.17.operator_norm.weight": "model.safetensors",
221
  "model.layers.18.feed_forward.expert_bias": "model.safetensors",
 
 
222
  "model.layers.18.feed_forward.gate.weight": "model.safetensors",
223
  "model.layers.18.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
224
  "model.layers.18.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
 
253
  "model.layers.19.conv.out_proj.scales": "model.safetensors",
254
  "model.layers.19.conv.out_proj.weight": "model.safetensors",
255
  "model.layers.19.feed_forward.expert_bias": "model.safetensors",
 
 
256
  "model.layers.19.feed_forward.gate.weight": "model.safetensors",
257
  "model.layers.19.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
258
  "model.layers.19.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
 
266
  "model.layers.19.ffn_norm.weight": "model.safetensors",
267
  "model.layers.19.operator_norm.weight": "model.safetensors",
268
  "model.layers.2.feed_forward.expert_bias": "model.safetensors",
 
 
269
  "model.layers.2.feed_forward.gate.weight": "model.safetensors",
270
  "model.layers.2.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
271
  "model.layers.2.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
 
300
  "model.layers.20.conv.out_proj.scales": "model.safetensors",
301
  "model.layers.20.conv.out_proj.weight": "model.safetensors",
302
  "model.layers.20.feed_forward.expert_bias": "model.safetensors",
 
 
303
  "model.layers.20.feed_forward.gate.weight": "model.safetensors",
304
  "model.layers.20.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
305
  "model.layers.20.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
 
313
  "model.layers.20.ffn_norm.weight": "model.safetensors",
314
  "model.layers.20.operator_norm.weight": "model.safetensors",
315
  "model.layers.21.feed_forward.expert_bias": "model.safetensors",
 
 
316
  "model.layers.21.feed_forward.gate.weight": "model.safetensors",
317
  "model.layers.21.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
318
  "model.layers.21.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
 
347
  "model.layers.22.conv.out_proj.scales": "model.safetensors",
348
  "model.layers.22.conv.out_proj.weight": "model.safetensors",
349
  "model.layers.22.feed_forward.expert_bias": "model.safetensors",
 
 
350
  "model.layers.22.feed_forward.gate.weight": "model.safetensors",
351
  "model.layers.22.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
352
  "model.layers.22.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
 
367
  "model.layers.23.conv.out_proj.scales": "model.safetensors",
368
  "model.layers.23.conv.out_proj.weight": "model.safetensors",
369
  "model.layers.23.feed_forward.expert_bias": "model.safetensors",
 
 
370
  "model.layers.23.feed_forward.gate.weight": "model.safetensors",
371
  "model.layers.23.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
372
  "model.layers.23.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
 
387
  "model.layers.3.conv.out_proj.scales": "model.safetensors",
388
  "model.layers.3.conv.out_proj.weight": "model.safetensors",
389
  "model.layers.3.feed_forward.expert_bias": "model.safetensors",
 
 
390
  "model.layers.3.feed_forward.gate.weight": "model.safetensors",
391
  "model.layers.3.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
392
  "model.layers.3.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
 
407
  "model.layers.4.conv.out_proj.scales": "model.safetensors",
408
  "model.layers.4.conv.out_proj.weight": "model.safetensors",
409
  "model.layers.4.feed_forward.expert_bias": "model.safetensors",
 
 
410
  "model.layers.4.feed_forward.gate.weight": "model.safetensors",
411
  "model.layers.4.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
412
  "model.layers.4.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
 
427
  "model.layers.5.conv.out_proj.scales": "model.safetensors",
428
  "model.layers.5.conv.out_proj.weight": "model.safetensors",
429
  "model.layers.5.feed_forward.expert_bias": "model.safetensors",
 
 
430
  "model.layers.5.feed_forward.gate.weight": "model.safetensors",
431
  "model.layers.5.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
432
  "model.layers.5.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
 
440
  "model.layers.5.ffn_norm.weight": "model.safetensors",
441
  "model.layers.5.operator_norm.weight": "model.safetensors",
442
  "model.layers.6.feed_forward.expert_bias": "model.safetensors",
 
 
443
  "model.layers.6.feed_forward.gate.weight": "model.safetensors",
444
  "model.layers.6.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
445
  "model.layers.6.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
 
474
  "model.layers.7.conv.out_proj.scales": "model.safetensors",
475
  "model.layers.7.conv.out_proj.weight": "model.safetensors",
476
  "model.layers.7.feed_forward.expert_bias": "model.safetensors",
 
 
477
  "model.layers.7.feed_forward.gate.weight": "model.safetensors",
478
  "model.layers.7.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
479
  "model.layers.7.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
 
494
  "model.layers.8.conv.out_proj.scales": "model.safetensors",
495
  "model.layers.8.conv.out_proj.weight": "model.safetensors",
496
  "model.layers.8.feed_forward.expert_bias": "model.safetensors",
 
 
497
  "model.layers.8.feed_forward.gate.weight": "model.safetensors",
498
  "model.layers.8.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
499
  "model.layers.8.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",
 
514
  "model.layers.9.conv.out_proj.scales": "model.safetensors",
515
  "model.layers.9.conv.out_proj.weight": "model.safetensors",
516
  "model.layers.9.feed_forward.expert_bias": "model.safetensors",
 
 
517
  "model.layers.9.feed_forward.gate.weight": "model.safetensors",
518
  "model.layers.9.feed_forward.switch_mlp.down_proj.biases": "model.safetensors",
519
  "model.layers.9.feed_forward.switch_mlp.down_proj.scales": "model.safetensors",