voidstream commited on
Commit
1658dad
·
verified ·
1 Parent(s): 39b5aec

Upload completeness_gate_receipt.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. completeness_gate_receipt.json +1011 -0
completeness_gate_receipt.json ADDED
@@ -0,0 +1,1011 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "verdict": "PASS",
3
+ "summary": {
4
+ "dense_tensors": 1597,
5
+ "output_tensors": 2236,
6
+ "compressed_weights": 213,
7
+ "accounted": 1597,
8
+ "missing": 0,
9
+ "skip_tensors_found": 979,
10
+ "skip_categories": {
11
+ "bias": "OK (162/162)",
12
+ "embedding": "OK (1/1)",
13
+ "layernorm": "OK (329/329)",
14
+ "output_head": "OK (1/1)",
15
+ "ssm_param": "OK (486/486)"
16
+ }
17
+ },
18
+ "failures": [],
19
+ "missing_tensors": [],
20
+ "skip_found": {
21
+ "output_head": [
22
+ "lm_head.weight"
23
+ ],
24
+ "layernorm": [
25
+ "model.blocks.0.input_layernorm.weight",
26
+ "model.blocks.1.input_layernorm.weight",
27
+ "model.final_layernorm.weight",
28
+ "model.layers.0.input_layernorm.weight",
29
+ "model.layers.0.mamba.norm.weight",
30
+ "model.layers.1.input_layernorm.weight",
31
+ "model.layers.1.mamba.norm.weight",
32
+ "model.layers.10.input_layernorm.weight",
33
+ "model.layers.10.mamba.norm.weight",
34
+ "model.layers.11.mamba_decoder.input_layernorm.weight",
35
+ "model.layers.11.mamba_decoder.mamba.norm.weight",
36
+ "model.layers.11.shared_transformer.input_layernorm.weight",
37
+ "model.layers.12.input_layernorm.weight",
38
+ "model.layers.12.mamba.norm.weight",
39
+ "model.layers.13.input_layernorm.weight",
40
+ "model.layers.13.mamba.norm.weight",
41
+ "model.layers.14.input_layernorm.weight",
42
+ "model.layers.14.mamba.norm.weight",
43
+ "model.layers.15.input_layernorm.weight",
44
+ "model.layers.15.mamba.norm.weight",
45
+ "model.layers.16.input_layernorm.weight",
46
+ "model.layers.16.mamba.norm.weight",
47
+ "model.layers.17.mamba_decoder.input_layernorm.weight",
48
+ "model.layers.17.mamba_decoder.mamba.norm.weight",
49
+ "model.layers.18.input_layernorm.weight",
50
+ "model.layers.18.mamba.norm.weight",
51
+ "model.layers.19.input_layernorm.weight",
52
+ "model.layers.19.mamba.norm.weight",
53
+ "model.layers.2.input_layernorm.weight",
54
+ "model.layers.2.mamba.norm.weight",
55
+ "model.layers.20.input_layernorm.weight",
56
+ "model.layers.20.mamba.norm.weight",
57
+ "model.layers.21.input_layernorm.weight",
58
+ "model.layers.21.mamba.norm.weight",
59
+ "model.layers.22.input_layernorm.weight",
60
+ "model.layers.22.mamba.norm.weight",
61
+ "model.layers.23.mamba_decoder.input_layernorm.weight",
62
+ "model.layers.23.mamba_decoder.mamba.norm.weight",
63
+ "model.layers.24.input_layernorm.weight",
64
+ "model.layers.24.mamba.norm.weight",
65
+ "model.layers.25.input_layernorm.weight",
66
+ "model.layers.25.mamba.norm.weight",
67
+ "model.layers.26.input_layernorm.weight",
68
+ "model.layers.26.mamba.norm.weight",
69
+ "model.layers.27.input_layernorm.weight",
70
+ "model.layers.27.mamba.norm.weight",
71
+ "model.layers.28.input_layernorm.weight",
72
+ "model.layers.28.mamba.norm.weight",
73
+ "model.layers.29.mamba_decoder.input_layernorm.weight",
74
+ "model.layers.29.mamba_decoder.mamba.norm.weight",
75
+ "model.layers.3.input_layernorm.weight",
76
+ "model.layers.3.mamba.norm.weight",
77
+ "model.layers.30.input_layernorm.weight",
78
+ "model.layers.30.mamba.norm.weight",
79
+ "model.layers.31.input_layernorm.weight",
80
+ "model.layers.31.mamba.norm.weight",
81
+ "model.layers.32.input_layernorm.weight",
82
+ "model.layers.32.mamba.norm.weight",
83
+ "model.layers.33.input_layernorm.weight",
84
+ "model.layers.33.mamba.norm.weight",
85
+ "model.layers.34.input_layernorm.weight",
86
+ "model.layers.34.mamba.norm.weight",
87
+ "model.layers.35.mamba_decoder.input_layernorm.weight",
88
+ "model.layers.35.mamba_decoder.mamba.norm.weight",
89
+ "model.layers.36.input_layernorm.weight",
90
+ "model.layers.36.mamba.norm.weight",
91
+ "model.layers.37.input_layernorm.weight",
92
+ "model.layers.37.mamba.norm.weight",
93
+ "model.layers.38.input_layernorm.weight",
94
+ "model.layers.38.mamba.norm.weight",
95
+ "model.layers.39.input_layernorm.weight",
96
+ "model.layers.39.mamba.norm.weight",
97
+ "model.layers.4.input_layernorm.weight",
98
+ "model.layers.4.mamba.norm.weight",
99
+ "model.layers.40.input_layernorm.weight",
100
+ "model.layers.40.mamba.norm.weight",
101
+ "model.layers.41.mamba_decoder.input_layernorm.weight",
102
+ "model.layers.41.mamba_decoder.mamba.norm.weight",
103
+ "model.layers.42.input_layernorm.weight",
104
+ "model.layers.42.mamba.norm.weight",
105
+ "model.layers.43.input_layernorm.weight",
106
+ "model.layers.43.mamba.norm.weight",
107
+ "model.layers.44.input_layernorm.weight",
108
+ "model.layers.44.mamba.norm.weight",
109
+ "model.layers.45.input_layernorm.weight",
110
+ "model.layers.45.mamba.norm.weight",
111
+ "model.layers.46.input_layernorm.weight",
112
+ "model.layers.46.mamba.norm.weight",
113
+ "model.layers.47.mamba_decoder.input_layernorm.weight",
114
+ "model.layers.47.mamba_decoder.mamba.norm.weight",
115
+ "model.layers.48.input_layernorm.weight",
116
+ "model.layers.48.mamba.norm.weight",
117
+ "model.layers.49.input_layernorm.weight",
118
+ "model.layers.49.mamba.norm.weight",
119
+ "model.layers.5.input_layernorm.weight",
120
+ "model.layers.5.mamba.norm.weight",
121
+ "model.layers.50.input_layernorm.weight",
122
+ "model.layers.50.mamba.norm.weight",
123
+ "model.layers.51.input_layernorm.weight",
124
+ "model.layers.51.mamba.norm.weight",
125
+ "model.layers.52.input_layernorm.weight",
126
+ "model.layers.52.mamba.norm.weight",
127
+ "model.layers.53.mamba_decoder.input_layernorm.weight",
128
+ "model.layers.53.mamba_decoder.mamba.norm.weight",
129
+ "model.layers.54.input_layernorm.weight",
130
+ "model.layers.54.mamba.norm.weight",
131
+ "model.layers.55.input_layernorm.weight",
132
+ "model.layers.55.mamba.norm.weight",
133
+ "model.layers.56.input_layernorm.weight",
134
+ "model.layers.56.mamba.norm.weight",
135
+ "model.layers.57.input_layernorm.weight",
136
+ "model.layers.57.mamba.norm.weight",
137
+ "model.layers.58.input_layernorm.weight",
138
+ "model.layers.58.mamba.norm.weight",
139
+ "model.layers.59.mamba_decoder.input_layernorm.weight",
140
+ "model.layers.59.mamba_decoder.mamba.norm.weight",
141
+ "model.layers.6.mamba_decoder.input_layernorm.weight",
142
+ "model.layers.6.mamba_decoder.mamba.norm.weight",
143
+ "model.layers.6.shared_transformer.input_layernorm.weight",
144
+ "model.layers.60.input_layernorm.weight",
145
+ "model.layers.60.mamba.norm.weight",
146
+ "model.layers.61.input_layernorm.weight",
147
+ "model.layers.61.mamba.norm.weight",
148
+ "model.layers.62.input_layernorm.weight",
149
+ "model.layers.62.mamba.norm.weight",
150
+ "model.layers.63.input_layernorm.weight",
151
+ "model.layers.63.mamba.norm.weight",
152
+ "model.layers.64.input_layernorm.weight",
153
+ "model.layers.64.mamba.norm.weight",
154
+ "model.layers.65.mamba_decoder.input_layernorm.weight",
155
+ "model.layers.65.mamba_decoder.mamba.norm.weight",
156
+ "model.layers.66.input_layernorm.weight",
157
+ "model.layers.66.mamba.norm.weight",
158
+ "model.layers.67.input_layernorm.weight",
159
+ "model.layers.67.mamba.norm.weight",
160
+ "model.layers.68.input_layernorm.weight",
161
+ "model.layers.68.mamba.norm.weight",
162
+ "model.layers.69.input_layernorm.weight",
163
+ "model.layers.69.mamba.norm.weight",
164
+ "model.layers.7.input_layernorm.weight",
165
+ "model.layers.7.mamba.norm.weight",
166
+ "model.layers.70.input_layernorm.weight",
167
+ "model.layers.70.mamba.norm.weight",
168
+ "model.layers.71.mamba_decoder.input_layernorm.weight",
169
+ "model.layers.71.mamba_decoder.mamba.norm.weight",
170
+ "model.layers.72.input_layernorm.weight",
171
+ "model.layers.72.mamba.norm.weight",
172
+ "model.layers.73.input_layernorm.weight",
173
+ "model.layers.73.mamba.norm.weight",
174
+ "model.layers.74.input_layernorm.weight",
175
+ "model.layers.74.mamba.norm.weight",
176
+ "model.layers.75.input_layernorm.weight",
177
+ "model.layers.75.mamba.norm.weight",
178
+ "model.layers.76.input_layernorm.weight",
179
+ "model.layers.76.mamba.norm.weight",
180
+ "model.layers.77.mamba_decoder.input_layernorm.weight",
181
+ "model.layers.77.mamba_decoder.mamba.norm.weight",
182
+ "model.layers.78.input_layernorm.weight",
183
+ "model.layers.78.mamba.norm.weight",
184
+ "model.layers.79.input_layernorm.weight",
185
+ "model.layers.79.mamba.norm.weight",
186
+ "model.layers.8.input_layernorm.weight",
187
+ "model.layers.8.mamba.norm.weight",
188
+ "model.layers.80.input_layernorm.weight",
189
+ "model.layers.80.mamba.norm.weight",
190
+ "model.layers.9.input_layernorm.weight",
191
+ "model.layers.9.mamba.norm.weight",
192
+ "model.mamba_layers.0.input_layernorm.weight",
193
+ "model.mamba_layers.0.mamba.norm.weight",
194
+ "model.mamba_layers.1.input_layernorm.weight",
195
+ "model.mamba_layers.1.mamba.norm.weight",
196
+ "model.mamba_layers.10.input_layernorm.weight",
197
+ "model.mamba_layers.10.mamba.norm.weight",
198
+ "model.mamba_layers.11.input_layernorm.weight",
199
+ "model.mamba_layers.11.mamba.norm.weight",
200
+ "model.mamba_layers.12.input_layernorm.weight",
201
+ "model.mamba_layers.12.mamba.norm.weight",
202
+ "model.mamba_layers.13.input_layernorm.weight",
203
+ "model.mamba_layers.13.mamba.norm.weight",
204
+ "model.mamba_layers.14.input_layernorm.weight",
205
+ "model.mamba_layers.14.mamba.norm.weight",
206
+ "model.mamba_layers.15.input_layernorm.weight",
207
+ "model.mamba_layers.15.mamba.norm.weight",
208
+ "model.mamba_layers.16.input_layernorm.weight",
209
+ "model.mamba_layers.16.mamba.norm.weight",
210
+ "model.mamba_layers.17.input_layernorm.weight",
211
+ "model.mamba_layers.17.mamba.norm.weight",
212
+ "model.mamba_layers.18.input_layernorm.weight",
213
+ "model.mamba_layers.18.mamba.norm.weight",
214
+ "model.mamba_layers.19.input_layernorm.weight",
215
+ "model.mamba_layers.19.mamba.norm.weight",
216
+ "model.mamba_layers.2.input_layernorm.weight",
217
+ "model.mamba_layers.2.mamba.norm.weight",
218
+ "model.mamba_layers.20.input_layernorm.weight",
219
+ "model.mamba_layers.20.mamba.norm.weight",
220
+ "model.mamba_layers.21.input_layernorm.weight",
221
+ "model.mamba_layers.21.mamba.norm.weight",
222
+ "model.mamba_layers.22.input_layernorm.weight",
223
+ "model.mamba_layers.22.mamba.norm.weight",
224
+ "model.mamba_layers.23.input_layernorm.weight",
225
+ "model.mamba_layers.23.mamba.norm.weight",
226
+ "model.mamba_layers.24.input_layernorm.weight",
227
+ "model.mamba_layers.24.mamba.norm.weight",
228
+ "model.mamba_layers.25.input_layernorm.weight",
229
+ "model.mamba_layers.25.mamba.norm.weight",
230
+ "model.mamba_layers.26.input_layernorm.weight",
231
+ "model.mamba_layers.26.mamba.norm.weight",
232
+ "model.mamba_layers.27.input_layernorm.weight",
233
+ "model.mamba_layers.27.mamba.norm.weight",
234
+ "model.mamba_layers.28.input_layernorm.weight",
235
+ "model.mamba_layers.28.mamba.norm.weight",
236
+ "model.mamba_layers.29.input_layernorm.weight",
237
+ "model.mamba_layers.29.mamba.norm.weight",
238
+ "model.mamba_layers.3.input_layernorm.weight",
239
+ "model.mamba_layers.3.mamba.norm.weight",
240
+ "model.mamba_layers.30.input_layernorm.weight",
241
+ "model.mamba_layers.30.mamba.norm.weight",
242
+ "model.mamba_layers.31.input_layernorm.weight",
243
+ "model.mamba_layers.31.mamba.norm.weight",
244
+ "model.mamba_layers.32.input_layernorm.weight",
245
+ "model.mamba_layers.32.mamba.norm.weight",
246
+ "model.mamba_layers.33.input_layernorm.weight",
247
+ "model.mamba_layers.33.mamba.norm.weight",
248
+ "model.mamba_layers.34.input_layernorm.weight",
249
+ "model.mamba_layers.34.mamba.norm.weight",
250
+ "model.mamba_layers.35.input_layernorm.weight",
251
+ "model.mamba_layers.35.mamba.norm.weight",
252
+ "model.mamba_layers.36.input_layernorm.weight",
253
+ "model.mamba_layers.36.mamba.norm.weight",
254
+ "model.mamba_layers.37.input_layernorm.weight",
255
+ "model.mamba_layers.37.mamba.norm.weight",
256
+ "model.mamba_layers.38.input_layernorm.weight",
257
+ "model.mamba_layers.38.mamba.norm.weight",
258
+ "model.mamba_layers.39.input_layernorm.weight",
259
+ "model.mamba_layers.39.mamba.norm.weight",
260
+ "model.mamba_layers.4.input_layernorm.weight",
261
+ "model.mamba_layers.4.mamba.norm.weight",
262
+ "model.mamba_layers.40.input_layernorm.weight",
263
+ "model.mamba_layers.40.mamba.norm.weight",
264
+ "model.mamba_layers.41.input_layernorm.weight",
265
+ "model.mamba_layers.41.mamba.norm.weight",
266
+ "model.mamba_layers.42.input_layernorm.weight",
267
+ "model.mamba_layers.42.mamba.norm.weight",
268
+ "model.mamba_layers.43.input_layernorm.weight",
269
+ "model.mamba_layers.43.mamba.norm.weight",
270
+ "model.mamba_layers.44.input_layernorm.weight",
271
+ "model.mamba_layers.44.mamba.norm.weight",
272
+ "model.mamba_layers.45.input_layernorm.weight",
273
+ "model.mamba_layers.45.mamba.norm.weight",
274
+ "model.mamba_layers.46.input_layernorm.weight",
275
+ "model.mamba_layers.46.mamba.norm.weight",
276
+ "model.mamba_layers.47.input_layernorm.weight",
277
+ "model.mamba_layers.47.mamba.norm.weight",
278
+ "model.mamba_layers.48.input_layernorm.weight",
279
+ "model.mamba_layers.48.mamba.norm.weight",
280
+ "model.mamba_layers.49.input_layernorm.weight",
281
+ "model.mamba_layers.49.mamba.norm.weight",
282
+ "model.mamba_layers.5.input_layernorm.weight",
283
+ "model.mamba_layers.5.mamba.norm.weight",
284
+ "model.mamba_layers.50.input_layernorm.weight",
285
+ "model.mamba_layers.50.mamba.norm.weight",
286
+ "model.mamba_layers.51.input_layernorm.weight",
287
+ "model.mamba_layers.51.mamba.norm.weight",
288
+ "model.mamba_layers.52.input_layernorm.weight",
289
+ "model.mamba_layers.52.mamba.norm.weight",
290
+ "model.mamba_layers.53.input_layernorm.weight",
291
+ "model.mamba_layers.53.mamba.norm.weight",
292
+ "model.mamba_layers.54.input_layernorm.weight",
293
+ "model.mamba_layers.54.mamba.norm.weight",
294
+ "model.mamba_layers.55.input_layernorm.weight",
295
+ "model.mamba_layers.55.mamba.norm.weight",
296
+ "model.mamba_layers.56.input_layernorm.weight",
297
+ "model.mamba_layers.56.mamba.norm.weight",
298
+ "model.mamba_layers.57.input_layernorm.weight",
299
+ "model.mamba_layers.57.mamba.norm.weight",
300
+ "model.mamba_layers.58.input_layernorm.weight",
301
+ "model.mamba_layers.58.mamba.norm.weight",
302
+ "model.mamba_layers.59.input_layernorm.weight",
303
+ "model.mamba_layers.59.mamba.norm.weight",
304
+ "model.mamba_layers.6.input_layernorm.weight",
305
+ "model.mamba_layers.6.mamba.norm.weight",
306
+ "model.mamba_layers.60.input_layernorm.weight",
307
+ "model.mamba_layers.60.mamba.norm.weight",
308
+ "model.mamba_layers.61.input_layernorm.weight",
309
+ "model.mamba_layers.61.mamba.norm.weight",
310
+ "model.mamba_layers.62.input_layernorm.weight",
311
+ "model.mamba_layers.62.mamba.norm.weight",
312
+ "model.mamba_layers.63.input_layernorm.weight",
313
+ "model.mamba_layers.63.mamba.norm.weight",
314
+ "model.mamba_layers.64.input_layernorm.weight",
315
+ "model.mamba_layers.64.mamba.norm.weight",
316
+ "model.mamba_layers.65.input_layernorm.weight",
317
+ "model.mamba_layers.65.mamba.norm.weight",
318
+ "model.mamba_layers.66.input_layernorm.weight",
319
+ "model.mamba_layers.66.mamba.norm.weight",
320
+ "model.mamba_layers.67.input_layernorm.weight",
321
+ "model.mamba_layers.67.mamba.norm.weight",
322
+ "model.mamba_layers.68.input_layernorm.weight",
323
+ "model.mamba_layers.68.mamba.norm.weight",
324
+ "model.mamba_layers.69.input_layernorm.weight",
325
+ "model.mamba_layers.69.mamba.norm.weight",
326
+ "model.mamba_layers.7.input_layernorm.weight",
327
+ "model.mamba_layers.7.mamba.norm.weight",
328
+ "model.mamba_layers.70.input_layernorm.weight",
329
+ "model.mamba_layers.70.mamba.norm.weight",
330
+ "model.mamba_layers.71.input_layernorm.weight",
331
+ "model.mamba_layers.71.mamba.norm.weight",
332
+ "model.mamba_layers.72.input_layernorm.weight",
333
+ "model.mamba_layers.72.mamba.norm.weight",
334
+ "model.mamba_layers.73.input_layernorm.weight",
335
+ "model.mamba_layers.73.mamba.norm.weight",
336
+ "model.mamba_layers.74.input_layernorm.weight",
337
+ "model.mamba_layers.74.mamba.norm.weight",
338
+ "model.mamba_layers.75.input_layernorm.weight",
339
+ "model.mamba_layers.75.mamba.norm.weight",
340
+ "model.mamba_layers.76.input_layernorm.weight",
341
+ "model.mamba_layers.76.mamba.norm.weight",
342
+ "model.mamba_layers.77.input_layernorm.weight",
343
+ "model.mamba_layers.77.mamba.norm.weight",
344
+ "model.mamba_layers.78.input_layernorm.weight",
345
+ "model.mamba_layers.78.mamba.norm.weight",
346
+ "model.mamba_layers.79.input_layernorm.weight",
347
+ "model.mamba_layers.79.mamba.norm.weight",
348
+ "model.mamba_layers.8.input_layernorm.weight",
349
+ "model.mamba_layers.8.mamba.norm.weight",
350
+ "model.mamba_layers.80.input_layernorm.weight",
351
+ "model.mamba_layers.80.mamba.norm.weight",
352
+ "model.mamba_layers.9.input_layernorm.weight",
353
+ "model.mamba_layers.9.mamba.norm.weight"
354
+ ],
355
+ "embedding": [
356
+ "model.embed_tokens.weight"
357
+ ],
358
+ "ssm_param": [
359
+ "model.layers.0.mamba.A_log",
360
+ "model.layers.0.mamba.D",
361
+ "model.layers.0.mamba.dt_bias",
362
+ "model.layers.1.mamba.A_log",
363
+ "model.layers.1.mamba.D",
364
+ "model.layers.1.mamba.dt_bias",
365
+ "model.layers.10.mamba.A_log",
366
+ "model.layers.10.mamba.D",
367
+ "model.layers.10.mamba.dt_bias",
368
+ "model.layers.11.mamba_decoder.mamba.A_log",
369
+ "model.layers.11.mamba_decoder.mamba.D",
370
+ "model.layers.11.mamba_decoder.mamba.dt_bias",
371
+ "model.layers.12.mamba.A_log",
372
+ "model.layers.12.mamba.D",
373
+ "model.layers.12.mamba.dt_bias",
374
+ "model.layers.13.mamba.A_log",
375
+ "model.layers.13.mamba.D",
376
+ "model.layers.13.mamba.dt_bias",
377
+ "model.layers.14.mamba.A_log",
378
+ "model.layers.14.mamba.D",
379
+ "model.layers.14.mamba.dt_bias",
380
+ "model.layers.15.mamba.A_log",
381
+ "model.layers.15.mamba.D",
382
+ "model.layers.15.mamba.dt_bias",
383
+ "model.layers.16.mamba.A_log",
384
+ "model.layers.16.mamba.D",
385
+ "model.layers.16.mamba.dt_bias",
386
+ "model.layers.17.mamba_decoder.mamba.A_log",
387
+ "model.layers.17.mamba_decoder.mamba.D",
388
+ "model.layers.17.mamba_decoder.mamba.dt_bias",
389
+ "model.layers.18.mamba.A_log",
390
+ "model.layers.18.mamba.D",
391
+ "model.layers.18.mamba.dt_bias",
392
+ "model.layers.19.mamba.A_log",
393
+ "model.layers.19.mamba.D",
394
+ "model.layers.19.mamba.dt_bias",
395
+ "model.layers.2.mamba.A_log",
396
+ "model.layers.2.mamba.D",
397
+ "model.layers.2.mamba.dt_bias",
398
+ "model.layers.20.mamba.A_log",
399
+ "model.layers.20.mamba.D",
400
+ "model.layers.20.mamba.dt_bias",
401
+ "model.layers.21.mamba.A_log",
402
+ "model.layers.21.mamba.D",
403
+ "model.layers.21.mamba.dt_bias",
404
+ "model.layers.22.mamba.A_log",
405
+ "model.layers.22.mamba.D",
406
+ "model.layers.22.mamba.dt_bias",
407
+ "model.layers.23.mamba_decoder.mamba.A_log",
408
+ "model.layers.23.mamba_decoder.mamba.D",
409
+ "model.layers.23.mamba_decoder.mamba.dt_bias",
410
+ "model.layers.24.mamba.A_log",
411
+ "model.layers.24.mamba.D",
412
+ "model.layers.24.mamba.dt_bias",
413
+ "model.layers.25.mamba.A_log",
414
+ "model.layers.25.mamba.D",
415
+ "model.layers.25.mamba.dt_bias",
416
+ "model.layers.26.mamba.A_log",
417
+ "model.layers.26.mamba.D",
418
+ "model.layers.26.mamba.dt_bias",
419
+ "model.layers.27.mamba.A_log",
420
+ "model.layers.27.mamba.D",
421
+ "model.layers.27.mamba.dt_bias",
422
+ "model.layers.28.mamba.A_log",
423
+ "model.layers.28.mamba.D",
424
+ "model.layers.28.mamba.dt_bias",
425
+ "model.layers.29.mamba_decoder.mamba.A_log",
426
+ "model.layers.29.mamba_decoder.mamba.D",
427
+ "model.layers.29.mamba_decoder.mamba.dt_bias",
428
+ "model.layers.3.mamba.A_log",
429
+ "model.layers.3.mamba.D",
430
+ "model.layers.3.mamba.dt_bias",
431
+ "model.layers.30.mamba.A_log",
432
+ "model.layers.30.mamba.D",
433
+ "model.layers.30.mamba.dt_bias",
434
+ "model.layers.31.mamba.A_log",
435
+ "model.layers.31.mamba.D",
436
+ "model.layers.31.mamba.dt_bias",
437
+ "model.layers.32.mamba.A_log",
438
+ "model.layers.32.mamba.D",
439
+ "model.layers.32.mamba.dt_bias",
440
+ "model.layers.33.mamba.A_log",
441
+ "model.layers.33.mamba.D",
442
+ "model.layers.33.mamba.dt_bias",
443
+ "model.layers.34.mamba.A_log",
444
+ "model.layers.34.mamba.D",
445
+ "model.layers.34.mamba.dt_bias",
446
+ "model.layers.35.mamba_decoder.mamba.A_log",
447
+ "model.layers.35.mamba_decoder.mamba.D",
448
+ "model.layers.35.mamba_decoder.mamba.dt_bias",
449
+ "model.layers.36.mamba.A_log",
450
+ "model.layers.36.mamba.D",
451
+ "model.layers.36.mamba.dt_bias",
452
+ "model.layers.37.mamba.A_log",
453
+ "model.layers.37.mamba.D",
454
+ "model.layers.37.mamba.dt_bias",
455
+ "model.layers.38.mamba.A_log",
456
+ "model.layers.38.mamba.D",
457
+ "model.layers.38.mamba.dt_bias",
458
+ "model.layers.39.mamba.A_log",
459
+ "model.layers.39.mamba.D",
460
+ "model.layers.39.mamba.dt_bias",
461
+ "model.layers.4.mamba.A_log",
462
+ "model.layers.4.mamba.D",
463
+ "model.layers.4.mamba.dt_bias",
464
+ "model.layers.40.mamba.A_log",
465
+ "model.layers.40.mamba.D",
466
+ "model.layers.40.mamba.dt_bias",
467
+ "model.layers.41.mamba_decoder.mamba.A_log",
468
+ "model.layers.41.mamba_decoder.mamba.D",
469
+ "model.layers.41.mamba_decoder.mamba.dt_bias",
470
+ "model.layers.42.mamba.A_log",
471
+ "model.layers.42.mamba.D",
472
+ "model.layers.42.mamba.dt_bias",
473
+ "model.layers.43.mamba.A_log",
474
+ "model.layers.43.mamba.D",
475
+ "model.layers.43.mamba.dt_bias",
476
+ "model.layers.44.mamba.A_log",
477
+ "model.layers.44.mamba.D",
478
+ "model.layers.44.mamba.dt_bias",
479
+ "model.layers.45.mamba.A_log",
480
+ "model.layers.45.mamba.D",
481
+ "model.layers.45.mamba.dt_bias",
482
+ "model.layers.46.mamba.A_log",
483
+ "model.layers.46.mamba.D",
484
+ "model.layers.46.mamba.dt_bias",
485
+ "model.layers.47.mamba_decoder.mamba.A_log",
486
+ "model.layers.47.mamba_decoder.mamba.D",
487
+ "model.layers.47.mamba_decoder.mamba.dt_bias",
488
+ "model.layers.48.mamba.A_log",
489
+ "model.layers.48.mamba.D",
490
+ "model.layers.48.mamba.dt_bias",
491
+ "model.layers.49.mamba.A_log",
492
+ "model.layers.49.mamba.D",
493
+ "model.layers.49.mamba.dt_bias",
494
+ "model.layers.5.mamba.A_log",
495
+ "model.layers.5.mamba.D",
496
+ "model.layers.5.mamba.dt_bias",
497
+ "model.layers.50.mamba.A_log",
498
+ "model.layers.50.mamba.D",
499
+ "model.layers.50.mamba.dt_bias",
500
+ "model.layers.51.mamba.A_log",
501
+ "model.layers.51.mamba.D",
502
+ "model.layers.51.mamba.dt_bias",
503
+ "model.layers.52.mamba.A_log",
504
+ "model.layers.52.mamba.D",
505
+ "model.layers.52.mamba.dt_bias",
506
+ "model.layers.53.mamba_decoder.mamba.A_log",
507
+ "model.layers.53.mamba_decoder.mamba.D",
508
+ "model.layers.53.mamba_decoder.mamba.dt_bias",
509
+ "model.layers.54.mamba.A_log",
510
+ "model.layers.54.mamba.D",
511
+ "model.layers.54.mamba.dt_bias",
512
+ "model.layers.55.mamba.A_log",
513
+ "model.layers.55.mamba.D",
514
+ "model.layers.55.mamba.dt_bias",
515
+ "model.layers.56.mamba.A_log",
516
+ "model.layers.56.mamba.D",
517
+ "model.layers.56.mamba.dt_bias",
518
+ "model.layers.57.mamba.A_log",
519
+ "model.layers.57.mamba.D",
520
+ "model.layers.57.mamba.dt_bias",
521
+ "model.layers.58.mamba.A_log",
522
+ "model.layers.58.mamba.D",
523
+ "model.layers.58.mamba.dt_bias",
524
+ "model.layers.59.mamba_decoder.mamba.A_log",
525
+ "model.layers.59.mamba_decoder.mamba.D",
526
+ "model.layers.59.mamba_decoder.mamba.dt_bias",
527
+ "model.layers.6.mamba_decoder.mamba.A_log",
528
+ "model.layers.6.mamba_decoder.mamba.D",
529
+ "model.layers.6.mamba_decoder.mamba.dt_bias",
530
+ "model.layers.60.mamba.A_log",
531
+ "model.layers.60.mamba.D",
532
+ "model.layers.60.mamba.dt_bias",
533
+ "model.layers.61.mamba.A_log",
534
+ "model.layers.61.mamba.D",
535
+ "model.layers.61.mamba.dt_bias",
536
+ "model.layers.62.mamba.A_log",
537
+ "model.layers.62.mamba.D",
538
+ "model.layers.62.mamba.dt_bias",
539
+ "model.layers.63.mamba.A_log",
540
+ "model.layers.63.mamba.D",
541
+ "model.layers.63.mamba.dt_bias",
542
+ "model.layers.64.mamba.A_log",
543
+ "model.layers.64.mamba.D",
544
+ "model.layers.64.mamba.dt_bias",
545
+ "model.layers.65.mamba_decoder.mamba.A_log",
546
+ "model.layers.65.mamba_decoder.mamba.D",
547
+ "model.layers.65.mamba_decoder.mamba.dt_bias",
548
+ "model.layers.66.mamba.A_log",
549
+ "model.layers.66.mamba.D",
550
+ "model.layers.66.mamba.dt_bias",
551
+ "model.layers.67.mamba.A_log",
552
+ "model.layers.67.mamba.D",
553
+ "model.layers.67.mamba.dt_bias",
554
+ "model.layers.68.mamba.A_log",
555
+ "model.layers.68.mamba.D",
556
+ "model.layers.68.mamba.dt_bias",
557
+ "model.layers.69.mamba.A_log",
558
+ "model.layers.69.mamba.D",
559
+ "model.layers.69.mamba.dt_bias",
560
+ "model.layers.7.mamba.A_log",
561
+ "model.layers.7.mamba.D",
562
+ "model.layers.7.mamba.dt_bias",
563
+ "model.layers.70.mamba.A_log",
564
+ "model.layers.70.mamba.D",
565
+ "model.layers.70.mamba.dt_bias",
566
+ "model.layers.71.mamba_decoder.mamba.A_log",
567
+ "model.layers.71.mamba_decoder.mamba.D",
568
+ "model.layers.71.mamba_decoder.mamba.dt_bias",
569
+ "model.layers.72.mamba.A_log",
570
+ "model.layers.72.mamba.D",
571
+ "model.layers.72.mamba.dt_bias",
572
+ "model.layers.73.mamba.A_log",
573
+ "model.layers.73.mamba.D",
574
+ "model.layers.73.mamba.dt_bias",
575
+ "model.layers.74.mamba.A_log",
576
+ "model.layers.74.mamba.D",
577
+ "model.layers.74.mamba.dt_bias",
578
+ "model.layers.75.mamba.A_log",
579
+ "model.layers.75.mamba.D",
580
+ "model.layers.75.mamba.dt_bias",
581
+ "model.layers.76.mamba.A_log",
582
+ "model.layers.76.mamba.D",
583
+ "model.layers.76.mamba.dt_bias",
584
+ "model.layers.77.mamba_decoder.mamba.A_log",
585
+ "model.layers.77.mamba_decoder.mamba.D",
586
+ "model.layers.77.mamba_decoder.mamba.dt_bias",
587
+ "model.layers.78.mamba.A_log",
588
+ "model.layers.78.mamba.D",
589
+ "model.layers.78.mamba.dt_bias",
590
+ "model.layers.79.mamba.A_log",
591
+ "model.layers.79.mamba.D",
592
+ "model.layers.79.mamba.dt_bias",
593
+ "model.layers.8.mamba.A_log",
594
+ "model.layers.8.mamba.D",
595
+ "model.layers.8.mamba.dt_bias",
596
+ "model.layers.80.mamba.A_log",
597
+ "model.layers.80.mamba.D",
598
+ "model.layers.80.mamba.dt_bias",
599
+ "model.layers.9.mamba.A_log",
600
+ "model.layers.9.mamba.D",
601
+ "model.layers.9.mamba.dt_bias",
602
+ "model.mamba_layers.0.mamba.A_log",
603
+ "model.mamba_layers.0.mamba.D",
604
+ "model.mamba_layers.0.mamba.dt_bias",
605
+ "model.mamba_layers.1.mamba.A_log",
606
+ "model.mamba_layers.1.mamba.D",
607
+ "model.mamba_layers.1.mamba.dt_bias",
608
+ "model.mamba_layers.10.mamba.A_log",
609
+ "model.mamba_layers.10.mamba.D",
610
+ "model.mamba_layers.10.mamba.dt_bias",
611
+ "model.mamba_layers.11.mamba.A_log",
612
+ "model.mamba_layers.11.mamba.D",
613
+ "model.mamba_layers.11.mamba.dt_bias",
614
+ "model.mamba_layers.12.mamba.A_log",
615
+ "model.mamba_layers.12.mamba.D",
616
+ "model.mamba_layers.12.mamba.dt_bias",
617
+ "model.mamba_layers.13.mamba.A_log",
618
+ "model.mamba_layers.13.mamba.D",
619
+ "model.mamba_layers.13.mamba.dt_bias",
620
+ "model.mamba_layers.14.mamba.A_log",
621
+ "model.mamba_layers.14.mamba.D",
622
+ "model.mamba_layers.14.mamba.dt_bias",
623
+ "model.mamba_layers.15.mamba.A_log",
624
+ "model.mamba_layers.15.mamba.D",
625
+ "model.mamba_layers.15.mamba.dt_bias",
626
+ "model.mamba_layers.16.mamba.A_log",
627
+ "model.mamba_layers.16.mamba.D",
628
+ "model.mamba_layers.16.mamba.dt_bias",
629
+ "model.mamba_layers.17.mamba.A_log",
630
+ "model.mamba_layers.17.mamba.D",
631
+ "model.mamba_layers.17.mamba.dt_bias",
632
+ "model.mamba_layers.18.mamba.A_log",
633
+ "model.mamba_layers.18.mamba.D",
634
+ "model.mamba_layers.18.mamba.dt_bias",
635
+ "model.mamba_layers.19.mamba.A_log",
636
+ "model.mamba_layers.19.mamba.D",
637
+ "model.mamba_layers.19.mamba.dt_bias",
638
+ "model.mamba_layers.2.mamba.A_log",
639
+ "model.mamba_layers.2.mamba.D",
640
+ "model.mamba_layers.2.mamba.dt_bias",
641
+ "model.mamba_layers.20.mamba.A_log",
642
+ "model.mamba_layers.20.mamba.D",
643
+ "model.mamba_layers.20.mamba.dt_bias",
644
+ "model.mamba_layers.21.mamba.A_log",
645
+ "model.mamba_layers.21.mamba.D",
646
+ "model.mamba_layers.21.mamba.dt_bias",
647
+ "model.mamba_layers.22.mamba.A_log",
648
+ "model.mamba_layers.22.mamba.D",
649
+ "model.mamba_layers.22.mamba.dt_bias",
650
+ "model.mamba_layers.23.mamba.A_log",
651
+ "model.mamba_layers.23.mamba.D",
652
+ "model.mamba_layers.23.mamba.dt_bias",
653
+ "model.mamba_layers.24.mamba.A_log",
654
+ "model.mamba_layers.24.mamba.D",
655
+ "model.mamba_layers.24.mamba.dt_bias",
656
+ "model.mamba_layers.25.mamba.A_log",
657
+ "model.mamba_layers.25.mamba.D",
658
+ "model.mamba_layers.25.mamba.dt_bias",
659
+ "model.mamba_layers.26.mamba.A_log",
660
+ "model.mamba_layers.26.mamba.D",
661
+ "model.mamba_layers.26.mamba.dt_bias",
662
+ "model.mamba_layers.27.mamba.A_log",
663
+ "model.mamba_layers.27.mamba.D",
664
+ "model.mamba_layers.27.mamba.dt_bias",
665
+ "model.mamba_layers.28.mamba.A_log",
666
+ "model.mamba_layers.28.mamba.D",
667
+ "model.mamba_layers.28.mamba.dt_bias",
668
+ "model.mamba_layers.29.mamba.A_log",
669
+ "model.mamba_layers.29.mamba.D",
670
+ "model.mamba_layers.29.mamba.dt_bias",
671
+ "model.mamba_layers.3.mamba.A_log",
672
+ "model.mamba_layers.3.mamba.D",
673
+ "model.mamba_layers.3.mamba.dt_bias",
674
+ "model.mamba_layers.30.mamba.A_log",
675
+ "model.mamba_layers.30.mamba.D",
676
+ "model.mamba_layers.30.mamba.dt_bias",
677
+ "model.mamba_layers.31.mamba.A_log",
678
+ "model.mamba_layers.31.mamba.D",
679
+ "model.mamba_layers.31.mamba.dt_bias",
680
+ "model.mamba_layers.32.mamba.A_log",
681
+ "model.mamba_layers.32.mamba.D",
682
+ "model.mamba_layers.32.mamba.dt_bias",
683
+ "model.mamba_layers.33.mamba.A_log",
684
+ "model.mamba_layers.33.mamba.D",
685
+ "model.mamba_layers.33.mamba.dt_bias",
686
+ "model.mamba_layers.34.mamba.A_log",
687
+ "model.mamba_layers.34.mamba.D",
688
+ "model.mamba_layers.34.mamba.dt_bias",
689
+ "model.mamba_layers.35.mamba.A_log",
690
+ "model.mamba_layers.35.mamba.D",
691
+ "model.mamba_layers.35.mamba.dt_bias",
692
+ "model.mamba_layers.36.mamba.A_log",
693
+ "model.mamba_layers.36.mamba.D",
694
+ "model.mamba_layers.36.mamba.dt_bias",
695
+ "model.mamba_layers.37.mamba.A_log",
696
+ "model.mamba_layers.37.mamba.D",
697
+ "model.mamba_layers.37.mamba.dt_bias",
698
+ "model.mamba_layers.38.mamba.A_log",
699
+ "model.mamba_layers.38.mamba.D",
700
+ "model.mamba_layers.38.mamba.dt_bias",
701
+ "model.mamba_layers.39.mamba.A_log",
702
+ "model.mamba_layers.39.mamba.D",
703
+ "model.mamba_layers.39.mamba.dt_bias",
704
+ "model.mamba_layers.4.mamba.A_log",
705
+ "model.mamba_layers.4.mamba.D",
706
+ "model.mamba_layers.4.mamba.dt_bias",
707
+ "model.mamba_layers.40.mamba.A_log",
708
+ "model.mamba_layers.40.mamba.D",
709
+ "model.mamba_layers.40.mamba.dt_bias",
710
+ "model.mamba_layers.41.mamba.A_log",
711
+ "model.mamba_layers.41.mamba.D",
712
+ "model.mamba_layers.41.mamba.dt_bias",
713
+ "model.mamba_layers.42.mamba.A_log",
714
+ "model.mamba_layers.42.mamba.D",
715
+ "model.mamba_layers.42.mamba.dt_bias",
716
+ "model.mamba_layers.43.mamba.A_log",
717
+ "model.mamba_layers.43.mamba.D",
718
+ "model.mamba_layers.43.mamba.dt_bias",
719
+ "model.mamba_layers.44.mamba.A_log",
720
+ "model.mamba_layers.44.mamba.D",
721
+ "model.mamba_layers.44.mamba.dt_bias",
722
+ "model.mamba_layers.45.mamba.A_log",
723
+ "model.mamba_layers.45.mamba.D",
724
+ "model.mamba_layers.45.mamba.dt_bias",
725
+ "model.mamba_layers.46.mamba.A_log",
726
+ "model.mamba_layers.46.mamba.D",
727
+ "model.mamba_layers.46.mamba.dt_bias",
728
+ "model.mamba_layers.47.mamba.A_log",
729
+ "model.mamba_layers.47.mamba.D",
730
+ "model.mamba_layers.47.mamba.dt_bias",
731
+ "model.mamba_layers.48.mamba.A_log",
732
+ "model.mamba_layers.48.mamba.D",
733
+ "model.mamba_layers.48.mamba.dt_bias",
734
+ "model.mamba_layers.49.mamba.A_log",
735
+ "model.mamba_layers.49.mamba.D",
736
+ "model.mamba_layers.49.mamba.dt_bias",
737
+ "model.mamba_layers.5.mamba.A_log",
738
+ "model.mamba_layers.5.mamba.D",
739
+ "model.mamba_layers.5.mamba.dt_bias",
740
+ "model.mamba_layers.50.mamba.A_log",
741
+ "model.mamba_layers.50.mamba.D",
742
+ "model.mamba_layers.50.mamba.dt_bias",
743
+ "model.mamba_layers.51.mamba.A_log",
744
+ "model.mamba_layers.51.mamba.D",
745
+ "model.mamba_layers.51.mamba.dt_bias",
746
+ "model.mamba_layers.52.mamba.A_log",
747
+ "model.mamba_layers.52.mamba.D",
748
+ "model.mamba_layers.52.mamba.dt_bias",
749
+ "model.mamba_layers.53.mamba.A_log",
750
+ "model.mamba_layers.53.mamba.D",
751
+ "model.mamba_layers.53.mamba.dt_bias",
752
+ "model.mamba_layers.54.mamba.A_log",
753
+ "model.mamba_layers.54.mamba.D",
754
+ "model.mamba_layers.54.mamba.dt_bias",
755
+ "model.mamba_layers.55.mamba.A_log",
756
+ "model.mamba_layers.55.mamba.D",
757
+ "model.mamba_layers.55.mamba.dt_bias",
758
+ "model.mamba_layers.56.mamba.A_log",
759
+ "model.mamba_layers.56.mamba.D",
760
+ "model.mamba_layers.56.mamba.dt_bias",
761
+ "model.mamba_layers.57.mamba.A_log",
762
+ "model.mamba_layers.57.mamba.D",
763
+ "model.mamba_layers.57.mamba.dt_bias",
764
+ "model.mamba_layers.58.mamba.A_log",
765
+ "model.mamba_layers.58.mamba.D",
766
+ "model.mamba_layers.58.mamba.dt_bias",
767
+ "model.mamba_layers.59.mamba.A_log",
768
+ "model.mamba_layers.59.mamba.D",
769
+ "model.mamba_layers.59.mamba.dt_bias",
770
+ "model.mamba_layers.6.mamba.A_log",
771
+ "model.mamba_layers.6.mamba.D",
772
+ "model.mamba_layers.6.mamba.dt_bias",
773
+ "model.mamba_layers.60.mamba.A_log",
774
+ "model.mamba_layers.60.mamba.D",
775
+ "model.mamba_layers.60.mamba.dt_bias",
776
+ "model.mamba_layers.61.mamba.A_log",
777
+ "model.mamba_layers.61.mamba.D",
778
+ "model.mamba_layers.61.mamba.dt_bias",
779
+ "model.mamba_layers.62.mamba.A_log",
780
+ "model.mamba_layers.62.mamba.D",
781
+ "model.mamba_layers.62.mamba.dt_bias",
782
+ "model.mamba_layers.63.mamba.A_log",
783
+ "model.mamba_layers.63.mamba.D",
784
+ "model.mamba_layers.63.mamba.dt_bias",
785
+ "model.mamba_layers.64.mamba.A_log",
786
+ "model.mamba_layers.64.mamba.D",
787
+ "model.mamba_layers.64.mamba.dt_bias",
788
+ "model.mamba_layers.65.mamba.A_log",
789
+ "model.mamba_layers.65.mamba.D",
790
+ "model.mamba_layers.65.mamba.dt_bias",
791
+ "model.mamba_layers.66.mamba.A_log",
792
+ "model.mamba_layers.66.mamba.D",
793
+ "model.mamba_layers.66.mamba.dt_bias",
794
+ "model.mamba_layers.67.mamba.A_log",
795
+ "model.mamba_layers.67.mamba.D",
796
+ "model.mamba_layers.67.mamba.dt_bias",
797
+ "model.mamba_layers.68.mamba.A_log",
798
+ "model.mamba_layers.68.mamba.D",
799
+ "model.mamba_layers.68.mamba.dt_bias",
800
+ "model.mamba_layers.69.mamba.A_log",
801
+ "model.mamba_layers.69.mamba.D",
802
+ "model.mamba_layers.69.mamba.dt_bias",
803
+ "model.mamba_layers.7.mamba.A_log",
804
+ "model.mamba_layers.7.mamba.D",
805
+ "model.mamba_layers.7.mamba.dt_bias",
806
+ "model.mamba_layers.70.mamba.A_log",
807
+ "model.mamba_layers.70.mamba.D",
808
+ "model.mamba_layers.70.mamba.dt_bias",
809
+ "model.mamba_layers.71.mamba.A_log",
810
+ "model.mamba_layers.71.mamba.D",
811
+ "model.mamba_layers.71.mamba.dt_bias",
812
+ "model.mamba_layers.72.mamba.A_log",
813
+ "model.mamba_layers.72.mamba.D",
814
+ "model.mamba_layers.72.mamba.dt_bias",
815
+ "model.mamba_layers.73.mamba.A_log",
816
+ "model.mamba_layers.73.mamba.D",
817
+ "model.mamba_layers.73.mamba.dt_bias",
818
+ "model.mamba_layers.74.mamba.A_log",
819
+ "model.mamba_layers.74.mamba.D",
820
+ "model.mamba_layers.74.mamba.dt_bias",
821
+ "model.mamba_layers.75.mamba.A_log",
822
+ "model.mamba_layers.75.mamba.D",
823
+ "model.mamba_layers.75.mamba.dt_bias",
824
+ "model.mamba_layers.76.mamba.A_log",
825
+ "model.mamba_layers.76.mamba.D",
826
+ "model.mamba_layers.76.mamba.dt_bias",
827
+ "model.mamba_layers.77.mamba.A_log",
828
+ "model.mamba_layers.77.mamba.D",
829
+ "model.mamba_layers.77.mamba.dt_bias",
830
+ "model.mamba_layers.78.mamba.A_log",
831
+ "model.mamba_layers.78.mamba.D",
832
+ "model.mamba_layers.78.mamba.dt_bias",
833
+ "model.mamba_layers.79.mamba.A_log",
834
+ "model.mamba_layers.79.mamba.D",
835
+ "model.mamba_layers.79.mamba.dt_bias",
836
+ "model.mamba_layers.8.mamba.A_log",
837
+ "model.mamba_layers.8.mamba.D",
838
+ "model.mamba_layers.8.mamba.dt_bias",
839
+ "model.mamba_layers.80.mamba.A_log",
840
+ "model.mamba_layers.80.mamba.D",
841
+ "model.mamba_layers.80.mamba.dt_bias",
842
+ "model.mamba_layers.9.mamba.A_log",
843
+ "model.mamba_layers.9.mamba.D",
844
+ "model.mamba_layers.9.mamba.dt_bias"
845
+ ],
846
+ "bias": [
847
+ "model.layers.0.mamba.conv1d.bias",
848
+ "model.layers.1.mamba.conv1d.bias",
849
+ "model.layers.10.mamba.conv1d.bias",
850
+ "model.layers.11.mamba_decoder.mamba.conv1d.bias",
851
+ "model.layers.12.mamba.conv1d.bias",
852
+ "model.layers.13.mamba.conv1d.bias",
853
+ "model.layers.14.mamba.conv1d.bias",
854
+ "model.layers.15.mamba.conv1d.bias",
855
+ "model.layers.16.mamba.conv1d.bias",
856
+ "model.layers.17.mamba_decoder.mamba.conv1d.bias",
857
+ "model.layers.18.mamba.conv1d.bias",
858
+ "model.layers.19.mamba.conv1d.bias",
859
+ "model.layers.2.mamba.conv1d.bias",
860
+ "model.layers.20.mamba.conv1d.bias",
861
+ "model.layers.21.mamba.conv1d.bias",
862
+ "model.layers.22.mamba.conv1d.bias",
863
+ "model.layers.23.mamba_decoder.mamba.conv1d.bias",
864
+ "model.layers.24.mamba.conv1d.bias",
865
+ "model.layers.25.mamba.conv1d.bias",
866
+ "model.layers.26.mamba.conv1d.bias",
867
+ "model.layers.27.mamba.conv1d.bias",
868
+ "model.layers.28.mamba.conv1d.bias",
869
+ "model.layers.29.mamba_decoder.mamba.conv1d.bias",
870
+ "model.layers.3.mamba.conv1d.bias",
871
+ "model.layers.30.mamba.conv1d.bias",
872
+ "model.layers.31.mamba.conv1d.bias",
873
+ "model.layers.32.mamba.conv1d.bias",
874
+ "model.layers.33.mamba.conv1d.bias",
875
+ "model.layers.34.mamba.conv1d.bias",
876
+ "model.layers.35.mamba_decoder.mamba.conv1d.bias",
877
+ "model.layers.36.mamba.conv1d.bias",
878
+ "model.layers.37.mamba.conv1d.bias",
879
+ "model.layers.38.mamba.conv1d.bias",
880
+ "model.layers.39.mamba.conv1d.bias",
881
+ "model.layers.4.mamba.conv1d.bias",
882
+ "model.layers.40.mamba.conv1d.bias",
883
+ "model.layers.41.mamba_decoder.mamba.conv1d.bias",
884
+ "model.layers.42.mamba.conv1d.bias",
885
+ "model.layers.43.mamba.conv1d.bias",
886
+ "model.layers.44.mamba.conv1d.bias",
887
+ "model.layers.45.mamba.conv1d.bias",
888
+ "model.layers.46.mamba.conv1d.bias",
889
+ "model.layers.47.mamba_decoder.mamba.conv1d.bias",
890
+ "model.layers.48.mamba.conv1d.bias",
891
+ "model.layers.49.mamba.conv1d.bias",
892
+ "model.layers.5.mamba.conv1d.bias",
893
+ "model.layers.50.mamba.conv1d.bias",
894
+ "model.layers.51.mamba.conv1d.bias",
895
+ "model.layers.52.mamba.conv1d.bias",
896
+ "model.layers.53.mamba_decoder.mamba.conv1d.bias",
897
+ "model.layers.54.mamba.conv1d.bias",
898
+ "model.layers.55.mamba.conv1d.bias",
899
+ "model.layers.56.mamba.conv1d.bias",
900
+ "model.layers.57.mamba.conv1d.bias",
901
+ "model.layers.58.mamba.conv1d.bias",
902
+ "model.layers.59.mamba_decoder.mamba.conv1d.bias",
903
+ "model.layers.6.mamba_decoder.mamba.conv1d.bias",
904
+ "model.layers.60.mamba.conv1d.bias",
905
+ "model.layers.61.mamba.conv1d.bias",
906
+ "model.layers.62.mamba.conv1d.bias",
907
+ "model.layers.63.mamba.conv1d.bias",
908
+ "model.layers.64.mamba.conv1d.bias",
909
+ "model.layers.65.mamba_decoder.mamba.conv1d.bias",
910
+ "model.layers.66.mamba.conv1d.bias",
911
+ "model.layers.67.mamba.conv1d.bias",
912
+ "model.layers.68.mamba.conv1d.bias",
913
+ "model.layers.69.mamba.conv1d.bias",
914
+ "model.layers.7.mamba.conv1d.bias",
915
+ "model.layers.70.mamba.conv1d.bias",
916
+ "model.layers.71.mamba_decoder.mamba.conv1d.bias",
917
+ "model.layers.72.mamba.conv1d.bias",
918
+ "model.layers.73.mamba.conv1d.bias",
919
+ "model.layers.74.mamba.conv1d.bias",
920
+ "model.layers.75.mamba.conv1d.bias",
921
+ "model.layers.76.mamba.conv1d.bias",
922
+ "model.layers.77.mamba_decoder.mamba.conv1d.bias",
923
+ "model.layers.78.mamba.conv1d.bias",
924
+ "model.layers.79.mamba.conv1d.bias",
925
+ "model.layers.8.mamba.conv1d.bias",
926
+ "model.layers.80.mamba.conv1d.bias",
927
+ "model.layers.9.mamba.conv1d.bias",
928
+ "model.mamba_layers.0.mamba.conv1d.bias",
929
+ "model.mamba_layers.1.mamba.conv1d.bias",
930
+ "model.mamba_layers.10.mamba.conv1d.bias",
931
+ "model.mamba_layers.11.mamba.conv1d.bias",
932
+ "model.mamba_layers.12.mamba.conv1d.bias",
933
+ "model.mamba_layers.13.mamba.conv1d.bias",
934
+ "model.mamba_layers.14.mamba.conv1d.bias",
935
+ "model.mamba_layers.15.mamba.conv1d.bias",
936
+ "model.mamba_layers.16.mamba.conv1d.bias",
937
+ "model.mamba_layers.17.mamba.conv1d.bias",
938
+ "model.mamba_layers.18.mamba.conv1d.bias",
939
+ "model.mamba_layers.19.mamba.conv1d.bias",
940
+ "model.mamba_layers.2.mamba.conv1d.bias",
941
+ "model.mamba_layers.20.mamba.conv1d.bias",
942
+ "model.mamba_layers.21.mamba.conv1d.bias",
943
+ "model.mamba_layers.22.mamba.conv1d.bias",
944
+ "model.mamba_layers.23.mamba.conv1d.bias",
945
+ "model.mamba_layers.24.mamba.conv1d.bias",
946
+ "model.mamba_layers.25.mamba.conv1d.bias",
947
+ "model.mamba_layers.26.mamba.conv1d.bias",
948
+ "model.mamba_layers.27.mamba.conv1d.bias",
949
+ "model.mamba_layers.28.mamba.conv1d.bias",
950
+ "model.mamba_layers.29.mamba.conv1d.bias",
951
+ "model.mamba_layers.3.mamba.conv1d.bias",
952
+ "model.mamba_layers.30.mamba.conv1d.bias",
953
+ "model.mamba_layers.31.mamba.conv1d.bias",
954
+ "model.mamba_layers.32.mamba.conv1d.bias",
955
+ "model.mamba_layers.33.mamba.conv1d.bias",
956
+ "model.mamba_layers.34.mamba.conv1d.bias",
957
+ "model.mamba_layers.35.mamba.conv1d.bias",
958
+ "model.mamba_layers.36.mamba.conv1d.bias",
959
+ "model.mamba_layers.37.mamba.conv1d.bias",
960
+ "model.mamba_layers.38.mamba.conv1d.bias",
961
+ "model.mamba_layers.39.mamba.conv1d.bias",
962
+ "model.mamba_layers.4.mamba.conv1d.bias",
963
+ "model.mamba_layers.40.mamba.conv1d.bias",
964
+ "model.mamba_layers.41.mamba.conv1d.bias",
965
+ "model.mamba_layers.42.mamba.conv1d.bias",
966
+ "model.mamba_layers.43.mamba.conv1d.bias",
967
+ "model.mamba_layers.44.mamba.conv1d.bias",
968
+ "model.mamba_layers.45.mamba.conv1d.bias",
969
+ "model.mamba_layers.46.mamba.conv1d.bias",
970
+ "model.mamba_layers.47.mamba.conv1d.bias",
971
+ "model.mamba_layers.48.mamba.conv1d.bias",
972
+ "model.mamba_layers.49.mamba.conv1d.bias",
973
+ "model.mamba_layers.5.mamba.conv1d.bias",
974
+ "model.mamba_layers.50.mamba.conv1d.bias",
975
+ "model.mamba_layers.51.mamba.conv1d.bias",
976
+ "model.mamba_layers.52.mamba.conv1d.bias",
977
+ "model.mamba_layers.53.mamba.conv1d.bias",
978
+ "model.mamba_layers.54.mamba.conv1d.bias",
979
+ "model.mamba_layers.55.mamba.conv1d.bias",
980
+ "model.mamba_layers.56.mamba.conv1d.bias",
981
+ "model.mamba_layers.57.mamba.conv1d.bias",
982
+ "model.mamba_layers.58.mamba.conv1d.bias",
983
+ "model.mamba_layers.59.mamba.conv1d.bias",
984
+ "model.mamba_layers.6.mamba.conv1d.bias",
985
+ "model.mamba_layers.60.mamba.conv1d.bias",
986
+ "model.mamba_layers.61.mamba.conv1d.bias",
987
+ "model.mamba_layers.62.mamba.conv1d.bias",
988
+ "model.mamba_layers.63.mamba.conv1d.bias",
989
+ "model.mamba_layers.64.mamba.conv1d.bias",
990
+ "model.mamba_layers.65.mamba.conv1d.bias",
991
+ "model.mamba_layers.66.mamba.conv1d.bias",
992
+ "model.mamba_layers.67.mamba.conv1d.bias",
993
+ "model.mamba_layers.68.mamba.conv1d.bias",
994
+ "model.mamba_layers.69.mamba.conv1d.bias",
995
+ "model.mamba_layers.7.mamba.conv1d.bias",
996
+ "model.mamba_layers.70.mamba.conv1d.bias",
997
+ "model.mamba_layers.71.mamba.conv1d.bias",
998
+ "model.mamba_layers.72.mamba.conv1d.bias",
999
+ "model.mamba_layers.73.mamba.conv1d.bias",
1000
+ "model.mamba_layers.74.mamba.conv1d.bias",
1001
+ "model.mamba_layers.75.mamba.conv1d.bias",
1002
+ "model.mamba_layers.76.mamba.conv1d.bias",
1003
+ "model.mamba_layers.77.mamba.conv1d.bias",
1004
+ "model.mamba_layers.78.mamba.conv1d.bias",
1005
+ "model.mamba_layers.79.mamba.conv1d.bias",
1006
+ "model.mamba_layers.8.mamba.conv1d.bias",
1007
+ "model.mamba_layers.80.mamba.conv1d.bias",
1008
+ "model.mamba_layers.9.mamba.conv1d.bias"
1009
+ ]
1010
+ }
1011
+ }