JackCloudman commited on
Commit
019eeda
·
verified ·
1 Parent(s): 39c1153

Delete consolidated.safetensors.index.json

Browse files
Files changed (1) hide show
  1. consolidated.safetensors.index.json +0 -802
consolidated.safetensors.index.json DELETED
@@ -1,802 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 245220139008
4
- },
5
- "weight_map": {
6
- "layers.0.attention.wk.weight": "consolidated-00001-of-00051.safetensors",
7
- "layers.0.attention.wo.weight": "consolidated-00001-of-00051.safetensors",
8
- "layers.0.attention.wq.weight": "consolidated-00001-of-00051.safetensors",
9
- "layers.0.attention.wv.weight": "consolidated-00001-of-00051.safetensors",
10
- "layers.0.attention_norm.weight": "consolidated-00001-of-00051.safetensors",
11
- "layers.0.feed_forward.w1.weight": "consolidated-00001-of-00051.safetensors",
12
- "layers.0.feed_forward.w2.weight": "consolidated-00001-of-00051.safetensors",
13
- "layers.0.feed_forward.w3.weight": "consolidated-00001-of-00051.safetensors",
14
- "layers.0.ffn_norm.weight": "consolidated-00001-of-00051.safetensors",
15
- "layers.1.attention.wk.weight": "consolidated-00001-of-00051.safetensors",
16
- "layers.1.attention.wo.weight": "consolidated-00001-of-00051.safetensors",
17
- "layers.1.attention.wq.weight": "consolidated-00001-of-00051.safetensors",
18
- "layers.1.attention.wv.weight": "consolidated-00001-of-00051.safetensors",
19
- "layers.1.attention_norm.weight": "consolidated-00001-of-00051.safetensors",
20
- "layers.1.feed_forward.w1.weight": "consolidated-00001-of-00051.safetensors",
21
- "layers.1.feed_forward.w2.weight": "consolidated-00001-of-00051.safetensors",
22
- "layers.1.feed_forward.w3.weight": "consolidated-00002-of-00051.safetensors",
23
- "layers.1.ffn_norm.weight": "consolidated-00002-of-00051.safetensors",
24
- "layers.10.attention.wk.weight": "consolidated-00002-of-00051.safetensors",
25
- "layers.10.attention.wo.weight": "consolidated-00002-of-00051.safetensors",
26
- "layers.10.attention.wq.weight": "consolidated-00002-of-00051.safetensors",
27
- "layers.10.attention.wv.weight": "consolidated-00002-of-00051.safetensors",
28
- "layers.10.attention_norm.weight": "consolidated-00002-of-00051.safetensors",
29
- "layers.10.feed_forward.w1.weight": "consolidated-00002-of-00051.safetensors",
30
- "layers.10.feed_forward.w2.weight": "consolidated-00002-of-00051.safetensors",
31
- "layers.10.feed_forward.w3.weight": "consolidated-00002-of-00051.safetensors",
32
- "layers.10.ffn_norm.weight": "consolidated-00002-of-00051.safetensors",
33
- "layers.11.attention.wk.weight": "consolidated-00002-of-00051.safetensors",
34
- "layers.11.attention.wo.weight": "consolidated-00002-of-00051.safetensors",
35
- "layers.11.attention.wq.weight": "consolidated-00002-of-00051.safetensors",
36
- "layers.11.attention.wv.weight": "consolidated-00002-of-00051.safetensors",
37
- "layers.11.attention_norm.weight": "consolidated-00002-of-00051.safetensors",
38
- "layers.11.feed_forward.w1.weight": "consolidated-00002-of-00051.safetensors",
39
- "layers.11.feed_forward.w2.weight": "consolidated-00003-of-00051.safetensors",
40
- "layers.11.feed_forward.w3.weight": "consolidated-00003-of-00051.safetensors",
41
- "layers.11.ffn_norm.weight": "consolidated-00003-of-00051.safetensors",
42
- "layers.12.attention.wk.weight": "consolidated-00003-of-00051.safetensors",
43
- "layers.12.attention.wo.weight": "consolidated-00003-of-00051.safetensors",
44
- "layers.12.attention.wq.weight": "consolidated-00003-of-00051.safetensors",
45
- "layers.12.attention.wv.weight": "consolidated-00003-of-00051.safetensors",
46
- "layers.12.attention_norm.weight": "consolidated-00003-of-00051.safetensors",
47
- "layers.12.feed_forward.w1.weight": "consolidated-00003-of-00051.safetensors",
48
- "layers.12.feed_forward.w2.weight": "consolidated-00003-of-00051.safetensors",
49
- "layers.12.feed_forward.w3.weight": "consolidated-00003-of-00051.safetensors",
50
- "layers.12.ffn_norm.weight": "consolidated-00003-of-00051.safetensors",
51
- "layers.13.attention.wk.weight": "consolidated-00003-of-00051.safetensors",
52
- "layers.13.attention.wo.weight": "consolidated-00003-of-00051.safetensors",
53
- "layers.13.attention.wq.weight": "consolidated-00003-of-00051.safetensors",
54
- "layers.13.attention.wv.weight": "consolidated-00003-of-00051.safetensors",
55
- "layers.13.attention_norm.weight": "consolidated-00003-of-00051.safetensors",
56
- "layers.13.feed_forward.w1.weight": "consolidated-00004-of-00051.safetensors",
57
- "layers.13.feed_forward.w2.weight": "consolidated-00004-of-00051.safetensors",
58
- "layers.13.feed_forward.w3.weight": "consolidated-00004-of-00051.safetensors",
59
- "layers.13.ffn_norm.weight": "consolidated-00004-of-00051.safetensors",
60
- "layers.14.attention.wk.weight": "consolidated-00004-of-00051.safetensors",
61
- "layers.14.attention.wo.weight": "consolidated-00004-of-00051.safetensors",
62
- "layers.14.attention.wq.weight": "consolidated-00004-of-00051.safetensors",
63
- "layers.14.attention.wv.weight": "consolidated-00004-of-00051.safetensors",
64
- "layers.14.attention_norm.weight": "consolidated-00004-of-00051.safetensors",
65
- "layers.14.feed_forward.w1.weight": "consolidated-00004-of-00051.safetensors",
66
- "layers.14.feed_forward.w2.weight": "consolidated-00004-of-00051.safetensors",
67
- "layers.14.feed_forward.w3.weight": "consolidated-00004-of-00051.safetensors",
68
- "layers.14.ffn_norm.weight": "consolidated-00004-of-00051.safetensors",
69
- "layers.15.attention.wk.weight": "consolidated-00004-of-00051.safetensors",
70
- "layers.15.attention.wo.weight": "consolidated-00005-of-00051.safetensors",
71
- "layers.15.attention.wq.weight": "consolidated-00005-of-00051.safetensors",
72
- "layers.15.attention.wv.weight": "consolidated-00005-of-00051.safetensors",
73
- "layers.15.attention_norm.weight": "consolidated-00005-of-00051.safetensors",
74
- "layers.15.feed_forward.w1.weight": "consolidated-00005-of-00051.safetensors",
75
- "layers.15.feed_forward.w2.weight": "consolidated-00005-of-00051.safetensors",
76
- "layers.15.feed_forward.w3.weight": "consolidated-00005-of-00051.safetensors",
77
- "layers.15.ffn_norm.weight": "consolidated-00005-of-00051.safetensors",
78
- "layers.16.attention.wk.weight": "consolidated-00005-of-00051.safetensors",
79
- "layers.16.attention.wo.weight": "consolidated-00005-of-00051.safetensors",
80
- "layers.16.attention.wq.weight": "consolidated-00005-of-00051.safetensors",
81
- "layers.16.attention.wv.weight": "consolidated-00005-of-00051.safetensors",
82
- "layers.16.attention_norm.weight": "consolidated-00005-of-00051.safetensors",
83
- "layers.16.feed_forward.w1.weight": "consolidated-00005-of-00051.safetensors",
84
- "layers.16.feed_forward.w2.weight": "consolidated-00005-of-00051.safetensors",
85
- "layers.16.feed_forward.w3.weight": "consolidated-00006-of-00051.safetensors",
86
- "layers.16.ffn_norm.weight": "consolidated-00006-of-00051.safetensors",
87
- "layers.17.attention.wk.weight": "consolidated-00006-of-00051.safetensors",
88
- "layers.17.attention.wo.weight": "consolidated-00006-of-00051.safetensors",
89
- "layers.17.attention.wq.weight": "consolidated-00006-of-00051.safetensors",
90
- "layers.17.attention.wv.weight": "consolidated-00006-of-00051.safetensors",
91
- "layers.17.attention_norm.weight": "consolidated-00006-of-00051.safetensors",
92
- "layers.17.feed_forward.w1.weight": "consolidated-00006-of-00051.safetensors",
93
- "layers.17.feed_forward.w2.weight": "consolidated-00006-of-00051.safetensors",
94
- "layers.17.feed_forward.w3.weight": "consolidated-00006-of-00051.safetensors",
95
- "layers.17.ffn_norm.weight": "consolidated-00006-of-00051.safetensors",
96
- "layers.18.attention.wk.weight": "consolidated-00006-of-00051.safetensors",
97
- "layers.18.attention.wo.weight": "consolidated-00006-of-00051.safetensors",
98
- "layers.18.attention.wq.weight": "consolidated-00006-of-00051.safetensors",
99
- "layers.18.attention.wv.weight": "consolidated-00006-of-00051.safetensors",
100
- "layers.18.attention_norm.weight": "consolidated-00006-of-00051.safetensors",
101
- "layers.18.feed_forward.w1.weight": "consolidated-00006-of-00051.safetensors",
102
- "layers.18.feed_forward.w2.weight": "consolidated-00007-of-00051.safetensors",
103
- "layers.18.feed_forward.w3.weight": "consolidated-00007-of-00051.safetensors",
104
- "layers.18.ffn_norm.weight": "consolidated-00007-of-00051.safetensors",
105
- "layers.19.attention.wk.weight": "consolidated-00007-of-00051.safetensors",
106
- "layers.19.attention.wo.weight": "consolidated-00007-of-00051.safetensors",
107
- "layers.19.attention.wq.weight": "consolidated-00007-of-00051.safetensors",
108
- "layers.19.attention.wv.weight": "consolidated-00007-of-00051.safetensors",
109
- "layers.19.attention_norm.weight": "consolidated-00007-of-00051.safetensors",
110
- "layers.19.feed_forward.w1.weight": "consolidated-00007-of-00051.safetensors",
111
- "layers.19.feed_forward.w2.weight": "consolidated-00007-of-00051.safetensors",
112
- "layers.19.feed_forward.w3.weight": "consolidated-00007-of-00051.safetensors",
113
- "layers.19.ffn_norm.weight": "consolidated-00007-of-00051.safetensors",
114
- "layers.2.attention.wk.weight": "consolidated-00007-of-00051.safetensors",
115
- "layers.2.attention.wo.weight": "consolidated-00007-of-00051.safetensors",
116
- "layers.2.attention.wq.weight": "consolidated-00007-of-00051.safetensors",
117
- "layers.2.attention.wv.weight": "consolidated-00007-of-00051.safetensors",
118
- "layers.2.attention_norm.weight": "consolidated-00007-of-00051.safetensors",
119
- "layers.2.feed_forward.w1.weight": "consolidated-00008-of-00051.safetensors",
120
- "layers.2.feed_forward.w2.weight": "consolidated-00008-of-00051.safetensors",
121
- "layers.2.feed_forward.w3.weight": "consolidated-00008-of-00051.safetensors",
122
- "layers.2.ffn_norm.weight": "consolidated-00008-of-00051.safetensors",
123
- "layers.20.attention.wk.weight": "consolidated-00008-of-00051.safetensors",
124
- "layers.20.attention.wo.weight": "consolidated-00008-of-00051.safetensors",
125
- "layers.20.attention.wq.weight": "consolidated-00008-of-00051.safetensors",
126
- "layers.20.attention.wv.weight": "consolidated-00008-of-00051.safetensors",
127
- "layers.20.attention_norm.weight": "consolidated-00008-of-00051.safetensors",
128
- "layers.20.feed_forward.w1.weight": "consolidated-00008-of-00051.safetensors",
129
- "layers.20.feed_forward.w2.weight": "consolidated-00008-of-00051.safetensors",
130
- "layers.20.feed_forward.w3.weight": "consolidated-00008-of-00051.safetensors",
131
- "layers.20.ffn_norm.weight": "consolidated-00008-of-00051.safetensors",
132
- "layers.21.attention.wk.weight": "consolidated-00008-of-00051.safetensors",
133
- "layers.21.attention.wo.weight": "consolidated-00009-of-00051.safetensors",
134
- "layers.21.attention.wq.weight": "consolidated-00009-of-00051.safetensors",
135
- "layers.21.attention.wv.weight": "consolidated-00009-of-00051.safetensors",
136
- "layers.21.attention_norm.weight": "consolidated-00009-of-00051.safetensors",
137
- "layers.21.feed_forward.w1.weight": "consolidated-00009-of-00051.safetensors",
138
- "layers.21.feed_forward.w2.weight": "consolidated-00009-of-00051.safetensors",
139
- "layers.21.feed_forward.w3.weight": "consolidated-00009-of-00051.safetensors",
140
- "layers.21.ffn_norm.weight": "consolidated-00009-of-00051.safetensors",
141
- "layers.22.attention.wk.weight": "consolidated-00009-of-00051.safetensors",
142
- "layers.22.attention.wo.weight": "consolidated-00009-of-00051.safetensors",
143
- "layers.22.attention.wq.weight": "consolidated-00009-of-00051.safetensors",
144
- "layers.22.attention.wv.weight": "consolidated-00009-of-00051.safetensors",
145
- "layers.22.attention_norm.weight": "consolidated-00009-of-00051.safetensors",
146
- "layers.22.feed_forward.w1.weight": "consolidated-00009-of-00051.safetensors",
147
- "layers.22.feed_forward.w2.weight": "consolidated-00009-of-00051.safetensors",
148
- "layers.22.feed_forward.w3.weight": "consolidated-00010-of-00051.safetensors",
149
- "layers.22.ffn_norm.weight": "consolidated-00010-of-00051.safetensors",
150
- "layers.23.attention.wk.weight": "consolidated-00010-of-00051.safetensors",
151
- "layers.23.attention.wo.weight": "consolidated-00010-of-00051.safetensors",
152
- "layers.23.attention.wq.weight": "consolidated-00010-of-00051.safetensors",
153
- "layers.23.attention.wv.weight": "consolidated-00010-of-00051.safetensors",
154
- "layers.23.attention_norm.weight": "consolidated-00010-of-00051.safetensors",
155
- "layers.23.feed_forward.w1.weight": "consolidated-00010-of-00051.safetensors",
156
- "layers.23.feed_forward.w2.weight": "consolidated-00010-of-00051.safetensors",
157
- "layers.23.feed_forward.w3.weight": "consolidated-00010-of-00051.safetensors",
158
- "layers.23.ffn_norm.weight": "consolidated-00010-of-00051.safetensors",
159
- "layers.24.attention.wk.weight": "consolidated-00010-of-00051.safetensors",
160
- "layers.24.attention.wo.weight": "consolidated-00010-of-00051.safetensors",
161
- "layers.24.attention.wq.weight": "consolidated-00010-of-00051.safetensors",
162
- "layers.24.attention.wv.weight": "consolidated-00010-of-00051.safetensors",
163
- "layers.24.attention_norm.weight": "consolidated-00010-of-00051.safetensors",
164
- "layers.24.feed_forward.w1.weight": "consolidated-00010-of-00051.safetensors",
165
- "layers.24.feed_forward.w2.weight": "consolidated-00011-of-00051.safetensors",
166
- "layers.24.feed_forward.w3.weight": "consolidated-00011-of-00051.safetensors",
167
- "layers.24.ffn_norm.weight": "consolidated-00011-of-00051.safetensors",
168
- "layers.25.attention.wk.weight": "consolidated-00011-of-00051.safetensors",
169
- "layers.25.attention.wo.weight": "consolidated-00011-of-00051.safetensors",
170
- "layers.25.attention.wq.weight": "consolidated-00011-of-00051.safetensors",
171
- "layers.25.attention.wv.weight": "consolidated-00011-of-00051.safetensors",
172
- "layers.25.attention_norm.weight": "consolidated-00011-of-00051.safetensors",
173
- "layers.25.feed_forward.w1.weight": "consolidated-00011-of-00051.safetensors",
174
- "layers.25.feed_forward.w2.weight": "consolidated-00011-of-00051.safetensors",
175
- "layers.25.feed_forward.w3.weight": "consolidated-00011-of-00051.safetensors",
176
- "layers.25.ffn_norm.weight": "consolidated-00011-of-00051.safetensors",
177
- "layers.26.attention.wk.weight": "consolidated-00011-of-00051.safetensors",
178
- "layers.26.attention.wo.weight": "consolidated-00011-of-00051.safetensors",
179
- "layers.26.attention.wq.weight": "consolidated-00011-of-00051.safetensors",
180
- "layers.26.attention.wv.weight": "consolidated-00011-of-00051.safetensors",
181
- "layers.26.attention_norm.weight": "consolidated-00011-of-00051.safetensors",
182
- "layers.26.feed_forward.w1.weight": "consolidated-00012-of-00051.safetensors",
183
- "layers.26.feed_forward.w2.weight": "consolidated-00012-of-00051.safetensors",
184
- "layers.26.feed_forward.w3.weight": "consolidated-00012-of-00051.safetensors",
185
- "layers.26.ffn_norm.weight": "consolidated-00012-of-00051.safetensors",
186
- "layers.27.attention.wk.weight": "consolidated-00012-of-00051.safetensors",
187
- "layers.27.attention.wo.weight": "consolidated-00012-of-00051.safetensors",
188
- "layers.27.attention.wq.weight": "consolidated-00012-of-00051.safetensors",
189
- "layers.27.attention.wv.weight": "consolidated-00012-of-00051.safetensors",
190
- "layers.27.attention_norm.weight": "consolidated-00012-of-00051.safetensors",
191
- "layers.27.feed_forward.w1.weight": "consolidated-00012-of-00051.safetensors",
192
- "layers.27.feed_forward.w2.weight": "consolidated-00012-of-00051.safetensors",
193
- "layers.27.feed_forward.w3.weight": "consolidated-00012-of-00051.safetensors",
194
- "layers.27.ffn_norm.weight": "consolidated-00012-of-00051.safetensors",
195
- "layers.28.attention.wk.weight": "consolidated-00012-of-00051.safetensors",
196
- "layers.28.attention.wo.weight": "consolidated-00013-of-00051.safetensors",
197
- "layers.28.attention.wq.weight": "consolidated-00013-of-00051.safetensors",
198
- "layers.28.attention.wv.weight": "consolidated-00013-of-00051.safetensors",
199
- "layers.28.attention_norm.weight": "consolidated-00013-of-00051.safetensors",
200
- "layers.28.feed_forward.w1.weight": "consolidated-00013-of-00051.safetensors",
201
- "layers.28.feed_forward.w2.weight": "consolidated-00013-of-00051.safetensors",
202
- "layers.28.feed_forward.w3.weight": "consolidated-00013-of-00051.safetensors",
203
- "layers.28.ffn_norm.weight": "consolidated-00013-of-00051.safetensors",
204
- "layers.29.attention.wk.weight": "consolidated-00013-of-00051.safetensors",
205
- "layers.29.attention.wo.weight": "consolidated-00013-of-00051.safetensors",
206
- "layers.29.attention.wq.weight": "consolidated-00013-of-00051.safetensors",
207
- "layers.29.attention.wv.weight": "consolidated-00013-of-00051.safetensors",
208
- "layers.29.attention_norm.weight": "consolidated-00013-of-00051.safetensors",
209
- "layers.29.feed_forward.w1.weight": "consolidated-00013-of-00051.safetensors",
210
- "layers.29.feed_forward.w2.weight": "consolidated-00013-of-00051.safetensors",
211
- "layers.29.feed_forward.w3.weight": "consolidated-00014-of-00051.safetensors",
212
- "layers.29.ffn_norm.weight": "consolidated-00014-of-00051.safetensors",
213
- "layers.3.attention.wk.weight": "consolidated-00014-of-00051.safetensors",
214
- "layers.3.attention.wo.weight": "consolidated-00014-of-00051.safetensors",
215
- "layers.3.attention.wq.weight": "consolidated-00014-of-00051.safetensors",
216
- "layers.3.attention.wv.weight": "consolidated-00014-of-00051.safetensors",
217
- "layers.3.attention_norm.weight": "consolidated-00014-of-00051.safetensors",
218
- "layers.3.feed_forward.w1.weight": "consolidated-00014-of-00051.safetensors",
219
- "layers.3.feed_forward.w2.weight": "consolidated-00014-of-00051.safetensors",
220
- "layers.3.feed_forward.w3.weight": "consolidated-00014-of-00051.safetensors",
221
- "layers.3.ffn_norm.weight": "consolidated-00014-of-00051.safetensors",
222
- "layers.30.attention.wk.weight": "consolidated-00014-of-00051.safetensors",
223
- "layers.30.attention.wo.weight": "consolidated-00014-of-00051.safetensors",
224
- "layers.30.attention.wq.weight": "consolidated-00014-of-00051.safetensors",
225
- "layers.30.attention.wv.weight": "consolidated-00014-of-00051.safetensors",
226
- "layers.30.attention_norm.weight": "consolidated-00014-of-00051.safetensors",
227
- "layers.30.feed_forward.w1.weight": "consolidated-00014-of-00051.safetensors",
228
- "layers.30.feed_forward.w2.weight": "consolidated-00015-of-00051.safetensors",
229
- "layers.30.feed_forward.w3.weight": "consolidated-00015-of-00051.safetensors",
230
- "layers.30.ffn_norm.weight": "consolidated-00015-of-00051.safetensors",
231
- "layers.31.attention.wk.weight": "consolidated-00015-of-00051.safetensors",
232
- "layers.31.attention.wo.weight": "consolidated-00015-of-00051.safetensors",
233
- "layers.31.attention.wq.weight": "consolidated-00015-of-00051.safetensors",
234
- "layers.31.attention.wv.weight": "consolidated-00015-of-00051.safetensors",
235
- "layers.31.attention_norm.weight": "consolidated-00015-of-00051.safetensors",
236
- "layers.31.feed_forward.w1.weight": "consolidated-00015-of-00051.safetensors",
237
- "layers.31.feed_forward.w2.weight": "consolidated-00015-of-00051.safetensors",
238
- "layers.31.feed_forward.w3.weight": "consolidated-00015-of-00051.safetensors",
239
- "layers.31.ffn_norm.weight": "consolidated-00015-of-00051.safetensors",
240
- "layers.32.attention.wk.weight": "consolidated-00015-of-00051.safetensors",
241
- "layers.32.attention.wo.weight": "consolidated-00015-of-00051.safetensors",
242
- "layers.32.attention.wq.weight": "consolidated-00015-of-00051.safetensors",
243
- "layers.32.attention.wv.weight": "consolidated-00015-of-00051.safetensors",
244
- "layers.32.attention_norm.weight": "consolidated-00015-of-00051.safetensors",
245
- "layers.32.feed_forward.w1.weight": "consolidated-00016-of-00051.safetensors",
246
- "layers.32.feed_forward.w2.weight": "consolidated-00016-of-00051.safetensors",
247
- "layers.32.feed_forward.w3.weight": "consolidated-00016-of-00051.safetensors",
248
- "layers.32.ffn_norm.weight": "consolidated-00016-of-00051.safetensors",
249
- "layers.33.attention.wk.weight": "consolidated-00016-of-00051.safetensors",
250
- "layers.33.attention.wo.weight": "consolidated-00016-of-00051.safetensors",
251
- "layers.33.attention.wq.weight": "consolidated-00016-of-00051.safetensors",
252
- "layers.33.attention.wv.weight": "consolidated-00016-of-00051.safetensors",
253
- "layers.33.attention_norm.weight": "consolidated-00016-of-00051.safetensors",
254
- "layers.33.feed_forward.w1.weight": "consolidated-00016-of-00051.safetensors",
255
- "layers.33.feed_forward.w2.weight": "consolidated-00016-of-00051.safetensors",
256
- "layers.33.feed_forward.w3.weight": "consolidated-00016-of-00051.safetensors",
257
- "layers.33.ffn_norm.weight": "consolidated-00016-of-00051.safetensors",
258
- "layers.34.attention.wk.weight": "consolidated-00016-of-00051.safetensors",
259
- "layers.34.attention.wo.weight": "consolidated-00017-of-00051.safetensors",
260
- "layers.34.attention.wq.weight": "consolidated-00017-of-00051.safetensors",
261
- "layers.34.attention.wv.weight": "consolidated-00017-of-00051.safetensors",
262
- "layers.34.attention_norm.weight": "consolidated-00017-of-00051.safetensors",
263
- "layers.34.feed_forward.w1.weight": "consolidated-00017-of-00051.safetensors",
264
- "layers.34.feed_forward.w2.weight": "consolidated-00017-of-00051.safetensors",
265
- "layers.34.feed_forward.w3.weight": "consolidated-00017-of-00051.safetensors",
266
- "layers.34.ffn_norm.weight": "consolidated-00017-of-00051.safetensors",
267
- "layers.35.attention.wk.weight": "consolidated-00017-of-00051.safetensors",
268
- "layers.35.attention.wo.weight": "consolidated-00017-of-00051.safetensors",
269
- "layers.35.attention.wq.weight": "consolidated-00017-of-00051.safetensors",
270
- "layers.35.attention.wv.weight": "consolidated-00017-of-00051.safetensors",
271
- "layers.35.attention_norm.weight": "consolidated-00017-of-00051.safetensors",
272
- "layers.35.feed_forward.w1.weight": "consolidated-00017-of-00051.safetensors",
273
- "layers.35.feed_forward.w2.weight": "consolidated-00017-of-00051.safetensors",
274
- "layers.35.feed_forward.w3.weight": "consolidated-00018-of-00051.safetensors",
275
- "layers.35.ffn_norm.weight": "consolidated-00018-of-00051.safetensors",
276
- "layers.36.attention.wk.weight": "consolidated-00018-of-00051.safetensors",
277
- "layers.36.attention.wo.weight": "consolidated-00018-of-00051.safetensors",
278
- "layers.36.attention.wq.weight": "consolidated-00018-of-00051.safetensors",
279
- "layers.36.attention.wv.weight": "consolidated-00018-of-00051.safetensors",
280
- "layers.36.attention_norm.weight": "consolidated-00018-of-00051.safetensors",
281
- "layers.36.feed_forward.w1.weight": "consolidated-00018-of-00051.safetensors",
282
- "layers.36.feed_forward.w2.weight": "consolidated-00018-of-00051.safetensors",
283
- "layers.36.feed_forward.w3.weight": "consolidated-00018-of-00051.safetensors",
284
- "layers.36.ffn_norm.weight": "consolidated-00018-of-00051.safetensors",
285
- "layers.37.attention.wk.weight": "consolidated-00018-of-00051.safetensors",
286
- "layers.37.attention.wo.weight": "consolidated-00018-of-00051.safetensors",
287
- "layers.37.attention.wq.weight": "consolidated-00018-of-00051.safetensors",
288
- "layers.37.attention.wv.weight": "consolidated-00018-of-00051.safetensors",
289
- "layers.37.attention_norm.weight": "consolidated-00018-of-00051.safetensors",
290
- "layers.37.feed_forward.w1.weight": "consolidated-00018-of-00051.safetensors",
291
- "layers.37.feed_forward.w2.weight": "consolidated-00019-of-00051.safetensors",
292
- "layers.37.feed_forward.w3.weight": "consolidated-00019-of-00051.safetensors",
293
- "layers.37.ffn_norm.weight": "consolidated-00019-of-00051.safetensors",
294
- "layers.38.attention.wk.weight": "consolidated-00019-of-00051.safetensors",
295
- "layers.38.attention.wo.weight": "consolidated-00019-of-00051.safetensors",
296
- "layers.38.attention.wq.weight": "consolidated-00019-of-00051.safetensors",
297
- "layers.38.attention.wv.weight": "consolidated-00019-of-00051.safetensors",
298
- "layers.38.attention_norm.weight": "consolidated-00019-of-00051.safetensors",
299
- "layers.38.feed_forward.w1.weight": "consolidated-00019-of-00051.safetensors",
300
- "layers.38.feed_forward.w2.weight": "consolidated-00019-of-00051.safetensors",
301
- "layers.38.feed_forward.w3.weight": "consolidated-00019-of-00051.safetensors",
302
- "layers.38.ffn_norm.weight": "consolidated-00019-of-00051.safetensors",
303
- "layers.39.attention.wk.weight": "consolidated-00019-of-00051.safetensors",
304
- "layers.39.attention.wo.weight": "consolidated-00019-of-00051.safetensors",
305
- "layers.39.attention.wq.weight": "consolidated-00019-of-00051.safetensors",
306
- "layers.39.attention.wv.weight": "consolidated-00019-of-00051.safetensors",
307
- "layers.39.attention_norm.weight": "consolidated-00019-of-00051.safetensors",
308
- "layers.39.feed_forward.w1.weight": "consolidated-00020-of-00051.safetensors",
309
- "layers.39.feed_forward.w2.weight": "consolidated-00020-of-00051.safetensors",
310
- "layers.39.feed_forward.w3.weight": "consolidated-00020-of-00051.safetensors",
311
- "layers.39.ffn_norm.weight": "consolidated-00020-of-00051.safetensors",
312
- "layers.4.attention.wk.weight": "consolidated-00020-of-00051.safetensors",
313
- "layers.4.attention.wo.weight": "consolidated-00020-of-00051.safetensors",
314
- "layers.4.attention.wq.weight": "consolidated-00020-of-00051.safetensors",
315
- "layers.4.attention.wv.weight": "consolidated-00020-of-00051.safetensors",
316
- "layers.4.attention_norm.weight": "consolidated-00020-of-00051.safetensors",
317
- "layers.4.feed_forward.w1.weight": "consolidated-00020-of-00051.safetensors",
318
- "layers.4.feed_forward.w2.weight": "consolidated-00020-of-00051.safetensors",
319
- "layers.4.feed_forward.w3.weight": "consolidated-00020-of-00051.safetensors",
320
- "layers.4.ffn_norm.weight": "consolidated-00020-of-00051.safetensors",
321
- "layers.40.attention.wk.weight": "consolidated-00020-of-00051.safetensors",
322
- "layers.40.attention.wo.weight": "consolidated-00021-of-00051.safetensors",
323
- "layers.40.attention.wq.weight": "consolidated-00021-of-00051.safetensors",
324
- "layers.40.attention.wv.weight": "consolidated-00021-of-00051.safetensors",
325
- "layers.40.attention_norm.weight": "consolidated-00021-of-00051.safetensors",
326
- "layers.40.feed_forward.w1.weight": "consolidated-00021-of-00051.safetensors",
327
- "layers.40.feed_forward.w2.weight": "consolidated-00021-of-00051.safetensors",
328
- "layers.40.feed_forward.w3.weight": "consolidated-00021-of-00051.safetensors",
329
- "layers.40.ffn_norm.weight": "consolidated-00021-of-00051.safetensors",
330
- "layers.41.attention.wk.weight": "consolidated-00021-of-00051.safetensors",
331
- "layers.41.attention.wo.weight": "consolidated-00021-of-00051.safetensors",
332
- "layers.41.attention.wq.weight": "consolidated-00021-of-00051.safetensors",
333
- "layers.41.attention.wv.weight": "consolidated-00021-of-00051.safetensors",
334
- "layers.41.attention_norm.weight": "consolidated-00021-of-00051.safetensors",
335
- "layers.41.feed_forward.w1.weight": "consolidated-00021-of-00051.safetensors",
336
- "layers.41.feed_forward.w2.weight": "consolidated-00021-of-00051.safetensors",
337
- "layers.41.feed_forward.w3.weight": "consolidated-00022-of-00051.safetensors",
338
- "layers.41.ffn_norm.weight": "consolidated-00022-of-00051.safetensors",
339
- "layers.42.attention.wk.weight": "consolidated-00022-of-00051.safetensors",
340
- "layers.42.attention.wo.weight": "consolidated-00022-of-00051.safetensors",
341
- "layers.42.attention.wq.weight": "consolidated-00022-of-00051.safetensors",
342
- "layers.42.attention.wv.weight": "consolidated-00022-of-00051.safetensors",
343
- "layers.42.attention_norm.weight": "consolidated-00022-of-00051.safetensors",
344
- "layers.42.feed_forward.w1.weight": "consolidated-00022-of-00051.safetensors",
345
- "layers.42.feed_forward.w2.weight": "consolidated-00022-of-00051.safetensors",
346
- "layers.42.feed_forward.w3.weight": "consolidated-00022-of-00051.safetensors",
347
- "layers.42.ffn_norm.weight": "consolidated-00022-of-00051.safetensors",
348
- "layers.43.attention.wk.weight": "consolidated-00022-of-00051.safetensors",
349
- "layers.43.attention.wo.weight": "consolidated-00022-of-00051.safetensors",
350
- "layers.43.attention.wq.weight": "consolidated-00022-of-00051.safetensors",
351
- "layers.43.attention.wv.weight": "consolidated-00022-of-00051.safetensors",
352
- "layers.43.attention_norm.weight": "consolidated-00022-of-00051.safetensors",
353
- "layers.43.feed_forward.w1.weight": "consolidated-00022-of-00051.safetensors",
354
- "layers.43.feed_forward.w2.weight": "consolidated-00023-of-00051.safetensors",
355
- "layers.43.feed_forward.w3.weight": "consolidated-00023-of-00051.safetensors",
356
- "layers.43.ffn_norm.weight": "consolidated-00023-of-00051.safetensors",
357
- "layers.44.attention.wk.weight": "consolidated-00023-of-00051.safetensors",
358
- "layers.44.attention.wo.weight": "consolidated-00023-of-00051.safetensors",
359
- "layers.44.attention.wq.weight": "consolidated-00023-of-00051.safetensors",
360
- "layers.44.attention.wv.weight": "consolidated-00023-of-00051.safetensors",
361
- "layers.44.attention_norm.weight": "consolidated-00023-of-00051.safetensors",
362
- "layers.44.feed_forward.w1.weight": "consolidated-00023-of-00051.safetensors",
363
- "layers.44.feed_forward.w2.weight": "consolidated-00023-of-00051.safetensors",
364
- "layers.44.feed_forward.w3.weight": "consolidated-00023-of-00051.safetensors",
365
- "layers.44.ffn_norm.weight": "consolidated-00023-of-00051.safetensors",
366
- "layers.45.attention.wk.weight": "consolidated-00023-of-00051.safetensors",
367
- "layers.45.attention.wo.weight": "consolidated-00023-of-00051.safetensors",
368
- "layers.45.attention.wq.weight": "consolidated-00023-of-00051.safetensors",
369
- "layers.45.attention.wv.weight": "consolidated-00023-of-00051.safetensors",
370
- "layers.45.attention_norm.weight": "consolidated-00023-of-00051.safetensors",
371
- "layers.45.feed_forward.w1.weight": "consolidated-00024-of-00051.safetensors",
372
- "layers.45.feed_forward.w2.weight": "consolidated-00024-of-00051.safetensors",
373
- "layers.45.feed_forward.w3.weight": "consolidated-00024-of-00051.safetensors",
374
- "layers.45.ffn_norm.weight": "consolidated-00024-of-00051.safetensors",
375
- "layers.46.attention.wk.weight": "consolidated-00024-of-00051.safetensors",
376
- "layers.46.attention.wo.weight": "consolidated-00024-of-00051.safetensors",
377
- "layers.46.attention.wq.weight": "consolidated-00024-of-00051.safetensors",
378
- "layers.46.attention.wv.weight": "consolidated-00024-of-00051.safetensors",
379
- "layers.46.attention_norm.weight": "consolidated-00024-of-00051.safetensors",
380
- "layers.46.feed_forward.w1.weight": "consolidated-00024-of-00051.safetensors",
381
- "layers.46.feed_forward.w2.weight": "consolidated-00024-of-00051.safetensors",
382
- "layers.46.feed_forward.w3.weight": "consolidated-00024-of-00051.safetensors",
383
- "layers.46.ffn_norm.weight": "consolidated-00024-of-00051.safetensors",
384
- "layers.47.attention.wk.weight": "consolidated-00024-of-00051.safetensors",
385
- "layers.47.attention.wo.weight": "consolidated-00025-of-00051.safetensors",
386
- "layers.47.attention.wq.weight": "consolidated-00025-of-00051.safetensors",
387
- "layers.47.attention.wv.weight": "consolidated-00025-of-00051.safetensors",
388
- "layers.47.attention_norm.weight": "consolidated-00025-of-00051.safetensors",
389
- "layers.47.feed_forward.w1.weight": "consolidated-00025-of-00051.safetensors",
390
- "layers.47.feed_forward.w2.weight": "consolidated-00025-of-00051.safetensors",
391
- "layers.47.feed_forward.w3.weight": "consolidated-00025-of-00051.safetensors",
392
- "layers.47.ffn_norm.weight": "consolidated-00025-of-00051.safetensors",
393
- "layers.48.attention.wk.weight": "consolidated-00025-of-00051.safetensors",
394
- "layers.48.attention.wo.weight": "consolidated-00025-of-00051.safetensors",
395
- "layers.48.attention.wq.weight": "consolidated-00025-of-00051.safetensors",
396
- "layers.48.attention.wv.weight": "consolidated-00025-of-00051.safetensors",
397
- "layers.48.attention_norm.weight": "consolidated-00025-of-00051.safetensors",
398
- "layers.48.feed_forward.w1.weight": "consolidated-00025-of-00051.safetensors",
399
- "layers.48.feed_forward.w2.weight": "consolidated-00025-of-00051.safetensors",
400
- "layers.48.feed_forward.w3.weight": "consolidated-00026-of-00051.safetensors",
401
- "layers.48.ffn_norm.weight": "consolidated-00026-of-00051.safetensors",
402
- "layers.49.attention.wk.weight": "consolidated-00026-of-00051.safetensors",
403
- "layers.49.attention.wo.weight": "consolidated-00026-of-00051.safetensors",
404
- "layers.49.attention.wq.weight": "consolidated-00026-of-00051.safetensors",
405
- "layers.49.attention.wv.weight": "consolidated-00026-of-00051.safetensors",
406
- "layers.49.attention_norm.weight": "consolidated-00026-of-00051.safetensors",
407
- "layers.49.feed_forward.w1.weight": "consolidated-00026-of-00051.safetensors",
408
- "layers.49.feed_forward.w2.weight": "consolidated-00026-of-00051.safetensors",
409
- "layers.49.feed_forward.w3.weight": "consolidated-00026-of-00051.safetensors",
410
- "layers.49.ffn_norm.weight": "consolidated-00026-of-00051.safetensors",
411
- "layers.5.attention.wk.weight": "consolidated-00026-of-00051.safetensors",
412
- "layers.5.attention.wo.weight": "consolidated-00026-of-00051.safetensors",
413
- "layers.5.attention.wq.weight": "consolidated-00026-of-00051.safetensors",
414
- "layers.5.attention.wv.weight": "consolidated-00026-of-00051.safetensors",
415
- "layers.5.attention_norm.weight": "consolidated-00026-of-00051.safetensors",
416
- "layers.5.feed_forward.w1.weight": "consolidated-00026-of-00051.safetensors",
417
- "layers.5.feed_forward.w2.weight": "consolidated-00027-of-00051.safetensors",
418
- "layers.5.feed_forward.w3.weight": "consolidated-00027-of-00051.safetensors",
419
- "layers.5.ffn_norm.weight": "consolidated-00027-of-00051.safetensors",
420
- "layers.50.attention.wk.weight": "consolidated-00027-of-00051.safetensors",
421
- "layers.50.attention.wo.weight": "consolidated-00027-of-00051.safetensors",
422
- "layers.50.attention.wq.weight": "consolidated-00027-of-00051.safetensors",
423
- "layers.50.attention.wv.weight": "consolidated-00027-of-00051.safetensors",
424
- "layers.50.attention_norm.weight": "consolidated-00027-of-00051.safetensors",
425
- "layers.50.feed_forward.w1.weight": "consolidated-00027-of-00051.safetensors",
426
- "layers.50.feed_forward.w2.weight": "consolidated-00027-of-00051.safetensors",
427
- "layers.50.feed_forward.w3.weight": "consolidated-00027-of-00051.safetensors",
428
- "layers.50.ffn_norm.weight": "consolidated-00027-of-00051.safetensors",
429
- "layers.51.attention.wk.weight": "consolidated-00027-of-00051.safetensors",
430
- "layers.51.attention.wo.weight": "consolidated-00027-of-00051.safetensors",
431
- "layers.51.attention.wq.weight": "consolidated-00027-of-00051.safetensors",
432
- "layers.51.attention.wv.weight": "consolidated-00027-of-00051.safetensors",
433
- "layers.51.attention_norm.weight": "consolidated-00027-of-00051.safetensors",
434
- "layers.51.feed_forward.w1.weight": "consolidated-00028-of-00051.safetensors",
435
- "layers.51.feed_forward.w2.weight": "consolidated-00028-of-00051.safetensors",
436
- "layers.51.feed_forward.w3.weight": "consolidated-00028-of-00051.safetensors",
437
- "layers.51.ffn_norm.weight": "consolidated-00028-of-00051.safetensors",
438
- "layers.52.attention.wk.weight": "consolidated-00028-of-00051.safetensors",
439
- "layers.52.attention.wo.weight": "consolidated-00028-of-00051.safetensors",
440
- "layers.52.attention.wq.weight": "consolidated-00028-of-00051.safetensors",
441
- "layers.52.attention.wv.weight": "consolidated-00028-of-00051.safetensors",
442
- "layers.52.attention_norm.weight": "consolidated-00028-of-00051.safetensors",
443
- "layers.52.feed_forward.w1.weight": "consolidated-00028-of-00051.safetensors",
444
- "layers.52.feed_forward.w2.weight": "consolidated-00028-of-00051.safetensors",
445
- "layers.52.feed_forward.w3.weight": "consolidated-00028-of-00051.safetensors",
446
- "layers.52.ffn_norm.weight": "consolidated-00028-of-00051.safetensors",
447
- "layers.53.attention.wk.weight": "consolidated-00028-of-00051.safetensors",
448
- "layers.53.attention.wo.weight": "consolidated-00029-of-00051.safetensors",
449
- "layers.53.attention.wq.weight": "consolidated-00029-of-00051.safetensors",
450
- "layers.53.attention.wv.weight": "consolidated-00029-of-00051.safetensors",
451
- "layers.53.attention_norm.weight": "consolidated-00029-of-00051.safetensors",
452
- "layers.53.feed_forward.w1.weight": "consolidated-00029-of-00051.safetensors",
453
- "layers.53.feed_forward.w2.weight": "consolidated-00029-of-00051.safetensors",
454
- "layers.53.feed_forward.w3.weight": "consolidated-00029-of-00051.safetensors",
455
- "layers.53.ffn_norm.weight": "consolidated-00029-of-00051.safetensors",
456
- "layers.54.attention.wk.weight": "consolidated-00029-of-00051.safetensors",
457
- "layers.54.attention.wo.weight": "consolidated-00029-of-00051.safetensors",
458
- "layers.54.attention.wq.weight": "consolidated-00029-of-00051.safetensors",
459
- "layers.54.attention.wv.weight": "consolidated-00029-of-00051.safetensors",
460
- "layers.54.attention_norm.weight": "consolidated-00029-of-00051.safetensors",
461
- "layers.54.feed_forward.w1.weight": "consolidated-00029-of-00051.safetensors",
462
- "layers.54.feed_forward.w2.weight": "consolidated-00029-of-00051.safetensors",
463
- "layers.54.feed_forward.w3.weight": "consolidated-00030-of-00051.safetensors",
464
- "layers.54.ffn_norm.weight": "consolidated-00030-of-00051.safetensors",
465
- "layers.55.attention.wk.weight": "consolidated-00030-of-00051.safetensors",
466
- "layers.55.attention.wo.weight": "consolidated-00030-of-00051.safetensors",
467
- "layers.55.attention.wq.weight": "consolidated-00030-of-00051.safetensors",
468
- "layers.55.attention.wv.weight": "consolidated-00030-of-00051.safetensors",
469
- "layers.55.attention_norm.weight": "consolidated-00030-of-00051.safetensors",
470
- "layers.55.feed_forward.w1.weight": "consolidated-00030-of-00051.safetensors",
471
- "layers.55.feed_forward.w2.weight": "consolidated-00030-of-00051.safetensors",
472
- "layers.55.feed_forward.w3.weight": "consolidated-00030-of-00051.safetensors",
473
- "layers.55.ffn_norm.weight": "consolidated-00030-of-00051.safetensors",
474
- "layers.56.attention.wk.weight": "consolidated-00030-of-00051.safetensors",
475
- "layers.56.attention.wo.weight": "consolidated-00030-of-00051.safetensors",
476
- "layers.56.attention.wq.weight": "consolidated-00030-of-00051.safetensors",
477
- "layers.56.attention.wv.weight": "consolidated-00030-of-00051.safetensors",
478
- "layers.56.attention_norm.weight": "consolidated-00030-of-00051.safetensors",
479
- "layers.56.feed_forward.w1.weight": "consolidated-00030-of-00051.safetensors",
480
- "layers.56.feed_forward.w2.weight": "consolidated-00031-of-00051.safetensors",
481
- "layers.56.feed_forward.w3.weight": "consolidated-00031-of-00051.safetensors",
482
- "layers.56.ffn_norm.weight": "consolidated-00031-of-00051.safetensors",
483
- "layers.57.attention.wk.weight": "consolidated-00031-of-00051.safetensors",
484
- "layers.57.attention.wo.weight": "consolidated-00031-of-00051.safetensors",
485
- "layers.57.attention.wq.weight": "consolidated-00031-of-00051.safetensors",
486
- "layers.57.attention.wv.weight": "consolidated-00031-of-00051.safetensors",
487
- "layers.57.attention_norm.weight": "consolidated-00031-of-00051.safetensors",
488
- "layers.57.feed_forward.w1.weight": "consolidated-00031-of-00051.safetensors",
489
- "layers.57.feed_forward.w2.weight": "consolidated-00031-of-00051.safetensors",
490
- "layers.57.feed_forward.w3.weight": "consolidated-00031-of-00051.safetensors",
491
- "layers.57.ffn_norm.weight": "consolidated-00031-of-00051.safetensors",
492
- "layers.58.attention.wk.weight": "consolidated-00031-of-00051.safetensors",
493
- "layers.58.attention.wo.weight": "consolidated-00031-of-00051.safetensors",
494
- "layers.58.attention.wq.weight": "consolidated-00031-of-00051.safetensors",
495
- "layers.58.attention.wv.weight": "consolidated-00031-of-00051.safetensors",
496
- "layers.58.attention_norm.weight": "consolidated-00031-of-00051.safetensors",
497
- "layers.58.feed_forward.w1.weight": "consolidated-00032-of-00051.safetensors",
498
- "layers.58.feed_forward.w2.weight": "consolidated-00032-of-00051.safetensors",
499
- "layers.58.feed_forward.w3.weight": "consolidated-00032-of-00051.safetensors",
500
- "layers.58.ffn_norm.weight": "consolidated-00032-of-00051.safetensors",
501
- "layers.59.attention.wk.weight": "consolidated-00032-of-00051.safetensors",
502
- "layers.59.attention.wo.weight": "consolidated-00032-of-00051.safetensors",
503
- "layers.59.attention.wq.weight": "consolidated-00032-of-00051.safetensors",
504
- "layers.59.attention.wv.weight": "consolidated-00032-of-00051.safetensors",
505
- "layers.59.attention_norm.weight": "consolidated-00032-of-00051.safetensors",
506
- "layers.59.feed_forward.w1.weight": "consolidated-00032-of-00051.safetensors",
507
- "layers.59.feed_forward.w2.weight": "consolidated-00032-of-00051.safetensors",
508
- "layers.59.feed_forward.w3.weight": "consolidated-00032-of-00051.safetensors",
509
- "layers.59.ffn_norm.weight": "consolidated-00032-of-00051.safetensors",
510
- "layers.6.attention.wk.weight": "consolidated-00032-of-00051.safetensors",
511
- "layers.6.attention.wo.weight": "consolidated-00033-of-00051.safetensors",
512
- "layers.6.attention.wq.weight": "consolidated-00033-of-00051.safetensors",
513
- "layers.6.attention.wv.weight": "consolidated-00033-of-00051.safetensors",
514
- "layers.6.attention_norm.weight": "consolidated-00033-of-00051.safetensors",
515
- "layers.6.feed_forward.w1.weight": "consolidated-00033-of-00051.safetensors",
516
- "layers.6.feed_forward.w2.weight": "consolidated-00033-of-00051.safetensors",
517
- "layers.6.feed_forward.w3.weight": "consolidated-00033-of-00051.safetensors",
518
- "layers.6.ffn_norm.weight": "consolidated-00033-of-00051.safetensors",
519
- "layers.60.attention.wk.weight": "consolidated-00033-of-00051.safetensors",
520
- "layers.60.attention.wo.weight": "consolidated-00033-of-00051.safetensors",
521
- "layers.60.attention.wq.weight": "consolidated-00033-of-00051.safetensors",
522
- "layers.60.attention.wv.weight": "consolidated-00033-of-00051.safetensors",
523
- "layers.60.attention_norm.weight": "consolidated-00033-of-00051.safetensors",
524
- "layers.60.feed_forward.w1.weight": "consolidated-00033-of-00051.safetensors",
525
- "layers.60.feed_forward.w2.weight": "consolidated-00033-of-00051.safetensors",
526
- "layers.60.feed_forward.w3.weight": "consolidated-00034-of-00051.safetensors",
527
- "layers.60.ffn_norm.weight": "consolidated-00034-of-00051.safetensors",
528
- "layers.61.attention.wk.weight": "consolidated-00034-of-00051.safetensors",
529
- "layers.61.attention.wo.weight": "consolidated-00034-of-00051.safetensors",
530
- "layers.61.attention.wq.weight": "consolidated-00034-of-00051.safetensors",
531
- "layers.61.attention.wv.weight": "consolidated-00034-of-00051.safetensors",
532
- "layers.61.attention_norm.weight": "consolidated-00034-of-00051.safetensors",
533
- "layers.61.feed_forward.w1.weight": "consolidated-00034-of-00051.safetensors",
534
- "layers.61.feed_forward.w2.weight": "consolidated-00034-of-00051.safetensors",
535
- "layers.61.feed_forward.w3.weight": "consolidated-00034-of-00051.safetensors",
536
- "layers.61.ffn_norm.weight": "consolidated-00034-of-00051.safetensors",
537
- "layers.62.attention.wk.weight": "consolidated-00034-of-00051.safetensors",
538
- "layers.62.attention.wo.weight": "consolidated-00034-of-00051.safetensors",
539
- "layers.62.attention.wq.weight": "consolidated-00034-of-00051.safetensors",
540
- "layers.62.attention.wv.weight": "consolidated-00034-of-00051.safetensors",
541
- "layers.62.attention_norm.weight": "consolidated-00034-of-00051.safetensors",
542
- "layers.62.feed_forward.w1.weight": "consolidated-00034-of-00051.safetensors",
543
- "layers.62.feed_forward.w2.weight": "consolidated-00035-of-00051.safetensors",
544
- "layers.62.feed_forward.w3.weight": "consolidated-00035-of-00051.safetensors",
545
- "layers.62.ffn_norm.weight": "consolidated-00035-of-00051.safetensors",
546
- "layers.63.attention.wk.weight": "consolidated-00035-of-00051.safetensors",
547
- "layers.63.attention.wo.weight": "consolidated-00035-of-00051.safetensors",
548
- "layers.63.attention.wq.weight": "consolidated-00035-of-00051.safetensors",
549
- "layers.63.attention.wv.weight": "consolidated-00035-of-00051.safetensors",
550
- "layers.63.attention_norm.weight": "consolidated-00035-of-00051.safetensors",
551
- "layers.63.feed_forward.w1.weight": "consolidated-00035-of-00051.safetensors",
552
- "layers.63.feed_forward.w2.weight": "consolidated-00035-of-00051.safetensors",
553
- "layers.63.feed_forward.w3.weight": "consolidated-00035-of-00051.safetensors",
554
- "layers.63.ffn_norm.weight": "consolidated-00035-of-00051.safetensors",
555
- "layers.64.attention.wk.weight": "consolidated-00035-of-00051.safetensors",
556
- "layers.64.attention.wo.weight": "consolidated-00035-of-00051.safetensors",
557
- "layers.64.attention.wq.weight": "consolidated-00035-of-00051.safetensors",
558
- "layers.64.attention.wv.weight": "consolidated-00035-of-00051.safetensors",
559
- "layers.64.attention_norm.weight": "consolidated-00035-of-00051.safetensors",
560
- "layers.64.feed_forward.w1.weight": "consolidated-00036-of-00051.safetensors",
561
- "layers.64.feed_forward.w2.weight": "consolidated-00036-of-00051.safetensors",
562
- "layers.64.feed_forward.w3.weight": "consolidated-00036-of-00051.safetensors",
563
- "layers.64.ffn_norm.weight": "consolidated-00036-of-00051.safetensors",
564
- "layers.65.attention.wk.weight": "consolidated-00036-of-00051.safetensors",
565
- "layers.65.attention.wo.weight": "consolidated-00036-of-00051.safetensors",
566
- "layers.65.attention.wq.weight": "consolidated-00036-of-00051.safetensors",
567
- "layers.65.attention.wv.weight": "consolidated-00036-of-00051.safetensors",
568
- "layers.65.attention_norm.weight": "consolidated-00036-of-00051.safetensors",
569
- "layers.65.feed_forward.w1.weight": "consolidated-00036-of-00051.safetensors",
570
- "layers.65.feed_forward.w2.weight": "consolidated-00036-of-00051.safetensors",
571
- "layers.65.feed_forward.w3.weight": "consolidated-00036-of-00051.safetensors",
572
- "layers.65.ffn_norm.weight": "consolidated-00036-of-00051.safetensors",
573
- "layers.66.attention.wk.weight": "consolidated-00036-of-00051.safetensors",
574
- "layers.66.attention.wo.weight": "consolidated-00037-of-00051.safetensors",
575
- "layers.66.attention.wq.weight": "consolidated-00037-of-00051.safetensors",
576
- "layers.66.attention.wv.weight": "consolidated-00037-of-00051.safetensors",
577
- "layers.66.attention_norm.weight": "consolidated-00037-of-00051.safetensors",
578
- "layers.66.feed_forward.w1.weight": "consolidated-00037-of-00051.safetensors",
579
- "layers.66.feed_forward.w2.weight": "consolidated-00037-of-00051.safetensors",
580
- "layers.66.feed_forward.w3.weight": "consolidated-00037-of-00051.safetensors",
581
- "layers.66.ffn_norm.weight": "consolidated-00037-of-00051.safetensors",
582
- "layers.67.attention.wk.weight": "consolidated-00037-of-00051.safetensors",
583
- "layers.67.attention.wo.weight": "consolidated-00037-of-00051.safetensors",
584
- "layers.67.attention.wq.weight": "consolidated-00037-of-00051.safetensors",
585
- "layers.67.attention.wv.weight": "consolidated-00037-of-00051.safetensors",
586
- "layers.67.attention_norm.weight": "consolidated-00037-of-00051.safetensors",
587
- "layers.67.feed_forward.w1.weight": "consolidated-00037-of-00051.safetensors",
588
- "layers.67.feed_forward.w2.weight": "consolidated-00037-of-00051.safetensors",
589
- "layers.67.feed_forward.w3.weight": "consolidated-00038-of-00051.safetensors",
590
- "layers.67.ffn_norm.weight": "consolidated-00038-of-00051.safetensors",
591
- "layers.68.attention.wk.weight": "consolidated-00038-of-00051.safetensors",
592
- "layers.68.attention.wo.weight": "consolidated-00038-of-00051.safetensors",
593
- "layers.68.attention.wq.weight": "consolidated-00038-of-00051.safetensors",
594
- "layers.68.attention.wv.weight": "consolidated-00038-of-00051.safetensors",
595
- "layers.68.attention_norm.weight": "consolidated-00038-of-00051.safetensors",
596
- "layers.68.feed_forward.w1.weight": "consolidated-00038-of-00051.safetensors",
597
- "layers.68.feed_forward.w2.weight": "consolidated-00038-of-00051.safetensors",
598
- "layers.68.feed_forward.w3.weight": "consolidated-00038-of-00051.safetensors",
599
- "layers.68.ffn_norm.weight": "consolidated-00038-of-00051.safetensors",
600
- "layers.69.attention.wk.weight": "consolidated-00038-of-00051.safetensors",
601
- "layers.69.attention.wo.weight": "consolidated-00038-of-00051.safetensors",
602
- "layers.69.attention.wq.weight": "consolidated-00038-of-00051.safetensors",
603
- "layers.69.attention.wv.weight": "consolidated-00038-of-00051.safetensors",
604
- "layers.69.attention_norm.weight": "consolidated-00038-of-00051.safetensors",
605
- "layers.69.feed_forward.w1.weight": "consolidated-00038-of-00051.safetensors",
606
- "layers.69.feed_forward.w2.weight": "consolidated-00039-of-00051.safetensors",
607
- "layers.69.feed_forward.w3.weight": "consolidated-00039-of-00051.safetensors",
608
- "layers.69.ffn_norm.weight": "consolidated-00039-of-00051.safetensors",
609
- "layers.7.attention.wk.weight": "consolidated-00039-of-00051.safetensors",
610
- "layers.7.attention.wo.weight": "consolidated-00039-of-00051.safetensors",
611
- "layers.7.attention.wq.weight": "consolidated-00039-of-00051.safetensors",
612
- "layers.7.attention.wv.weight": "consolidated-00039-of-00051.safetensors",
613
- "layers.7.attention_norm.weight": "consolidated-00039-of-00051.safetensors",
614
- "layers.7.feed_forward.w1.weight": "consolidated-00039-of-00051.safetensors",
615
- "layers.7.feed_forward.w2.weight": "consolidated-00039-of-00051.safetensors",
616
- "layers.7.feed_forward.w3.weight": "consolidated-00039-of-00051.safetensors",
617
- "layers.7.ffn_norm.weight": "consolidated-00039-of-00051.safetensors",
618
- "layers.70.attention.wk.weight": "consolidated-00039-of-00051.safetensors",
619
- "layers.70.attention.wo.weight": "consolidated-00039-of-00051.safetensors",
620
- "layers.70.attention.wq.weight": "consolidated-00039-of-00051.safetensors",
621
- "layers.70.attention.wv.weight": "consolidated-00039-of-00051.safetensors",
622
- "layers.70.attention_norm.weight": "consolidated-00039-of-00051.safetensors",
623
- "layers.70.feed_forward.w1.weight": "consolidated-00040-of-00051.safetensors",
624
- "layers.70.feed_forward.w2.weight": "consolidated-00040-of-00051.safetensors",
625
- "layers.70.feed_forward.w3.weight": "consolidated-00040-of-00051.safetensors",
626
- "layers.70.ffn_norm.weight": "consolidated-00040-of-00051.safetensors",
627
- "layers.71.attention.wk.weight": "consolidated-00040-of-00051.safetensors",
628
- "layers.71.attention.wo.weight": "consolidated-00040-of-00051.safetensors",
629
- "layers.71.attention.wq.weight": "consolidated-00040-of-00051.safetensors",
630
- "layers.71.attention.wv.weight": "consolidated-00040-of-00051.safetensors",
631
- "layers.71.attention_norm.weight": "consolidated-00040-of-00051.safetensors",
632
- "layers.71.feed_forward.w1.weight": "consolidated-00040-of-00051.safetensors",
633
- "layers.71.feed_forward.w2.weight": "consolidated-00040-of-00051.safetensors",
634
- "layers.71.feed_forward.w3.weight": "consolidated-00040-of-00051.safetensors",
635
- "layers.71.ffn_norm.weight": "consolidated-00040-of-00051.safetensors",
636
- "layers.72.attention.wk.weight": "consolidated-00040-of-00051.safetensors",
637
- "layers.72.attention.wo.weight": "consolidated-00041-of-00051.safetensors",
638
- "layers.72.attention.wq.weight": "consolidated-00041-of-00051.safetensors",
639
- "layers.72.attention.wv.weight": "consolidated-00041-of-00051.safetensors",
640
- "layers.72.attention_norm.weight": "consolidated-00041-of-00051.safetensors",
641
- "layers.72.feed_forward.w1.weight": "consolidated-00041-of-00051.safetensors",
642
- "layers.72.feed_forward.w2.weight": "consolidated-00041-of-00051.safetensors",
643
- "layers.72.feed_forward.w3.weight": "consolidated-00041-of-00051.safetensors",
644
- "layers.72.ffn_norm.weight": "consolidated-00041-of-00051.safetensors",
645
- "layers.73.attention.wk.weight": "consolidated-00041-of-00051.safetensors",
646
- "layers.73.attention.wo.weight": "consolidated-00041-of-00051.safetensors",
647
- "layers.73.attention.wq.weight": "consolidated-00041-of-00051.safetensors",
648
- "layers.73.attention.wv.weight": "consolidated-00041-of-00051.safetensors",
649
- "layers.73.attention_norm.weight": "consolidated-00041-of-00051.safetensors",
650
- "layers.73.feed_forward.w1.weight": "consolidated-00041-of-00051.safetensors",
651
- "layers.73.feed_forward.w2.weight": "consolidated-00041-of-00051.safetensors",
652
- "layers.73.feed_forward.w3.weight": "consolidated-00042-of-00051.safetensors",
653
- "layers.73.ffn_norm.weight": "consolidated-00042-of-00051.safetensors",
654
- "layers.74.attention.wk.weight": "consolidated-00042-of-00051.safetensors",
655
- "layers.74.attention.wo.weight": "consolidated-00042-of-00051.safetensors",
656
- "layers.74.attention.wq.weight": "consolidated-00042-of-00051.safetensors",
657
- "layers.74.attention.wv.weight": "consolidated-00042-of-00051.safetensors",
658
- "layers.74.attention_norm.weight": "consolidated-00042-of-00051.safetensors",
659
- "layers.74.feed_forward.w1.weight": "consolidated-00042-of-00051.safetensors",
660
- "layers.74.feed_forward.w2.weight": "consolidated-00042-of-00051.safetensors",
661
- "layers.74.feed_forward.w3.weight": "consolidated-00042-of-00051.safetensors",
662
- "layers.74.ffn_norm.weight": "consolidated-00042-of-00051.safetensors",
663
- "layers.75.attention.wk.weight": "consolidated-00042-of-00051.safetensors",
664
- "layers.75.attention.wo.weight": "consolidated-00042-of-00051.safetensors",
665
- "layers.75.attention.wq.weight": "consolidated-00042-of-00051.safetensors",
666
- "layers.75.attention.wv.weight": "consolidated-00042-of-00051.safetensors",
667
- "layers.75.attention_norm.weight": "consolidated-00042-of-00051.safetensors",
668
- "layers.75.feed_forward.w1.weight": "consolidated-00042-of-00051.safetensors",
669
- "layers.75.feed_forward.w2.weight": "consolidated-00043-of-00051.safetensors",
670
- "layers.75.feed_forward.w3.weight": "consolidated-00043-of-00051.safetensors",
671
- "layers.75.ffn_norm.weight": "consolidated-00043-of-00051.safetensors",
672
- "layers.76.attention.wk.weight": "consolidated-00043-of-00051.safetensors",
673
- "layers.76.attention.wo.weight": "consolidated-00043-of-00051.safetensors",
674
- "layers.76.attention.wq.weight": "consolidated-00043-of-00051.safetensors",
675
- "layers.76.attention.wv.weight": "consolidated-00043-of-00051.safetensors",
676
- "layers.76.attention_norm.weight": "consolidated-00043-of-00051.safetensors",
677
- "layers.76.feed_forward.w1.weight": "consolidated-00043-of-00051.safetensors",
678
- "layers.76.feed_forward.w2.weight": "consolidated-00043-of-00051.safetensors",
679
- "layers.76.feed_forward.w3.weight": "consolidated-00043-of-00051.safetensors",
680
- "layers.76.ffn_norm.weight": "consolidated-00043-of-00051.safetensors",
681
- "layers.77.attention.wk.weight": "consolidated-00043-of-00051.safetensors",
682
- "layers.77.attention.wo.weight": "consolidated-00043-of-00051.safetensors",
683
- "layers.77.attention.wq.weight": "consolidated-00043-of-00051.safetensors",
684
- "layers.77.attention.wv.weight": "consolidated-00043-of-00051.safetensors",
685
- "layers.77.attention_norm.weight": "consolidated-00043-of-00051.safetensors",
686
- "layers.77.feed_forward.w1.weight": "consolidated-00044-of-00051.safetensors",
687
- "layers.77.feed_forward.w2.weight": "consolidated-00044-of-00051.safetensors",
688
- "layers.77.feed_forward.w3.weight": "consolidated-00044-of-00051.safetensors",
689
- "layers.77.ffn_norm.weight": "consolidated-00044-of-00051.safetensors",
690
- "layers.78.attention.wk.weight": "consolidated-00044-of-00051.safetensors",
691
- "layers.78.attention.wo.weight": "consolidated-00044-of-00051.safetensors",
692
- "layers.78.attention.wq.weight": "consolidated-00044-of-00051.safetensors",
693
- "layers.78.attention.wv.weight": "consolidated-00044-of-00051.safetensors",
694
- "layers.78.attention_norm.weight": "consolidated-00044-of-00051.safetensors",
695
- "layers.78.feed_forward.w1.weight": "consolidated-00044-of-00051.safetensors",
696
- "layers.78.feed_forward.w2.weight": "consolidated-00044-of-00051.safetensors",
697
- "layers.78.feed_forward.w3.weight": "consolidated-00044-of-00051.safetensors",
698
- "layers.78.ffn_norm.weight": "consolidated-00044-of-00051.safetensors",
699
- "layers.79.attention.wk.weight": "consolidated-00044-of-00051.safetensors",
700
- "layers.79.attention.wo.weight": "consolidated-00045-of-00051.safetensors",
701
- "layers.79.attention.wq.weight": "consolidated-00045-of-00051.safetensors",
702
- "layers.79.attention.wv.weight": "consolidated-00045-of-00051.safetensors",
703
- "layers.79.attention_norm.weight": "consolidated-00045-of-00051.safetensors",
704
- "layers.79.feed_forward.w1.weight": "consolidated-00045-of-00051.safetensors",
705
- "layers.79.feed_forward.w2.weight": "consolidated-00045-of-00051.safetensors",
706
- "layers.79.feed_forward.w3.weight": "consolidated-00045-of-00051.safetensors",
707
- "layers.79.ffn_norm.weight": "consolidated-00045-of-00051.safetensors",
708
- "layers.8.attention.wk.weight": "consolidated-00045-of-00051.safetensors",
709
- "layers.8.attention.wo.weight": "consolidated-00045-of-00051.safetensors",
710
- "layers.8.attention.wq.weight": "consolidated-00045-of-00051.safetensors",
711
- "layers.8.attention.wv.weight": "consolidated-00045-of-00051.safetensors",
712
- "layers.8.attention_norm.weight": "consolidated-00045-of-00051.safetensors",
713
- "layers.8.feed_forward.w1.weight": "consolidated-00045-of-00051.safetensors",
714
- "layers.8.feed_forward.w2.weight": "consolidated-00045-of-00051.safetensors",
715
- "layers.8.feed_forward.w3.weight": "consolidated-00046-of-00051.safetensors",
716
- "layers.8.ffn_norm.weight": "consolidated-00046-of-00051.safetensors",
717
- "layers.80.attention.wk.weight": "consolidated-00046-of-00051.safetensors",
718
- "layers.80.attention.wo.weight": "consolidated-00046-of-00051.safetensors",
719
- "layers.80.attention.wq.weight": "consolidated-00046-of-00051.safetensors",
720
- "layers.80.attention.wv.weight": "consolidated-00046-of-00051.safetensors",
721
- "layers.80.attention_norm.weight": "consolidated-00046-of-00051.safetensors",
722
- "layers.80.feed_forward.w1.weight": "consolidated-00046-of-00051.safetensors",
723
- "layers.80.feed_forward.w2.weight": "consolidated-00046-of-00051.safetensors",
724
- "layers.80.feed_forward.w3.weight": "consolidated-00046-of-00051.safetensors",
725
- "layers.80.ffn_norm.weight": "consolidated-00046-of-00051.safetensors",
726
- "layers.81.attention.wk.weight": "consolidated-00046-of-00051.safetensors",
727
- "layers.81.attention.wo.weight": "consolidated-00046-of-00051.safetensors",
728
- "layers.81.attention.wq.weight": "consolidated-00046-of-00051.safetensors",
729
- "layers.81.attention.wv.weight": "consolidated-00046-of-00051.safetensors",
730
- "layers.81.attention_norm.weight": "consolidated-00046-of-00051.safetensors",
731
- "layers.81.feed_forward.w1.weight": "consolidated-00046-of-00051.safetensors",
732
- "layers.81.feed_forward.w2.weight": "consolidated-00047-of-00051.safetensors",
733
- "layers.81.feed_forward.w3.weight": "consolidated-00047-of-00051.safetensors",
734
- "layers.81.ffn_norm.weight": "consolidated-00047-of-00051.safetensors",
735
- "layers.82.attention.wk.weight": "consolidated-00047-of-00051.safetensors",
736
- "layers.82.attention.wo.weight": "consolidated-00047-of-00051.safetensors",
737
- "layers.82.attention.wq.weight": "consolidated-00047-of-00051.safetensors",
738
- "layers.82.attention.wv.weight": "consolidated-00047-of-00051.safetensors",
739
- "layers.82.attention_norm.weight": "consolidated-00047-of-00051.safetensors",
740
- "layers.82.feed_forward.w1.weight": "consolidated-00047-of-00051.safetensors",
741
- "layers.82.feed_forward.w2.weight": "consolidated-00047-of-00051.safetensors",
742
- "layers.82.feed_forward.w3.weight": "consolidated-00047-of-00051.safetensors",
743
- "layers.82.ffn_norm.weight": "consolidated-00047-of-00051.safetensors",
744
- "layers.83.attention.wk.weight": "consolidated-00047-of-00051.safetensors",
745
- "layers.83.attention.wo.weight": "consolidated-00047-of-00051.safetensors",
746
- "layers.83.attention.wq.weight": "consolidated-00047-of-00051.safetensors",
747
- "layers.83.attention.wv.weight": "consolidated-00047-of-00051.safetensors",
748
- "layers.83.attention_norm.weight": "consolidated-00047-of-00051.safetensors",
749
- "layers.83.feed_forward.w1.weight": "consolidated-00048-of-00051.safetensors",
750
- "layers.83.feed_forward.w2.weight": "consolidated-00048-of-00051.safetensors",
751
- "layers.83.feed_forward.w3.weight": "consolidated-00048-of-00051.safetensors",
752
- "layers.83.ffn_norm.weight": "consolidated-00048-of-00051.safetensors",
753
- "layers.84.attention.wk.weight": "consolidated-00048-of-00051.safetensors",
754
- "layers.84.attention.wo.weight": "consolidated-00048-of-00051.safetensors",
755
- "layers.84.attention.wq.weight": "consolidated-00048-of-00051.safetensors",
756
- "layers.84.attention.wv.weight": "consolidated-00048-of-00051.safetensors",
757
- "layers.84.attention_norm.weight": "consolidated-00048-of-00051.safetensors",
758
- "layers.84.feed_forward.w1.weight": "consolidated-00048-of-00051.safetensors",
759
- "layers.84.feed_forward.w2.weight": "consolidated-00048-of-00051.safetensors",
760
- "layers.84.feed_forward.w3.weight": "consolidated-00048-of-00051.safetensors",
761
- "layers.84.ffn_norm.weight": "consolidated-00048-of-00051.safetensors",
762
- "layers.85.attention.wk.weight": "consolidated-00048-of-00051.safetensors",
763
- "layers.85.attention.wo.weight": "consolidated-00049-of-00051.safetensors",
764
- "layers.85.attention.wq.weight": "consolidated-00049-of-00051.safetensors",
765
- "layers.85.attention.wv.weight": "consolidated-00049-of-00051.safetensors",
766
- "layers.85.attention_norm.weight": "consolidated-00049-of-00051.safetensors",
767
- "layers.85.feed_forward.w1.weight": "consolidated-00049-of-00051.safetensors",
768
- "layers.85.feed_forward.w2.weight": "consolidated-00049-of-00051.safetensors",
769
- "layers.85.feed_forward.w3.weight": "consolidated-00049-of-00051.safetensors",
770
- "layers.85.ffn_norm.weight": "consolidated-00049-of-00051.safetensors",
771
- "layers.86.attention.wk.weight": "consolidated-00049-of-00051.safetensors",
772
- "layers.86.attention.wo.weight": "consolidated-00049-of-00051.safetensors",
773
- "layers.86.attention.wq.weight": "consolidated-00049-of-00051.safetensors",
774
- "layers.86.attention.wv.weight": "consolidated-00049-of-00051.safetensors",
775
- "layers.86.attention_norm.weight": "consolidated-00049-of-00051.safetensors",
776
- "layers.86.feed_forward.w1.weight": "consolidated-00049-of-00051.safetensors",
777
- "layers.86.feed_forward.w2.weight": "consolidated-00049-of-00051.safetensors",
778
- "layers.86.feed_forward.w3.weight": "consolidated-00050-of-00051.safetensors",
779
- "layers.86.ffn_norm.weight": "consolidated-00050-of-00051.safetensors",
780
- "layers.87.attention.wk.weight": "consolidated-00050-of-00051.safetensors",
781
- "layers.87.attention.wo.weight": "consolidated-00050-of-00051.safetensors",
782
- "layers.87.attention.wq.weight": "consolidated-00050-of-00051.safetensors",
783
- "layers.87.attention.wv.weight": "consolidated-00050-of-00051.safetensors",
784
- "layers.87.attention_norm.weight": "consolidated-00050-of-00051.safetensors",
785
- "layers.87.feed_forward.w1.weight": "consolidated-00050-of-00051.safetensors",
786
- "layers.87.feed_forward.w2.weight": "consolidated-00050-of-00051.safetensors",
787
- "layers.87.feed_forward.w3.weight": "consolidated-00050-of-00051.safetensors",
788
- "layers.87.ffn_norm.weight": "consolidated-00050-of-00051.safetensors",
789
- "layers.9.attention.wk.weight": "consolidated-00050-of-00051.safetensors",
790
- "layers.9.attention.wo.weight": "consolidated-00050-of-00051.safetensors",
791
- "layers.9.attention.wq.weight": "consolidated-00050-of-00051.safetensors",
792
- "layers.9.attention.wv.weight": "consolidated-00050-of-00051.safetensors",
793
- "layers.9.attention_norm.weight": "consolidated-00050-of-00051.safetensors",
794
- "layers.9.feed_forward.w1.weight": "consolidated-00050-of-00051.safetensors",
795
- "layers.9.feed_forward.w2.weight": "consolidated-00051-of-00051.safetensors",
796
- "layers.9.feed_forward.w3.weight": "consolidated-00051-of-00051.safetensors",
797
- "layers.9.ffn_norm.weight": "consolidated-00051-of-00051.safetensors",
798
- "norm.weight": "consolidated-00051-of-00051.safetensors",
799
- "output.weight": "consolidated-00051-of-00051.safetensors",
800
- "tok_embeddings.weight": "consolidated-00051-of-00051.safetensors"
801
- }
802
- }