liuxz0801 commited on
Commit
9ce90c1
1 Parent(s): 2957bd9

Upload 5 files

Browse files
pytorch_model.bin.index.json CHANGED
@@ -1,390 +1 @@
1
- {
2
- "metadata": {
3
- "total_size": 24772864000
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "pytorch_model_00041-of-00041.bin",
7
- "transformer.h.0.input_layernorm.weight": "pytorch_model_00002-of-00041.bin",
8
- "transformer.h.0.mlp.down_proj.bias": "pytorch_model_00002-of-00041.bin",
9
- "transformer.h.0.mlp.down_proj.weight": "pytorch_model_00002-of-00041.bin",
10
- "transformer.h.0.mlp.gate_proj.weight": "pytorch_model_00002-of-00041.bin",
11
- "transformer.h.0.mlp.up_proj.weight": "pytorch_model_00002-of-00041.bin",
12
- "transformer.h.0.post_attention_layernorm.weight": "pytorch_model_00002-of-00041.bin",
13
- "transformer.h.0.self_attention.dense.bias": "pytorch_model_00002-of-00041.bin",
14
- "transformer.h.0.self_attention.dense.weight": "pytorch_model_00002-of-00041.bin",
15
- "transformer.h.0.self_attention.key_value.weight": "pytorch_model_00002-of-00041.bin",
16
- "transformer.h.0.self_attention.query.weight": "pytorch_model_00002-of-00041.bin",
17
- "transformer.h.1.input_layernorm.weight": "pytorch_model_00003-of-00041.bin",
18
- "transformer.h.1.mlp.down_proj.bias": "pytorch_model_00003-of-00041.bin",
19
- "transformer.h.1.mlp.down_proj.weight": "pytorch_model_00003-of-00041.bin",
20
- "transformer.h.1.mlp.gate_proj.weight": "pytorch_model_00003-of-00041.bin",
21
- "transformer.h.1.mlp.up_proj.weight": "pytorch_model_00003-of-00041.bin",
22
- "transformer.h.1.post_attention_layernorm.weight": "pytorch_model_00003-of-00041.bin",
23
- "transformer.h.1.self_attention.dense.bias": "pytorch_model_00003-of-00041.bin",
24
- "transformer.h.1.self_attention.dense.weight": "pytorch_model_00003-of-00041.bin",
25
- "transformer.h.1.self_attention.key_value.weight": "pytorch_model_00003-of-00041.bin",
26
- "transformer.h.1.self_attention.query.weight": "pytorch_model_00003-of-00041.bin",
27
- "transformer.h.10.input_layernorm.weight": "pytorch_model_00012-of-00041.bin",
28
- "transformer.h.10.mlp.down_proj.bias": "pytorch_model_00012-of-00041.bin",
29
- "transformer.h.10.mlp.down_proj.weight": "pytorch_model_00012-of-00041.bin",
30
- "transformer.h.10.mlp.gate_proj.weight": "pytorch_model_00012-of-00041.bin",
31
- "transformer.h.10.mlp.up_proj.weight": "pytorch_model_00012-of-00041.bin",
32
- "transformer.h.10.post_attention_layernorm.weight": "pytorch_model_00012-of-00041.bin",
33
- "transformer.h.10.self_attention.dense.bias": "pytorch_model_00012-of-00041.bin",
34
- "transformer.h.10.self_attention.dense.weight": "pytorch_model_00012-of-00041.bin",
35
- "transformer.h.10.self_attention.key_value.weight": "pytorch_model_00012-of-00041.bin",
36
- "transformer.h.10.self_attention.query.weight": "pytorch_model_00012-of-00041.bin",
37
- "transformer.h.11.input_layernorm.weight": "pytorch_model_00013-of-00041.bin",
38
- "transformer.h.11.mlp.down_proj.bias": "pytorch_model_00013-of-00041.bin",
39
- "transformer.h.11.mlp.down_proj.weight": "pytorch_model_00013-of-00041.bin",
40
- "transformer.h.11.mlp.gate_proj.weight": "pytorch_model_00013-of-00041.bin",
41
- "transformer.h.11.mlp.up_proj.weight": "pytorch_model_00013-of-00041.bin",
42
- "transformer.h.11.post_attention_layernorm.weight": "pytorch_model_00013-of-00041.bin",
43
- "transformer.h.11.self_attention.dense.bias": "pytorch_model_00013-of-00041.bin",
44
- "transformer.h.11.self_attention.dense.weight": "pytorch_model_00013-of-00041.bin",
45
- "transformer.h.11.self_attention.key_value.weight": "pytorch_model_00013-of-00041.bin",
46
- "transformer.h.11.self_attention.query.weight": "pytorch_model_00013-of-00041.bin",
47
- "transformer.h.12.input_layernorm.weight": "pytorch_model_00014-of-00041.bin",
48
- "transformer.h.12.mlp.down_proj.bias": "pytorch_model_00014-of-00041.bin",
49
- "transformer.h.12.mlp.down_proj.weight": "pytorch_model_00014-of-00041.bin",
50
- "transformer.h.12.mlp.gate_proj.weight": "pytorch_model_00014-of-00041.bin",
51
- "transformer.h.12.mlp.up_proj.weight": "pytorch_model_00014-of-00041.bin",
52
- "transformer.h.12.post_attention_layernorm.weight": "pytorch_model_00014-of-00041.bin",
53
- "transformer.h.12.self_attention.dense.bias": "pytorch_model_00014-of-00041.bin",
54
- "transformer.h.12.self_attention.dense.weight": "pytorch_model_00014-of-00041.bin",
55
- "transformer.h.12.self_attention.key_value.weight": "pytorch_model_00014-of-00041.bin",
56
- "transformer.h.12.self_attention.query.weight": "pytorch_model_00014-of-00041.bin",
57
- "transformer.h.13.input_layernorm.weight": "pytorch_model_00015-of-00041.bin",
58
- "transformer.h.13.mlp.down_proj.bias": "pytorch_model_00015-of-00041.bin",
59
- "transformer.h.13.mlp.down_proj.weight": "pytorch_model_00015-of-00041.bin",
60
- "transformer.h.13.mlp.gate_proj.weight": "pytorch_model_00015-of-00041.bin",
61
- "transformer.h.13.mlp.up_proj.weight": "pytorch_model_00015-of-00041.bin",
62
- "transformer.h.13.post_attention_layernorm.weight": "pytorch_model_00015-of-00041.bin",
63
- "transformer.h.13.self_attention.dense.bias": "pytorch_model_00015-of-00041.bin",
64
- "transformer.h.13.self_attention.dense.weight": "pytorch_model_00015-of-00041.bin",
65
- "transformer.h.13.self_attention.key_value.weight": "pytorch_model_00015-of-00041.bin",
66
- "transformer.h.13.self_attention.query.weight": "pytorch_model_00015-of-00041.bin",
67
- "transformer.h.14.input_layernorm.weight": "pytorch_model_00016-of-00041.bin",
68
- "transformer.h.14.mlp.down_proj.bias": "pytorch_model_00016-of-00041.bin",
69
- "transformer.h.14.mlp.down_proj.weight": "pytorch_model_00016-of-00041.bin",
70
- "transformer.h.14.mlp.gate_proj.weight": "pytorch_model_00016-of-00041.bin",
71
- "transformer.h.14.mlp.up_proj.weight": "pytorch_model_00016-of-00041.bin",
72
- "transformer.h.14.post_attention_layernorm.weight": "pytorch_model_00016-of-00041.bin",
73
- "transformer.h.14.self_attention.dense.bias": "pytorch_model_00016-of-00041.bin",
74
- "transformer.h.14.self_attention.dense.weight": "pytorch_model_00016-of-00041.bin",
75
- "transformer.h.14.self_attention.key_value.weight": "pytorch_model_00016-of-00041.bin",
76
- "transformer.h.14.self_attention.query.weight": "pytorch_model_00016-of-00041.bin",
77
- "transformer.h.15.input_layernorm.weight": "pytorch_model_00017-of-00041.bin",
78
- "transformer.h.15.mlp.down_proj.bias": "pytorch_model_00017-of-00041.bin",
79
- "transformer.h.15.mlp.down_proj.weight": "pytorch_model_00017-of-00041.bin",
80
- "transformer.h.15.mlp.gate_proj.weight": "pytorch_model_00017-of-00041.bin",
81
- "transformer.h.15.mlp.up_proj.weight": "pytorch_model_00017-of-00041.bin",
82
- "transformer.h.15.post_attention_layernorm.weight": "pytorch_model_00017-of-00041.bin",
83
- "transformer.h.15.self_attention.dense.bias": "pytorch_model_00017-of-00041.bin",
84
- "transformer.h.15.self_attention.dense.weight": "pytorch_model_00017-of-00041.bin",
85
- "transformer.h.15.self_attention.key_value.weight": "pytorch_model_00017-of-00041.bin",
86
- "transformer.h.15.self_attention.query.weight": "pytorch_model_00017-of-00041.bin",
87
- "transformer.h.16.input_layernorm.weight": "pytorch_model_00018-of-00041.bin",
88
- "transformer.h.16.mlp.down_proj.bias": "pytorch_model_00018-of-00041.bin",
89
- "transformer.h.16.mlp.down_proj.weight": "pytorch_model_00018-of-00041.bin",
90
- "transformer.h.16.mlp.gate_proj.weight": "pytorch_model_00018-of-00041.bin",
91
- "transformer.h.16.mlp.up_proj.weight": "pytorch_model_00018-of-00041.bin",
92
- "transformer.h.16.post_attention_layernorm.weight": "pytorch_model_00018-of-00041.bin",
93
- "transformer.h.16.self_attention.dense.bias": "pytorch_model_00018-of-00041.bin",
94
- "transformer.h.16.self_attention.dense.weight": "pytorch_model_00018-of-00041.bin",
95
- "transformer.h.16.self_attention.key_value.weight": "pytorch_model_00018-of-00041.bin",
96
- "transformer.h.16.self_attention.query.weight": "pytorch_model_00018-of-00041.bin",
97
- "transformer.h.17.input_layernorm.weight": "pytorch_model_00019-of-00041.bin",
98
- "transformer.h.17.mlp.down_proj.bias": "pytorch_model_00019-of-00041.bin",
99
- "transformer.h.17.mlp.down_proj.weight": "pytorch_model_00019-of-00041.bin",
100
- "transformer.h.17.mlp.gate_proj.weight": "pytorch_model_00019-of-00041.bin",
101
- "transformer.h.17.mlp.up_proj.weight": "pytorch_model_00019-of-00041.bin",
102
- "transformer.h.17.post_attention_layernorm.weight": "pytorch_model_00019-of-00041.bin",
103
- "transformer.h.17.self_attention.dense.bias": "pytorch_model_00019-of-00041.bin",
104
- "transformer.h.17.self_attention.dense.weight": "pytorch_model_00019-of-00041.bin",
105
- "transformer.h.17.self_attention.key_value.weight": "pytorch_model_00019-of-00041.bin",
106
- "transformer.h.17.self_attention.query.weight": "pytorch_model_00019-of-00041.bin",
107
- "transformer.h.18.input_layernorm.weight": "pytorch_model_00020-of-00041.bin",
108
- "transformer.h.18.mlp.down_proj.bias": "pytorch_model_00020-of-00041.bin",
109
- "transformer.h.18.mlp.down_proj.weight": "pytorch_model_00020-of-00041.bin",
110
- "transformer.h.18.mlp.gate_proj.weight": "pytorch_model_00020-of-00041.bin",
111
- "transformer.h.18.mlp.up_proj.weight": "pytorch_model_00020-of-00041.bin",
112
- "transformer.h.18.post_attention_layernorm.weight": "pytorch_model_00020-of-00041.bin",
113
- "transformer.h.18.self_attention.dense.bias": "pytorch_model_00020-of-00041.bin",
114
- "transformer.h.18.self_attention.dense.weight": "pytorch_model_00020-of-00041.bin",
115
- "transformer.h.18.self_attention.key_value.weight": "pytorch_model_00020-of-00041.bin",
116
- "transformer.h.18.self_attention.query.weight": "pytorch_model_00020-of-00041.bin",
117
- "transformer.h.19.input_layernorm.weight": "pytorch_model_00021-of-00041.bin",
118
- "transformer.h.19.mlp.down_proj.bias": "pytorch_model_00021-of-00041.bin",
119
- "transformer.h.19.mlp.down_proj.weight": "pytorch_model_00021-of-00041.bin",
120
- "transformer.h.19.mlp.gate_proj.weight": "pytorch_model_00021-of-00041.bin",
121
- "transformer.h.19.mlp.up_proj.weight": "pytorch_model_00021-of-00041.bin",
122
- "transformer.h.19.post_attention_layernorm.weight": "pytorch_model_00021-of-00041.bin",
123
- "transformer.h.19.self_attention.dense.bias": "pytorch_model_00021-of-00041.bin",
124
- "transformer.h.19.self_attention.dense.weight": "pytorch_model_00021-of-00041.bin",
125
- "transformer.h.19.self_attention.key_value.weight": "pytorch_model_00021-of-00041.bin",
126
- "transformer.h.19.self_attention.query.weight": "pytorch_model_00021-of-00041.bin",
127
- "transformer.h.2.input_layernorm.weight": "pytorch_model_00004-of-00041.bin",
128
- "transformer.h.2.mlp.down_proj.bias": "pytorch_model_00004-of-00041.bin",
129
- "transformer.h.2.mlp.down_proj.weight": "pytorch_model_00004-of-00041.bin",
130
- "transformer.h.2.mlp.gate_proj.weight": "pytorch_model_00004-of-00041.bin",
131
- "transformer.h.2.mlp.up_proj.weight": "pytorch_model_00004-of-00041.bin",
132
- "transformer.h.2.post_attention_layernorm.weight": "pytorch_model_00004-of-00041.bin",
133
- "transformer.h.2.self_attention.dense.bias": "pytorch_model_00004-of-00041.bin",
134
- "transformer.h.2.self_attention.dense.weight": "pytorch_model_00004-of-00041.bin",
135
- "transformer.h.2.self_attention.key_value.weight": "pytorch_model_00004-of-00041.bin",
136
- "transformer.h.2.self_attention.query.weight": "pytorch_model_00004-of-00041.bin",
137
- "transformer.h.20.input_layernorm.weight": "pytorch_model_00022-of-00041.bin",
138
- "transformer.h.20.mlp.down_proj.bias": "pytorch_model_00022-of-00041.bin",
139
- "transformer.h.20.mlp.down_proj.weight": "pytorch_model_00022-of-00041.bin",
140
- "transformer.h.20.mlp.gate_proj.weight": "pytorch_model_00022-of-00041.bin",
141
- "transformer.h.20.mlp.up_proj.weight": "pytorch_model_00022-of-00041.bin",
142
- "transformer.h.20.post_attention_layernorm.weight": "pytorch_model_00022-of-00041.bin",
143
- "transformer.h.20.self_attention.dense.bias": "pytorch_model_00022-of-00041.bin",
144
- "transformer.h.20.self_attention.dense.weight": "pytorch_model_00022-of-00041.bin",
145
- "transformer.h.20.self_attention.key_value.weight": "pytorch_model_00022-of-00041.bin",
146
- "transformer.h.20.self_attention.query.weight": "pytorch_model_00022-of-00041.bin",
147
- "transformer.h.21.input_layernorm.weight": "pytorch_model_00023-of-00041.bin",
148
- "transformer.h.21.mlp.down_proj.bias": "pytorch_model_00023-of-00041.bin",
149
- "transformer.h.21.mlp.down_proj.weight": "pytorch_model_00023-of-00041.bin",
150
- "transformer.h.21.mlp.gate_proj.weight": "pytorch_model_00023-of-00041.bin",
151
- "transformer.h.21.mlp.up_proj.weight": "pytorch_model_00023-of-00041.bin",
152
- "transformer.h.21.post_attention_layernorm.weight": "pytorch_model_00023-of-00041.bin",
153
- "transformer.h.21.self_attention.dense.bias": "pytorch_model_00023-of-00041.bin",
154
- "transformer.h.21.self_attention.dense.weight": "pytorch_model_00023-of-00041.bin",
155
- "transformer.h.21.self_attention.key_value.weight": "pytorch_model_00023-of-00041.bin",
156
- "transformer.h.21.self_attention.query.weight": "pytorch_model_00023-of-00041.bin",
157
- "transformer.h.22.input_layernorm.weight": "pytorch_model_00024-of-00041.bin",
158
- "transformer.h.22.mlp.down_proj.bias": "pytorch_model_00024-of-00041.bin",
159
- "transformer.h.22.mlp.down_proj.weight": "pytorch_model_00024-of-00041.bin",
160
- "transformer.h.22.mlp.gate_proj.weight": "pytorch_model_00024-of-00041.bin",
161
- "transformer.h.22.mlp.up_proj.weight": "pytorch_model_00024-of-00041.bin",
162
- "transformer.h.22.post_attention_layernorm.weight": "pytorch_model_00024-of-00041.bin",
163
- "transformer.h.22.self_attention.dense.bias": "pytorch_model_00024-of-00041.bin",
164
- "transformer.h.22.self_attention.dense.weight": "pytorch_model_00024-of-00041.bin",
165
- "transformer.h.22.self_attention.key_value.weight": "pytorch_model_00024-of-00041.bin",
166
- "transformer.h.22.self_attention.query.weight": "pytorch_model_00024-of-00041.bin",
167
- "transformer.h.23.input_layernorm.weight": "pytorch_model_00025-of-00041.bin",
168
- "transformer.h.23.mlp.down_proj.bias": "pytorch_model_00025-of-00041.bin",
169
- "transformer.h.23.mlp.down_proj.weight": "pytorch_model_00025-of-00041.bin",
170
- "transformer.h.23.mlp.gate_proj.weight": "pytorch_model_00025-of-00041.bin",
171
- "transformer.h.23.mlp.up_proj.weight": "pytorch_model_00025-of-00041.bin",
172
- "transformer.h.23.post_attention_layernorm.weight": "pytorch_model_00025-of-00041.bin",
173
- "transformer.h.23.self_attention.dense.bias": "pytorch_model_00025-of-00041.bin",
174
- "transformer.h.23.self_attention.dense.weight": "pytorch_model_00025-of-00041.bin",
175
- "transformer.h.23.self_attention.key_value.weight": "pytorch_model_00025-of-00041.bin",
176
- "transformer.h.23.self_attention.query.weight": "pytorch_model_00025-of-00041.bin",
177
- "transformer.h.24.input_layernorm.weight": "pytorch_model_00026-of-00041.bin",
178
- "transformer.h.24.mlp.down_proj.bias": "pytorch_model_00026-of-00041.bin",
179
- "transformer.h.24.mlp.down_proj.weight": "pytorch_model_00026-of-00041.bin",
180
- "transformer.h.24.mlp.gate_proj.weight": "pytorch_model_00026-of-00041.bin",
181
- "transformer.h.24.mlp.up_proj.weight": "pytorch_model_00026-of-00041.bin",
182
- "transformer.h.24.post_attention_layernorm.weight": "pytorch_model_00026-of-00041.bin",
183
- "transformer.h.24.self_attention.dense.bias": "pytorch_model_00026-of-00041.bin",
184
- "transformer.h.24.self_attention.dense.weight": "pytorch_model_00026-of-00041.bin",
185
- "transformer.h.24.self_attention.key_value.weight": "pytorch_model_00026-of-00041.bin",
186
- "transformer.h.24.self_attention.query.weight": "pytorch_model_00026-of-00041.bin",
187
- "transformer.h.25.input_layernorm.weight": "pytorch_model_00027-of-00041.bin",
188
- "transformer.h.25.mlp.down_proj.bias": "pytorch_model_00027-of-00041.bin",
189
- "transformer.h.25.mlp.down_proj.weight": "pytorch_model_00027-of-00041.bin",
190
- "transformer.h.25.mlp.gate_proj.weight": "pytorch_model_00027-of-00041.bin",
191
- "transformer.h.25.mlp.up_proj.weight": "pytorch_model_00027-of-00041.bin",
192
- "transformer.h.25.post_attention_layernorm.weight": "pytorch_model_00027-of-00041.bin",
193
- "transformer.h.25.self_attention.dense.bias": "pytorch_model_00027-of-00041.bin",
194
- "transformer.h.25.self_attention.dense.weight": "pytorch_model_00027-of-00041.bin",
195
- "transformer.h.25.self_attention.key_value.weight": "pytorch_model_00027-of-00041.bin",
196
- "transformer.h.25.self_attention.query.weight": "pytorch_model_00027-of-00041.bin",
197
- "transformer.h.26.input_layernorm.weight": "pytorch_model_00028-of-00041.bin",
198
- "transformer.h.26.mlp.down_proj.bias": "pytorch_model_00028-of-00041.bin",
199
- "transformer.h.26.mlp.down_proj.weight": "pytorch_model_00028-of-00041.bin",
200
- "transformer.h.26.mlp.gate_proj.weight": "pytorch_model_00028-of-00041.bin",
201
- "transformer.h.26.mlp.up_proj.weight": "pytorch_model_00028-of-00041.bin",
202
- "transformer.h.26.post_attention_layernorm.weight": "pytorch_model_00028-of-00041.bin",
203
- "transformer.h.26.self_attention.dense.bias": "pytorch_model_00028-of-00041.bin",
204
- "transformer.h.26.self_attention.dense.weight": "pytorch_model_00028-of-00041.bin",
205
- "transformer.h.26.self_attention.key_value.weight": "pytorch_model_00028-of-00041.bin",
206
- "transformer.h.26.self_attention.query.weight": "pytorch_model_00028-of-00041.bin",
207
- "transformer.h.27.input_layernorm.weight": "pytorch_model_00029-of-00041.bin",
208
- "transformer.h.27.mlp.down_proj.bias": "pytorch_model_00029-of-00041.bin",
209
- "transformer.h.27.mlp.down_proj.weight": "pytorch_model_00029-of-00041.bin",
210
- "transformer.h.27.mlp.gate_proj.weight": "pytorch_model_00029-of-00041.bin",
211
- "transformer.h.27.mlp.up_proj.weight": "pytorch_model_00029-of-00041.bin",
212
- "transformer.h.27.post_attention_layernorm.weight": "pytorch_model_00029-of-00041.bin",
213
- "transformer.h.27.self_attention.dense.bias": "pytorch_model_00029-of-00041.bin",
214
- "transformer.h.27.self_attention.dense.weight": "pytorch_model_00029-of-00041.bin",
215
- "transformer.h.27.self_attention.key_value.weight": "pytorch_model_00029-of-00041.bin",
216
- "transformer.h.27.self_attention.query.weight": "pytorch_model_00029-of-00041.bin",
217
- "transformer.h.28.input_layernorm.weight": "pytorch_model_00030-of-00041.bin",
218
- "transformer.h.28.mlp.down_proj.bias": "pytorch_model_00030-of-00041.bin",
219
- "transformer.h.28.mlp.down_proj.weight": "pytorch_model_00030-of-00041.bin",
220
- "transformer.h.28.mlp.gate_proj.weight": "pytorch_model_00030-of-00041.bin",
221
- "transformer.h.28.mlp.up_proj.weight": "pytorch_model_00030-of-00041.bin",
222
- "transformer.h.28.post_attention_layernorm.weight": "pytorch_model_00030-of-00041.bin",
223
- "transformer.h.28.self_attention.dense.bias": "pytorch_model_00030-of-00041.bin",
224
- "transformer.h.28.self_attention.dense.weight": "pytorch_model_00030-of-00041.bin",
225
- "transformer.h.28.self_attention.key_value.weight": "pytorch_model_00030-of-00041.bin",
226
- "transformer.h.28.self_attention.query.weight": "pytorch_model_00030-of-00041.bin",
227
- "transformer.h.29.input_layernorm.weight": "pytorch_model_00031-of-00041.bin",
228
- "transformer.h.29.mlp.down_proj.bias": "pytorch_model_00031-of-00041.bin",
229
- "transformer.h.29.mlp.down_proj.weight": "pytorch_model_00031-of-00041.bin",
230
- "transformer.h.29.mlp.gate_proj.weight": "pytorch_model_00031-of-00041.bin",
231
- "transformer.h.29.mlp.up_proj.weight": "pytorch_model_00031-of-00041.bin",
232
- "transformer.h.29.post_attention_layernorm.weight": "pytorch_model_00031-of-00041.bin",
233
- "transformer.h.29.self_attention.dense.bias": "pytorch_model_00031-of-00041.bin",
234
- "transformer.h.29.self_attention.dense.weight": "pytorch_model_00031-of-00041.bin",
235
- "transformer.h.29.self_attention.key_value.weight": "pytorch_model_00031-of-00041.bin",
236
- "transformer.h.29.self_attention.query.weight": "pytorch_model_00031-of-00041.bin",
237
- "transformer.h.3.input_layernorm.weight": "pytorch_model_00005-of-00041.bin",
238
- "transformer.h.3.mlp.down_proj.bias": "pytorch_model_00005-of-00041.bin",
239
- "transformer.h.3.mlp.down_proj.weight": "pytorch_model_00005-of-00041.bin",
240
- "transformer.h.3.mlp.gate_proj.weight": "pytorch_model_00005-of-00041.bin",
241
- "transformer.h.3.mlp.up_proj.weight": "pytorch_model_00005-of-00041.bin",
242
- "transformer.h.3.post_attention_layernorm.weight": "pytorch_model_00005-of-00041.bin",
243
- "transformer.h.3.self_attention.dense.bias": "pytorch_model_00005-of-00041.bin",
244
- "transformer.h.3.self_attention.dense.weight": "pytorch_model_00005-of-00041.bin",
245
- "transformer.h.3.self_attention.key_value.weight": "pytorch_model_00005-of-00041.bin",
246
- "transformer.h.3.self_attention.query.weight": "pytorch_model_00005-of-00041.bin",
247
- "transformer.h.30.input_layernorm.weight": "pytorch_model_00032-of-00041.bin",
248
- "transformer.h.30.mlp.down_proj.bias": "pytorch_model_00032-of-00041.bin",
249
- "transformer.h.30.mlp.down_proj.weight": "pytorch_model_00032-of-00041.bin",
250
- "transformer.h.30.mlp.gate_proj.weight": "pytorch_model_00032-of-00041.bin",
251
- "transformer.h.30.mlp.up_proj.weight": "pytorch_model_00032-of-00041.bin",
252
- "transformer.h.30.post_attention_layernorm.weight": "pytorch_model_00032-of-00041.bin",
253
- "transformer.h.30.self_attention.dense.bias": "pytorch_model_00032-of-00041.bin",
254
- "transformer.h.30.self_attention.dense.weight": "pytorch_model_00032-of-00041.bin",
255
- "transformer.h.30.self_attention.key_value.weight": "pytorch_model_00032-of-00041.bin",
256
- "transformer.h.30.self_attention.query.weight": "pytorch_model_00032-of-00041.bin",
257
- "transformer.h.31.input_layernorm.weight": "pytorch_model_00033-of-00041.bin",
258
- "transformer.h.31.mlp.down_proj.bias": "pytorch_model_00033-of-00041.bin",
259
- "transformer.h.31.mlp.down_proj.weight": "pytorch_model_00033-of-00041.bin",
260
- "transformer.h.31.mlp.gate_proj.weight": "pytorch_model_00033-of-00041.bin",
261
- "transformer.h.31.mlp.up_proj.weight": "pytorch_model_00033-of-00041.bin",
262
- "transformer.h.31.post_attention_layernorm.weight": "pytorch_model_00033-of-00041.bin",
263
- "transformer.h.31.self_attention.dense.bias": "pytorch_model_00033-of-00041.bin",
264
- "transformer.h.31.self_attention.dense.weight": "pytorch_model_00033-of-00041.bin",
265
- "transformer.h.31.self_attention.key_value.weight": "pytorch_model_00033-of-00041.bin",
266
- "transformer.h.31.self_attention.query.weight": "pytorch_model_00033-of-00041.bin",
267
- "transformer.h.32.input_layernorm.weight": "pytorch_model_00034-of-00041.bin",
268
- "transformer.h.32.mlp.down_proj.bias": "pytorch_model_00034-of-00041.bin",
269
- "transformer.h.32.mlp.down_proj.weight": "pytorch_model_00034-of-00041.bin",
270
- "transformer.h.32.mlp.gate_proj.weight": "pytorch_model_00034-of-00041.bin",
271
- "transformer.h.32.mlp.up_proj.weight": "pytorch_model_00034-of-00041.bin",
272
- "transformer.h.32.post_attention_layernorm.weight": "pytorch_model_00034-of-00041.bin",
273
- "transformer.h.32.self_attention.dense.bias": "pytorch_model_00034-of-00041.bin",
274
- "transformer.h.32.self_attention.dense.weight": "pytorch_model_00034-of-00041.bin",
275
- "transformer.h.32.self_attention.key_value.weight": "pytorch_model_00034-of-00041.bin",
276
- "transformer.h.32.self_attention.query.weight": "pytorch_model_00034-of-00041.bin",
277
- "transformer.h.33.input_layernorm.weight": "pytorch_model_00035-of-00041.bin",
278
- "transformer.h.33.mlp.down_proj.bias": "pytorch_model_00035-of-00041.bin",
279
- "transformer.h.33.mlp.down_proj.weight": "pytorch_model_00035-of-00041.bin",
280
- "transformer.h.33.mlp.gate_proj.weight": "pytorch_model_00035-of-00041.bin",
281
- "transformer.h.33.mlp.up_proj.weight": "pytorch_model_00035-of-00041.bin",
282
- "transformer.h.33.post_attention_layernorm.weight": "pytorch_model_00035-of-00041.bin",
283
- "transformer.h.33.self_attention.dense.bias": "pytorch_model_00035-of-00041.bin",
284
- "transformer.h.33.self_attention.dense.weight": "pytorch_model_00035-of-00041.bin",
285
- "transformer.h.33.self_attention.key_value.weight": "pytorch_model_00035-of-00041.bin",
286
- "transformer.h.33.self_attention.query.weight": "pytorch_model_00035-of-00041.bin",
287
- "transformer.h.34.input_layernorm.weight": "pytorch_model_00036-of-00041.bin",
288
- "transformer.h.34.mlp.down_proj.bias": "pytorch_model_00036-of-00041.bin",
289
- "transformer.h.34.mlp.down_proj.weight": "pytorch_model_00036-of-00041.bin",
290
- "transformer.h.34.mlp.gate_proj.weight": "pytorch_model_00036-of-00041.bin",
291
- "transformer.h.34.mlp.up_proj.weight": "pytorch_model_00036-of-00041.bin",
292
- "transformer.h.34.post_attention_layernorm.weight": "pytorch_model_00036-of-00041.bin",
293
- "transformer.h.34.self_attention.dense.bias": "pytorch_model_00036-of-00041.bin",
294
- "transformer.h.34.self_attention.dense.weight": "pytorch_model_00036-of-00041.bin",
295
- "transformer.h.34.self_attention.key_value.weight": "pytorch_model_00036-of-00041.bin",
296
- "transformer.h.34.self_attention.query.weight": "pytorch_model_00036-of-00041.bin",
297
- "transformer.h.35.input_layernorm.weight": "pytorch_model_00037-of-00041.bin",
298
- "transformer.h.35.mlp.down_proj.bias": "pytorch_model_00037-of-00041.bin",
299
- "transformer.h.35.mlp.down_proj.weight": "pytorch_model_00037-of-00041.bin",
300
- "transformer.h.35.mlp.gate_proj.weight": "pytorch_model_00037-of-00041.bin",
301
- "transformer.h.35.mlp.up_proj.weight": "pytorch_model_00037-of-00041.bin",
302
- "transformer.h.35.post_attention_layernorm.weight": "pytorch_model_00037-of-00041.bin",
303
- "transformer.h.35.self_attention.dense.bias": "pytorch_model_00037-of-00041.bin",
304
- "transformer.h.35.self_attention.dense.weight": "pytorch_model_00037-of-00041.bin",
305
- "transformer.h.35.self_attention.key_value.weight": "pytorch_model_00037-of-00041.bin",
306
- "transformer.h.35.self_attention.query.weight": "pytorch_model_00037-of-00041.bin",
307
- "transformer.h.36.input_layernorm.weight": "pytorch_model_00038-of-00041.bin",
308
- "transformer.h.36.mlp.down_proj.bias": "pytorch_model_00038-of-00041.bin",
309
- "transformer.h.36.mlp.down_proj.weight": "pytorch_model_00038-of-00041.bin",
310
- "transformer.h.36.mlp.gate_proj.weight": "pytorch_model_00038-of-00041.bin",
311
- "transformer.h.36.mlp.up_proj.weight": "pytorch_model_00038-of-00041.bin",
312
- "transformer.h.36.post_attention_layernorm.weight": "pytorch_model_00038-of-00041.bin",
313
- "transformer.h.36.self_attention.dense.bias": "pytorch_model_00038-of-00041.bin",
314
- "transformer.h.36.self_attention.dense.weight": "pytorch_model_00038-of-00041.bin",
315
- "transformer.h.36.self_attention.key_value.weight": "pytorch_model_00038-of-00041.bin",
316
- "transformer.h.36.self_attention.query.weight": "pytorch_model_00038-of-00041.bin",
317
- "transformer.h.37.input_layernorm.weight": "pytorch_model_00039-of-00041.bin",
318
- "transformer.h.37.mlp.down_proj.bias": "pytorch_model_00039-of-00041.bin",
319
- "transformer.h.37.mlp.down_proj.weight": "pytorch_model_00039-of-00041.bin",
320
- "transformer.h.37.mlp.gate_proj.weight": "pytorch_model_00039-of-00041.bin",
321
- "transformer.h.37.mlp.up_proj.weight": "pytorch_model_00039-of-00041.bin",
322
- "transformer.h.37.post_attention_layernorm.weight": "pytorch_model_00039-of-00041.bin",
323
- "transformer.h.37.self_attention.dense.bias": "pytorch_model_00039-of-00041.bin",
324
- "transformer.h.37.self_attention.dense.weight": "pytorch_model_00039-of-00041.bin",
325
- "transformer.h.37.self_attention.key_value.weight": "pytorch_model_00039-of-00041.bin",
326
- "transformer.h.37.self_attention.query.weight": "pytorch_model_00039-of-00041.bin",
327
- "transformer.h.4.input_layernorm.weight": "pytorch_model_00006-of-00041.bin",
328
- "transformer.h.4.mlp.down_proj.bias": "pytorch_model_00006-of-00041.bin",
329
- "transformer.h.4.mlp.down_proj.weight": "pytorch_model_00006-of-00041.bin",
330
- "transformer.h.4.mlp.gate_proj.weight": "pytorch_model_00006-of-00041.bin",
331
- "transformer.h.4.mlp.up_proj.weight": "pytorch_model_00006-of-00041.bin",
332
- "transformer.h.4.post_attention_layernorm.weight": "pytorch_model_00006-of-00041.bin",
333
- "transformer.h.4.self_attention.dense.bias": "pytorch_model_00006-of-00041.bin",
334
- "transformer.h.4.self_attention.dense.weight": "pytorch_model_00006-of-00041.bin",
335
- "transformer.h.4.self_attention.key_value.weight": "pytorch_model_00006-of-00041.bin",
336
- "transformer.h.4.self_attention.query.weight": "pytorch_model_00006-of-00041.bin",
337
- "transformer.h.5.input_layernorm.weight": "pytorch_model_00007-of-00041.bin",
338
- "transformer.h.5.mlp.down_proj.bias": "pytorch_model_00007-of-00041.bin",
339
- "transformer.h.5.mlp.down_proj.weight": "pytorch_model_00007-of-00041.bin",
340
- "transformer.h.5.mlp.gate_proj.weight": "pytorch_model_00007-of-00041.bin",
341
- "transformer.h.5.mlp.up_proj.weight": "pytorch_model_00007-of-00041.bin",
342
- "transformer.h.5.post_attention_layernorm.weight": "pytorch_model_00007-of-00041.bin",
343
- "transformer.h.5.self_attention.dense.bias": "pytorch_model_00007-of-00041.bin",
344
- "transformer.h.5.self_attention.dense.weight": "pytorch_model_00007-of-00041.bin",
345
- "transformer.h.5.self_attention.key_value.weight": "pytorch_model_00007-of-00041.bin",
346
- "transformer.h.5.self_attention.query.weight": "pytorch_model_00007-of-00041.bin",
347
- "transformer.h.6.input_layernorm.weight": "pytorch_model_00008-of-00041.bin",
348
- "transformer.h.6.mlp.down_proj.bias": "pytorch_model_00008-of-00041.bin",
349
- "transformer.h.6.mlp.down_proj.weight": "pytorch_model_00008-of-00041.bin",
350
- "transformer.h.6.mlp.gate_proj.weight": "pytorch_model_00008-of-00041.bin",
351
- "transformer.h.6.mlp.up_proj.weight": "pytorch_model_00008-of-00041.bin",
352
- "transformer.h.6.post_attention_layernorm.weight": "pytorch_model_00008-of-00041.bin",
353
- "transformer.h.6.self_attention.dense.bias": "pytorch_model_00008-of-00041.bin",
354
- "transformer.h.6.self_attention.dense.weight": "pytorch_model_00008-of-00041.bin",
355
- "transformer.h.6.self_attention.key_value.weight": "pytorch_model_00008-of-00041.bin",
356
- "transformer.h.6.self_attention.query.weight": "pytorch_model_00008-of-00041.bin",
357
- "transformer.h.7.input_layernorm.weight": "pytorch_model_00009-of-00041.bin",
358
- "transformer.h.7.mlp.down_proj.bias": "pytorch_model_00009-of-00041.bin",
359
- "transformer.h.7.mlp.down_proj.weight": "pytorch_model_00009-of-00041.bin",
360
- "transformer.h.7.mlp.gate_proj.weight": "pytorch_model_00009-of-00041.bin",
361
- "transformer.h.7.mlp.up_proj.weight": "pytorch_model_00009-of-00041.bin",
362
- "transformer.h.7.post_attention_layernorm.weight": "pytorch_model_00009-of-00041.bin",
363
- "transformer.h.7.self_attention.dense.bias": "pytorch_model_00009-of-00041.bin",
364
- "transformer.h.7.self_attention.dense.weight": "pytorch_model_00009-of-00041.bin",
365
- "transformer.h.7.self_attention.key_value.weight": "pytorch_model_00009-of-00041.bin",
366
- "transformer.h.7.self_attention.query.weight": "pytorch_model_00009-of-00041.bin",
367
- "transformer.h.8.input_layernorm.weight": "pytorch_model_00010-of-00041.bin",
368
- "transformer.h.8.mlp.down_proj.bias": "pytorch_model_00010-of-00041.bin",
369
- "transformer.h.8.mlp.down_proj.weight": "pytorch_model_00010-of-00041.bin",
370
- "transformer.h.8.mlp.gate_proj.weight": "pytorch_model_00010-of-00041.bin",
371
- "transformer.h.8.mlp.up_proj.weight": "pytorch_model_00010-of-00041.bin",
372
- "transformer.h.8.post_attention_layernorm.weight": "pytorch_model_00010-of-00041.bin",
373
- "transformer.h.8.self_attention.dense.bias": "pytorch_model_00010-of-00041.bin",
374
- "transformer.h.8.self_attention.dense.weight": "pytorch_model_00010-of-00041.bin",
375
- "transformer.h.8.self_attention.key_value.weight": "pytorch_model_00010-of-00041.bin",
376
- "transformer.h.8.self_attention.query.weight": "pytorch_model_00010-of-00041.bin",
377
- "transformer.h.9.input_layernorm.weight": "pytorch_model_00011-of-00041.bin",
378
- "transformer.h.9.mlp.down_proj.bias": "pytorch_model_00011-of-00041.bin",
379
- "transformer.h.9.mlp.down_proj.weight": "pytorch_model_00011-of-00041.bin",
380
- "transformer.h.9.mlp.gate_proj.weight": "pytorch_model_00011-of-00041.bin",
381
- "transformer.h.9.mlp.up_proj.weight": "pytorch_model_00011-of-00041.bin",
382
- "transformer.h.9.post_attention_layernorm.weight": "pytorch_model_00011-of-00041.bin",
383
- "transformer.h.9.self_attention.dense.bias": "pytorch_model_00011-of-00041.bin",
384
- "transformer.h.9.self_attention.dense.weight": "pytorch_model_00011-of-00041.bin",
385
- "transformer.h.9.self_attention.key_value.weight": "pytorch_model_00011-of-00041.bin",
386
- "transformer.h.9.self_attention.query.weight": "pytorch_model_00011-of-00041.bin",
387
- "transformer.ln_f.weight": "pytorch_model_00040-of-00041.bin",
388
- "transformer.word_embeddings.weight": "pytorch_model_00001-of-00041.bin"
389
- }
390
- }
 
1
+ {"metadata": {"total_size": 24772864000}, "weight_map": {"lm_head.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.0.input_layernorm.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.0.mlp.down_proj.bias": "pytorch_model_00001-of-00004.bin", "transformer.h.0.mlp.down_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.0.mlp.gate_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.0.mlp.up_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.0.post_attention_layernorm.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.0.self_attention.dense.bias": "pytorch_model_00001-of-00004.bin", "transformer.h.0.self_attention.dense.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.0.self_attention.key_value.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.0.self_attention.query.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.1.input_layernorm.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.1.mlp.down_proj.bias": "pytorch_model_00001-of-00004.bin", "transformer.h.1.mlp.down_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.1.mlp.gate_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.1.mlp.up_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.1.post_attention_layernorm.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.1.self_attention.dense.bias": "pytorch_model_00001-of-00004.bin", "transformer.h.1.self_attention.dense.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.1.self_attention.key_value.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.1.self_attention.query.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.10.input_layernorm.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.10.mlp.down_proj.bias": "pytorch_model_00002-of-00004.bin", "transformer.h.10.mlp.down_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.10.mlp.gate_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.10.mlp.up_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.10.post_attention_layernorm.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.10.self_attention.dense.bias": "pytorch_model_00002-of-00004.bin", "transformer.h.10.self_attention.dense.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.10.self_attention.key_value.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.10.self_attention.query.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.11.input_layernorm.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.11.mlp.down_proj.bias": "pytorch_model_00002-of-00004.bin", "transformer.h.11.mlp.down_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.11.mlp.gate_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.11.mlp.up_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.11.post_attention_layernorm.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.11.self_attention.dense.bias": "pytorch_model_00002-of-00004.bin", "transformer.h.11.self_attention.dense.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.11.self_attention.key_value.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.11.self_attention.query.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.12.input_layernorm.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.12.mlp.down_proj.bias": "pytorch_model_00002-of-00004.bin", "transformer.h.12.mlp.down_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.12.mlp.gate_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.12.mlp.up_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.12.post_attention_layernorm.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.12.self_attention.dense.bias": "pytorch_model_00002-of-00004.bin", "transformer.h.12.self_attention.dense.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.12.self_attention.key_value.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.12.self_attention.query.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.13.input_layernorm.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.13.mlp.down_proj.bias": "pytorch_model_00002-of-00004.bin", "transformer.h.13.mlp.down_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.13.mlp.gate_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.13.mlp.up_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.13.post_attention_layernorm.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.13.self_attention.dense.bias": "pytorch_model_00002-of-00004.bin", "transformer.h.13.self_attention.dense.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.13.self_attention.key_value.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.13.self_attention.query.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.14.input_layernorm.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.14.mlp.down_proj.bias": "pytorch_model_00002-of-00004.bin", "transformer.h.14.mlp.down_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.14.mlp.gate_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.14.mlp.up_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.14.post_attention_layernorm.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.14.self_attention.dense.bias": "pytorch_model_00002-of-00004.bin", "transformer.h.14.self_attention.dense.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.14.self_attention.key_value.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.14.self_attention.query.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.15.input_layernorm.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.15.mlp.down_proj.bias": "pytorch_model_00002-of-00004.bin", "transformer.h.15.mlp.down_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.15.mlp.gate_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.15.mlp.up_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.15.post_attention_layernorm.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.15.self_attention.dense.bias": "pytorch_model_00002-of-00004.bin", "transformer.h.15.self_attention.dense.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.15.self_attention.key_value.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.15.self_attention.query.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.16.input_layernorm.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.16.mlp.down_proj.bias": "pytorch_model_00002-of-00004.bin", "transformer.h.16.mlp.down_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.16.mlp.gate_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.16.mlp.up_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.16.post_attention_layernorm.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.16.self_attention.dense.bias": "pytorch_model_00002-of-00004.bin", "transformer.h.16.self_attention.dense.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.16.self_attention.key_value.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.16.self_attention.query.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.17.input_layernorm.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.17.mlp.down_proj.bias": "pytorch_model_00002-of-00004.bin", "transformer.h.17.mlp.down_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.17.mlp.gate_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.17.mlp.up_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.17.post_attention_layernorm.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.17.self_attention.dense.bias": "pytorch_model_00002-of-00004.bin", "transformer.h.17.self_attention.dense.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.17.self_attention.key_value.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.17.self_attention.query.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.18.input_layernorm.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.18.mlp.down_proj.bias": "pytorch_model_00002-of-00004.bin", "transformer.h.18.mlp.down_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.18.mlp.gate_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.18.mlp.up_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.18.post_attention_layernorm.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.18.self_attention.dense.bias": "pytorch_model_00002-of-00004.bin", "transformer.h.18.self_attention.dense.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.18.self_attention.key_value.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.18.self_attention.query.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.19.input_layernorm.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.19.mlp.down_proj.bias": "pytorch_model_00003-of-00004.bin", "transformer.h.19.mlp.down_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.19.mlp.gate_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.19.mlp.up_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.19.post_attention_layernorm.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.19.self_attention.dense.bias": "pytorch_model_00003-of-00004.bin", "transformer.h.19.self_attention.dense.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.19.self_attention.key_value.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.19.self_attention.query.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.2.input_layernorm.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.2.mlp.down_proj.bias": "pytorch_model_00001-of-00004.bin", "transformer.h.2.mlp.down_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.2.mlp.gate_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.2.mlp.up_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.2.post_attention_layernorm.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.2.self_attention.dense.bias": "pytorch_model_00001-of-00004.bin", "transformer.h.2.self_attention.dense.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.2.self_attention.key_value.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.2.self_attention.query.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.20.input_layernorm.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.20.mlp.down_proj.bias": "pytorch_model_00003-of-00004.bin", "transformer.h.20.mlp.down_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.20.mlp.gate_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.20.mlp.up_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.20.post_attention_layernorm.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.20.self_attention.dense.bias": "pytorch_model_00003-of-00004.bin", "transformer.h.20.self_attention.dense.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.20.self_attention.key_value.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.20.self_attention.query.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.21.input_layernorm.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.21.mlp.down_proj.bias": "pytorch_model_00003-of-00004.bin", "transformer.h.21.mlp.down_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.21.mlp.gate_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.21.mlp.up_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.21.post_attention_layernorm.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.21.self_attention.dense.bias": "pytorch_model_00003-of-00004.bin", "transformer.h.21.self_attention.dense.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.21.self_attention.key_value.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.21.self_attention.query.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.22.input_layernorm.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.22.mlp.down_proj.bias": "pytorch_model_00003-of-00004.bin", "transformer.h.22.mlp.down_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.22.mlp.gate_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.22.mlp.up_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.22.post_attention_layernorm.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.22.self_attention.dense.bias": "pytorch_model_00003-of-00004.bin", "transformer.h.22.self_attention.dense.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.22.self_attention.key_value.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.22.self_attention.query.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.23.input_layernorm.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.23.mlp.down_proj.bias": "pytorch_model_00003-of-00004.bin", "transformer.h.23.mlp.down_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.23.mlp.gate_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.23.mlp.up_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.23.post_attention_layernorm.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.23.self_attention.dense.bias": "pytorch_model_00003-of-00004.bin", "transformer.h.23.self_attention.dense.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.23.self_attention.key_value.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.23.self_attention.query.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.24.input_layernorm.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.24.mlp.down_proj.bias": "pytorch_model_00003-of-00004.bin", "transformer.h.24.mlp.down_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.24.mlp.gate_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.24.mlp.up_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.24.post_attention_layernorm.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.24.self_attention.dense.bias": "pytorch_model_00003-of-00004.bin", "transformer.h.24.self_attention.dense.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.24.self_attention.key_value.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.24.self_attention.query.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.25.input_layernorm.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.25.mlp.down_proj.bias": "pytorch_model_00003-of-00004.bin", "transformer.h.25.mlp.down_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.25.mlp.gate_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.25.mlp.up_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.25.post_attention_layernorm.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.25.self_attention.dense.bias": "pytorch_model_00003-of-00004.bin", "transformer.h.25.self_attention.dense.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.25.self_attention.key_value.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.25.self_attention.query.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.26.input_layernorm.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.26.mlp.down_proj.bias": "pytorch_model_00003-of-00004.bin", "transformer.h.26.mlp.down_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.26.mlp.gate_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.26.mlp.up_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.26.post_attention_layernorm.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.26.self_attention.dense.bias": "pytorch_model_00003-of-00004.bin", "transformer.h.26.self_attention.dense.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.26.self_attention.key_value.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.26.self_attention.query.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.27.input_layernorm.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.27.mlp.down_proj.bias": "pytorch_model_00003-of-00004.bin", "transformer.h.27.mlp.down_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.27.mlp.gate_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.27.mlp.up_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.27.post_attention_layernorm.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.27.self_attention.dense.bias": "pytorch_model_00003-of-00004.bin", "transformer.h.27.self_attention.dense.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.27.self_attention.key_value.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.27.self_attention.query.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.28.input_layernorm.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.28.mlp.down_proj.bias": "pytorch_model_00003-of-00004.bin", "transformer.h.28.mlp.down_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.28.mlp.gate_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.28.mlp.up_proj.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.28.post_attention_layernorm.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.28.self_attention.dense.bias": "pytorch_model_00003-of-00004.bin", "transformer.h.28.self_attention.dense.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.28.self_attention.key_value.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.28.self_attention.query.weight": "pytorch_model_00003-of-00004.bin", "transformer.h.29.input_layernorm.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.29.mlp.down_proj.bias": "pytorch_model_00004-of-00004.bin", "transformer.h.29.mlp.down_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.29.mlp.gate_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.29.mlp.up_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.29.post_attention_layernorm.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.29.self_attention.dense.bias": "pytorch_model_00004-of-00004.bin", "transformer.h.29.self_attention.dense.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.29.self_attention.key_value.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.29.self_attention.query.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.3.input_layernorm.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.3.mlp.down_proj.bias": "pytorch_model_00001-of-00004.bin", "transformer.h.3.mlp.down_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.3.mlp.gate_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.3.mlp.up_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.3.post_attention_layernorm.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.3.self_attention.dense.bias": "pytorch_model_00001-of-00004.bin", "transformer.h.3.self_attention.dense.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.3.self_attention.key_value.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.3.self_attention.query.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.30.input_layernorm.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.30.mlp.down_proj.bias": "pytorch_model_00004-of-00004.bin", "transformer.h.30.mlp.down_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.30.mlp.gate_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.30.mlp.up_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.30.post_attention_layernorm.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.30.self_attention.dense.bias": "pytorch_model_00004-of-00004.bin", "transformer.h.30.self_attention.dense.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.30.self_attention.key_value.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.30.self_attention.query.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.31.input_layernorm.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.31.mlp.down_proj.bias": "pytorch_model_00004-of-00004.bin", "transformer.h.31.mlp.down_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.31.mlp.gate_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.31.mlp.up_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.31.post_attention_layernorm.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.31.self_attention.dense.bias": "pytorch_model_00004-of-00004.bin", "transformer.h.31.self_attention.dense.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.31.self_attention.key_value.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.31.self_attention.query.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.32.input_layernorm.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.32.mlp.down_proj.bias": "pytorch_model_00004-of-00004.bin", "transformer.h.32.mlp.down_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.32.mlp.gate_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.32.mlp.up_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.32.post_attention_layernorm.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.32.self_attention.dense.bias": "pytorch_model_00004-of-00004.bin", "transformer.h.32.self_attention.dense.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.32.self_attention.key_value.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.32.self_attention.query.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.33.input_layernorm.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.33.mlp.down_proj.bias": "pytorch_model_00004-of-00004.bin", "transformer.h.33.mlp.down_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.33.mlp.gate_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.33.mlp.up_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.33.post_attention_layernorm.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.33.self_attention.dense.bias": "pytorch_model_00004-of-00004.bin", "transformer.h.33.self_attention.dense.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.33.self_attention.key_value.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.33.self_attention.query.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.34.input_layernorm.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.34.mlp.down_proj.bias": "pytorch_model_00004-of-00004.bin", "transformer.h.34.mlp.down_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.34.mlp.gate_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.34.mlp.up_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.34.post_attention_layernorm.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.34.self_attention.dense.bias": "pytorch_model_00004-of-00004.bin", "transformer.h.34.self_attention.dense.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.34.self_attention.key_value.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.34.self_attention.query.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.35.input_layernorm.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.35.mlp.down_proj.bias": "pytorch_model_00004-of-00004.bin", "transformer.h.35.mlp.down_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.35.mlp.gate_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.35.mlp.up_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.35.post_attention_layernorm.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.35.self_attention.dense.bias": "pytorch_model_00004-of-00004.bin", "transformer.h.35.self_attention.dense.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.35.self_attention.key_value.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.35.self_attention.query.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.36.input_layernorm.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.36.mlp.down_proj.bias": "pytorch_model_00004-of-00004.bin", "transformer.h.36.mlp.down_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.36.mlp.gate_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.36.mlp.up_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.36.post_attention_layernorm.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.36.self_attention.dense.bias": "pytorch_model_00004-of-00004.bin", "transformer.h.36.self_attention.dense.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.36.self_attention.key_value.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.36.self_attention.query.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.37.input_layernorm.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.37.mlp.down_proj.bias": "pytorch_model_00004-of-00004.bin", "transformer.h.37.mlp.down_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.37.mlp.gate_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.37.mlp.up_proj.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.37.post_attention_layernorm.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.37.self_attention.dense.bias": "pytorch_model_00004-of-00004.bin", "transformer.h.37.self_attention.dense.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.37.self_attention.key_value.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.37.self_attention.query.weight": "pytorch_model_00004-of-00004.bin", "transformer.h.4.input_layernorm.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.4.mlp.down_proj.bias": "pytorch_model_00001-of-00004.bin", "transformer.h.4.mlp.down_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.4.mlp.gate_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.4.mlp.up_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.4.post_attention_layernorm.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.4.self_attention.dense.bias": "pytorch_model_00001-of-00004.bin", "transformer.h.4.self_attention.dense.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.4.self_attention.key_value.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.4.self_attention.query.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.5.input_layernorm.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.5.mlp.down_proj.bias": "pytorch_model_00001-of-00004.bin", "transformer.h.5.mlp.down_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.5.mlp.gate_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.5.mlp.up_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.5.post_attention_layernorm.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.5.self_attention.dense.bias": "pytorch_model_00001-of-00004.bin", "transformer.h.5.self_attention.dense.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.5.self_attention.key_value.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.5.self_attention.query.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.6.input_layernorm.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.6.mlp.down_proj.bias": "pytorch_model_00001-of-00004.bin", "transformer.h.6.mlp.down_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.6.mlp.gate_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.6.mlp.up_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.6.post_attention_layernorm.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.6.self_attention.dense.bias": "pytorch_model_00001-of-00004.bin", "transformer.h.6.self_attention.dense.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.6.self_attention.key_value.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.6.self_attention.query.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.7.input_layernorm.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.7.mlp.down_proj.bias": "pytorch_model_00001-of-00004.bin", "transformer.h.7.mlp.down_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.7.mlp.gate_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.7.mlp.up_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.7.post_attention_layernorm.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.7.self_attention.dense.bias": "pytorch_model_00001-of-00004.bin", "transformer.h.7.self_attention.dense.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.7.self_attention.key_value.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.7.self_attention.query.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.8.input_layernorm.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.8.mlp.down_proj.bias": "pytorch_model_00001-of-00004.bin", "transformer.h.8.mlp.down_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.8.mlp.gate_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.8.mlp.up_proj.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.8.post_attention_layernorm.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.8.self_attention.dense.bias": "pytorch_model_00001-of-00004.bin", "transformer.h.8.self_attention.dense.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.8.self_attention.key_value.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.8.self_attention.query.weight": "pytorch_model_00001-of-00004.bin", "transformer.h.9.input_layernorm.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.9.mlp.down_proj.bias": "pytorch_model_00002-of-00004.bin", "transformer.h.9.mlp.down_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.9.mlp.gate_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.9.mlp.up_proj.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.9.post_attention_layernorm.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.9.self_attention.dense.bias": "pytorch_model_00002-of-00004.bin", "transformer.h.9.self_attention.dense.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.9.self_attention.key_value.weight": "pytorch_model_00002-of-00004.bin", "transformer.h.9.self_attention.query.weight": "pytorch_model_00002-of-00004.bin", "transformer.ln_f.weight": "pytorch_model_00004-of-00004.bin", "transformer.word_embeddings.weight": "pytorch_model_00001-of-00004.bin"}}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
pytorch_model_00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbfb8f381ef6ddfa20e737d8219797942a715b9c38b58dcc772b609c645eeb33
3
+ size 6514022701
pytorch_model_00002-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe6d067afb3f6b73c02d1482643fd34ebe8873a6a7b4588ec058dd90f711f445
3
+ size 5872469271
pytorch_model_00003-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:598230fe6f668b9339a9d3afb7d85a9de6bfb6c415af612ed7a564b1e0af1fd3
3
+ size 5872469271
pytorch_model_00004-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2dcf7fcd403e212fec68103143faf538a72f43e5470eb5cfa1f4eb0e5025589
3
+ size 6514033127