Hugging Face's logo

bigscience
/
bloom

Text Generation
Transformers
PyTorch
TensorBoard
Safetensors
bloom
Eval Results
text-generation-inference
Model card Files
xet
Metrics Community
283
sgugger commited on
Commit
eff12ac
·
1 Parent(s): 20ac6a9

Add safetensors index

Browse files
Files changed (1) hide show
  1. model.safetensors.index.json +852 -0
model.safetensors.index.json ADDED
@@ -0,0 +1,852 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 352494542848
4
+ },
5
+ "weight_map": {
6
+ "h.0.input_layernorm.bias": "model_00002-of-00072.safetensors",
7
+ "h.0.input_layernorm.weight": "model_00002-of-00072.safetensors",
8
+ "h.0.mlp.dense_4h_to_h.bias": "model_00002-of-00072.safetensors",
9
+ "h.0.mlp.dense_4h_to_h.weight": "model_00002-of-00072.safetensors",
10
+ "h.0.mlp.dense_h_to_4h.bias": "model_00002-of-00072.safetensors",
11
+ "h.0.mlp.dense_h_to_4h.weight": "model_00002-of-00072.safetensors",
12
+ "h.0.post_attention_layernorm.bias": "model_00002-of-00072.safetensors",
13
+ "h.0.post_attention_layernorm.weight": "model_00002-of-00072.safetensors",
14
+ "h.0.self_attention.dense.bias": "model_00002-of-00072.safetensors",
15
+ "h.0.self_attention.dense.weight": "model_00002-of-00072.safetensors",
16
+ "h.0.self_attention.query_key_value.bias": "model_00002-of-00072.safetensors",
17
+ "h.0.self_attention.query_key_value.weight": "model_00002-of-00072.safetensors",
18
+ "h.1.input_layernorm.bias": "model_00003-of-00072.safetensors",
19
+ "h.1.input_layernorm.weight": "model_00003-of-00072.safetensors",
20
+ "h.1.mlp.dense_4h_to_h.bias": "model_00003-of-00072.safetensors",
21
+ "h.1.mlp.dense_4h_to_h.weight": "model_00003-of-00072.safetensors",
22
+ "h.1.mlp.dense_h_to_4h.bias": "model_00003-of-00072.safetensors",
23
+ "h.1.mlp.dense_h_to_4h.weight": "model_00003-of-00072.safetensors",
24
+ "h.1.post_attention_layernorm.bias": "model_00003-of-00072.safetensors",
25
+ "h.1.post_attention_layernorm.weight": "model_00003-of-00072.safetensors",
26
+ "h.1.self_attention.dense.bias": "model_00003-of-00072.safetensors",
27
+ "h.1.self_attention.dense.weight": "model_00003-of-00072.safetensors",
28
+ "h.1.self_attention.query_key_value.bias": "model_00003-of-00072.safetensors",
29
+ "h.1.self_attention.query_key_value.weight": "model_00003-of-00072.safetensors",
30
+ "h.10.input_layernorm.bias": "model_00012-of-00072.safetensors",
31
+ "h.10.input_layernorm.weight": "model_00012-of-00072.safetensors",
32
+ "h.10.mlp.dense_4h_to_h.bias": "model_00012-of-00072.safetensors",
33
+ "h.10.mlp.dense_4h_to_h.weight": "model_00012-of-00072.safetensors",
34
+ "h.10.mlp.dense_h_to_4h.bias": "model_00012-of-00072.safetensors",
35
+ "h.10.mlp.dense_h_to_4h.weight": "model_00012-of-00072.safetensors",
36
+ "h.10.post_attention_layernorm.bias": "model_00012-of-00072.safetensors",
37
+ "h.10.post_attention_layernorm.weight": "model_00012-of-00072.safetensors",
38
+ "h.10.self_attention.dense.bias": "model_00012-of-00072.safetensors",
39
+ "h.10.self_attention.dense.weight": "model_00012-of-00072.safetensors",
40
+ "h.10.self_attention.query_key_value.bias": "model_00012-of-00072.safetensors",
41
+ "h.10.self_attention.query_key_value.weight": "model_00012-of-00072.safetensors",
42
+ "h.11.input_layernorm.bias": "model_00013-of-00072.safetensors",
43
+ "h.11.input_layernorm.weight": "model_00013-of-00072.safetensors",
44
+ "h.11.mlp.dense_4h_to_h.bias": "model_00013-of-00072.safetensors",
45
+ "h.11.mlp.dense_4h_to_h.weight": "model_00013-of-00072.safetensors",
46
+ "h.11.mlp.dense_h_to_4h.bias": "model_00013-of-00072.safetensors",
47
+ "h.11.mlp.dense_h_to_4h.weight": "model_00013-of-00072.safetensors",
48
+ "h.11.post_attention_layernorm.bias": "model_00013-of-00072.safetensors",
49
+ "h.11.post_attention_layernorm.weight": "model_00013-of-00072.safetensors",
50
+ "h.11.self_attention.dense.bias": "model_00013-of-00072.safetensors",
51
+ "h.11.self_attention.dense.weight": "model_00013-of-00072.safetensors",
52
+ "h.11.self_attention.query_key_value.bias": "model_00013-of-00072.safetensors",
53
+ "h.11.self_attention.query_key_value.weight": "model_00013-of-00072.safetensors",
54
+ "h.12.input_layernorm.bias": "model_00014-of-00072.safetensors",
55
+ "h.12.input_layernorm.weight": "model_00014-of-00072.safetensors",
56
+ "h.12.mlp.dense_4h_to_h.bias": "model_00014-of-00072.safetensors",
57
+ "h.12.mlp.dense_4h_to_h.weight": "model_00014-of-00072.safetensors",
58
+ "h.12.mlp.dense_h_to_4h.bias": "model_00014-of-00072.safetensors",
59
+ "h.12.mlp.dense_h_to_4h.weight": "model_00014-of-00072.safetensors",
60
+ "h.12.post_attention_layernorm.bias": "model_00014-of-00072.safetensors",
61
+ "h.12.post_attention_layernorm.weight": "model_00014-of-00072.safetensors",
62
+ "h.12.self_attention.dense.bias": "model_00014-of-00072.safetensors",
63
+ "h.12.self_attention.dense.weight": "model_00014-of-00072.safetensors",
64
+ "h.12.self_attention.query_key_value.bias": "model_00014-of-00072.safetensors",
65
+ "h.12.self_attention.query_key_value.weight": "model_00014-of-00072.safetensors",
66
+ "h.13.input_layernorm.bias": "model_00015-of-00072.safetensors",
67
+ "h.13.input_layernorm.weight": "model_00015-of-00072.safetensors",
68
+ "h.13.mlp.dense_4h_to_h.bias": "model_00015-of-00072.safetensors",
69
+ "h.13.mlp.dense_4h_to_h.weight": "model_00015-of-00072.safetensors",
70
+ "h.13.mlp.dense_h_to_4h.bias": "model_00015-of-00072.safetensors",
71
+ "h.13.mlp.dense_h_to_4h.weight": "model_00015-of-00072.safetensors",
72
+ "h.13.post_attention_layernorm.bias": "model_00015-of-00072.safetensors",
73
+ "h.13.post_attention_layernorm.weight": "model_00015-of-00072.safetensors",
74
+ "h.13.self_attention.dense.bias": "model_00015-of-00072.safetensors",
75
+ "h.13.self_attention.dense.weight": "model_00015-of-00072.safetensors",
76
+ "h.13.self_attention.query_key_value.bias": "model_00015-of-00072.safetensors",
77
+ "h.13.self_attention.query_key_value.weight": "model_00015-of-00072.safetensors",
78
+ "h.14.input_layernorm.bias": "model_00016-of-00072.safetensors",
79
+ "h.14.input_layernorm.weight": "model_00016-of-00072.safetensors",
80
+ "h.14.mlp.dense_4h_to_h.bias": "model_00016-of-00072.safetensors",
81
+ "h.14.mlp.dense_4h_to_h.weight": "model_00016-of-00072.safetensors",
82
+ "h.14.mlp.dense_h_to_4h.bias": "model_00016-of-00072.safetensors",
83
+ "h.14.mlp.dense_h_to_4h.weight": "model_00016-of-00072.safetensors",
84
+ "h.14.post_attention_layernorm.bias": "model_00016-of-00072.safetensors",
85
+ "h.14.post_attention_layernorm.weight": "model_00016-of-00072.safetensors",
86
+ "h.14.self_attention.dense.bias": "model_00016-of-00072.safetensors",
87
+ "h.14.self_attention.dense.weight": "model_00016-of-00072.safetensors",
88
+ "h.14.self_attention.query_key_value.bias": "model_00016-of-00072.safetensors",
89
+ "h.14.self_attention.query_key_value.weight": "model_00016-of-00072.safetensors",
90
+ "h.15.input_layernorm.bias": "model_00017-of-00072.safetensors",
91
+ "h.15.input_layernorm.weight": "model_00017-of-00072.safetensors",
92
+ "h.15.mlp.dense_4h_to_h.bias": "model_00017-of-00072.safetensors",
93
+ "h.15.mlp.dense_4h_to_h.weight": "model_00017-of-00072.safetensors",
94
+ "h.15.mlp.dense_h_to_4h.bias": "model_00017-of-00072.safetensors",
95
+ "h.15.mlp.dense_h_to_4h.weight": "model_00017-of-00072.safetensors",
96
+ "h.15.post_attention_layernorm.bias": "model_00017-of-00072.safetensors",
97
+ "h.15.post_attention_layernorm.weight": "model_00017-of-00072.safetensors",
98
+ "h.15.self_attention.dense.bias": "model_00017-of-00072.safetensors",
99
+ "h.15.self_attention.dense.weight": "model_00017-of-00072.safetensors",
100
+ "h.15.self_attention.query_key_value.bias": "model_00017-of-00072.safetensors",
101
+ "h.15.self_attention.query_key_value.weight": "model_00017-of-00072.safetensors",
102
+ "h.16.input_layernorm.bias": "model_00018-of-00072.safetensors",
103
+ "h.16.input_layernorm.weight": "model_00018-of-00072.safetensors",
104
+ "h.16.mlp.dense_4h_to_h.bias": "model_00018-of-00072.safetensors",
105
+ "h.16.mlp.dense_4h_to_h.weight": "model_00018-of-00072.safetensors",
106
+ "h.16.mlp.dense_h_to_4h.bias": "model_00018-of-00072.safetensors",
107
+ "h.16.mlp.dense_h_to_4h.weight": "model_00018-of-00072.safetensors",
108
+ "h.16.post_attention_layernorm.bias": "model_00018-of-00072.safetensors",
109
+ "h.16.post_attention_layernorm.weight": "model_00018-of-00072.safetensors",
110
+ "h.16.self_attention.dense.bias": "model_00018-of-00072.safetensors",
111
+ "h.16.self_attention.dense.weight": "model_00018-of-00072.safetensors",
112
+ "h.16.self_attention.query_key_value.bias": "model_00018-of-00072.safetensors",
113
+ "h.16.self_attention.query_key_value.weight": "model_00018-of-00072.safetensors",
114
+ "h.17.input_layernorm.bias": "model_00019-of-00072.safetensors",
115
+ "h.17.input_layernorm.weight": "model_00019-of-00072.safetensors",
116
+ "h.17.mlp.dense_4h_to_h.bias": "model_00019-of-00072.safetensors",
117
+ "h.17.mlp.dense_4h_to_h.weight": "model_00019-of-00072.safetensors",
118
+ "h.17.mlp.dense_h_to_4h.bias": "model_00019-of-00072.safetensors",
119
+ "h.17.mlp.dense_h_to_4h.weight": "model_00019-of-00072.safetensors",
120
+ "h.17.post_attention_layernorm.bias": "model_00019-of-00072.safetensors",
121
+ "h.17.post_attention_layernorm.weight": "model_00019-of-00072.safetensors",
122
+ "h.17.self_attention.dense.bias": "model_00019-of-00072.safetensors",
123
+ "h.17.self_attention.dense.weight": "model_00019-of-00072.safetensors",
124
+ "h.17.self_attention.query_key_value.bias": "model_00019-of-00072.safetensors",
125
+ "h.17.self_attention.query_key_value.weight": "model_00019-of-00072.safetensors",
126
+ "h.18.input_layernorm.bias": "model_00020-of-00072.safetensors",
127
+ "h.18.input_layernorm.weight": "model_00020-of-00072.safetensors",
128
+ "h.18.mlp.dense_4h_to_h.bias": "model_00020-of-00072.safetensors",
129
+ "h.18.mlp.dense_4h_to_h.weight": "model_00020-of-00072.safetensors",
130
+ "h.18.mlp.dense_h_to_4h.bias": "model_00020-of-00072.safetensors",
131
+ "h.18.mlp.dense_h_to_4h.weight": "model_00020-of-00072.safetensors",
132
+ "h.18.post_attention_layernorm.bias": "model_00020-of-00072.safetensors",
133
+ "h.18.post_attention_layernorm.weight": "model_00020-of-00072.safetensors",
134
+ "h.18.self_attention.dense.bias": "model_00020-of-00072.safetensors",
135
+ "h.18.self_attention.dense.weight": "model_00020-of-00072.safetensors",
136
+ "h.18.self_attention.query_key_value.bias": "model_00020-of-00072.safetensors",
137
+ "h.18.self_attention.query_key_value.weight": "model_00020-of-00072.safetensors",
138
+ "h.19.input_layernorm.bias": "model_00021-of-00072.safetensors",
139
+ "h.19.input_layernorm.weight": "model_00021-of-00072.safetensors",
140
+ "h.19.mlp.dense_4h_to_h.bias": "model_00021-of-00072.safetensors",
141
+ "h.19.mlp.dense_4h_to_h.weight": "model_00021-of-00072.safetensors",
142
+ "h.19.mlp.dense_h_to_4h.bias": "model_00021-of-00072.safetensors",
143
+ "h.19.mlp.dense_h_to_4h.weight": "model_00021-of-00072.safetensors",
144
+ "h.19.post_attention_layernorm.bias": "model_00021-of-00072.safetensors",
145
+ "h.19.post_attention_layernorm.weight": "model_00021-of-00072.safetensors",
146
+ "h.19.self_attention.dense.bias": "model_00021-of-00072.safetensors",
147
+ "h.19.self_attention.dense.weight": "model_00021-of-00072.safetensors",
148
+ "h.19.self_attention.query_key_value.bias": "model_00021-of-00072.safetensors",
149
+ "h.19.self_attention.query_key_value.weight": "model_00021-of-00072.safetensors",
150
+ "h.2.input_layernorm.bias": "model_00004-of-00072.safetensors",
151
+ "h.2.input_layernorm.weight": "model_00004-of-00072.safetensors",
152
+ "h.2.mlp.dense_4h_to_h.bias": "model_00004-of-00072.safetensors",
153
+ "h.2.mlp.dense_4h_to_h.weight": "model_00004-of-00072.safetensors",
154
+ "h.2.mlp.dense_h_to_4h.bias": "model_00004-of-00072.safetensors",
155
+ "h.2.mlp.dense_h_to_4h.weight": "model_00004-of-00072.safetensors",
156
+ "h.2.post_attention_layernorm.bias": "model_00004-of-00072.safetensors",
157
+ "h.2.post_attention_layernorm.weight": "model_00004-of-00072.safetensors",
158
+ "h.2.self_attention.dense.bias": "model_00004-of-00072.safetensors",
159
+ "h.2.self_attention.dense.weight": "model_00004-of-00072.safetensors",
160
+ "h.2.self_attention.query_key_value.bias": "model_00004-of-00072.safetensors",
161
+ "h.2.self_attention.query_key_value.weight": "model_00004-of-00072.safetensors",
162
+ "h.20.input_layernorm.bias": "model_00022-of-00072.safetensors",
163
+ "h.20.input_layernorm.weight": "model_00022-of-00072.safetensors",
164
+ "h.20.mlp.dense_4h_to_h.bias": "model_00022-of-00072.safetensors",
165
+ "h.20.mlp.dense_4h_to_h.weight": "model_00022-of-00072.safetensors",
166
+ "h.20.mlp.dense_h_to_4h.bias": "model_00022-of-00072.safetensors",
167
+ "h.20.mlp.dense_h_to_4h.weight": "model_00022-of-00072.safetensors",
168
+ "h.20.post_attention_layernorm.bias": "model_00022-of-00072.safetensors",
169
+ "h.20.post_attention_layernorm.weight": "model_00022-of-00072.safetensors",
170
+ "h.20.self_attention.dense.bias": "model_00022-of-00072.safetensors",
171
+ "h.20.self_attention.dense.weight": "model_00022-of-00072.safetensors",
172
+ "h.20.self_attention.query_key_value.bias": "model_00022-of-00072.safetensors",
173
+ "h.20.self_attention.query_key_value.weight": "model_00022-of-00072.safetensors",
174
+ "h.21.input_layernorm.bias": "model_00023-of-00072.safetensors",
175
+ "h.21.input_layernorm.weight": "model_00023-of-00072.safetensors",
176
+ "h.21.mlp.dense_4h_to_h.bias": "model_00023-of-00072.safetensors",
177
+ "h.21.mlp.dense_4h_to_h.weight": "model_00023-of-00072.safetensors",
178
+ "h.21.mlp.dense_h_to_4h.bias": "model_00023-of-00072.safetensors",
179
+ "h.21.mlp.dense_h_to_4h.weight": "model_00023-of-00072.safetensors",
180
+ "h.21.post_attention_layernorm.bias": "model_00023-of-00072.safetensors",
181
+ "h.21.post_attention_layernorm.weight": "model_00023-of-00072.safetensors",
182
+ "h.21.self_attention.dense.bias": "model_00023-of-00072.safetensors",
183
+ "h.21.self_attention.dense.weight": "model_00023-of-00072.safetensors",
184
+ "h.21.self_attention.query_key_value.bias": "model_00023-of-00072.safetensors",
185
+ "h.21.self_attention.query_key_value.weight": "model_00023-of-00072.safetensors",
186
+ "h.22.input_layernorm.bias": "model_00024-of-00072.safetensors",
187
+ "h.22.input_layernorm.weight": "model_00024-of-00072.safetensors",
188
+ "h.22.mlp.dense_4h_to_h.bias": "model_00024-of-00072.safetensors",
189
+ "h.22.mlp.dense_4h_to_h.weight": "model_00024-of-00072.safetensors",
190
+ "h.22.mlp.dense_h_to_4h.bias": "model_00024-of-00072.safetensors",
191
+ "h.22.mlp.dense_h_to_4h.weight": "model_00024-of-00072.safetensors",
192
+ "h.22.post_attention_layernorm.bias": "model_00024-of-00072.safetensors",
193
+ "h.22.post_attention_layernorm.weight": "model_00024-of-00072.safetensors",
194
+ "h.22.self_attention.dense.bias": "model_00024-of-00072.safetensors",
195
+ "h.22.self_attention.dense.weight": "model_00024-of-00072.safetensors",
196
+ "h.22.self_attention.query_key_value.bias": "model_00024-of-00072.safetensors",
197
+ "h.22.self_attention.query_key_value.weight": "model_00024-of-00072.safetensors",
198
+ "h.23.input_layernorm.bias": "model_00025-of-00072.safetensors",
199
+ "h.23.input_layernorm.weight": "model_00025-of-00072.safetensors",
200
+ "h.23.mlp.dense_4h_to_h.bias": "model_00025-of-00072.safetensors",
201
+ "h.23.mlp.dense_4h_to_h.weight": "model_00025-of-00072.safetensors",
202
+ "h.23.mlp.dense_h_to_4h.bias": "model_00025-of-00072.safetensors",
203
+ "h.23.mlp.dense_h_to_4h.weight": "model_00025-of-00072.safetensors",
204
+ "h.23.post_attention_layernorm.bias": "model_00025-of-00072.safetensors",
205
+ "h.23.post_attention_layernorm.weight": "model_00025-of-00072.safetensors",
206
+ "h.23.self_attention.dense.bias": "model_00025-of-00072.safetensors",
207
+ "h.23.self_attention.dense.weight": "model_00025-of-00072.safetensors",
208
+ "h.23.self_attention.query_key_value.bias": "model_00025-of-00072.safetensors",
209
+ "h.23.self_attention.query_key_value.weight": "model_00025-of-00072.safetensors",
210
+ "h.24.input_layernorm.bias": "model_00026-of-00072.safetensors",
211
+ "h.24.input_layernorm.weight": "model_00026-of-00072.safetensors",
212
+ "h.24.mlp.dense_4h_to_h.bias": "model_00026-of-00072.safetensors",
213
+ "h.24.mlp.dense_4h_to_h.weight": "model_00026-of-00072.safetensors",
214
+ "h.24.mlp.dense_h_to_4h.bias": "model_00026-of-00072.safetensors",
215
+ "h.24.mlp.dense_h_to_4h.weight": "model_00026-of-00072.safetensors",
216
+ "h.24.post_attention_layernorm.bias": "model_00026-of-00072.safetensors",
217
+ "h.24.post_attention_layernorm.weight": "model_00026-of-00072.safetensors",
218
+ "h.24.self_attention.dense.bias": "model_00026-of-00072.safetensors",
219
+ "h.24.self_attention.dense.weight": "model_00026-of-00072.safetensors",
220
+ "h.24.self_attention.query_key_value.bias": "model_00026-of-00072.safetensors",
221
+ "h.24.self_attention.query_key_value.weight": "model_00026-of-00072.safetensors",
222
+ "h.25.input_layernorm.bias": "model_00027-of-00072.safetensors",
223
+ "h.25.input_layernorm.weight": "model_00027-of-00072.safetensors",
224
+ "h.25.mlp.dense_4h_to_h.bias": "model_00027-of-00072.safetensors",
225
+ "h.25.mlp.dense_4h_to_h.weight": "model_00027-of-00072.safetensors",
226
+ "h.25.mlp.dense_h_to_4h.bias": "model_00027-of-00072.safetensors",
227
+ "h.25.mlp.dense_h_to_4h.weight": "model_00027-of-00072.safetensors",
228
+ "h.25.post_attention_layernorm.bias": "model_00027-of-00072.safetensors",
229
+ "h.25.post_attention_layernorm.weight": "model_00027-of-00072.safetensors",
230
+ "h.25.self_attention.dense.bias": "model_00027-of-00072.safetensors",
231
+ "h.25.self_attention.dense.weight": "model_00027-of-00072.safetensors",
232
+ "h.25.self_attention.query_key_value.bias": "model_00027-of-00072.safetensors",
233
+ "h.25.self_attention.query_key_value.weight": "model_00027-of-00072.safetensors",
234
+ "h.26.input_layernorm.bias": "model_00028-of-00072.safetensors",
235
+ "h.26.input_layernorm.weight": "model_00028-of-00072.safetensors",
236
+ "h.26.mlp.dense_4h_to_h.bias": "model_00028-of-00072.safetensors",
237
+ "h.26.mlp.dense_4h_to_h.weight": "model_00028-of-00072.safetensors",
238
+ "h.26.mlp.dense_h_to_4h.bias": "model_00028-of-00072.safetensors",
239
+ "h.26.mlp.dense_h_to_4h.weight": "model_00028-of-00072.safetensors",
240
+ "h.26.post_attention_layernorm.bias": "model_00028-of-00072.safetensors",
241
+ "h.26.post_attention_layernorm.weight": "model_00028-of-00072.safetensors",
242
+ "h.26.self_attention.dense.bias": "model_00028-of-00072.safetensors",
243
+ "h.26.self_attention.dense.weight": "model_00028-of-00072.safetensors",
244
+ "h.26.self_attention.query_key_value.bias": "model_00028-of-00072.safetensors",
245
+ "h.26.self_attention.query_key_value.weight": "model_00028-of-00072.safetensors",
246
+ "h.27.input_layernorm.bias": "model_00029-of-00072.safetensors",
247
+ "h.27.input_layernorm.weight": "model_00029-of-00072.safetensors",
248
+ "h.27.mlp.dense_4h_to_h.bias": "model_00029-of-00072.safetensors",
249
+ "h.27.mlp.dense_4h_to_h.weight": "model_00029-of-00072.safetensors",
250
+ "h.27.mlp.dense_h_to_4h.bias": "model_00029-of-00072.safetensors",
251
+ "h.27.mlp.dense_h_to_4h.weight": "model_00029-of-00072.safetensors",
252
+ "h.27.post_attention_layernorm.bias": "model_00029-of-00072.safetensors",
253
+ "h.27.post_attention_layernorm.weight": "model_00029-of-00072.safetensors",
254
+ "h.27.self_attention.dense.bias": "model_00029-of-00072.safetensors",
255
+ "h.27.self_attention.dense.weight": "model_00029-of-00072.safetensors",
256
+ "h.27.self_attention.query_key_value.bias": "model_00029-of-00072.safetensors",
257
+ "h.27.self_attention.query_key_value.weight": "model_00029-of-00072.safetensors",
258
+ "h.28.input_layernorm.bias": "model_00030-of-00072.safetensors",
259
+ "h.28.input_layernorm.weight": "model_00030-of-00072.safetensors",
260
+ "h.28.mlp.dense_4h_to_h.bias": "model_00030-of-00072.safetensors",
261
+ "h.28.mlp.dense_4h_to_h.weight": "model_00030-of-00072.safetensors",
262
+ "h.28.mlp.dense_h_to_4h.bias": "model_00030-of-00072.safetensors",
263
+ "h.28.mlp.dense_h_to_4h.weight": "model_00030-of-00072.safetensors",
264
+ "h.28.post_attention_layernorm.bias": "model_00030-of-00072.safetensors",
265
+ "h.28.post_attention_layernorm.weight": "model_00030-of-00072.safetensors",
266
+ "h.28.self_attention.dense.bias": "model_00030-of-00072.safetensors",
267
+ "h.28.self_attention.dense.weight": "model_00030-of-00072.safetensors",
268
+ "h.28.self_attention.query_key_value.bias": "model_00030-of-00072.safetensors",
269
+ "h.28.self_attention.query_key_value.weight": "model_00030-of-00072.safetensors",
270
+ "h.29.input_layernorm.bias": "model_00031-of-00072.safetensors",
271
+ "h.29.input_layernorm.weight": "model_00031-of-00072.safetensors",
272
+ "h.29.mlp.dense_4h_to_h.bias": "model_00031-of-00072.safetensors",
273
+ "h.29.mlp.dense_4h_to_h.weight": "model_00031-of-00072.safetensors",
274
+ "h.29.mlp.dense_h_to_4h.bias": "model_00031-of-00072.safetensors",
275
+ "h.29.mlp.dense_h_to_4h.weight": "model_00031-of-00072.safetensors",
276
+ "h.29.post_attention_layernorm.bias": "model_00031-of-00072.safetensors",
277
+ "h.29.post_attention_layernorm.weight": "model_00031-of-00072.safetensors",
278
+ "h.29.self_attention.dense.bias": "model_00031-of-00072.safetensors",
279
+ "h.29.self_attention.dense.weight": "model_00031-of-00072.safetensors",
280
+ "h.29.self_attention.query_key_value.bias": "model_00031-of-00072.safetensors",
281
+ "h.29.self_attention.query_key_value.weight": "model_00031-of-00072.safetensors",
282
+ "h.3.input_layernorm.bias": "model_00005-of-00072.safetensors",
283
+ "h.3.input_layernorm.weight": "model_00005-of-00072.safetensors",
284
+ "h.3.mlp.dense_4h_to_h.bias": "model_00005-of-00072.safetensors",
285
+ "h.3.mlp.dense_4h_to_h.weight": "model_00005-of-00072.safetensors",
286
+ "h.3.mlp.dense_h_to_4h.bias": "model_00005-of-00072.safetensors",
287
+ "h.3.mlp.dense_h_to_4h.weight": "model_00005-of-00072.safetensors",
288
+ "h.3.post_attention_layernorm.bias": "model_00005-of-00072.safetensors",
289
+ "h.3.post_attention_layernorm.weight": "model_00005-of-00072.safetensors",
290
+ "h.3.self_attention.dense.bias": "model_00005-of-00072.safetensors",
291
+ "h.3.self_attention.dense.weight": "model_00005-of-00072.safetensors",
292
+ "h.3.self_attention.query_key_value.bias": "model_00005-of-00072.safetensors",
293
+ "h.3.self_attention.query_key_value.weight": "model_00005-of-00072.safetensors",
294
+ "h.30.input_layernorm.bias": "model_00032-of-00072.safetensors",
295
+ "h.30.input_layernorm.weight": "model_00032-of-00072.safetensors",
296
+ "h.30.mlp.dense_4h_to_h.bias": "model_00032-of-00072.safetensors",
297
+ "h.30.mlp.dense_4h_to_h.weight": "model_00032-of-00072.safetensors",
298
+ "h.30.mlp.dense_h_to_4h.bias": "model_00032-of-00072.safetensors",
299
+ "h.30.mlp.dense_h_to_4h.weight": "model_00032-of-00072.safetensors",
300
+ "h.30.post_attention_layernorm.bias": "model_00032-of-00072.safetensors",
301
+ "h.30.post_attention_layernorm.weight": "model_00032-of-00072.safetensors",
302
+ "h.30.self_attention.dense.bias": "model_00032-of-00072.safetensors",
303
+ "h.30.self_attention.dense.weight": "model_00032-of-00072.safetensors",
304
+ "h.30.self_attention.query_key_value.bias": "model_00032-of-00072.safetensors",
305
+ "h.30.self_attention.query_key_value.weight": "model_00032-of-00072.safetensors",
306
+ "h.31.input_layernorm.bias": "model_00033-of-00072.safetensors",
307
+ "h.31.input_layernorm.weight": "model_00033-of-00072.safetensors",
308
+ "h.31.mlp.dense_4h_to_h.bias": "model_00033-of-00072.safetensors",
309
+ "h.31.mlp.dense_4h_to_h.weight": "model_00033-of-00072.safetensors",
310
+ "h.31.mlp.dense_h_to_4h.bias": "model_00033-of-00072.safetensors",
311
+ "h.31.mlp.dense_h_to_4h.weight": "model_00033-of-00072.safetensors",
312
+ "h.31.post_attention_layernorm.bias": "model_00033-of-00072.safetensors",
313
+ "h.31.post_attention_layernorm.weight": "model_00033-of-00072.safetensors",
314
+ "h.31.self_attention.dense.bias": "model_00033-of-00072.safetensors",
315
+ "h.31.self_attention.dense.weight": "model_00033-of-00072.safetensors",
316
+ "h.31.self_attention.query_key_value.bias": "model_00033-of-00072.safetensors",
317
+ "h.31.self_attention.query_key_value.weight": "model_00033-of-00072.safetensors",
318
+ "h.32.input_layernorm.bias": "model_00034-of-00072.safetensors",
319
+ "h.32.input_layernorm.weight": "model_00034-of-00072.safetensors",
320
+ "h.32.mlp.dense_4h_to_h.bias": "model_00034-of-00072.safetensors",
321
+ "h.32.mlp.dense_4h_to_h.weight": "model_00034-of-00072.safetensors",
322
+ "h.32.mlp.dense_h_to_4h.bias": "model_00034-of-00072.safetensors",
323
+ "h.32.mlp.dense_h_to_4h.weight": "model_00034-of-00072.safetensors",
324
+ "h.32.post_attention_layernorm.bias": "model_00034-of-00072.safetensors",
325
+ "h.32.post_attention_layernorm.weight": "model_00034-of-00072.safetensors",
326
+ "h.32.self_attention.dense.bias": "model_00034-of-00072.safetensors",
327
+ "h.32.self_attention.dense.weight": "model_00034-of-00072.safetensors",
328
+ "h.32.self_attention.query_key_value.bias": "model_00034-of-00072.safetensors",
329
+ "h.32.self_attention.query_key_value.weight": "model_00034-of-00072.safetensors",
330
+ "h.33.input_layernorm.bias": "model_00035-of-00072.safetensors",
331
+ "h.33.input_layernorm.weight": "model_00035-of-00072.safetensors",
332
+ "h.33.mlp.dense_4h_to_h.bias": "model_00035-of-00072.safetensors",
333
+ "h.33.mlp.dense_4h_to_h.weight": "model_00035-of-00072.safetensors",
334
+ "h.33.mlp.dense_h_to_4h.bias": "model_00035-of-00072.safetensors",
335
+ "h.33.mlp.dense_h_to_4h.weight": "model_00035-of-00072.safetensors",
336
+ "h.33.post_attention_layernorm.bias": "model_00035-of-00072.safetensors",
337
+ "h.33.post_attention_layernorm.weight": "model_00035-of-00072.safetensors",
338
+ "h.33.self_attention.dense.bias": "model_00035-of-00072.safetensors",
339
+ "h.33.self_attention.dense.weight": "model_00035-of-00072.safetensors",
340
+ "h.33.self_attention.query_key_value.bias": "model_00035-of-00072.safetensors",
341
+ "h.33.self_attention.query_key_value.weight": "model_00035-of-00072.safetensors",
342
+ "h.34.input_layernorm.bias": "model_00036-of-00072.safetensors",
343
+ "h.34.input_layernorm.weight": "model_00036-of-00072.safetensors",
344
+ "h.34.mlp.dense_4h_to_h.bias": "model_00036-of-00072.safetensors",
345
+ "h.34.mlp.dense_4h_to_h.weight": "model_00036-of-00072.safetensors",
346
+ "h.34.mlp.dense_h_to_4h.bias": "model_00036-of-00072.safetensors",
347
+ "h.34.mlp.dense_h_to_4h.weight": "model_00036-of-00072.safetensors",
348
+ "h.34.post_attention_layernorm.bias": "model_00036-of-00072.safetensors",
349
+ "h.34.post_attention_layernorm.weight": "model_00036-of-00072.safetensors",
350
+ "h.34.self_attention.dense.bias": "model_00036-of-00072.safetensors",
351
+ "h.34.self_attention.dense.weight": "model_00036-of-00072.safetensors",
352
+ "h.34.self_attention.query_key_value.bias": "model_00036-of-00072.safetensors",
353
+ "h.34.self_attention.query_key_value.weight": "model_00036-of-00072.safetensors",
354
+ "h.35.input_layernorm.bias": "model_00037-of-00072.safetensors",
355
+ "h.35.input_layernorm.weight": "model_00037-of-00072.safetensors",
356
+ "h.35.mlp.dense_4h_to_h.bias": "model_00037-of-00072.safetensors",
357
+ "h.35.mlp.dense_4h_to_h.weight": "model_00037-of-00072.safetensors",
358
+ "h.35.mlp.dense_h_to_4h.bias": "model_00037-of-00072.safetensors",
359
+ "h.35.mlp.dense_h_to_4h.weight": "model_00037-of-00072.safetensors",
360
+ "h.35.post_attention_layernorm.bias": "model_00037-of-00072.safetensors",
361
+ "h.35.post_attention_layernorm.weight": "model_00037-of-00072.safetensors",
362
+ "h.35.self_attention.dense.bias": "model_00037-of-00072.safetensors",
363
+ "h.35.self_attention.dense.weight": "model_00037-of-00072.safetensors",
364
+ "h.35.self_attention.query_key_value.bias": "model_00037-of-00072.safetensors",
365
+ "h.35.self_attention.query_key_value.weight": "model_00037-of-00072.safetensors",
366
+ "h.36.input_layernorm.bias": "model_00038-of-00072.safetensors",
367
+ "h.36.input_layernorm.weight": "model_00038-of-00072.safetensors",
368
+ "h.36.mlp.dense_4h_to_h.bias": "model_00038-of-00072.safetensors",
369
+ "h.36.mlp.dense_4h_to_h.weight": "model_00038-of-00072.safetensors",
370
+ "h.36.mlp.dense_h_to_4h.bias": "model_00038-of-00072.safetensors",
371
+ "h.36.mlp.dense_h_to_4h.weight": "model_00038-of-00072.safetensors",
372
+ "h.36.post_attention_layernorm.bias": "model_00038-of-00072.safetensors",
373
+ "h.36.post_attention_layernorm.weight": "model_00038-of-00072.safetensors",
374
+ "h.36.self_attention.dense.bias": "model_00038-of-00072.safetensors",
375
+ "h.36.self_attention.dense.weight": "model_00038-of-00072.safetensors",
376
+ "h.36.self_attention.query_key_value.bias": "model_00038-of-00072.safetensors",
377
+ "h.36.self_attention.query_key_value.weight": "model_00038-of-00072.safetensors",
378
+ "h.37.input_layernorm.bias": "model_00039-of-00072.safetensors",
379
+ "h.37.input_layernorm.weight": "model_00039-of-00072.safetensors",
380
+ "h.37.mlp.dense_4h_to_h.bias": "model_00039-of-00072.safetensors",
381
+ "h.37.mlp.dense_4h_to_h.weight": "model_00039-of-00072.safetensors",
382
+ "h.37.mlp.dense_h_to_4h.bias": "model_00039-of-00072.safetensors",
383
+ "h.37.mlp.dense_h_to_4h.weight": "model_00039-of-00072.safetensors",
384
+ "h.37.post_attention_layernorm.bias": "model_00039-of-00072.safetensors",
385
+ "h.37.post_attention_layernorm.weight": "model_00039-of-00072.safetensors",
386
+ "h.37.self_attention.dense.bias": "model_00039-of-00072.safetensors",
387
+ "h.37.self_attention.dense.weight": "model_00039-of-00072.safetensors",
388
+ "h.37.self_attention.query_key_value.bias": "model_00039-of-00072.safetensors",
389
+ "h.37.self_attention.query_key_value.weight": "model_00039-of-00072.safetensors",
390
+ "h.38.input_layernorm.bias": "model_00040-of-00072.safetensors",
391
+ "h.38.input_layernorm.weight": "model_00040-of-00072.safetensors",
392
+ "h.38.mlp.dense_4h_to_h.bias": "model_00040-of-00072.safetensors",
393
+ "h.38.mlp.dense_4h_to_h.weight": "model_00040-of-00072.safetensors",
394
+ "h.38.mlp.dense_h_to_4h.bias": "model_00040-of-00072.safetensors",
395
+ "h.38.mlp.dense_h_to_4h.weight": "model_00040-of-00072.safetensors",
396
+ "h.38.post_attention_layernorm.bias": "model_00040-of-00072.safetensors",
397
+ "h.38.post_attention_layernorm.weight": "model_00040-of-00072.safetensors",
398
+ "h.38.self_attention.dense.bias": "model_00040-of-00072.safetensors",
399
+ "h.38.self_attention.dense.weight": "model_00040-of-00072.safetensors",
400
+ "h.38.self_attention.query_key_value.bias": "model_00040-of-00072.safetensors",
401
+ "h.38.self_attention.query_key_value.weight": "model_00040-of-00072.safetensors",
402
+ "h.39.input_layernorm.bias": "model_00041-of-00072.safetensors",
403
+ "h.39.input_layernorm.weight": "model_00041-of-00072.safetensors",
404
+ "h.39.mlp.dense_4h_to_h.bias": "model_00041-of-00072.safetensors",
405
+ "h.39.mlp.dense_4h_to_h.weight": "model_00041-of-00072.safetensors",
406
+ "h.39.mlp.dense_h_to_4h.bias": "model_00041-of-00072.safetensors",
407
+ "h.39.mlp.dense_h_to_4h.weight": "model_00041-of-00072.safetensors",
408
+ "h.39.post_attention_layernorm.bias": "model_00041-of-00072.safetensors",
409
+ "h.39.post_attention_layernorm.weight": "model_00041-of-00072.safetensors",
410
+ "h.39.self_attention.dense.bias": "model_00041-of-00072.safetensors",
411
+ "h.39.self_attention.dense.weight": "model_00041-of-00072.safetensors",
412
+ "h.39.self_attention.query_key_value.bias": "model_00041-of-00072.safetensors",
413
+ "h.39.self_attention.query_key_value.weight": "model_00041-of-00072.safetensors",
414
+ "h.4.input_layernorm.bias": "model_00006-of-00072.safetensors",
415
+ "h.4.input_layernorm.weight": "model_00006-of-00072.safetensors",
416
+ "h.4.mlp.dense_4h_to_h.bias": "model_00006-of-00072.safetensors",
417
+ "h.4.mlp.dense_4h_to_h.weight": "model_00006-of-00072.safetensors",
418
+ "h.4.mlp.dense_h_to_4h.bias": "model_00006-of-00072.safetensors",
419
+ "h.4.mlp.dense_h_to_4h.weight": "model_00006-of-00072.safetensors",
420
+ "h.4.post_attention_layernorm.bias": "model_00006-of-00072.safetensors",
421
+ "h.4.post_attention_layernorm.weight": "model_00006-of-00072.safetensors",
422
+ "h.4.self_attention.dense.bias": "model_00006-of-00072.safetensors",
423
+ "h.4.self_attention.dense.weight": "model_00006-of-00072.safetensors",
424
+ "h.4.self_attention.query_key_value.bias": "model_00006-of-00072.safetensors",
425
+ "h.4.self_attention.query_key_value.weight": "model_00006-of-00072.safetensors",
426
+ "h.40.input_layernorm.bias": "model_00042-of-00072.safetensors",
427
+ "h.40.input_layernorm.weight": "model_00042-of-00072.safetensors",
428
+ "h.40.mlp.dense_4h_to_h.bias": "model_00042-of-00072.safetensors",
429
+ "h.40.mlp.dense_4h_to_h.weight": "model_00042-of-00072.safetensors",
430
+ "h.40.mlp.dense_h_to_4h.bias": "model_00042-of-00072.safetensors",
431
+ "h.40.mlp.dense_h_to_4h.weight": "model_00042-of-00072.safetensors",
432
+ "h.40.post_attention_layernorm.bias": "model_00042-of-00072.safetensors",
433
+ "h.40.post_attention_layernorm.weight": "model_00042-of-00072.safetensors",
434
+ "h.40.self_attention.dense.bias": "model_00042-of-00072.safetensors",
435
+ "h.40.self_attention.dense.weight": "model_00042-of-00072.safetensors",
436
+ "h.40.self_attention.query_key_value.bias": "model_00042-of-00072.safetensors",
437
+ "h.40.self_attention.query_key_value.weight": "model_00042-of-00072.safetensors",
438
+ "h.41.input_layernorm.bias": "model_00043-of-00072.safetensors",
439
+ "h.41.input_layernorm.weight": "model_00043-of-00072.safetensors",
440
+ "h.41.mlp.dense_4h_to_h.bias": "model_00043-of-00072.safetensors",
441
+ "h.41.mlp.dense_4h_to_h.weight": "model_00043-of-00072.safetensors",
442
+ "h.41.mlp.dense_h_to_4h.bias": "model_00043-of-00072.safetensors",
443
+ "h.41.mlp.dense_h_to_4h.weight": "model_00043-of-00072.safetensors",
444
+ "h.41.post_attention_layernorm.bias": "model_00043-of-00072.safetensors",
445
+ "h.41.post_attention_layernorm.weight": "model_00043-of-00072.safetensors",
446
+ "h.41.self_attention.dense.bias": "model_00043-of-00072.safetensors",
447
+ "h.41.self_attention.dense.weight": "model_00043-of-00072.safetensors",
448
+ "h.41.self_attention.query_key_value.bias": "model_00043-of-00072.safetensors",
449
+ "h.41.self_attention.query_key_value.weight": "model_00043-of-00072.safetensors",
450
+ "h.42.input_layernorm.bias": "model_00044-of-00072.safetensors",
451
+ "h.42.input_layernorm.weight": "model_00044-of-00072.safetensors",
452
+ "h.42.mlp.dense_4h_to_h.bias": "model_00044-of-00072.safetensors",
453
+ "h.42.mlp.dense_4h_to_h.weight": "model_00044-of-00072.safetensors",
454
+ "h.42.mlp.dense_h_to_4h.bias": "model_00044-of-00072.safetensors",
455
+ "h.42.mlp.dense_h_to_4h.weight": "model_00044-of-00072.safetensors",
456
+ "h.42.post_attention_layernorm.bias": "model_00044-of-00072.safetensors",
457
+ "h.42.post_attention_layernorm.weight": "model_00044-of-00072.safetensors",
458
+ "h.42.self_attention.dense.bias": "model_00044-of-00072.safetensors",
459
+ "h.42.self_attention.dense.weight": "model_00044-of-00072.safetensors",
460
+ "h.42.self_attention.query_key_value.bias": "model_00044-of-00072.safetensors",
461
+ "h.42.self_attention.query_key_value.weight": "model_00044-of-00072.safetensors",
462
+ "h.43.input_layernorm.bias": "model_00045-of-00072.safetensors",
463
+ "h.43.input_layernorm.weight": "model_00045-of-00072.safetensors",
464
+ "h.43.mlp.dense_4h_to_h.bias": "model_00045-of-00072.safetensors",
465
+ "h.43.mlp.dense_4h_to_h.weight": "model_00045-of-00072.safetensors",
466
+ "h.43.mlp.dense_h_to_4h.bias": "model_00045-of-00072.safetensors",
467
+ "h.43.mlp.dense_h_to_4h.weight": "model_00045-of-00072.safetensors",
468
+ "h.43.post_attention_layernorm.bias": "model_00045-of-00072.safetensors",
469
+ "h.43.post_attention_layernorm.weight": "model_00045-of-00072.safetensors",
470
+ "h.43.self_attention.dense.bias": "model_00045-of-00072.safetensors",
471
+ "h.43.self_attention.dense.weight": "model_00045-of-00072.safetensors",
472
+ "h.43.self_attention.query_key_value.bias": "model_00045-of-00072.safetensors",
473
+ "h.43.self_attention.query_key_value.weight": "model_00045-of-00072.safetensors",
474
+ "h.44.input_layernorm.bias": "model_00046-of-00072.safetensors",
475
+ "h.44.input_layernorm.weight": "model_00046-of-00072.safetensors",
476
+ "h.44.mlp.dense_4h_to_h.bias": "model_00046-of-00072.safetensors",
477
+ "h.44.mlp.dense_4h_to_h.weight": "model_00046-of-00072.safetensors",
478
+ "h.44.mlp.dense_h_to_4h.bias": "model_00046-of-00072.safetensors",
479
+ "h.44.mlp.dense_h_to_4h.weight": "model_00046-of-00072.safetensors",
480
+ "h.44.post_attention_layernorm.bias": "model_00046-of-00072.safetensors",
481
+ "h.44.post_attention_layernorm.weight": "model_00046-of-00072.safetensors",
482
+ "h.44.self_attention.dense.bias": "model_00046-of-00072.safetensors",
483
+ "h.44.self_attention.dense.weight": "model_00046-of-00072.safetensors",
484
+ "h.44.self_attention.query_key_value.bias": "model_00046-of-00072.safetensors",
485
+ "h.44.self_attention.query_key_value.weight": "model_00046-of-00072.safetensors",
486
+ "h.45.input_layernorm.bias": "model_00047-of-00072.safetensors",
487
+ "h.45.input_layernorm.weight": "model_00047-of-00072.safetensors",
488
+ "h.45.mlp.dense_4h_to_h.bias": "model_00047-of-00072.safetensors",
489
+ "h.45.mlp.dense_4h_to_h.weight": "model_00047-of-00072.safetensors",
490
+ "h.45.mlp.dense_h_to_4h.bias": "model_00047-of-00072.safetensors",
491
+ "h.45.mlp.dense_h_to_4h.weight": "model_00047-of-00072.safetensors",
492
+ "h.45.post_attention_layernorm.bias": "model_00047-of-00072.safetensors",
493
+ "h.45.post_attention_layernorm.weight": "model_00047-of-00072.safetensors",
494
+ "h.45.self_attention.dense.bias": "model_00047-of-00072.safetensors",
495
+ "h.45.self_attention.dense.weight": "model_00047-of-00072.safetensors",
496
+ "h.45.self_attention.query_key_value.bias": "model_00047-of-00072.safetensors",
497
+ "h.45.self_attention.query_key_value.weight": "model_00047-of-00072.safetensors",
498
+ "h.46.input_layernorm.bias": "model_00048-of-00072.safetensors",
499
+ "h.46.input_layernorm.weight": "model_00048-of-00072.safetensors",
500
+ "h.46.mlp.dense_4h_to_h.bias": "model_00048-of-00072.safetensors",
501
+ "h.46.mlp.dense_4h_to_h.weight": "model_00048-of-00072.safetensors",
502
+ "h.46.mlp.dense_h_to_4h.bias": "model_00048-of-00072.safetensors",
503
+ "h.46.mlp.dense_h_to_4h.weight": "model_00048-of-00072.safetensors",
504
+ "h.46.post_attention_layernorm.bias": "model_00048-of-00072.safetensors",
505
+ "h.46.post_attention_layernorm.weight": "model_00048-of-00072.safetensors",
506
+ "h.46.self_attention.dense.bias": "model_00048-of-00072.safetensors",
507
+ "h.46.self_attention.dense.weight": "model_00048-of-00072.safetensors",
508
+ "h.46.self_attention.query_key_value.bias": "model_00048-of-00072.safetensors",
509
+ "h.46.self_attention.query_key_value.weight": "model_00048-of-00072.safetensors",
510
+ "h.47.input_layernorm.bias": "model_00049-of-00072.safetensors",
511
+ "h.47.input_layernorm.weight": "model_00049-of-00072.safetensors",
512
+ "h.47.mlp.dense_4h_to_h.bias": "model_00049-of-00072.safetensors",
513
+ "h.47.mlp.dense_4h_to_h.weight": "model_00049-of-00072.safetensors",
514
+ "h.47.mlp.dense_h_to_4h.bias": "model_00049-of-00072.safetensors",
515
+ "h.47.mlp.dense_h_to_4h.weight": "model_00049-of-00072.safetensors",
516
+ "h.47.post_attention_layernorm.bias": "model_00049-of-00072.safetensors",
517
+ "h.47.post_attention_layernorm.weight": "model_00049-of-00072.safetensors",
518
+ "h.47.self_attention.dense.bias": "model_00049-of-00072.safetensors",
519
+ "h.47.self_attention.dense.weight": "model_00049-of-00072.safetensors",
520
+ "h.47.self_attention.query_key_value.bias": "model_00049-of-00072.safetensors",
521
+ "h.47.self_attention.query_key_value.weight": "model_00049-of-00072.safetensors",
522
+ "h.48.input_layernorm.bias": "model_00050-of-00072.safetensors",
523
+ "h.48.input_layernorm.weight": "model_00050-of-00072.safetensors",
524
+ "h.48.mlp.dense_4h_to_h.bias": "model_00050-of-00072.safetensors",
525
+ "h.48.mlp.dense_4h_to_h.weight": "model_00050-of-00072.safetensors",
526
+ "h.48.mlp.dense_h_to_4h.bias": "model_00050-of-00072.safetensors",
527
+ "h.48.mlp.dense_h_to_4h.weight": "model_00050-of-00072.safetensors",
528
+ "h.48.post_attention_layernorm.bias": "model_00050-of-00072.safetensors",
529
+ "h.48.post_attention_layernorm.weight": "model_00050-of-00072.safetensors",
530
+ "h.48.self_attention.dense.bias": "model_00050-of-00072.safetensors",
531
+ "h.48.self_attention.dense.weight": "model_00050-of-00072.safetensors",
532
+ "h.48.self_attention.query_key_value.bias": "model_00050-of-00072.safetensors",
533
+ "h.48.self_attention.query_key_value.weight": "model_00050-of-00072.safetensors",
534
+ "h.49.input_layernorm.bias": "model_00051-of-00072.safetensors",
535
+ "h.49.input_layernorm.weight": "model_00051-of-00072.safetensors",
536
+ "h.49.mlp.dense_4h_to_h.bias": "model_00051-of-00072.safetensors",
537
+ "h.49.mlp.dense_4h_to_h.weight": "model_00051-of-00072.safetensors",
538
+ "h.49.mlp.dense_h_to_4h.bias": "model_00051-of-00072.safetensors",
539
+ "h.49.mlp.dense_h_to_4h.weight": "model_00051-of-00072.safetensors",
540
+ "h.49.post_attention_layernorm.bias": "model_00051-of-00072.safetensors",
541
+ "h.49.post_attention_layernorm.weight": "model_00051-of-00072.safetensors",
542
+ "h.49.self_attention.dense.bias": "model_00051-of-00072.safetensors",
543
+ "h.49.self_attention.dense.weight": "model_00051-of-00072.safetensors",
544
+ "h.49.self_attention.query_key_value.bias": "model_00051-of-00072.safetensors",
545
+ "h.49.self_attention.query_key_value.weight": "model_00051-of-00072.safetensors",
546
+ "h.5.input_layernorm.bias": "model_00007-of-00072.safetensors",
547
+ "h.5.input_layernorm.weight": "model_00007-of-00072.safetensors",
548
+ "h.5.mlp.dense_4h_to_h.bias": "model_00007-of-00072.safetensors",
549
+ "h.5.mlp.dense_4h_to_h.weight": "model_00007-of-00072.safetensors",
550
+ "h.5.mlp.dense_h_to_4h.bias": "model_00007-of-00072.safetensors",
551
+ "h.5.mlp.dense_h_to_4h.weight": "model_00007-of-00072.safetensors",
552
+ "h.5.post_attention_layernorm.bias": "model_00007-of-00072.safetensors",
553
+ "h.5.post_attention_layernorm.weight": "model_00007-of-00072.safetensors",
554
+ "h.5.self_attention.dense.bias": "model_00007-of-00072.safetensors",
555
+ "h.5.self_attention.dense.weight": "model_00007-of-00072.safetensors",
556
+ "h.5.self_attention.query_key_value.bias": "model_00007-of-00072.safetensors",
557
+ "h.5.self_attention.query_key_value.weight": "model_00007-of-00072.safetensors",
558
+ "h.50.input_layernorm.bias": "model_00052-of-00072.safetensors",
559
+ "h.50.input_layernorm.weight": "model_00052-of-00072.safetensors",
560
+ "h.50.mlp.dense_4h_to_h.bias": "model_00052-of-00072.safetensors",
561
+ "h.50.mlp.dense_4h_to_h.weight": "model_00052-of-00072.safetensors",
562
+ "h.50.mlp.dense_h_to_4h.bias": "model_00052-of-00072.safetensors",
563
+ "h.50.mlp.dense_h_to_4h.weight": "model_00052-of-00072.safetensors",
564
+ "h.50.post_attention_layernorm.bias": "model_00052-of-00072.safetensors",
565
+ "h.50.post_attention_layernorm.weight": "model_00052-of-00072.safetensors",
566
+ "h.50.self_attention.dense.bias": "model_00052-of-00072.safetensors",
567
+ "h.50.self_attention.dense.weight": "model_00052-of-00072.safetensors",
568
+ "h.50.self_attention.query_key_value.bias": "model_00052-of-00072.safetensors",
569
+ "h.50.self_attention.query_key_value.weight": "model_00052-of-00072.safetensors",
570
+ "h.51.input_layernorm.bias": "model_00053-of-00072.safetensors",
571
+ "h.51.input_layernorm.weight": "model_00053-of-00072.safetensors",
572
+ "h.51.mlp.dense_4h_to_h.bias": "model_00053-of-00072.safetensors",
573
+ "h.51.mlp.dense_4h_to_h.weight": "model_00053-of-00072.safetensors",
574
+ "h.51.mlp.dense_h_to_4h.bias": "model_00053-of-00072.safetensors",
575
+ "h.51.mlp.dense_h_to_4h.weight": "model_00053-of-00072.safetensors",
576
+ "h.51.post_attention_layernorm.bias": "model_00053-of-00072.safetensors",
577
+ "h.51.post_attention_layernorm.weight": "model_00053-of-00072.safetensors",
578
+ "h.51.self_attention.dense.bias": "model_00053-of-00072.safetensors",
579
+ "h.51.self_attention.dense.weight": "model_00053-of-00072.safetensors",
580
+ "h.51.self_attention.query_key_value.bias": "model_00053-of-00072.safetensors",
581
+ "h.51.self_attention.query_key_value.weight": "model_00053-of-00072.safetensors",
582
+ "h.52.input_layernorm.bias": "model_00054-of-00072.safetensors",
583
+ "h.52.input_layernorm.weight": "model_00054-of-00072.safetensors",
584
+ "h.52.mlp.dense_4h_to_h.bias": "model_00054-of-00072.safetensors",
585
+ "h.52.mlp.dense_4h_to_h.weight": "model_00054-of-00072.safetensors",
586
+ "h.52.mlp.dense_h_to_4h.bias": "model_00054-of-00072.safetensors",
587
+ "h.52.mlp.dense_h_to_4h.weight": "model_00054-of-00072.safetensors",
588
+ "h.52.post_attention_layernorm.bias": "model_00054-of-00072.safetensors",
589
+ "h.52.post_attention_layernorm.weight": "model_00054-of-00072.safetensors",
590
+ "h.52.self_attention.dense.bias": "model_00054-of-00072.safetensors",
591
+ "h.52.self_attention.dense.weight": "model_00054-of-00072.safetensors",
592
+ "h.52.self_attention.query_key_value.bias": "model_00054-of-00072.safetensors",
593
+ "h.52.self_attention.query_key_value.weight": "model_00054-of-00072.safetensors",
594
+ "h.53.input_layernorm.bias": "model_00055-of-00072.safetensors",
595
+ "h.53.input_layernorm.weight": "model_00055-of-00072.safetensors",
596
+ "h.53.mlp.dense_4h_to_h.bias": "model_00055-of-00072.safetensors",
597
+ "h.53.mlp.dense_4h_to_h.weight": "model_00055-of-00072.safetensors",
598
+ "h.53.mlp.dense_h_to_4h.bias": "model_00055-of-00072.safetensors",
599
+ "h.53.mlp.dense_h_to_4h.weight": "model_00055-of-00072.safetensors",
600
+ "h.53.post_attention_layernorm.bias": "model_00055-of-00072.safetensors",
601
+ "h.53.post_attention_layernorm.weight": "model_00055-of-00072.safetensors",
602
+ "h.53.self_attention.dense.bias": "model_00055-of-00072.safetensors",
603
+ "h.53.self_attention.dense.weight": "model_00055-of-00072.safetensors",
604
+ "h.53.self_attention.query_key_value.bias": "model_00055-of-00072.safetensors",
605
+ "h.53.self_attention.query_key_value.weight": "model_00055-of-00072.safetensors",
606
+ "h.54.input_layernorm.bias": "model_00056-of-00072.safetensors",
607
+ "h.54.input_layernorm.weight": "model_00056-of-00072.safetensors",
608
+ "h.54.mlp.dense_4h_to_h.bias": "model_00056-of-00072.safetensors",
609
+ "h.54.mlp.dense_4h_to_h.weight": "model_00056-of-00072.safetensors",
610
+ "h.54.mlp.dense_h_to_4h.bias": "model_00056-of-00072.safetensors",
611
+ "h.54.mlp.dense_h_to_4h.weight": "model_00056-of-00072.safetensors",
612
+ "h.54.post_attention_layernorm.bias": "model_00056-of-00072.safetensors",
613
+ "h.54.post_attention_layernorm.weight": "model_00056-of-00072.safetensors",
614
+ "h.54.self_attention.dense.bias": "model_00056-of-00072.safetensors",
615
+ "h.54.self_attention.dense.weight": "model_00056-of-00072.safetensors",
616
+ "h.54.self_attention.query_key_value.bias": "model_00056-of-00072.safetensors",
617
+ "h.54.self_attention.query_key_value.weight": "model_00056-of-00072.safetensors",
618
+ "h.55.input_layernorm.bias": "model_00057-of-00072.safetensors",
619
+ "h.55.input_layernorm.weight": "model_00057-of-00072.safetensors",
620
+ "h.55.mlp.dense_4h_to_h.bias": "model_00057-of-00072.safetensors",
621
+ "h.55.mlp.dense_4h_to_h.weight": "model_00057-of-00072.safetensors",
622
+ "h.55.mlp.dense_h_to_4h.bias": "model_00057-of-00072.safetensors",
623
+ "h.55.mlp.dense_h_to_4h.weight": "model_00057-of-00072.safetensors",
624
+ "h.55.post_attention_layernorm.bias": "model_00057-of-00072.safetensors",
625
+ "h.55.post_attention_layernorm.weight": "model_00057-of-00072.safetensors",
626
+ "h.55.self_attention.dense.bias": "model_00057-of-00072.safetensors",
627
+ "h.55.self_attention.dense.weight": "model_00057-of-00072.safetensors",
628
+ "h.55.self_attention.query_key_value.bias": "model_00057-of-00072.safetensors",
629
+ "h.55.self_attention.query_key_value.weight": "model_00057-of-00072.safetensors",
630
+ "h.56.input_layernorm.bias": "model_00058-of-00072.safetensors",
631
+ "h.56.input_layernorm.weight": "model_00058-of-00072.safetensors",
632
+ "h.56.mlp.dense_4h_to_h.bias": "model_00058-of-00072.safetensors",
633
+ "h.56.mlp.dense_4h_to_h.weight": "model_00058-of-00072.safetensors",
634
+ "h.56.mlp.dense_h_to_4h.bias": "model_00058-of-00072.safetensors",
635
+ "h.56.mlp.dense_h_to_4h.weight": "model_00058-of-00072.safetensors",
636
+ "h.56.post_attention_layernorm.bias": "model_00058-of-00072.safetensors",
637
+ "h.56.post_attention_layernorm.weight": "model_00058-of-00072.safetensors",
638
+ "h.56.self_attention.dense.bias": "model_00058-of-00072.safetensors",
639
+ "h.56.self_attention.dense.weight": "model_00058-of-00072.safetensors",
640
+ "h.56.self_attention.query_key_value.bias": "model_00058-of-00072.safetensors",
641
+ "h.56.self_attention.query_key_value.weight": "model_00058-of-00072.safetensors",
642
+ "h.57.input_layernorm.bias": "model_00059-of-00072.safetensors",
643
+ "h.57.input_layernorm.weight": "model_00059-of-00072.safetensors",
644
+ "h.57.mlp.dense_4h_to_h.bias": "model_00059-of-00072.safetensors",
645
+ "h.57.mlp.dense_4h_to_h.weight": "model_00059-of-00072.safetensors",
646
+ "h.57.mlp.dense_h_to_4h.bias": "model_00059-of-00072.safetensors",
647
+ "h.57.mlp.dense_h_to_4h.weight": "model_00059-of-00072.safetensors",
648
+ "h.57.post_attention_layernorm.bias": "model_00059-of-00072.safetensors",
649
+ "h.57.post_attention_layernorm.weight": "model_00059-of-00072.safetensors",
650
+ "h.57.self_attention.dense.bias": "model_00059-of-00072.safetensors",
651
+ "h.57.self_attention.dense.weight": "model_00059-of-00072.safetensors",
652
+ "h.57.self_attention.query_key_value.bias": "model_00059-of-00072.safetensors",
653
+ "h.57.self_attention.query_key_value.weight": "model_00059-of-00072.safetensors",
654
+ "h.58.input_layernorm.bias": "model_00060-of-00072.safetensors",
655
+ "h.58.input_layernorm.weight": "model_00060-of-00072.safetensors",
656
+ "h.58.mlp.dense_4h_to_h.bias": "model_00060-of-00072.safetensors",
657
+ "h.58.mlp.dense_4h_to_h.weight": "model_00060-of-00072.safetensors",
658
+ "h.58.mlp.dense_h_to_4h.bias": "model_00060-of-00072.safetensors",
659
+ "h.58.mlp.dense_h_to_4h.weight": "model_00060-of-00072.safetensors",
660
+ "h.58.post_attention_layernorm.bias": "model_00060-of-00072.safetensors",
661
+ "h.58.post_attention_layernorm.weight": "model_00060-of-00072.safetensors",
662
+ "h.58.self_attention.dense.bias": "model_00060-of-00072.safetensors",
663
+ "h.58.self_attention.dense.weight": "model_00060-of-00072.safetensors",
664
+ "h.58.self_attention.query_key_value.bias": "model_00060-of-00072.safetensors",
665
+ "h.58.self_attention.query_key_value.weight": "model_00060-of-00072.safetensors",
666
+ "h.59.input_layernorm.bias": "model_00061-of-00072.safetensors",
667
+ "h.59.input_layernorm.weight": "model_00061-of-00072.safetensors",
668
+ "h.59.mlp.dense_4h_to_h.bias": "model_00061-of-00072.safetensors",
669
+ "h.59.mlp.dense_4h_to_h.weight": "model_00061-of-00072.safetensors",
670
+ "h.59.mlp.dense_h_to_4h.bias": "model_00061-of-00072.safetensors",
671
+ "h.59.mlp.dense_h_to_4h.weight": "model_00061-of-00072.safetensors",
672
+ "h.59.post_attention_layernorm.bias": "model_00061-of-00072.safetensors",
673
+ "h.59.post_attention_layernorm.weight": "model_00061-of-00072.safetensors",
674
+ "h.59.self_attention.dense.bias": "model_00061-of-00072.safetensors",
675
+ "h.59.self_attention.dense.weight": "model_00061-of-00072.safetensors",
676
+ "h.59.self_attention.query_key_value.bias": "model_00061-of-00072.safetensors",
677
+ "h.59.self_attention.query_key_value.weight": "model_00061-of-00072.safetensors",
678
+ "h.6.input_layernorm.bias": "model_00008-of-00072.safetensors",
679
+ "h.6.input_layernorm.weight": "model_00008-of-00072.safetensors",
680
+ "h.6.mlp.dense_4h_to_h.bias": "model_00008-of-00072.safetensors",
681
+ "h.6.mlp.dense_4h_to_h.weight": "model_00008-of-00072.safetensors",
682
+ "h.6.mlp.dense_h_to_4h.bias": "model_00008-of-00072.safetensors",
683
+ "h.6.mlp.dense_h_to_4h.weight": "model_00008-of-00072.safetensors",
684
+ "h.6.post_attention_layernorm.bias": "model_00008-of-00072.safetensors",
685
+ "h.6.post_attention_layernorm.weight": "model_00008-of-00072.safetensors",
686
+ "h.6.self_attention.dense.bias": "model_00008-of-00072.safetensors",
687
+ "h.6.self_attention.dense.weight": "model_00008-of-00072.safetensors",
688
+ "h.6.self_attention.query_key_value.bias": "model_00008-of-00072.safetensors",
689
+ "h.6.self_attention.query_key_value.weight": "model_00008-of-00072.safetensors",
690
+ "h.60.input_layernorm.bias": "model_00062-of-00072.safetensors",
691
+ "h.60.input_layernorm.weight": "model_00062-of-00072.safetensors",
692
+ "h.60.mlp.dense_4h_to_h.bias": "model_00062-of-00072.safetensors",
693
+ "h.60.mlp.dense_4h_to_h.weight": "model_00062-of-00072.safetensors",
694
+ "h.60.mlp.dense_h_to_4h.bias": "model_00062-of-00072.safetensors",
695
+ "h.60.mlp.dense_h_to_4h.weight": "model_00062-of-00072.safetensors",
696
+ "h.60.post_attention_layernorm.bias": "model_00062-of-00072.safetensors",
697
+ "h.60.post_attention_layernorm.weight": "model_00062-of-00072.safetensors",
698
+ "h.60.self_attention.dense.bias": "model_00062-of-00072.safetensors",
699
+ "h.60.self_attention.dense.weight": "model_00062-of-00072.safetensors",
700
+ "h.60.self_attention.query_key_value.bias": "model_00062-of-00072.safetensors",
701
+ "h.60.self_attention.query_key_value.weight": "model_00062-of-00072.safetensors",
702
+ "h.61.input_layernorm.bias": "model_00063-of-00072.safetensors",
703
+ "h.61.input_layernorm.weight": "model_00063-of-00072.safetensors",
704
+ "h.61.mlp.dense_4h_to_h.bias": "model_00063-of-00072.safetensors",
705
+ "h.61.mlp.dense_4h_to_h.weight": "model_00063-of-00072.safetensors",
706
+ "h.61.mlp.dense_h_to_4h.bias": "model_00063-of-00072.safetensors",
707
+ "h.61.mlp.dense_h_to_4h.weight": "model_00063-of-00072.safetensors",
708
+ "h.61.post_attention_layernorm.bias": "model_00063-of-00072.safetensors",
709
+ "h.61.post_attention_layernorm.weight": "model_00063-of-00072.safetensors",
710
+ "h.61.self_attention.dense.bias": "model_00063-of-00072.safetensors",
711
+ "h.61.self_attention.dense.weight": "model_00063-of-00072.safetensors",
712
+ "h.61.self_attention.query_key_value.bias": "model_00063-of-00072.safetensors",
713
+ "h.61.self_attention.query_key_value.weight": "model_00063-of-00072.safetensors",
714
+ "h.62.input_layernorm.bias": "model_00064-of-00072.safetensors",
715
+ "h.62.input_layernorm.weight": "model_00064-of-00072.safetensors",
716
+ "h.62.mlp.dense_4h_to_h.bias": "model_00064-of-00072.safetensors",
717
+ "h.62.mlp.dense_4h_to_h.weight": "model_00064-of-00072.safetensors",
718
+ "h.62.mlp.dense_h_to_4h.bias": "model_00064-of-00072.safetensors",
719
+ "h.62.mlp.dense_h_to_4h.weight": "model_00064-of-00072.safetensors",
720
+ "h.62.post_attention_layernorm.bias": "model_00064-of-00072.safetensors",
721
+ "h.62.post_attention_layernorm.weight": "model_00064-of-00072.safetensors",
722
+ "h.62.self_attention.dense.bias": "model_00064-of-00072.safetensors",
723
+ "h.62.self_attention.dense.weight": "model_00064-of-00072.safetensors",
724
+ "h.62.self_attention.query_key_value.bias": "model_00064-of-00072.safetensors",
725
+ "h.62.self_attention.query_key_value.weight": "model_00064-of-00072.safetensors",
726
+ "h.63.input_layernorm.bias": "model_00065-of-00072.safetensors",
727
+ "h.63.input_layernorm.weight": "model_00065-of-00072.safetensors",
728
+ "h.63.mlp.dense_4h_to_h.bias": "model_00065-of-00072.safetensors",
729
+ "h.63.mlp.dense_4h_to_h.weight": "model_00065-of-00072.safetensors",
730
+ "h.63.mlp.dense_h_to_4h.bias": "model_00065-of-00072.safetensors",
731
+ "h.63.mlp.dense_h_to_4h.weight": "model_00065-of-00072.safetensors",
732
+ "h.63.post_attention_layernorm.bias": "model_00065-of-00072.safetensors",
733
+ "h.63.post_attention_layernorm.weight": "model_00065-of-00072.safetensors",
734
+ "h.63.self_attention.dense.bias": "model_00065-of-00072.safetensors",
735
+ "h.63.self_attention.dense.weight": "model_00065-of-00072.safetensors",
736
+ "h.63.self_attention.query_key_value.bias": "model_00065-of-00072.safetensors",
737
+ "h.63.self_attention.query_key_value.weight": "model_00065-of-00072.safetensors",
738
+ "h.64.input_layernorm.bias": "model_00066-of-00072.safetensors",
739
+ "h.64.input_layernorm.weight": "model_00066-of-00072.safetensors",
740
+ "h.64.mlp.dense_4h_to_h.bias": "model_00066-of-00072.safetensors",
741
+ "h.64.mlp.dense_4h_to_h.weight": "model_00066-of-00072.safetensors",
742
+ "h.64.mlp.dense_h_to_4h.bias": "model_00066-of-00072.safetensors",
743
+ "h.64.mlp.dense_h_to_4h.weight": "model_00066-of-00072.safetensors",
744
+ "h.64.post_attention_layernorm.bias": "model_00066-of-00072.safetensors",
745
+ "h.64.post_attention_layernorm.weight": "model_00066-of-00072.safetensors",
746
+ "h.64.self_attention.dense.bias": "model_00066-of-00072.safetensors",
747
+ "h.64.self_attention.dense.weight": "model_00066-of-00072.safetensors",
748
+ "h.64.self_attention.query_key_value.bias": "model_00066-of-00072.safetensors",
749
+ "h.64.self_attention.query_key_value.weight": "model_00066-of-00072.safetensors",
750
+ "h.65.input_layernorm.bias": "model_00067-of-00072.safetensors",
751
+ "h.65.input_layernorm.weight": "model_00067-of-00072.safetensors",
752
+ "h.65.mlp.dense_4h_to_h.bias": "model_00067-of-00072.safetensors",
753
+ "h.65.mlp.dense_4h_to_h.weight": "model_00067-of-00072.safetensors",
754
+ "h.65.mlp.dense_h_to_4h.bias": "model_00067-of-00072.safetensors",
755
+ "h.65.mlp.dense_h_to_4h.weight": "model_00067-of-00072.safetensors",
756
+ "h.65.post_attention_layernorm.bias": "model_00067-of-00072.safetensors",
757
+ "h.65.post_attention_layernorm.weight": "model_00067-of-00072.safetensors",
758
+ "h.65.self_attention.dense.bias": "model_00067-of-00072.safetensors",
759
+ "h.65.self_attention.dense.weight": "model_00067-of-00072.safetensors",
760
+ "h.65.self_attention.query_key_value.bias": "model_00067-of-00072.safetensors",
761
+ "h.65.self_attention.query_key_value.weight": "model_00067-of-00072.safetensors",
762
+ "h.66.input_layernorm.bias": "model_00068-of-00072.safetensors",
763
+ "h.66.input_layernorm.weight": "model_00068-of-00072.safetensors",
764
+ "h.66.mlp.dense_4h_to_h.bias": "model_00068-of-00072.safetensors",
765
+ "h.66.mlp.dense_4h_to_h.weight": "model_00068-of-00072.safetensors",
766
+ "h.66.mlp.dense_h_to_4h.bias": "model_00068-of-00072.safetensors",
767
+ "h.66.mlp.dense_h_to_4h.weight": "model_00068-of-00072.safetensors",
768
+ "h.66.post_attention_layernorm.bias": "model_00068-of-00072.safetensors",
769
+ "h.66.post_attention_layernorm.weight": "model_00068-of-00072.safetensors",
770
+ "h.66.self_attention.dense.bias": "model_00068-of-00072.safetensors",
771
+ "h.66.self_attention.dense.weight": "model_00068-of-00072.safetensors",
772
+ "h.66.self_attention.query_key_value.bias": "model_00068-of-00072.safetensors",
773
+ "h.66.self_attention.query_key_value.weight": "model_00068-of-00072.safetensors",
774
+ "h.67.input_layernorm.bias": "model_00069-of-00072.safetensors",
775
+ "h.67.input_layernorm.weight": "model_00069-of-00072.safetensors",
776
+ "h.67.mlp.dense_4h_to_h.bias": "model_00069-of-00072.safetensors",
777
+ "h.67.mlp.dense_4h_to_h.weight": "model_00069-of-00072.safetensors",
778
+ "h.67.mlp.dense_h_to_4h.bias": "model_00069-of-00072.safetensors",
779
+ "h.67.mlp.dense_h_to_4h.weight": "model_00069-of-00072.safetensors",
780
+ "h.67.post_attention_layernorm.bias": "model_00069-of-00072.safetensors",
781
+ "h.67.post_attention_layernorm.weight": "model_00069-of-00072.safetensors",
782
+ "h.67.self_attention.dense.bias": "model_00069-of-00072.safetensors",
783
+ "h.67.self_attention.dense.weight": "model_00069-of-00072.safetensors",
784
+ "h.67.self_attention.query_key_value.bias": "model_00069-of-00072.safetensors",
785
+ "h.67.self_attention.query_key_value.weight": "model_00069-of-00072.safetensors",
786
+ "h.68.input_layernorm.bias": "model_00070-of-00072.safetensors",
787
+ "h.68.input_layernorm.weight": "model_00070-of-00072.safetensors",
788
+ "h.68.mlp.dense_4h_to_h.bias": "model_00070-of-00072.safetensors",
789
+ "h.68.mlp.dense_4h_to_h.weight": "model_00070-of-00072.safetensors",
790
+ "h.68.mlp.dense_h_to_4h.bias": "model_00070-of-00072.safetensors",
791
+ "h.68.mlp.dense_h_to_4h.weight": "model_00070-of-00072.safetensors",
792
+ "h.68.post_attention_layernorm.bias": "model_00070-of-00072.safetensors",
793
+ "h.68.post_attention_layernorm.weight": "model_00070-of-00072.safetensors",
794
+ "h.68.self_attention.dense.bias": "model_00070-of-00072.safetensors",
795
+ "h.68.self_attention.dense.weight": "model_00070-of-00072.safetensors",
796
+ "h.68.self_attention.query_key_value.bias": "model_00070-of-00072.safetensors",
797
+ "h.68.self_attention.query_key_value.weight": "model_00070-of-00072.safetensors",
798
+ "h.69.input_layernorm.bias": "model_00071-of-00072.safetensors",
799
+ "h.69.input_layernorm.weight": "model_00071-of-00072.safetensors",
800
+ "h.69.mlp.dense_4h_to_h.bias": "model_00071-of-00072.safetensors",
801
+ "h.69.mlp.dense_4h_to_h.weight": "model_00071-of-00072.safetensors",
802
+ "h.69.mlp.dense_h_to_4h.bias": "model_00071-of-00072.safetensors",
803
+ "h.69.mlp.dense_h_to_4h.weight": "model_00071-of-00072.safetensors",
804
+ "h.69.post_attention_layernorm.bias": "model_00071-of-00072.safetensors",
805
+ "h.69.post_attention_layernorm.weight": "model_00071-of-00072.safetensors",
806
+ "h.69.self_attention.dense.bias": "model_00071-of-00072.safetensors",
807
+ "h.69.self_attention.dense.weight": "model_00071-of-00072.safetensors",
808
+ "h.69.self_attention.query_key_value.bias": "model_00071-of-00072.safetensors",
809
+ "h.69.self_attention.query_key_value.weight": "model_00071-of-00072.safetensors",
810
+ "h.7.input_layernorm.bias": "model_00009-of-00072.safetensors",
811
+ "h.7.input_layernorm.weight": "model_00009-of-00072.safetensors",
812
+ "h.7.mlp.dense_4h_to_h.bias": "model_00009-of-00072.safetensors",
813
+ "h.7.mlp.dense_4h_to_h.weight": "model_00009-of-00072.safetensors",
814
+ "h.7.mlp.dense_h_to_4h.bias": "model_00009-of-00072.safetensors",
815
+ "h.7.mlp.dense_h_to_4h.weight": "model_00009-of-00072.safetensors",
816
+ "h.7.post_attention_layernorm.bias": "model_00009-of-00072.safetensors",
817
+ "h.7.post_attention_layernorm.weight": "model_00009-of-00072.safetensors",
818
+ "h.7.self_attention.dense.bias": "model_00009-of-00072.safetensors",
819
+ "h.7.self_attention.dense.weight": "model_00009-of-00072.safetensors",
820
+ "h.7.self_attention.query_key_value.bias": "model_00009-of-00072.safetensors",
821
+ "h.7.self_attention.query_key_value.weight": "model_00009-of-00072.safetensors",
822
+ "h.8.input_layernorm.bias": "model_00010-of-00072.safetensors",
823
+ "h.8.input_layernorm.weight": "model_00010-of-00072.safetensors",
824
+ "h.8.mlp.dense_4h_to_h.bias": "model_00010-of-00072.safetensors",
825
+ "h.8.mlp.dense_4h_to_h.weight": "model_00010-of-00072.safetensors",
826
+ "h.8.mlp.dense_h_to_4h.bias": "model_00010-of-00072.safetensors",
827
+ "h.8.mlp.dense_h_to_4h.weight": "model_00010-of-00072.safetensors",
828
+ "h.8.post_attention_layernorm.bias": "model_00010-of-00072.safetensors",
829
+ "h.8.post_attention_layernorm.weight": "model_00010-of-00072.safetensors",
830
+ "h.8.self_attention.dense.bias": "model_00010-of-00072.safetensors",
831
+ "h.8.self_attention.dense.weight": "model_00010-of-00072.safetensors",
832
+ "h.8.self_attention.query_key_value.bias": "model_00010-of-00072.safetensors",
833
+ "h.8.self_attention.query_key_value.weight": "model_00010-of-00072.safetensors",
834
+ "h.9.input_layernorm.bias": "model_00011-of-00072.safetensors",
835
+ "h.9.input_layernorm.weight": "model_00011-of-00072.safetensors",
836
+ "h.9.mlp.dense_4h_to_h.bias": "model_00011-of-00072.safetensors",
837
+ "h.9.mlp.dense_4h_to_h.weight": "model_00011-of-00072.safetensors",
838
+ "h.9.mlp.dense_h_to_4h.bias": "model_00011-of-00072.safetensors",
839
+ "h.9.mlp.dense_h_to_4h.weight": "model_00011-of-00072.safetensors",
840
+ "h.9.post_attention_layernorm.bias": "model_00011-of-00072.safetensors",
841
+ "h.9.post_attention_layernorm.weight": "model_00011-of-00072.safetensors",
842
+ "h.9.self_attention.dense.bias": "model_00011-of-00072.safetensors",
843
+ "h.9.self_attention.dense.weight": "model_00011-of-00072.safetensors",
844
+ "h.9.self_attention.query_key_value.bias": "model_00011-of-00072.safetensors",
845
+ "h.9.self_attention.query_key_value.weight": "model_00011-of-00072.safetensors",
846
+ "ln_f.bias": "model_00072-of-00072.safetensors",
847
+ "ln_f.weight": "model_00072-of-00072.safetensors",
848
+ "word_embeddings.weight": "model_00001-of-00072.safetensors",
849
+ "word_embeddings_layernorm.bias": "model_00001-of-00072.safetensors",
850
+ "word_embeddings_layernorm.weight": "model_00001-of-00072.safetensors"
851
+ }
852
+ }