Hugging Face's logo

bigscience
/
bloom

Text Generation Transformers PyTorch TensorBoard Safetensors 46 languages
bloom Eval Results Carbon Emissions Inference Endpoints text-generation-inference 4 papers
Model card Files Metrics Community
275
bigscience-bot commited on
Commit
510180a
•
1 Parent(s): e1cf111

new data

Browse files
Files changed (2) hide show
  1. config.json +26 -0
  2. pytorch_model.bin.index.json +852 -0
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_residual_connection_post_layernorm": false,
3
+ "attention_dropout": 0.0,
4
+ "attention_softmax_in_fp32": true,
5
+ "bias_dropout_fusion": true,
6
+ "bos_token_id": 50256,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 50256,
9
+ "hidden_dropout": 0.0,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "masked_softmax_fusion": true,
13
+ "model_type": "bloom",
14
+ "n_embed": 14336,
15
+ "n_inner": null,
16
+ "n_layer": 70,
17
+ "num_attention_heads": 112,
18
+ "offset_alibi": 100,
19
+ "pretraining_tp": 4,
20
+ "seq_length": 2048,
21
+ "skip_bias_add": true,
22
+ "skip_bias_add_qkv": false,
23
+ "transformers_version": "4.20.0.dev0",
24
+ "use_cache": false,
25
+ "vocab_size": 250880
26
+ }
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,852 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 256701667093757598507563477393900852847546398236101558255428058075828224
4
+ },
5
+ "weight_map": {
6
+ "h.0.input_layernorm.bias": "pytorch_model_00002-of-00072.bin",
7
+ "h.0.input_layernorm.weight": "pytorch_model_00002-of-00072.bin",
8
+ "h.0.mlp.dense_4h_to_h.bias": "pytorch_model_00002-of-00072.bin",
9
+ "h.0.mlp.dense_4h_to_h.weight": "pytorch_model_00002-of-00072.bin",
10
+ "h.0.mlp.dense_h_to_4h.bias": "pytorch_model_00002-of-00072.bin",
11
+ "h.0.mlp.dense_h_to_4h.weight": "pytorch_model_00002-of-00072.bin",
12
+ "h.0.post_attention_layernorm.bias": "pytorch_model_00002-of-00072.bin",
13
+ "h.0.post_attention_layernorm.weight": "pytorch_model_00002-of-00072.bin",
14
+ "h.0.self_attention.dense.bias": "pytorch_model_00002-of-00072.bin",
15
+ "h.0.self_attention.dense.weight": "pytorch_model_00002-of-00072.bin",
16
+ "h.0.self_attention.query_key_value.bias": "pytorch_model_00002-of-00072.bin",
17
+ "h.0.self_attention.query_key_value.weight": "pytorch_model_00002-of-00072.bin",
18
+ "h.1.input_layernorm.bias": "pytorch_model_00003-of-00072.bin",
19
+ "h.1.input_layernorm.weight": "pytorch_model_00003-of-00072.bin",
20
+ "h.1.mlp.dense_4h_to_h.bias": "pytorch_model_00003-of-00072.bin",
21
+ "h.1.mlp.dense_4h_to_h.weight": "pytorch_model_00003-of-00072.bin",
22
+ "h.1.mlp.dense_h_to_4h.bias": "pytorch_model_00003-of-00072.bin",
23
+ "h.1.mlp.dense_h_to_4h.weight": "pytorch_model_00003-of-00072.bin",
24
+ "h.1.post_attention_layernorm.bias": "pytorch_model_00003-of-00072.bin",
25
+ "h.1.post_attention_layernorm.weight": "pytorch_model_00003-of-00072.bin",
26
+ "h.1.self_attention.dense.bias": "pytorch_model_00003-of-00072.bin",
27
+ "h.1.self_attention.dense.weight": "pytorch_model_00003-of-00072.bin",
28
+ "h.1.self_attention.query_key_value.bias": "pytorch_model_00003-of-00072.bin",
29
+ "h.1.self_attention.query_key_value.weight": "pytorch_model_00003-of-00072.bin",
30
+ "h.10.input_layernorm.bias": "pytorch_model_00012-of-00072.bin",
31
+ "h.10.input_layernorm.weight": "pytorch_model_00012-of-00072.bin",
32
+ "h.10.mlp.dense_4h_to_h.bias": "pytorch_model_00012-of-00072.bin",
33
+ "h.10.mlp.dense_4h_to_h.weight": "pytorch_model_00012-of-00072.bin",
34
+ "h.10.mlp.dense_h_to_4h.bias": "pytorch_model_00012-of-00072.bin",
35
+ "h.10.mlp.dense_h_to_4h.weight": "pytorch_model_00012-of-00072.bin",
36
+ "h.10.post_attention_layernorm.bias": "pytorch_model_00012-of-00072.bin",
37
+ "h.10.post_attention_layernorm.weight": "pytorch_model_00012-of-00072.bin",
38
+ "h.10.self_attention.dense.bias": "pytorch_model_00012-of-00072.bin",
39
+ "h.10.self_attention.dense.weight": "pytorch_model_00012-of-00072.bin",
40
+ "h.10.self_attention.query_key_value.bias": "pytorch_model_00012-of-00072.bin",
41
+ "h.10.self_attention.query_key_value.weight": "pytorch_model_00012-of-00072.bin",
42
+ "h.11.input_layernorm.bias": "pytorch_model_00013-of-00072.bin",
43
+ "h.11.input_layernorm.weight": "pytorch_model_00013-of-00072.bin",
44
+ "h.11.mlp.dense_4h_to_h.bias": "pytorch_model_00013-of-00072.bin",
45
+ "h.11.mlp.dense_4h_to_h.weight": "pytorch_model_00013-of-00072.bin",
46
+ "h.11.mlp.dense_h_to_4h.bias": "pytorch_model_00013-of-00072.bin",
47
+ "h.11.mlp.dense_h_to_4h.weight": "pytorch_model_00013-of-00072.bin",
48
+ "h.11.post_attention_layernorm.bias": "pytorch_model_00013-of-00072.bin",
49
+ "h.11.post_attention_layernorm.weight": "pytorch_model_00013-of-00072.bin",
50
+ "h.11.self_attention.dense.bias": "pytorch_model_00013-of-00072.bin",
51
+ "h.11.self_attention.dense.weight": "pytorch_model_00013-of-00072.bin",
52
+ "h.11.self_attention.query_key_value.bias": "pytorch_model_00013-of-00072.bin",
53
+ "h.11.self_attention.query_key_value.weight": "pytorch_model_00013-of-00072.bin",
54
+ "h.12.input_layernorm.bias": "pytorch_model_00014-of-00072.bin",
55
+ "h.12.input_layernorm.weight": "pytorch_model_00014-of-00072.bin",
56
+ "h.12.mlp.dense_4h_to_h.bias": "pytorch_model_00014-of-00072.bin",
57
+ "h.12.mlp.dense_4h_to_h.weight": "pytorch_model_00014-of-00072.bin",
58
+ "h.12.mlp.dense_h_to_4h.bias": "pytorch_model_00014-of-00072.bin",
59
+ "h.12.mlp.dense_h_to_4h.weight": "pytorch_model_00014-of-00072.bin",
60
+ "h.12.post_attention_layernorm.bias": "pytorch_model_00014-of-00072.bin",
61
+ "h.12.post_attention_layernorm.weight": "pytorch_model_00014-of-00072.bin",
62
+ "h.12.self_attention.dense.bias": "pytorch_model_00014-of-00072.bin",
63
+ "h.12.self_attention.dense.weight": "pytorch_model_00014-of-00072.bin",
64
+ "h.12.self_attention.query_key_value.bias": "pytorch_model_00014-of-00072.bin",
65
+ "h.12.self_attention.query_key_value.weight": "pytorch_model_00014-of-00072.bin",
66
+ "h.13.input_layernorm.bias": "pytorch_model_00015-of-00072.bin",
67
+ "h.13.input_layernorm.weight": "pytorch_model_00015-of-00072.bin",
68
+ "h.13.mlp.dense_4h_to_h.bias": "pytorch_model_00015-of-00072.bin",
69
+ "h.13.mlp.dense_4h_to_h.weight": "pytorch_model_00015-of-00072.bin",
70
+ "h.13.mlp.dense_h_to_4h.bias": "pytorch_model_00015-of-00072.bin",
71
+ "h.13.mlp.dense_h_to_4h.weight": "pytorch_model_00015-of-00072.bin",
72
+ "h.13.post_attention_layernorm.bias": "pytorch_model_00015-of-00072.bin",
73
+ "h.13.post_attention_layernorm.weight": "pytorch_model_00015-of-00072.bin",
74
+ "h.13.self_attention.dense.bias": "pytorch_model_00015-of-00072.bin",
75
+ "h.13.self_attention.dense.weight": "pytorch_model_00015-of-00072.bin",
76
+ "h.13.self_attention.query_key_value.bias": "pytorch_model_00015-of-00072.bin",
77
+ "h.13.self_attention.query_key_value.weight": "pytorch_model_00015-of-00072.bin",
78
+ "h.14.input_layernorm.bias": "pytorch_model_00016-of-00072.bin",
79
+ "h.14.input_layernorm.weight": "pytorch_model_00016-of-00072.bin",
80
+ "h.14.mlp.dense_4h_to_h.bias": "pytorch_model_00016-of-00072.bin",
81
+ "h.14.mlp.dense_4h_to_h.weight": "pytorch_model_00016-of-00072.bin",
82
+ "h.14.mlp.dense_h_to_4h.bias": "pytorch_model_00016-of-00072.bin",
83
+ "h.14.mlp.dense_h_to_4h.weight": "pytorch_model_00016-of-00072.bin",
84
+ "h.14.post_attention_layernorm.bias": "pytorch_model_00016-of-00072.bin",
85
+ "h.14.post_attention_layernorm.weight": "pytorch_model_00016-of-00072.bin",
86
+ "h.14.self_attention.dense.bias": "pytorch_model_00016-of-00072.bin",
87
+ "h.14.self_attention.dense.weight": "pytorch_model_00016-of-00072.bin",
88
+ "h.14.self_attention.query_key_value.bias": "pytorch_model_00016-of-00072.bin",
89
+ "h.14.self_attention.query_key_value.weight": "pytorch_model_00016-of-00072.bin",
90
+ "h.15.input_layernorm.bias": "pytorch_model_00017-of-00072.bin",
91
+ "h.15.input_layernorm.weight": "pytorch_model_00017-of-00072.bin",
92
+ "h.15.mlp.dense_4h_to_h.bias": "pytorch_model_00017-of-00072.bin",
93
+ "h.15.mlp.dense_4h_to_h.weight": "pytorch_model_00017-of-00072.bin",
94
+ "h.15.mlp.dense_h_to_4h.bias": "pytorch_model_00017-of-00072.bin",
95
+ "h.15.mlp.dense_h_to_4h.weight": "pytorch_model_00017-of-00072.bin",
96
+ "h.15.post_attention_layernorm.bias": "pytorch_model_00017-of-00072.bin",
97
+ "h.15.post_attention_layernorm.weight": "pytorch_model_00017-of-00072.bin",
98
+ "h.15.self_attention.dense.bias": "pytorch_model_00017-of-00072.bin",
99
+ "h.15.self_attention.dense.weight": "pytorch_model_00017-of-00072.bin",
100
+ "h.15.self_attention.query_key_value.bias": "pytorch_model_00017-of-00072.bin",
101
+ "h.15.self_attention.query_key_value.weight": "pytorch_model_00017-of-00072.bin",
102
+ "h.16.input_layernorm.bias": "pytorch_model_00018-of-00072.bin",
103
+ "h.16.input_layernorm.weight": "pytorch_model_00018-of-00072.bin",
104
+ "h.16.mlp.dense_4h_to_h.bias": "pytorch_model_00018-of-00072.bin",
105
+ "h.16.mlp.dense_4h_to_h.weight": "pytorch_model_00018-of-00072.bin",
106
+ "h.16.mlp.dense_h_to_4h.bias": "pytorch_model_00018-of-00072.bin",
107
+ "h.16.mlp.dense_h_to_4h.weight": "pytorch_model_00018-of-00072.bin",
108
+ "h.16.post_attention_layernorm.bias": "pytorch_model_00018-of-00072.bin",
109
+ "h.16.post_attention_layernorm.weight": "pytorch_model_00018-of-00072.bin",
110
+ "h.16.self_attention.dense.bias": "pytorch_model_00018-of-00072.bin",
111
+ "h.16.self_attention.dense.weight": "pytorch_model_00018-of-00072.bin",
112
+ "h.16.self_attention.query_key_value.bias": "pytorch_model_00018-of-00072.bin",
113
+ "h.16.self_attention.query_key_value.weight": "pytorch_model_00018-of-00072.bin",
114
+ "h.17.input_layernorm.bias": "pytorch_model_00019-of-00072.bin",
115
+ "h.17.input_layernorm.weight": "pytorch_model_00019-of-00072.bin",
116
+ "h.17.mlp.dense_4h_to_h.bias": "pytorch_model_00019-of-00072.bin",
117
+ "h.17.mlp.dense_4h_to_h.weight": "pytorch_model_00019-of-00072.bin",
118
+ "h.17.mlp.dense_h_to_4h.bias": "pytorch_model_00019-of-00072.bin",
119
+ "h.17.mlp.dense_h_to_4h.weight": "pytorch_model_00019-of-00072.bin",
120
+ "h.17.post_attention_layernorm.bias": "pytorch_model_00019-of-00072.bin",
121
+ "h.17.post_attention_layernorm.weight": "pytorch_model_00019-of-00072.bin",
122
+ "h.17.self_attention.dense.bias": "pytorch_model_00019-of-00072.bin",
123
+ "h.17.self_attention.dense.weight": "pytorch_model_00019-of-00072.bin",
124
+ "h.17.self_attention.query_key_value.bias": "pytorch_model_00019-of-00072.bin",
125
+ "h.17.self_attention.query_key_value.weight": "pytorch_model_00019-of-00072.bin",
126
+ "h.18.input_layernorm.bias": "pytorch_model_00020-of-00072.bin",
127
+ "h.18.input_layernorm.weight": "pytorch_model_00020-of-00072.bin",
128
+ "h.18.mlp.dense_4h_to_h.bias": "pytorch_model_00020-of-00072.bin",
129
+ "h.18.mlp.dense_4h_to_h.weight": "pytorch_model_00020-of-00072.bin",
130
+ "h.18.mlp.dense_h_to_4h.bias": "pytorch_model_00020-of-00072.bin",
131
+ "h.18.mlp.dense_h_to_4h.weight": "pytorch_model_00020-of-00072.bin",
132
+ "h.18.post_attention_layernorm.bias": "pytorch_model_00020-of-00072.bin",
133
+ "h.18.post_attention_layernorm.weight": "pytorch_model_00020-of-00072.bin",
134
+ "h.18.self_attention.dense.bias": "pytorch_model_00020-of-00072.bin",
135
+ "h.18.self_attention.dense.weight": "pytorch_model_00020-of-00072.bin",
136
+ "h.18.self_attention.query_key_value.bias": "pytorch_model_00020-of-00072.bin",
137
+ "h.18.self_attention.query_key_value.weight": "pytorch_model_00020-of-00072.bin",
138
+ "h.19.input_layernorm.bias": "pytorch_model_00021-of-00072.bin",
139
+ "h.19.input_layernorm.weight": "pytorch_model_00021-of-00072.bin",
140
+ "h.19.mlp.dense_4h_to_h.bias": "pytorch_model_00021-of-00072.bin",
141
+ "h.19.mlp.dense_4h_to_h.weight": "pytorch_model_00021-of-00072.bin",
142
+ "h.19.mlp.dense_h_to_4h.bias": "pytorch_model_00021-of-00072.bin",
143
+ "h.19.mlp.dense_h_to_4h.weight": "pytorch_model_00021-of-00072.bin",
144
+ "h.19.post_attention_layernorm.bias": "pytorch_model_00021-of-00072.bin",
145
+ "h.19.post_attention_layernorm.weight": "pytorch_model_00021-of-00072.bin",
146
+ "h.19.self_attention.dense.bias": "pytorch_model_00021-of-00072.bin",
147
+ "h.19.self_attention.dense.weight": "pytorch_model_00021-of-00072.bin",
148
+ "h.19.self_attention.query_key_value.bias": "pytorch_model_00021-of-00072.bin",
149
+ "h.19.self_attention.query_key_value.weight": "pytorch_model_00021-of-00072.bin",
150
+ "h.2.input_layernorm.bias": "pytorch_model_00004-of-00072.bin",
151
+ "h.2.input_layernorm.weight": "pytorch_model_00004-of-00072.bin",
152
+ "h.2.mlp.dense_4h_to_h.bias": "pytorch_model_00004-of-00072.bin",
153
+ "h.2.mlp.dense_4h_to_h.weight": "pytorch_model_00004-of-00072.bin",
154
+ "h.2.mlp.dense_h_to_4h.bias": "pytorch_model_00004-of-00072.bin",
155
+ "h.2.mlp.dense_h_to_4h.weight": "pytorch_model_00004-of-00072.bin",
156
+ "h.2.post_attention_layernorm.bias": "pytorch_model_00004-of-00072.bin",
157
+ "h.2.post_attention_layernorm.weight": "pytorch_model_00004-of-00072.bin",
158
+ "h.2.self_attention.dense.bias": "pytorch_model_00004-of-00072.bin",
159
+ "h.2.self_attention.dense.weight": "pytorch_model_00004-of-00072.bin",
160
+ "h.2.self_attention.query_key_value.bias": "pytorch_model_00004-of-00072.bin",
161
+ "h.2.self_attention.query_key_value.weight": "pytorch_model_00004-of-00072.bin",
162
+ "h.20.input_layernorm.bias": "pytorch_model_00022-of-00072.bin",
163
+ "h.20.input_layernorm.weight": "pytorch_model_00022-of-00072.bin",
164
+ "h.20.mlp.dense_4h_to_h.bias": "pytorch_model_00022-of-00072.bin",
165
+ "h.20.mlp.dense_4h_to_h.weight": "pytorch_model_00022-of-00072.bin",
166
+ "h.20.mlp.dense_h_to_4h.bias": "pytorch_model_00022-of-00072.bin",
167
+ "h.20.mlp.dense_h_to_4h.weight": "pytorch_model_00022-of-00072.bin",
168
+ "h.20.post_attention_layernorm.bias": "pytorch_model_00022-of-00072.bin",
169
+ "h.20.post_attention_layernorm.weight": "pytorch_model_00022-of-00072.bin",
170
+ "h.20.self_attention.dense.bias": "pytorch_model_00022-of-00072.bin",
171
+ "h.20.self_attention.dense.weight": "pytorch_model_00022-of-00072.bin",
172
+ "h.20.self_attention.query_key_value.bias": "pytorch_model_00022-of-00072.bin",
173
+ "h.20.self_attention.query_key_value.weight": "pytorch_model_00022-of-00072.bin",
174
+ "h.21.input_layernorm.bias": "pytorch_model_00023-of-00072.bin",
175
+ "h.21.input_layernorm.weight": "pytorch_model_00023-of-00072.bin",
176
+ "h.21.mlp.dense_4h_to_h.bias": "pytorch_model_00023-of-00072.bin",
177
+ "h.21.mlp.dense_4h_to_h.weight": "pytorch_model_00023-of-00072.bin",
178
+ "h.21.mlp.dense_h_to_4h.bias": "pytorch_model_00023-of-00072.bin",
179
+ "h.21.mlp.dense_h_to_4h.weight": "pytorch_model_00023-of-00072.bin",
180
+ "h.21.post_attention_layernorm.bias": "pytorch_model_00023-of-00072.bin",
181
+ "h.21.post_attention_layernorm.weight": "pytorch_model_00023-of-00072.bin",
182
+ "h.21.self_attention.dense.bias": "pytorch_model_00023-of-00072.bin",
183
+ "h.21.self_attention.dense.weight": "pytorch_model_00023-of-00072.bin",
184
+ "h.21.self_attention.query_key_value.bias": "pytorch_model_00023-of-00072.bin",
185
+ "h.21.self_attention.query_key_value.weight": "pytorch_model_00023-of-00072.bin",
186
+ "h.22.input_layernorm.bias": "pytorch_model_00024-of-00072.bin",
187
+ "h.22.input_layernorm.weight": "pytorch_model_00024-of-00072.bin",
188
+ "h.22.mlp.dense_4h_to_h.bias": "pytorch_model_00024-of-00072.bin",
189
+ "h.22.mlp.dense_4h_to_h.weight": "pytorch_model_00024-of-00072.bin",
190
+ "h.22.mlp.dense_h_to_4h.bias": "pytorch_model_00024-of-00072.bin",
191
+ "h.22.mlp.dense_h_to_4h.weight": "pytorch_model_00024-of-00072.bin",
192
+ "h.22.post_attention_layernorm.bias": "pytorch_model_00024-of-00072.bin",
193
+ "h.22.post_attention_layernorm.weight": "pytorch_model_00024-of-00072.bin",
194
+ "h.22.self_attention.dense.bias": "pytorch_model_00024-of-00072.bin",
195
+ "h.22.self_attention.dense.weight": "pytorch_model_00024-of-00072.bin",
196
+ "h.22.self_attention.query_key_value.bias": "pytorch_model_00024-of-00072.bin",
197
+ "h.22.self_attention.query_key_value.weight": "pytorch_model_00024-of-00072.bin",
198
+ "h.23.input_layernorm.bias": "pytorch_model_00025-of-00072.bin",
199
+ "h.23.input_layernorm.weight": "pytorch_model_00025-of-00072.bin",
200
+ "h.23.mlp.dense_4h_to_h.bias": "pytorch_model_00025-of-00072.bin",
201
+ "h.23.mlp.dense_4h_to_h.weight": "pytorch_model_00025-of-00072.bin",
202
+ "h.23.mlp.dense_h_to_4h.bias": "pytorch_model_00025-of-00072.bin",
203
+ "h.23.mlp.dense_h_to_4h.weight": "pytorch_model_00025-of-00072.bin",
204
+ "h.23.post_attention_layernorm.bias": "pytorch_model_00025-of-00072.bin",
205
+ "h.23.post_attention_layernorm.weight": "pytorch_model_00025-of-00072.bin",
206
+ "h.23.self_attention.dense.bias": "pytorch_model_00025-of-00072.bin",
207
+ "h.23.self_attention.dense.weight": "pytorch_model_00025-of-00072.bin",
208
+ "h.23.self_attention.query_key_value.bias": "pytorch_model_00025-of-00072.bin",
209
+ "h.23.self_attention.query_key_value.weight": "pytorch_model_00025-of-00072.bin",
210
+ "h.24.input_layernorm.bias": "pytorch_model_00026-of-00072.bin",
211
+ "h.24.input_layernorm.weight": "pytorch_model_00026-of-00072.bin",
212
+ "h.24.mlp.dense_4h_to_h.bias": "pytorch_model_00026-of-00072.bin",
213
+ "h.24.mlp.dense_4h_to_h.weight": "pytorch_model_00026-of-00072.bin",
214
+ "h.24.mlp.dense_h_to_4h.bias": "pytorch_model_00026-of-00072.bin",
215
+ "h.24.mlp.dense_h_to_4h.weight": "pytorch_model_00026-of-00072.bin",
216
+ "h.24.post_attention_layernorm.bias": "pytorch_model_00026-of-00072.bin",
217
+ "h.24.post_attention_layernorm.weight": "pytorch_model_00026-of-00072.bin",
218
+ "h.24.self_attention.dense.bias": "pytorch_model_00026-of-00072.bin",
219
+ "h.24.self_attention.dense.weight": "pytorch_model_00026-of-00072.bin",
220
+ "h.24.self_attention.query_key_value.bias": "pytorch_model_00026-of-00072.bin",
221
+ "h.24.self_attention.query_key_value.weight": "pytorch_model_00026-of-00072.bin",
222
+ "h.25.input_layernorm.bias": "pytorch_model_00027-of-00072.bin",
223
+ "h.25.input_layernorm.weight": "pytorch_model_00027-of-00072.bin",
224
+ "h.25.mlp.dense_4h_to_h.bias": "pytorch_model_00027-of-00072.bin",
225
+ "h.25.mlp.dense_4h_to_h.weight": "pytorch_model_00027-of-00072.bin",
226
+ "h.25.mlp.dense_h_to_4h.bias": "pytorch_model_00027-of-00072.bin",
227
+ "h.25.mlp.dense_h_to_4h.weight": "pytorch_model_00027-of-00072.bin",
228
+ "h.25.post_attention_layernorm.bias": "pytorch_model_00027-of-00072.bin",
229
+ "h.25.post_attention_layernorm.weight": "pytorch_model_00027-of-00072.bin",
230
+ "h.25.self_attention.dense.bias": "pytorch_model_00027-of-00072.bin",
231
+ "h.25.self_attention.dense.weight": "pytorch_model_00027-of-00072.bin",
232
+ "h.25.self_attention.query_key_value.bias": "pytorch_model_00027-of-00072.bin",
233
+ "h.25.self_attention.query_key_value.weight": "pytorch_model_00027-of-00072.bin",
234
+ "h.26.input_layernorm.bias": "pytorch_model_00028-of-00072.bin",
235
+ "h.26.input_layernorm.weight": "pytorch_model_00028-of-00072.bin",
236
+ "h.26.mlp.dense_4h_to_h.bias": "pytorch_model_00028-of-00072.bin",
237
+ "h.26.mlp.dense_4h_to_h.weight": "pytorch_model_00028-of-00072.bin",
238
+ "h.26.mlp.dense_h_to_4h.bias": "pytorch_model_00028-of-00072.bin",
239
+ "h.26.mlp.dense_h_to_4h.weight": "pytorch_model_00028-of-00072.bin",
240
+ "h.26.post_attention_layernorm.bias": "pytorch_model_00028-of-00072.bin",
241
+ "h.26.post_attention_layernorm.weight": "pytorch_model_00028-of-00072.bin",
242
+ "h.26.self_attention.dense.bias": "pytorch_model_00028-of-00072.bin",
243
+ "h.26.self_attention.dense.weight": "pytorch_model_00028-of-00072.bin",
244
+ "h.26.self_attention.query_key_value.bias": "pytorch_model_00028-of-00072.bin",
245
+ "h.26.self_attention.query_key_value.weight": "pytorch_model_00028-of-00072.bin",
246
+ "h.27.input_layernorm.bias": "pytorch_model_00029-of-00072.bin",
247
+ "h.27.input_layernorm.weight": "pytorch_model_00029-of-00072.bin",
248
+ "h.27.mlp.dense_4h_to_h.bias": "pytorch_model_00029-of-00072.bin",
249
+ "h.27.mlp.dense_4h_to_h.weight": "pytorch_model_00029-of-00072.bin",
250
+ "h.27.mlp.dense_h_to_4h.bias": "pytorch_model_00029-of-00072.bin",
251
+ "h.27.mlp.dense_h_to_4h.weight": "pytorch_model_00029-of-00072.bin",
252
+ "h.27.post_attention_layernorm.bias": "pytorch_model_00029-of-00072.bin",
253
+ "h.27.post_attention_layernorm.weight": "pytorch_model_00029-of-00072.bin",
254
+ "h.27.self_attention.dense.bias": "pytorch_model_00029-of-00072.bin",
255
+ "h.27.self_attention.dense.weight": "pytorch_model_00029-of-00072.bin",
256
+ "h.27.self_attention.query_key_value.bias": "pytorch_model_00029-of-00072.bin",
257
+ "h.27.self_attention.query_key_value.weight": "pytorch_model_00029-of-00072.bin",
258
+ "h.28.input_layernorm.bias": "pytorch_model_00030-of-00072.bin",
259
+ "h.28.input_layernorm.weight": "pytorch_model_00030-of-00072.bin",
260
+ "h.28.mlp.dense_4h_to_h.bias": "pytorch_model_00030-of-00072.bin",
261
+ "h.28.mlp.dense_4h_to_h.weight": "pytorch_model_00030-of-00072.bin",
262
+ "h.28.mlp.dense_h_to_4h.bias": "pytorch_model_00030-of-00072.bin",
263
+ "h.28.mlp.dense_h_to_4h.weight": "pytorch_model_00030-of-00072.bin",
264
+ "h.28.post_attention_layernorm.bias": "pytorch_model_00030-of-00072.bin",
265
+ "h.28.post_attention_layernorm.weight": "pytorch_model_00030-of-00072.bin",
266
+ "h.28.self_attention.dense.bias": "pytorch_model_00030-of-00072.bin",
267
+ "h.28.self_attention.dense.weight": "pytorch_model_00030-of-00072.bin",
268
+ "h.28.self_attention.query_key_value.bias": "pytorch_model_00030-of-00072.bin",
269
+ "h.28.self_attention.query_key_value.weight": "pytorch_model_00030-of-00072.bin",
270
+ "h.29.input_layernorm.bias": "pytorch_model_00031-of-00072.bin",
271
+ "h.29.input_layernorm.weight": "pytorch_model_00031-of-00072.bin",
272
+ "h.29.mlp.dense_4h_to_h.bias": "pytorch_model_00031-of-00072.bin",
273
+ "h.29.mlp.dense_4h_to_h.weight": "pytorch_model_00031-of-00072.bin",
274
+ "h.29.mlp.dense_h_to_4h.bias": "pytorch_model_00031-of-00072.bin",
275
+ "h.29.mlp.dense_h_to_4h.weight": "pytorch_model_00031-of-00072.bin",
276
+ "h.29.post_attention_layernorm.bias": "pytorch_model_00031-of-00072.bin",
277
+ "h.29.post_attention_layernorm.weight": "pytorch_model_00031-of-00072.bin",
278
+ "h.29.self_attention.dense.bias": "pytorch_model_00031-of-00072.bin",
279
+ "h.29.self_attention.dense.weight": "pytorch_model_00031-of-00072.bin",
280
+ "h.29.self_attention.query_key_value.bias": "pytorch_model_00031-of-00072.bin",
281
+ "h.29.self_attention.query_key_value.weight": "pytorch_model_00031-of-00072.bin",
282
+ "h.3.input_layernorm.bias": "pytorch_model_00005-of-00072.bin",
283
+ "h.3.input_layernorm.weight": "pytorch_model_00005-of-00072.bin",
284
+ "h.3.mlp.dense_4h_to_h.bias": "pytorch_model_00005-of-00072.bin",
285
+ "h.3.mlp.dense_4h_to_h.weight": "pytorch_model_00005-of-00072.bin",
286
+ "h.3.mlp.dense_h_to_4h.bias": "pytorch_model_00005-of-00072.bin",
287
+ "h.3.mlp.dense_h_to_4h.weight": "pytorch_model_00005-of-00072.bin",
288
+ "h.3.post_attention_layernorm.bias": "pytorch_model_00005-of-00072.bin",
289
+ "h.3.post_attention_layernorm.weight": "pytorch_model_00005-of-00072.bin",
290
+ "h.3.self_attention.dense.bias": "pytorch_model_00005-of-00072.bin",
291
+ "h.3.self_attention.dense.weight": "pytorch_model_00005-of-00072.bin",
292
+ "h.3.self_attention.query_key_value.bias": "pytorch_model_00005-of-00072.bin",
293
+ "h.3.self_attention.query_key_value.weight": "pytorch_model_00005-of-00072.bin",
294
+ "h.30.input_layernorm.bias": "pytorch_model_00032-of-00072.bin",
295
+ "h.30.input_layernorm.weight": "pytorch_model_00032-of-00072.bin",
296
+ "h.30.mlp.dense_4h_to_h.bias": "pytorch_model_00032-of-00072.bin",
297
+ "h.30.mlp.dense_4h_to_h.weight": "pytorch_model_00032-of-00072.bin",
298
+ "h.30.mlp.dense_h_to_4h.bias": "pytorch_model_00032-of-00072.bin",
299
+ "h.30.mlp.dense_h_to_4h.weight": "pytorch_model_00032-of-00072.bin",
300
+ "h.30.post_attention_layernorm.bias": "pytorch_model_00032-of-00072.bin",
301
+ "h.30.post_attention_layernorm.weight": "pytorch_model_00032-of-00072.bin",
302
+ "h.30.self_attention.dense.bias": "pytorch_model_00032-of-00072.bin",
303
+ "h.30.self_attention.dense.weight": "pytorch_model_00032-of-00072.bin",
304
+ "h.30.self_attention.query_key_value.bias": "pytorch_model_00032-of-00072.bin",
305
+ "h.30.self_attention.query_key_value.weight": "pytorch_model_00032-of-00072.bin",
306
+ "h.31.input_layernorm.bias": "pytorch_model_00033-of-00072.bin",
307
+ "h.31.input_layernorm.weight": "pytorch_model_00033-of-00072.bin",
308
+ "h.31.mlp.dense_4h_to_h.bias": "pytorch_model_00033-of-00072.bin",
309
+ "h.31.mlp.dense_4h_to_h.weight": "pytorch_model_00033-of-00072.bin",
310
+ "h.31.mlp.dense_h_to_4h.bias": "pytorch_model_00033-of-00072.bin",
311
+ "h.31.mlp.dense_h_to_4h.weight": "pytorch_model_00033-of-00072.bin",
312
+ "h.31.post_attention_layernorm.bias": "pytorch_model_00033-of-00072.bin",
313
+ "h.31.post_attention_layernorm.weight": "pytorch_model_00033-of-00072.bin",
314
+ "h.31.self_attention.dense.bias": "pytorch_model_00033-of-00072.bin",
315
+ "h.31.self_attention.dense.weight": "pytorch_model_00033-of-00072.bin",
316
+ "h.31.self_attention.query_key_value.bias": "pytorch_model_00033-of-00072.bin",
317
+ "h.31.self_attention.query_key_value.weight": "pytorch_model_00033-of-00072.bin",
318
+ "h.32.input_layernorm.bias": "pytorch_model_00034-of-00072.bin",
319
+ "h.32.input_layernorm.weight": "pytorch_model_00034-of-00072.bin",
320
+ "h.32.mlp.dense_4h_to_h.bias": "pytorch_model_00034-of-00072.bin",
321
+ "h.32.mlp.dense_4h_to_h.weight": "pytorch_model_00034-of-00072.bin",
322
+ "h.32.mlp.dense_h_to_4h.bias": "pytorch_model_00034-of-00072.bin",
323
+ "h.32.mlp.dense_h_to_4h.weight": "pytorch_model_00034-of-00072.bin",
324
+ "h.32.post_attention_layernorm.bias": "pytorch_model_00034-of-00072.bin",
325
+ "h.32.post_attention_layernorm.weight": "pytorch_model_00034-of-00072.bin",
326
+ "h.32.self_attention.dense.bias": "pytorch_model_00034-of-00072.bin",
327
+ "h.32.self_attention.dense.weight": "pytorch_model_00034-of-00072.bin",
328
+ "h.32.self_attention.query_key_value.bias": "pytorch_model_00034-of-00072.bin",
329
+ "h.32.self_attention.query_key_value.weight": "pytorch_model_00034-of-00072.bin",
330
+ "h.33.input_layernorm.bias": "pytorch_model_00035-of-00072.bin",
331
+ "h.33.input_layernorm.weight": "pytorch_model_00035-of-00072.bin",
332
+ "h.33.mlp.dense_4h_to_h.bias": "pytorch_model_00035-of-00072.bin",
333
+ "h.33.mlp.dense_4h_to_h.weight": "pytorch_model_00035-of-00072.bin",
334
+ "h.33.mlp.dense_h_to_4h.bias": "pytorch_model_00035-of-00072.bin",
335
+ "h.33.mlp.dense_h_to_4h.weight": "pytorch_model_00035-of-00072.bin",
336
+ "h.33.post_attention_layernorm.bias": "pytorch_model_00035-of-00072.bin",
337
+ "h.33.post_attention_layernorm.weight": "pytorch_model_00035-of-00072.bin",
338
+ "h.33.self_attention.dense.bias": "pytorch_model_00035-of-00072.bin",
339
+ "h.33.self_attention.dense.weight": "pytorch_model_00035-of-00072.bin",
340
+ "h.33.self_attention.query_key_value.bias": "pytorch_model_00035-of-00072.bin",
341
+ "h.33.self_attention.query_key_value.weight": "pytorch_model_00035-of-00072.bin",
342
+ "h.34.input_layernorm.bias": "pytorch_model_00036-of-00072.bin",
343
+ "h.34.input_layernorm.weight": "pytorch_model_00036-of-00072.bin",
344
+ "h.34.mlp.dense_4h_to_h.bias": "pytorch_model_00036-of-00072.bin",
345
+ "h.34.mlp.dense_4h_to_h.weight": "pytorch_model_00036-of-00072.bin",
346
+ "h.34.mlp.dense_h_to_4h.bias": "pytorch_model_00036-of-00072.bin",
347
+ "h.34.mlp.dense_h_to_4h.weight": "pytorch_model_00036-of-00072.bin",
348
+ "h.34.post_attention_layernorm.bias": "pytorch_model_00036-of-00072.bin",
349
+ "h.34.post_attention_layernorm.weight": "pytorch_model_00036-of-00072.bin",
350
+ "h.34.self_attention.dense.bias": "pytorch_model_00036-of-00072.bin",
351
+ "h.34.self_attention.dense.weight": "pytorch_model_00036-of-00072.bin",
352
+ "h.34.self_attention.query_key_value.bias": "pytorch_model_00036-of-00072.bin",
353
+ "h.34.self_attention.query_key_value.weight": "pytorch_model_00036-of-00072.bin",
354
+ "h.35.input_layernorm.bias": "pytorch_model_00037-of-00072.bin",
355
+ "h.35.input_layernorm.weight": "pytorch_model_00037-of-00072.bin",
356
+ "h.35.mlp.dense_4h_to_h.bias": "pytorch_model_00037-of-00072.bin",
357
+ "h.35.mlp.dense_4h_to_h.weight": "pytorch_model_00037-of-00072.bin",
358
+ "h.35.mlp.dense_h_to_4h.bias": "pytorch_model_00037-of-00072.bin",
359
+ "h.35.mlp.dense_h_to_4h.weight": "pytorch_model_00037-of-00072.bin",
360
+ "h.35.post_attention_layernorm.bias": "pytorch_model_00037-of-00072.bin",
361
+ "h.35.post_attention_layernorm.weight": "pytorch_model_00037-of-00072.bin",
362
+ "h.35.self_attention.dense.bias": "pytorch_model_00037-of-00072.bin",
363
+ "h.35.self_attention.dense.weight": "pytorch_model_00037-of-00072.bin",
364
+ "h.35.self_attention.query_key_value.bias": "pytorch_model_00037-of-00072.bin",
365
+ "h.35.self_attention.query_key_value.weight": "pytorch_model_00037-of-00072.bin",
366
+ "h.36.input_layernorm.bias": "pytorch_model_00038-of-00072.bin",
367
+ "h.36.input_layernorm.weight": "pytorch_model_00038-of-00072.bin",
368
+ "h.36.mlp.dense_4h_to_h.bias": "pytorch_model_00038-of-00072.bin",
369
+ "h.36.mlp.dense_4h_to_h.weight": "pytorch_model_00038-of-00072.bin",
370
+ "h.36.mlp.dense_h_to_4h.bias": "pytorch_model_00038-of-00072.bin",
371
+ "h.36.mlp.dense_h_to_4h.weight": "pytorch_model_00038-of-00072.bin",
372
+ "h.36.post_attention_layernorm.bias": "pytorch_model_00038-of-00072.bin",
373
+ "h.36.post_attention_layernorm.weight": "pytorch_model_00038-of-00072.bin",
374
+ "h.36.self_attention.dense.bias": "pytorch_model_00038-of-00072.bin",
375
+ "h.36.self_attention.dense.weight": "pytorch_model_00038-of-00072.bin",
376
+ "h.36.self_attention.query_key_value.bias": "pytorch_model_00038-of-00072.bin",
377
+ "h.36.self_attention.query_key_value.weight": "pytorch_model_00038-of-00072.bin",
378
+ "h.37.input_layernorm.bias": "pytorch_model_00039-of-00072.bin",
379
+ "h.37.input_layernorm.weight": "pytorch_model_00039-of-00072.bin",
380
+ "h.37.mlp.dense_4h_to_h.bias": "pytorch_model_00039-of-00072.bin",
381
+ "h.37.mlp.dense_4h_to_h.weight": "pytorch_model_00039-of-00072.bin",
382
+ "h.37.mlp.dense_h_to_4h.bias": "pytorch_model_00039-of-00072.bin",
383
+ "h.37.mlp.dense_h_to_4h.weight": "pytorch_model_00039-of-00072.bin",
384
+ "h.37.post_attention_layernorm.bias": "pytorch_model_00039-of-00072.bin",
385
+ "h.37.post_attention_layernorm.weight": "pytorch_model_00039-of-00072.bin",
386
+ "h.37.self_attention.dense.bias": "pytorch_model_00039-of-00072.bin",
387
+ "h.37.self_attention.dense.weight": "pytorch_model_00039-of-00072.bin",
388
+ "h.37.self_attention.query_key_value.bias": "pytorch_model_00039-of-00072.bin",
389
+ "h.37.self_attention.query_key_value.weight": "pytorch_model_00039-of-00072.bin",
390
+ "h.38.input_layernorm.bias": "pytorch_model_00040-of-00072.bin",
391
+ "h.38.input_layernorm.weight": "pytorch_model_00040-of-00072.bin",
392
+ "h.38.mlp.dense_4h_to_h.bias": "pytorch_model_00040-of-00072.bin",
393
+ "h.38.mlp.dense_4h_to_h.weight": "pytorch_model_00040-of-00072.bin",
394
+ "h.38.mlp.dense_h_to_4h.bias": "pytorch_model_00040-of-00072.bin",
395
+ "h.38.mlp.dense_h_to_4h.weight": "pytorch_model_00040-of-00072.bin",
396
+ "h.38.post_attention_layernorm.bias": "pytorch_model_00040-of-00072.bin",
397
+ "h.38.post_attention_layernorm.weight": "pytorch_model_00040-of-00072.bin",
398
+ "h.38.self_attention.dense.bias": "pytorch_model_00040-of-00072.bin",
399
+ "h.38.self_attention.dense.weight": "pytorch_model_00040-of-00072.bin",
400
+ "h.38.self_attention.query_key_value.bias": "pytorch_model_00040-of-00072.bin",
401
+ "h.38.self_attention.query_key_value.weight": "pytorch_model_00040-of-00072.bin",
402
+ "h.39.input_layernorm.bias": "pytorch_model_00041-of-00072.bin",
403
+ "h.39.input_layernorm.weight": "pytorch_model_00041-of-00072.bin",
404
+ "h.39.mlp.dense_4h_to_h.bias": "pytorch_model_00041-of-00072.bin",
405
+ "h.39.mlp.dense_4h_to_h.weight": "pytorch_model_00041-of-00072.bin",
406
+ "h.39.mlp.dense_h_to_4h.bias": "pytorch_model_00041-of-00072.bin",
407
+ "h.39.mlp.dense_h_to_4h.weight": "pytorch_model_00041-of-00072.bin",
408
+ "h.39.post_attention_layernorm.bias": "pytorch_model_00041-of-00072.bin",
409
+ "h.39.post_attention_layernorm.weight": "pytorch_model_00041-of-00072.bin",
410
+ "h.39.self_attention.dense.bias": "pytorch_model_00041-of-00072.bin",
411
+ "h.39.self_attention.dense.weight": "pytorch_model_00041-of-00072.bin",
412
+ "h.39.self_attention.query_key_value.bias": "pytorch_model_00041-of-00072.bin",
413
+ "h.39.self_attention.query_key_value.weight": "pytorch_model_00041-of-00072.bin",
414
+ "h.4.input_layernorm.bias": "pytorch_model_00006-of-00072.bin",
415
+ "h.4.input_layernorm.weight": "pytorch_model_00006-of-00072.bin",
416
+ "h.4.mlp.dense_4h_to_h.bias": "pytorch_model_00006-of-00072.bin",
417
+ "h.4.mlp.dense_4h_to_h.weight": "pytorch_model_00006-of-00072.bin",
418
+ "h.4.mlp.dense_h_to_4h.bias": "pytorch_model_00006-of-00072.bin",
419
+ "h.4.mlp.dense_h_to_4h.weight": "pytorch_model_00006-of-00072.bin",
420
+ "h.4.post_attention_layernorm.bias": "pytorch_model_00006-of-00072.bin",
421
+ "h.4.post_attention_layernorm.weight": "pytorch_model_00006-of-00072.bin",
422
+ "h.4.self_attention.dense.bias": "pytorch_model_00006-of-00072.bin",
423
+ "h.4.self_attention.dense.weight": "pytorch_model_00006-of-00072.bin",
424
+ "h.4.self_attention.query_key_value.bias": "pytorch_model_00006-of-00072.bin",
425
+ "h.4.self_attention.query_key_value.weight": "pytorch_model_00006-of-00072.bin",
426
+ "h.40.input_layernorm.bias": "pytorch_model_00042-of-00072.bin",
427
+ "h.40.input_layernorm.weight": "pytorch_model_00042-of-00072.bin",
428
+ "h.40.mlp.dense_4h_to_h.bias": "pytorch_model_00042-of-00072.bin",
429
+ "h.40.mlp.dense_4h_to_h.weight": "pytorch_model_00042-of-00072.bin",
430
+ "h.40.mlp.dense_h_to_4h.bias": "pytorch_model_00042-of-00072.bin",
431
+ "h.40.mlp.dense_h_to_4h.weight": "pytorch_model_00042-of-00072.bin",
432
+ "h.40.post_attention_layernorm.bias": "pytorch_model_00042-of-00072.bin",
433
+ "h.40.post_attention_layernorm.weight": "pytorch_model_00042-of-00072.bin",
434
+ "h.40.self_attention.dense.bias": "pytorch_model_00042-of-00072.bin",
435
+ "h.40.self_attention.dense.weight": "pytorch_model_00042-of-00072.bin",
436
+ "h.40.self_attention.query_key_value.bias": "pytorch_model_00042-of-00072.bin",
437
+ "h.40.self_attention.query_key_value.weight": "pytorch_model_00042-of-00072.bin",
438
+ "h.41.input_layernorm.bias": "pytorch_model_00043-of-00072.bin",
439
+ "h.41.input_layernorm.weight": "pytorch_model_00043-of-00072.bin",
440
+ "h.41.mlp.dense_4h_to_h.bias": "pytorch_model_00043-of-00072.bin",
441
+ "h.41.mlp.dense_4h_to_h.weight": "pytorch_model_00043-of-00072.bin",
442
+ "h.41.mlp.dense_h_to_4h.bias": "pytorch_model_00043-of-00072.bin",
443
+ "h.41.mlp.dense_h_to_4h.weight": "pytorch_model_00043-of-00072.bin",
444
+ "h.41.post_attention_layernorm.bias": "pytorch_model_00043-of-00072.bin",
445
+ "h.41.post_attention_layernorm.weight": "pytorch_model_00043-of-00072.bin",
446
+ "h.41.self_attention.dense.bias": "pytorch_model_00043-of-00072.bin",
447
+ "h.41.self_attention.dense.weight": "pytorch_model_00043-of-00072.bin",
448
+ "h.41.self_attention.query_key_value.bias": "pytorch_model_00043-of-00072.bin",
449
+ "h.41.self_attention.query_key_value.weight": "pytorch_model_00043-of-00072.bin",
450
+ "h.42.input_layernorm.bias": "pytorch_model_00044-of-00072.bin",
451
+ "h.42.input_layernorm.weight": "pytorch_model_00044-of-00072.bin",
452
+ "h.42.mlp.dense_4h_to_h.bias": "pytorch_model_00044-of-00072.bin",
453
+ "h.42.mlp.dense_4h_to_h.weight": "pytorch_model_00044-of-00072.bin",
454
+ "h.42.mlp.dense_h_to_4h.bias": "pytorch_model_00044-of-00072.bin",
455
+ "h.42.mlp.dense_h_to_4h.weight": "pytorch_model_00044-of-00072.bin",
456
+ "h.42.post_attention_layernorm.bias": "pytorch_model_00044-of-00072.bin",
457
+ "h.42.post_attention_layernorm.weight": "pytorch_model_00044-of-00072.bin",
458
+ "h.42.self_attention.dense.bias": "pytorch_model_00044-of-00072.bin",
459
+ "h.42.self_attention.dense.weight": "pytorch_model_00044-of-00072.bin",
460
+ "h.42.self_attention.query_key_value.bias": "pytorch_model_00044-of-00072.bin",
461
+ "h.42.self_attention.query_key_value.weight": "pytorch_model_00044-of-00072.bin",
462
+ "h.43.input_layernorm.bias": "pytorch_model_00045-of-00072.bin",
463
+ "h.43.input_layernorm.weight": "pytorch_model_00045-of-00072.bin",
464
+ "h.43.mlp.dense_4h_to_h.bias": "pytorch_model_00045-of-00072.bin",
465
+ "h.43.mlp.dense_4h_to_h.weight": "pytorch_model_00045-of-00072.bin",
466
+ "h.43.mlp.dense_h_to_4h.bias": "pytorch_model_00045-of-00072.bin",
467
+ "h.43.mlp.dense_h_to_4h.weight": "pytorch_model_00045-of-00072.bin",
468
+ "h.43.post_attention_layernorm.bias": "pytorch_model_00045-of-00072.bin",
469
+ "h.43.post_attention_layernorm.weight": "pytorch_model_00045-of-00072.bin",
470
+ "h.43.self_attention.dense.bias": "pytorch_model_00045-of-00072.bin",
471
+ "h.43.self_attention.dense.weight": "pytorch_model_00045-of-00072.bin",
472
+ "h.43.self_attention.query_key_value.bias": "pytorch_model_00045-of-00072.bin",
473
+ "h.43.self_attention.query_key_value.weight": "pytorch_model_00045-of-00072.bin",
474
+ "h.44.input_layernorm.bias": "pytorch_model_00046-of-00072.bin",
475
+ "h.44.input_layernorm.weight": "pytorch_model_00046-of-00072.bin",
476
+ "h.44.mlp.dense_4h_to_h.bias": "pytorch_model_00046-of-00072.bin",
477
+ "h.44.mlp.dense_4h_to_h.weight": "pytorch_model_00046-of-00072.bin",
478
+ "h.44.mlp.dense_h_to_4h.bias": "pytorch_model_00046-of-00072.bin",
479
+ "h.44.mlp.dense_h_to_4h.weight": "pytorch_model_00046-of-00072.bin",
480
+ "h.44.post_attention_layernorm.bias": "pytorch_model_00046-of-00072.bin",
481
+ "h.44.post_attention_layernorm.weight": "pytorch_model_00046-of-00072.bin",
482
+ "h.44.self_attention.dense.bias": "pytorch_model_00046-of-00072.bin",
483
+ "h.44.self_attention.dense.weight": "pytorch_model_00046-of-00072.bin",
484
+ "h.44.self_attention.query_key_value.bias": "pytorch_model_00046-of-00072.bin",
485
+ "h.44.self_attention.query_key_value.weight": "pytorch_model_00046-of-00072.bin",
486
+ "h.45.input_layernorm.bias": "pytorch_model_00047-of-00072.bin",
487
+ "h.45.input_layernorm.weight": "pytorch_model_00047-of-00072.bin",
488
+ "h.45.mlp.dense_4h_to_h.bias": "pytorch_model_00047-of-00072.bin",
489
+ "h.45.mlp.dense_4h_to_h.weight": "pytorch_model_00047-of-00072.bin",
490
+ "h.45.mlp.dense_h_to_4h.bias": "pytorch_model_00047-of-00072.bin",
491
+ "h.45.mlp.dense_h_to_4h.weight": "pytorch_model_00047-of-00072.bin",
492
+ "h.45.post_attention_layernorm.bias": "pytorch_model_00047-of-00072.bin",
493
+ "h.45.post_attention_layernorm.weight": "pytorch_model_00047-of-00072.bin",
494
+ "h.45.self_attention.dense.bias": "pytorch_model_00047-of-00072.bin",
495
+ "h.45.self_attention.dense.weight": "pytorch_model_00047-of-00072.bin",
496
+ "h.45.self_attention.query_key_value.bias": "pytorch_model_00047-of-00072.bin",
497
+ "h.45.self_attention.query_key_value.weight": "pytorch_model_00047-of-00072.bin",
498
+ "h.46.input_layernorm.bias": "pytorch_model_00048-of-00072.bin",
499
+ "h.46.input_layernorm.weight": "pytorch_model_00048-of-00072.bin",
500
+ "h.46.mlp.dense_4h_to_h.bias": "pytorch_model_00048-of-00072.bin",
501
+ "h.46.mlp.dense_4h_to_h.weight": "pytorch_model_00048-of-00072.bin",
502
+ "h.46.mlp.dense_h_to_4h.bias": "pytorch_model_00048-of-00072.bin",
503
+ "h.46.mlp.dense_h_to_4h.weight": "pytorch_model_00048-of-00072.bin",
504
+ "h.46.post_attention_layernorm.bias": "pytorch_model_00048-of-00072.bin",
505
+ "h.46.post_attention_layernorm.weight": "pytorch_model_00048-of-00072.bin",
506
+ "h.46.self_attention.dense.bias": "pytorch_model_00048-of-00072.bin",
507
+ "h.46.self_attention.dense.weight": "pytorch_model_00048-of-00072.bin",
508
+ "h.46.self_attention.query_key_value.bias": "pytorch_model_00048-of-00072.bin",
509
+ "h.46.self_attention.query_key_value.weight": "pytorch_model_00048-of-00072.bin",
510
+ "h.47.input_layernorm.bias": "pytorch_model_00049-of-00072.bin",
511
+ "h.47.input_layernorm.weight": "pytorch_model_00049-of-00072.bin",
512
+ "h.47.mlp.dense_4h_to_h.bias": "pytorch_model_00049-of-00072.bin",
513
+ "h.47.mlp.dense_4h_to_h.weight": "pytorch_model_00049-of-00072.bin",
514
+ "h.47.mlp.dense_h_to_4h.bias": "pytorch_model_00049-of-00072.bin",
515
+ "h.47.mlp.dense_h_to_4h.weight": "pytorch_model_00049-of-00072.bin",
516
+ "h.47.post_attention_layernorm.bias": "pytorch_model_00049-of-00072.bin",
517
+ "h.47.post_attention_layernorm.weight": "pytorch_model_00049-of-00072.bin",
518
+ "h.47.self_attention.dense.bias": "pytorch_model_00049-of-00072.bin",
519
+ "h.47.self_attention.dense.weight": "pytorch_model_00049-of-00072.bin",
520
+ "h.47.self_attention.query_key_value.bias": "pytorch_model_00049-of-00072.bin",
521
+ "h.47.self_attention.query_key_value.weight": "pytorch_model_00049-of-00072.bin",
522
+ "h.48.input_layernorm.bias": "pytorch_model_00050-of-00072.bin",
523
+ "h.48.input_layernorm.weight": "pytorch_model_00050-of-00072.bin",
524
+ "h.48.mlp.dense_4h_to_h.bias": "pytorch_model_00050-of-00072.bin",
525
+ "h.48.mlp.dense_4h_to_h.weight": "pytorch_model_00050-of-00072.bin",
526
+ "h.48.mlp.dense_h_to_4h.bias": "pytorch_model_00050-of-00072.bin",
527
+ "h.48.mlp.dense_h_to_4h.weight": "pytorch_model_00050-of-00072.bin",
528
+ "h.48.post_attention_layernorm.bias": "pytorch_model_00050-of-00072.bin",
529
+ "h.48.post_attention_layernorm.weight": "pytorch_model_00050-of-00072.bin",
530
+ "h.48.self_attention.dense.bias": "pytorch_model_00050-of-00072.bin",
531
+ "h.48.self_attention.dense.weight": "pytorch_model_00050-of-00072.bin",
532
+ "h.48.self_attention.query_key_value.bias": "pytorch_model_00050-of-00072.bin",
533
+ "h.48.self_attention.query_key_value.weight": "pytorch_model_00050-of-00072.bin",
534
+ "h.49.input_layernorm.bias": "pytorch_model_00051-of-00072.bin",
535
+ "h.49.input_layernorm.weight": "pytorch_model_00051-of-00072.bin",
536
+ "h.49.mlp.dense_4h_to_h.bias": "pytorch_model_00051-of-00072.bin",
537
+ "h.49.mlp.dense_4h_to_h.weight": "pytorch_model_00051-of-00072.bin",
538
+ "h.49.mlp.dense_h_to_4h.bias": "pytorch_model_00051-of-00072.bin",
539
+ "h.49.mlp.dense_h_to_4h.weight": "pytorch_model_00051-of-00072.bin",
540
+ "h.49.post_attention_layernorm.bias": "pytorch_model_00051-of-00072.bin",
541
+ "h.49.post_attention_layernorm.weight": "pytorch_model_00051-of-00072.bin",
542
+ "h.49.self_attention.dense.bias": "pytorch_model_00051-of-00072.bin",
543
+ "h.49.self_attention.dense.weight": "pytorch_model_00051-of-00072.bin",
544
+ "h.49.self_attention.query_key_value.bias": "pytorch_model_00051-of-00072.bin",
545
+ "h.49.self_attention.query_key_value.weight": "pytorch_model_00051-of-00072.bin",
546
+ "h.5.input_layernorm.bias": "pytorch_model_00007-of-00072.bin",
547
+ "h.5.input_layernorm.weight": "pytorch_model_00007-of-00072.bin",
548
+ "h.5.mlp.dense_4h_to_h.bias": "pytorch_model_00007-of-00072.bin",
549
+ "h.5.mlp.dense_4h_to_h.weight": "pytorch_model_00007-of-00072.bin",
550
+ "h.5.mlp.dense_h_to_4h.bias": "pytorch_model_00007-of-00072.bin",
551
+ "h.5.mlp.dense_h_to_4h.weight": "pytorch_model_00007-of-00072.bin",
552
+ "h.5.post_attention_layernorm.bias": "pytorch_model_00007-of-00072.bin",
553
+ "h.5.post_attention_layernorm.weight": "pytorch_model_00007-of-00072.bin",
554
+ "h.5.self_attention.dense.bias": "pytorch_model_00007-of-00072.bin",
555
+ "h.5.self_attention.dense.weight": "pytorch_model_00007-of-00072.bin",
556
+ "h.5.self_attention.query_key_value.bias": "pytorch_model_00007-of-00072.bin",
557
+ "h.5.self_attention.query_key_value.weight": "pytorch_model_00007-of-00072.bin",
558
+ "h.50.input_layernorm.bias": "pytorch_model_00052-of-00072.bin",
559
+ "h.50.input_layernorm.weight": "pytorch_model_00052-of-00072.bin",
560
+ "h.50.mlp.dense_4h_to_h.bias": "pytorch_model_00052-of-00072.bin",
561
+ "h.50.mlp.dense_4h_to_h.weight": "pytorch_model_00052-of-00072.bin",
562
+ "h.50.mlp.dense_h_to_4h.bias": "pytorch_model_00052-of-00072.bin",
563
+ "h.50.mlp.dense_h_to_4h.weight": "pytorch_model_00052-of-00072.bin",
564
+ "h.50.post_attention_layernorm.bias": "pytorch_model_00052-of-00072.bin",
565
+ "h.50.post_attention_layernorm.weight": "pytorch_model_00052-of-00072.bin",
566
+ "h.50.self_attention.dense.bias": "pytorch_model_00052-of-00072.bin",
567
+ "h.50.self_attention.dense.weight": "pytorch_model_00052-of-00072.bin",
568
+ "h.50.self_attention.query_key_value.bias": "pytorch_model_00052-of-00072.bin",
569
+ "h.50.self_attention.query_key_value.weight": "pytorch_model_00052-of-00072.bin",
570
+ "h.51.input_layernorm.bias": "pytorch_model_00053-of-00072.bin",
571
+ "h.51.input_layernorm.weight": "pytorch_model_00053-of-00072.bin",
572
+ "h.51.mlp.dense_4h_to_h.bias": "pytorch_model_00053-of-00072.bin",
573
+ "h.51.mlp.dense_4h_to_h.weight": "pytorch_model_00053-of-00072.bin",
574
+ "h.51.mlp.dense_h_to_4h.bias": "pytorch_model_00053-of-00072.bin",
575
+ "h.51.mlp.dense_h_to_4h.weight": "pytorch_model_00053-of-00072.bin",
576
+ "h.51.post_attention_layernorm.bias": "pytorch_model_00053-of-00072.bin",
577
+ "h.51.post_attention_layernorm.weight": "pytorch_model_00053-of-00072.bin",
578
+ "h.51.self_attention.dense.bias": "pytorch_model_00053-of-00072.bin",
579
+ "h.51.self_attention.dense.weight": "pytorch_model_00053-of-00072.bin",
580
+ "h.51.self_attention.query_key_value.bias": "pytorch_model_00053-of-00072.bin",
581
+ "h.51.self_attention.query_key_value.weight": "pytorch_model_00053-of-00072.bin",
582
+ "h.52.input_layernorm.bias": "pytorch_model_00054-of-00072.bin",
583
+ "h.52.input_layernorm.weight": "pytorch_model_00054-of-00072.bin",
584
+ "h.52.mlp.dense_4h_to_h.bias": "pytorch_model_00054-of-00072.bin",
585
+ "h.52.mlp.dense_4h_to_h.weight": "pytorch_model_00054-of-00072.bin",
586
+ "h.52.mlp.dense_h_to_4h.bias": "pytorch_model_00054-of-00072.bin",
587
+ "h.52.mlp.dense_h_to_4h.weight": "pytorch_model_00054-of-00072.bin",
588
+ "h.52.post_attention_layernorm.bias": "pytorch_model_00054-of-00072.bin",
589
+ "h.52.post_attention_layernorm.weight": "pytorch_model_00054-of-00072.bin",
590
+ "h.52.self_attention.dense.bias": "pytorch_model_00054-of-00072.bin",
591
+ "h.52.self_attention.dense.weight": "pytorch_model_00054-of-00072.bin",
592
+ "h.52.self_attention.query_key_value.bias": "pytorch_model_00054-of-00072.bin",
593
+ "h.52.self_attention.query_key_value.weight": "pytorch_model_00054-of-00072.bin",
594
+ "h.53.input_layernorm.bias": "pytorch_model_00055-of-00072.bin",
595
+ "h.53.input_layernorm.weight": "pytorch_model_00055-of-00072.bin",
596
+ "h.53.mlp.dense_4h_to_h.bias": "pytorch_model_00055-of-00072.bin",
597
+ "h.53.mlp.dense_4h_to_h.weight": "pytorch_model_00055-of-00072.bin",
598
+ "h.53.mlp.dense_h_to_4h.bias": "pytorch_model_00055-of-00072.bin",
599
+ "h.53.mlp.dense_h_to_4h.weight": "pytorch_model_00055-of-00072.bin",
600
+ "h.53.post_attention_layernorm.bias": "pytorch_model_00055-of-00072.bin",
601
+ "h.53.post_attention_layernorm.weight": "pytorch_model_00055-of-00072.bin",
602
+ "h.53.self_attention.dense.bias": "pytorch_model_00055-of-00072.bin",
603
+ "h.53.self_attention.dense.weight": "pytorch_model_00055-of-00072.bin",
604
+ "h.53.self_attention.query_key_value.bias": "pytorch_model_00055-of-00072.bin",
605
+ "h.53.self_attention.query_key_value.weight": "pytorch_model_00055-of-00072.bin",
606
+ "h.54.input_layernorm.bias": "pytorch_model_00056-of-00072.bin",
607
+ "h.54.input_layernorm.weight": "pytorch_model_00056-of-00072.bin",
608
+ "h.54.mlp.dense_4h_to_h.bias": "pytorch_model_00056-of-00072.bin",
609
+ "h.54.mlp.dense_4h_to_h.weight": "pytorch_model_00056-of-00072.bin",
610
+ "h.54.mlp.dense_h_to_4h.bias": "pytorch_model_00056-of-00072.bin",
611
+ "h.54.mlp.dense_h_to_4h.weight": "pytorch_model_00056-of-00072.bin",
612
+ "h.54.post_attention_layernorm.bias": "pytorch_model_00056-of-00072.bin",
613
+ "h.54.post_attention_layernorm.weight": "pytorch_model_00056-of-00072.bin",
614
+ "h.54.self_attention.dense.bias": "pytorch_model_00056-of-00072.bin",
615
+ "h.54.self_attention.dense.weight": "pytorch_model_00056-of-00072.bin",
616
+ "h.54.self_attention.query_key_value.bias": "pytorch_model_00056-of-00072.bin",
617
+ "h.54.self_attention.query_key_value.weight": "pytorch_model_00056-of-00072.bin",
618
+ "h.55.input_layernorm.bias": "pytorch_model_00057-of-00072.bin",
619
+ "h.55.input_layernorm.weight": "pytorch_model_00057-of-00072.bin",
620
+ "h.55.mlp.dense_4h_to_h.bias": "pytorch_model_00057-of-00072.bin",
621
+ "h.55.mlp.dense_4h_to_h.weight": "pytorch_model_00057-of-00072.bin",
622
+ "h.55.mlp.dense_h_to_4h.bias": "pytorch_model_00057-of-00072.bin",
623
+ "h.55.mlp.dense_h_to_4h.weight": "pytorch_model_00057-of-00072.bin",
624
+ "h.55.post_attention_layernorm.bias": "pytorch_model_00057-of-00072.bin",
625
+ "h.55.post_attention_layernorm.weight": "pytorch_model_00057-of-00072.bin",
626
+ "h.55.self_attention.dense.bias": "pytorch_model_00057-of-00072.bin",
627
+ "h.55.self_attention.dense.weight": "pytorch_model_00057-of-00072.bin",
628
+ "h.55.self_attention.query_key_value.bias": "pytorch_model_00057-of-00072.bin",
629
+ "h.55.self_attention.query_key_value.weight": "pytorch_model_00057-of-00072.bin",
630
+ "h.56.input_layernorm.bias": "pytorch_model_00058-of-00072.bin",
631
+ "h.56.input_layernorm.weight": "pytorch_model_00058-of-00072.bin",
632
+ "h.56.mlp.dense_4h_to_h.bias": "pytorch_model_00058-of-00072.bin",
633
+ "h.56.mlp.dense_4h_to_h.weight": "pytorch_model_00058-of-00072.bin",
634
+ "h.56.mlp.dense_h_to_4h.bias": "pytorch_model_00058-of-00072.bin",
635
+ "h.56.mlp.dense_h_to_4h.weight": "pytorch_model_00058-of-00072.bin",
636
+ "h.56.post_attention_layernorm.bias": "pytorch_model_00058-of-00072.bin",
637
+ "h.56.post_attention_layernorm.weight": "pytorch_model_00058-of-00072.bin",
638
+ "h.56.self_attention.dense.bias": "pytorch_model_00058-of-00072.bin",
639
+ "h.56.self_attention.dense.weight": "pytorch_model_00058-of-00072.bin",
640
+ "h.56.self_attention.query_key_value.bias": "pytorch_model_00058-of-00072.bin",
641
+ "h.56.self_attention.query_key_value.weight": "pytorch_model_00058-of-00072.bin",
642
+ "h.57.input_layernorm.bias": "pytorch_model_00059-of-00072.bin",
643
+ "h.57.input_layernorm.weight": "pytorch_model_00059-of-00072.bin",
644
+ "h.57.mlp.dense_4h_to_h.bias": "pytorch_model_00059-of-00072.bin",
645
+ "h.57.mlp.dense_4h_to_h.weight": "pytorch_model_00059-of-00072.bin",
646
+ "h.57.mlp.dense_h_to_4h.bias": "pytorch_model_00059-of-00072.bin",
647
+ "h.57.mlp.dense_h_to_4h.weight": "pytorch_model_00059-of-00072.bin",
648
+ "h.57.post_attention_layernorm.bias": "pytorch_model_00059-of-00072.bin",
649
+ "h.57.post_attention_layernorm.weight": "pytorch_model_00059-of-00072.bin",
650
+ "h.57.self_attention.dense.bias": "pytorch_model_00059-of-00072.bin",
651
+ "h.57.self_attention.dense.weight": "pytorch_model_00059-of-00072.bin",
652
+ "h.57.self_attention.query_key_value.bias": "pytorch_model_00059-of-00072.bin",
653
+ "h.57.self_attention.query_key_value.weight": "pytorch_model_00059-of-00072.bin",
654
+ "h.58.input_layernorm.bias": "pytorch_model_00060-of-00072.bin",
655
+ "h.58.input_layernorm.weight": "pytorch_model_00060-of-00072.bin",
656
+ "h.58.mlp.dense_4h_to_h.bias": "pytorch_model_00060-of-00072.bin",
657
+ "h.58.mlp.dense_4h_to_h.weight": "pytorch_model_00060-of-00072.bin",
658
+ "h.58.mlp.dense_h_to_4h.bias": "pytorch_model_00060-of-00072.bin",
659
+ "h.58.mlp.dense_h_to_4h.weight": "pytorch_model_00060-of-00072.bin",
660
+ "h.58.post_attention_layernorm.bias": "pytorch_model_00060-of-00072.bin",
661
+ "h.58.post_attention_layernorm.weight": "pytorch_model_00060-of-00072.bin",
662
+ "h.58.self_attention.dense.bias": "pytorch_model_00060-of-00072.bin",
663
+ "h.58.self_attention.dense.weight": "pytorch_model_00060-of-00072.bin",
664
+ "h.58.self_attention.query_key_value.bias": "pytorch_model_00060-of-00072.bin",
665
+ "h.58.self_attention.query_key_value.weight": "pytorch_model_00060-of-00072.bin",
666
+ "h.59.input_layernorm.bias": "pytorch_model_00061-of-00072.bin",
667
+ "h.59.input_layernorm.weight": "pytorch_model_00061-of-00072.bin",
668
+ "h.59.mlp.dense_4h_to_h.bias": "pytorch_model_00061-of-00072.bin",
669
+ "h.59.mlp.dense_4h_to_h.weight": "pytorch_model_00061-of-00072.bin",
670
+ "h.59.mlp.dense_h_to_4h.bias": "pytorch_model_00061-of-00072.bin",
671
+ "h.59.mlp.dense_h_to_4h.weight": "pytorch_model_00061-of-00072.bin",
672
+ "h.59.post_attention_layernorm.bias": "pytorch_model_00061-of-00072.bin",
673
+ "h.59.post_attention_layernorm.weight": "pytorch_model_00061-of-00072.bin",
674
+ "h.59.self_attention.dense.bias": "pytorch_model_00061-of-00072.bin",
675
+ "h.59.self_attention.dense.weight": "pytorch_model_00061-of-00072.bin",
676
+ "h.59.self_attention.query_key_value.bias": "pytorch_model_00061-of-00072.bin",
677
+ "h.59.self_attention.query_key_value.weight": "pytorch_model_00061-of-00072.bin",
678
+ "h.6.input_layernorm.bias": "pytorch_model_00008-of-00072.bin",
679
+ "h.6.input_layernorm.weight": "pytorch_model_00008-of-00072.bin",
680
+ "h.6.mlp.dense_4h_to_h.bias": "pytorch_model_00008-of-00072.bin",
681
+ "h.6.mlp.dense_4h_to_h.weight": "pytorch_model_00008-of-00072.bin",
682
+ "h.6.mlp.dense_h_to_4h.bias": "pytorch_model_00008-of-00072.bin",
683
+ "h.6.mlp.dense_h_to_4h.weight": "pytorch_model_00008-of-00072.bin",
684
+ "h.6.post_attention_layernorm.bias": "pytorch_model_00008-of-00072.bin",
685
+ "h.6.post_attention_layernorm.weight": "pytorch_model_00008-of-00072.bin",
686
+ "h.6.self_attention.dense.bias": "pytorch_model_00008-of-00072.bin",
687
+ "h.6.self_attention.dense.weight": "pytorch_model_00008-of-00072.bin",
688
+ "h.6.self_attention.query_key_value.bias": "pytorch_model_00008-of-00072.bin",
689
+ "h.6.self_attention.query_key_value.weight": "pytorch_model_00008-of-00072.bin",
690
+ "h.60.input_layernorm.bias": "pytorch_model_00062-of-00072.bin",
691
+ "h.60.input_layernorm.weight": "pytorch_model_00062-of-00072.bin",
692
+ "h.60.mlp.dense_4h_to_h.bias": "pytorch_model_00062-of-00072.bin",
693
+ "h.60.mlp.dense_4h_to_h.weight": "pytorch_model_00062-of-00072.bin",
694
+ "h.60.mlp.dense_h_to_4h.bias": "pytorch_model_00062-of-00072.bin",
695
+ "h.60.mlp.dense_h_to_4h.weight": "pytorch_model_00062-of-00072.bin",
696
+ "h.60.post_attention_layernorm.bias": "pytorch_model_00062-of-00072.bin",
697
+ "h.60.post_attention_layernorm.weight": "pytorch_model_00062-of-00072.bin",
698
+ "h.60.self_attention.dense.bias": "pytorch_model_00062-of-00072.bin",
699
+ "h.60.self_attention.dense.weight": "pytorch_model_00062-of-00072.bin",
700
+ "h.60.self_attention.query_key_value.bias": "pytorch_model_00062-of-00072.bin",
701
+ "h.60.self_attention.query_key_value.weight": "pytorch_model_00062-of-00072.bin",
702
+ "h.61.input_layernorm.bias": "pytorch_model_00063-of-00072.bin",
703
+ "h.61.input_layernorm.weight": "pytorch_model_00063-of-00072.bin",
704
+ "h.61.mlp.dense_4h_to_h.bias": "pytorch_model_00063-of-00072.bin",
705
+ "h.61.mlp.dense_4h_to_h.weight": "pytorch_model_00063-of-00072.bin",
706
+ "h.61.mlp.dense_h_to_4h.bias": "pytorch_model_00063-of-00072.bin",
707
+ "h.61.mlp.dense_h_to_4h.weight": "pytorch_model_00063-of-00072.bin",
708
+ "h.61.post_attention_layernorm.bias": "pytorch_model_00063-of-00072.bin",
709
+ "h.61.post_attention_layernorm.weight": "pytorch_model_00063-of-00072.bin",
710
+ "h.61.self_attention.dense.bias": "pytorch_model_00063-of-00072.bin",
711
+ "h.61.self_attention.dense.weight": "pytorch_model_00063-of-00072.bin",
712
+ "h.61.self_attention.query_key_value.bias": "pytorch_model_00063-of-00072.bin",
713
+ "h.61.self_attention.query_key_value.weight": "pytorch_model_00063-of-00072.bin",
714
+ "h.62.input_layernorm.bias": "pytorch_model_00064-of-00072.bin",
715
+ "h.62.input_layernorm.weight": "pytorch_model_00064-of-00072.bin",
716
+ "h.62.mlp.dense_4h_to_h.bias": "pytorch_model_00064-of-00072.bin",
717
+ "h.62.mlp.dense_4h_to_h.weight": "pytorch_model_00064-of-00072.bin",
718
+ "h.62.mlp.dense_h_to_4h.bias": "pytorch_model_00064-of-00072.bin",
719
+ "h.62.mlp.dense_h_to_4h.weight": "pytorch_model_00064-of-00072.bin",
720
+ "h.62.post_attention_layernorm.bias": "pytorch_model_00064-of-00072.bin",
721
+ "h.62.post_attention_layernorm.weight": "pytorch_model_00064-of-00072.bin",
722
+ "h.62.self_attention.dense.bias": "pytorch_model_00064-of-00072.bin",
723
+ "h.62.self_attention.dense.weight": "pytorch_model_00064-of-00072.bin",
724
+ "h.62.self_attention.query_key_value.bias": "pytorch_model_00064-of-00072.bin",
725
+ "h.62.self_attention.query_key_value.weight": "pytorch_model_00064-of-00072.bin",
726
+ "h.63.input_layernorm.bias": "pytorch_model_00065-of-00072.bin",
727
+ "h.63.input_layernorm.weight": "pytorch_model_00065-of-00072.bin",
728
+ "h.63.mlp.dense_4h_to_h.bias": "pytorch_model_00065-of-00072.bin",
729
+ "h.63.mlp.dense_4h_to_h.weight": "pytorch_model_00065-of-00072.bin",
730
+ "h.63.mlp.dense_h_to_4h.bias": "pytorch_model_00065-of-00072.bin",
731
+ "h.63.mlp.dense_h_to_4h.weight": "pytorch_model_00065-of-00072.bin",
732
+ "h.63.post_attention_layernorm.bias": "pytorch_model_00065-of-00072.bin",
733
+ "h.63.post_attention_layernorm.weight": "pytorch_model_00065-of-00072.bin",
734
+ "h.63.self_attention.dense.bias": "pytorch_model_00065-of-00072.bin",
735
+ "h.63.self_attention.dense.weight": "pytorch_model_00065-of-00072.bin",
736
+ "h.63.self_attention.query_key_value.bias": "pytorch_model_00065-of-00072.bin",
737
+ "h.63.self_attention.query_key_value.weight": "pytorch_model_00065-of-00072.bin",
738
+ "h.64.input_layernorm.bias": "pytorch_model_00066-of-00072.bin",
739
+ "h.64.input_layernorm.weight": "pytorch_model_00066-of-00072.bin",
740
+ "h.64.mlp.dense_4h_to_h.bias": "pytorch_model_00066-of-00072.bin",
741
+ "h.64.mlp.dense_4h_to_h.weight": "pytorch_model_00066-of-00072.bin",
742
+ "h.64.mlp.dense_h_to_4h.bias": "pytorch_model_00066-of-00072.bin",
743
+ "h.64.mlp.dense_h_to_4h.weight": "pytorch_model_00066-of-00072.bin",
744
+ "h.64.post_attention_layernorm.bias": "pytorch_model_00066-of-00072.bin",
745
+ "h.64.post_attention_layernorm.weight": "pytorch_model_00066-of-00072.bin",
746
+ "h.64.self_attention.dense.bias": "pytorch_model_00066-of-00072.bin",
747
+ "h.64.self_attention.dense.weight": "pytorch_model_00066-of-00072.bin",
748
+ "h.64.self_attention.query_key_value.bias": "pytorch_model_00066-of-00072.bin",
749
+ "h.64.self_attention.query_key_value.weight": "pytorch_model_00066-of-00072.bin",
750
+ "h.65.input_layernorm.bias": "pytorch_model_00067-of-00072.bin",
751
+ "h.65.input_layernorm.weight": "pytorch_model_00067-of-00072.bin",
752
+ "h.65.mlp.dense_4h_to_h.bias": "pytorch_model_00067-of-00072.bin",
753
+ "h.65.mlp.dense_4h_to_h.weight": "pytorch_model_00067-of-00072.bin",
754
+ "h.65.mlp.dense_h_to_4h.bias": "pytorch_model_00067-of-00072.bin",
755
+ "h.65.mlp.dense_h_to_4h.weight": "pytorch_model_00067-of-00072.bin",
756
+ "h.65.post_attention_layernorm.bias": "pytorch_model_00067-of-00072.bin",
757
+ "h.65.post_attention_layernorm.weight": "pytorch_model_00067-of-00072.bin",
758
+ "h.65.self_attention.dense.bias": "pytorch_model_00067-of-00072.bin",
759
+ "h.65.self_attention.dense.weight": "pytorch_model_00067-of-00072.bin",
760
+ "h.65.self_attention.query_key_value.bias": "pytorch_model_00067-of-00072.bin",
761
+ "h.65.self_attention.query_key_value.weight": "pytorch_model_00067-of-00072.bin",
762
+ "h.66.input_layernorm.bias": "pytorch_model_00068-of-00072.bin",
763
+ "h.66.input_layernorm.weight": "pytorch_model_00068-of-00072.bin",
764
+ "h.66.mlp.dense_4h_to_h.bias": "pytorch_model_00068-of-00072.bin",
765
+ "h.66.mlp.dense_4h_to_h.weight": "pytorch_model_00068-of-00072.bin",
766
+ "h.66.mlp.dense_h_to_4h.bias": "pytorch_model_00068-of-00072.bin",
767
+ "h.66.mlp.dense_h_to_4h.weight": "pytorch_model_00068-of-00072.bin",
768
+ "h.66.post_attention_layernorm.bias": "pytorch_model_00068-of-00072.bin",
769
+ "h.66.post_attention_layernorm.weight": "pytorch_model_00068-of-00072.bin",
770
+ "h.66.self_attention.dense.bias": "pytorch_model_00068-of-00072.bin",
771
+ "h.66.self_attention.dense.weight": "pytorch_model_00068-of-00072.bin",
772
+ "h.66.self_attention.query_key_value.bias": "pytorch_model_00068-of-00072.bin",
773
+ "h.66.self_attention.query_key_value.weight": "pytorch_model_00068-of-00072.bin",
774
+ "h.67.input_layernorm.bias": "pytorch_model_00069-of-00072.bin",
775
+ "h.67.input_layernorm.weight": "pytorch_model_00069-of-00072.bin",
776
+ "h.67.mlp.dense_4h_to_h.bias": "pytorch_model_00069-of-00072.bin",
777
+ "h.67.mlp.dense_4h_to_h.weight": "pytorch_model_00069-of-00072.bin",
778
+ "h.67.mlp.dense_h_to_4h.bias": "pytorch_model_00069-of-00072.bin",
779
+ "h.67.mlp.dense_h_to_4h.weight": "pytorch_model_00069-of-00072.bin",
780
+ "h.67.post_attention_layernorm.bias": "pytorch_model_00069-of-00072.bin",
781
+ "h.67.post_attention_layernorm.weight": "pytorch_model_00069-of-00072.bin",
782
+ "h.67.self_attention.dense.bias": "pytorch_model_00069-of-00072.bin",
783
+ "h.67.self_attention.dense.weight": "pytorch_model_00069-of-00072.bin",
784
+ "h.67.self_attention.query_key_value.bias": "pytorch_model_00069-of-00072.bin",
785
+ "h.67.self_attention.query_key_value.weight": "pytorch_model_00069-of-00072.bin",
786
+ "h.68.input_layernorm.bias": "pytorch_model_00070-of-00072.bin",
787
+ "h.68.input_layernorm.weight": "pytorch_model_00070-of-00072.bin",
788
+ "h.68.mlp.dense_4h_to_h.bias": "pytorch_model_00070-of-00072.bin",
789
+ "h.68.mlp.dense_4h_to_h.weight": "pytorch_model_00070-of-00072.bin",
790
+ "h.68.mlp.dense_h_to_4h.bias": "pytorch_model_00070-of-00072.bin",
791
+ "h.68.mlp.dense_h_to_4h.weight": "pytorch_model_00070-of-00072.bin",
792
+ "h.68.post_attention_layernorm.bias": "pytorch_model_00070-of-00072.bin",
793
+ "h.68.post_attention_layernorm.weight": "pytorch_model_00070-of-00072.bin",
794
+ "h.68.self_attention.dense.bias": "pytorch_model_00070-of-00072.bin",
795
+ "h.68.self_attention.dense.weight": "pytorch_model_00070-of-00072.bin",
796
+ "h.68.self_attention.query_key_value.bias": "pytorch_model_00070-of-00072.bin",
797
+ "h.68.self_attention.query_key_value.weight": "pytorch_model_00070-of-00072.bin",
798
+ "h.69.input_layernorm.bias": "pytorch_model_00071-of-00072.bin",
799
+ "h.69.input_layernorm.weight": "pytorch_model_00071-of-00072.bin",
800
+ "h.69.mlp.dense_4h_to_h.bias": "pytorch_model_00071-of-00072.bin",
801
+ "h.69.mlp.dense_4h_to_h.weight": "pytorch_model_00071-of-00072.bin",
802
+ "h.69.mlp.dense_h_to_4h.bias": "pytorch_model_00071-of-00072.bin",
803
+ "h.69.mlp.dense_h_to_4h.weight": "pytorch_model_00071-of-00072.bin",
804
+ "h.69.post_attention_layernorm.bias": "pytorch_model_00071-of-00072.bin",
805
+ "h.69.post_attention_layernorm.weight": "pytorch_model_00071-of-00072.bin",
806
+ "h.69.self_attention.dense.bias": "pytorch_model_00071-of-00072.bin",
807
+ "h.69.self_attention.dense.weight": "pytorch_model_00071-of-00072.bin",
808
+ "h.69.self_attention.query_key_value.bias": "pytorch_model_00071-of-00072.bin",
809
+ "h.69.self_attention.query_key_value.weight": "pytorch_model_00071-of-00072.bin",
810
+ "h.7.input_layernorm.bias": "pytorch_model_00009-of-00072.bin",
811
+ "h.7.input_layernorm.weight": "pytorch_model_00009-of-00072.bin",
812
+ "h.7.mlp.dense_4h_to_h.bias": "pytorch_model_00009-of-00072.bin",
813
+ "h.7.mlp.dense_4h_to_h.weight": "pytorch_model_00009-of-00072.bin",
814
+ "h.7.mlp.dense_h_to_4h.bias": "pytorch_model_00009-of-00072.bin",
815
+ "h.7.mlp.dense_h_to_4h.weight": "pytorch_model_00009-of-00072.bin",
816
+ "h.7.post_attention_layernorm.bias": "pytorch_model_00009-of-00072.bin",
817
+ "h.7.post_attention_layernorm.weight": "pytorch_model_00009-of-00072.bin",
818
+ "h.7.self_attention.dense.bias": "pytorch_model_00009-of-00072.bin",
819
+ "h.7.self_attention.dense.weight": "pytorch_model_00009-of-00072.bin",
820
+ "h.7.self_attention.query_key_value.bias": "pytorch_model_00009-of-00072.bin",
821
+ "h.7.self_attention.query_key_value.weight": "pytorch_model_00009-of-00072.bin",
822
+ "h.8.input_layernorm.bias": "pytorch_model_00010-of-00072.bin",
823
+ "h.8.input_layernorm.weight": "pytorch_model_00010-of-00072.bin",
824
+ "h.8.mlp.dense_4h_to_h.bias": "pytorch_model_00010-of-00072.bin",
825
+ "h.8.mlp.dense_4h_to_h.weight": "pytorch_model_00010-of-00072.bin",
826
+ "h.8.mlp.dense_h_to_4h.bias": "pytorch_model_00010-of-00072.bin",
827
+ "h.8.mlp.dense_h_to_4h.weight": "pytorch_model_00010-of-00072.bin",
828
+ "h.8.post_attention_layernorm.bias": "pytorch_model_00010-of-00072.bin",
829
+ "h.8.post_attention_layernorm.weight": "pytorch_model_00010-of-00072.bin",
830
+ "h.8.self_attention.dense.bias": "pytorch_model_00010-of-00072.bin",
831
+ "h.8.self_attention.dense.weight": "pytorch_model_00010-of-00072.bin",
832
+ "h.8.self_attention.query_key_value.bias": "pytorch_model_00010-of-00072.bin",
833
+ "h.8.self_attention.query_key_value.weight": "pytorch_model_00010-of-00072.bin",
834
+ "h.9.input_layernorm.bias": "pytorch_model_00011-of-00072.bin",
835
+ "h.9.input_layernorm.weight": "pytorch_model_00011-of-00072.bin",
836
+ "h.9.mlp.dense_4h_to_h.bias": "pytorch_model_00011-of-00072.bin",
837
+ "h.9.mlp.dense_4h_to_h.weight": "pytorch_model_00011-of-00072.bin",
838
+ "h.9.mlp.dense_h_to_4h.bias": "pytorch_model_00011-of-00072.bin",
839
+ "h.9.mlp.dense_h_to_4h.weight": "pytorch_model_00011-of-00072.bin",
840
+ "h.9.post_attention_layernorm.bias": "pytorch_model_00011-of-00072.bin",
841
+ "h.9.post_attention_layernorm.weight": "pytorch_model_00011-of-00072.bin",
842
+ "h.9.self_attention.dense.bias": "pytorch_model_00011-of-00072.bin",
843
+ "h.9.self_attention.dense.weight": "pytorch_model_00011-of-00072.bin",
844
+ "h.9.self_attention.query_key_value.bias": "pytorch_model_00011-of-00072.bin",
845
+ "h.9.self_attention.query_key_value.weight": "pytorch_model_00011-of-00072.bin",
846
+ "ln_f.bias": "pytorch_model_00072-of-00072.bin",
847
+ "ln_f.weight": "pytorch_model_00072-of-00072.bin",
848
+ "word_embeddings.weight": "pytorch_model_00001-of-00072.bin",
849
+ "word_embeddings_layernorm.bias": "pytorch_model_00001-of-00072.bin",
850
+ "word_embeddings_layernorm.weight": "pytorch_model_00001-of-00072.bin"
851
+ }
852
+ }