Caleb Ellington commited on
Commit
4bc2a3a
1 Parent(s): 7a4939e

initial commit

Browse files
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_linear_bias": true,
3
+ "architectures": [
4
+ "RNABertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "hidden_act": "swiglu",
8
+ "hidden_dropout_prob": 0.0,
9
+ "hidden_size": 4352,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11584,
12
+ "layer_norm_eps": 1e-05,
13
+ "max_position_embeddings": 4000,
14
+ "model_type": "rnabert",
15
+ "normalization_type": "LayerNorm",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "rope",
20
+ "rotary_percent": 1.0,
21
+ "seq_len_interpolation_factor": null,
22
+ "tokenizer_type": "BertWordPieceLowerCase",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.38.0.dev0",
25
+ "type_vocab_size": 2,
26
+ "use_cache": true,
27
+ "vocab_size": 16
28
+ }
generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 0,
4
+ "transformers_version": "4.38.0.dev0"
5
+ }
pytorch_model-00001-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ba3763086b661544e8337e6f0f04c200b1b541e991b5fc77c906abe62adf560
3
+ size 4844744783
pytorch_model-00002-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83d0ed46bbd9cccf5ea015d8313ce679bb77687e31bcaa634346f0e24f733c6a
3
+ size 4944657678
pytorch_model-00003-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76068ef9852c9e4dc9bb5d0b108477dcd0fd95d2e8ddf2d6ec630d7008680bf6
3
+ size 4970354042
pytorch_model-00004-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edb2db9a29231a136771ab9a480822c3cc798a1f1444e01992e8f076873192e9
3
+ size 4818798602
pytorch_model-00005-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0561ad5c930e8245e9a9a08ed1eab89afa3ab32e0261335f2bf2113ea97442f
3
+ size 4944693210
pytorch_model-00006-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9ee229b7197b26b1e20b03b4283a9bad4600da9e1de1c44abbbefa1ea4d9ed9
3
+ size 4617097724
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,593 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 29140145216
4
+ },
5
+ "weight_map": {
6
+ "bert.embeddings.word_embeddings.weight": "pytorch_model-00001-of-00006.bin",
7
+ "bert.encoder.layer.0.attention.ln.bias": "pytorch_model-00001-of-00006.bin",
8
+ "bert.encoder.layer.0.attention.ln.weight": "pytorch_model-00001-of-00006.bin",
9
+ "bert.encoder.layer.0.attention.output.dense.bias": "pytorch_model-00001-of-00006.bin",
10
+ "bert.encoder.layer.0.attention.output.dense.weight": "pytorch_model-00001-of-00006.bin",
11
+ "bert.encoder.layer.0.attention.self.key.bias": "pytorch_model-00001-of-00006.bin",
12
+ "bert.encoder.layer.0.attention.self.key.weight": "pytorch_model-00001-of-00006.bin",
13
+ "bert.encoder.layer.0.attention.self.query.bias": "pytorch_model-00001-of-00006.bin",
14
+ "bert.encoder.layer.0.attention.self.query.weight": "pytorch_model-00001-of-00006.bin",
15
+ "bert.encoder.layer.0.attention.self.value.bias": "pytorch_model-00001-of-00006.bin",
16
+ "bert.encoder.layer.0.attention.self.value.weight": "pytorch_model-00001-of-00006.bin",
17
+ "bert.encoder.layer.0.ln.bias": "pytorch_model-00001-of-00006.bin",
18
+ "bert.encoder.layer.0.ln.weight": "pytorch_model-00001-of-00006.bin",
19
+ "bert.encoder.layer.0.mlp.down_proj.bias": "pytorch_model-00001-of-00006.bin",
20
+ "bert.encoder.layer.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
21
+ "bert.encoder.layer.0.mlp.gate_proj.bias": "pytorch_model-00001-of-00006.bin",
22
+ "bert.encoder.layer.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
23
+ "bert.encoder.layer.0.mlp.up_proj.bias": "pytorch_model-00001-of-00006.bin",
24
+ "bert.encoder.layer.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
25
+ "bert.encoder.layer.1.attention.ln.bias": "pytorch_model-00001-of-00006.bin",
26
+ "bert.encoder.layer.1.attention.ln.weight": "pytorch_model-00001-of-00006.bin",
27
+ "bert.encoder.layer.1.attention.output.dense.bias": "pytorch_model-00001-of-00006.bin",
28
+ "bert.encoder.layer.1.attention.output.dense.weight": "pytorch_model-00001-of-00006.bin",
29
+ "bert.encoder.layer.1.attention.self.key.bias": "pytorch_model-00001-of-00006.bin",
30
+ "bert.encoder.layer.1.attention.self.key.weight": "pytorch_model-00001-of-00006.bin",
31
+ "bert.encoder.layer.1.attention.self.query.bias": "pytorch_model-00001-of-00006.bin",
32
+ "bert.encoder.layer.1.attention.self.query.weight": "pytorch_model-00001-of-00006.bin",
33
+ "bert.encoder.layer.1.attention.self.value.bias": "pytorch_model-00001-of-00006.bin",
34
+ "bert.encoder.layer.1.attention.self.value.weight": "pytorch_model-00001-of-00006.bin",
35
+ "bert.encoder.layer.1.ln.bias": "pytorch_model-00001-of-00006.bin",
36
+ "bert.encoder.layer.1.ln.weight": "pytorch_model-00001-of-00006.bin",
37
+ "bert.encoder.layer.1.mlp.down_proj.bias": "pytorch_model-00001-of-00006.bin",
38
+ "bert.encoder.layer.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
39
+ "bert.encoder.layer.1.mlp.gate_proj.bias": "pytorch_model-00001-of-00006.bin",
40
+ "bert.encoder.layer.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
41
+ "bert.encoder.layer.1.mlp.up_proj.bias": "pytorch_model-00001-of-00006.bin",
42
+ "bert.encoder.layer.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
43
+ "bert.encoder.layer.10.attention.ln.bias": "pytorch_model-00002-of-00006.bin",
44
+ "bert.encoder.layer.10.attention.ln.weight": "pytorch_model-00002-of-00006.bin",
45
+ "bert.encoder.layer.10.attention.output.dense.bias": "pytorch_model-00002-of-00006.bin",
46
+ "bert.encoder.layer.10.attention.output.dense.weight": "pytorch_model-00002-of-00006.bin",
47
+ "bert.encoder.layer.10.attention.self.key.bias": "pytorch_model-00002-of-00006.bin",
48
+ "bert.encoder.layer.10.attention.self.key.weight": "pytorch_model-00002-of-00006.bin",
49
+ "bert.encoder.layer.10.attention.self.query.bias": "pytorch_model-00002-of-00006.bin",
50
+ "bert.encoder.layer.10.attention.self.query.weight": "pytorch_model-00002-of-00006.bin",
51
+ "bert.encoder.layer.10.attention.self.value.bias": "pytorch_model-00002-of-00006.bin",
52
+ "bert.encoder.layer.10.attention.self.value.weight": "pytorch_model-00002-of-00006.bin",
53
+ "bert.encoder.layer.10.ln.bias": "pytorch_model-00002-of-00006.bin",
54
+ "bert.encoder.layer.10.ln.weight": "pytorch_model-00002-of-00006.bin",
55
+ "bert.encoder.layer.10.mlp.down_proj.bias": "pytorch_model-00002-of-00006.bin",
56
+ "bert.encoder.layer.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
57
+ "bert.encoder.layer.10.mlp.gate_proj.bias": "pytorch_model-00003-of-00006.bin",
58
+ "bert.encoder.layer.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
59
+ "bert.encoder.layer.10.mlp.up_proj.bias": "pytorch_model-00002-of-00006.bin",
60
+ "bert.encoder.layer.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
61
+ "bert.encoder.layer.11.attention.ln.bias": "pytorch_model-00003-of-00006.bin",
62
+ "bert.encoder.layer.11.attention.ln.weight": "pytorch_model-00003-of-00006.bin",
63
+ "bert.encoder.layer.11.attention.output.dense.bias": "pytorch_model-00003-of-00006.bin",
64
+ "bert.encoder.layer.11.attention.output.dense.weight": "pytorch_model-00003-of-00006.bin",
65
+ "bert.encoder.layer.11.attention.self.key.bias": "pytorch_model-00003-of-00006.bin",
66
+ "bert.encoder.layer.11.attention.self.key.weight": "pytorch_model-00003-of-00006.bin",
67
+ "bert.encoder.layer.11.attention.self.query.bias": "pytorch_model-00003-of-00006.bin",
68
+ "bert.encoder.layer.11.attention.self.query.weight": "pytorch_model-00003-of-00006.bin",
69
+ "bert.encoder.layer.11.attention.self.value.bias": "pytorch_model-00003-of-00006.bin",
70
+ "bert.encoder.layer.11.attention.self.value.weight": "pytorch_model-00003-of-00006.bin",
71
+ "bert.encoder.layer.11.ln.bias": "pytorch_model-00003-of-00006.bin",
72
+ "bert.encoder.layer.11.ln.weight": "pytorch_model-00003-of-00006.bin",
73
+ "bert.encoder.layer.11.mlp.down_proj.bias": "pytorch_model-00003-of-00006.bin",
74
+ "bert.encoder.layer.11.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
75
+ "bert.encoder.layer.11.mlp.gate_proj.bias": "pytorch_model-00003-of-00006.bin",
76
+ "bert.encoder.layer.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
77
+ "bert.encoder.layer.11.mlp.up_proj.bias": "pytorch_model-00003-of-00006.bin",
78
+ "bert.encoder.layer.11.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
79
+ "bert.encoder.layer.12.attention.ln.bias": "pytorch_model-00003-of-00006.bin",
80
+ "bert.encoder.layer.12.attention.ln.weight": "pytorch_model-00003-of-00006.bin",
81
+ "bert.encoder.layer.12.attention.output.dense.bias": "pytorch_model-00003-of-00006.bin",
82
+ "bert.encoder.layer.12.attention.output.dense.weight": "pytorch_model-00003-of-00006.bin",
83
+ "bert.encoder.layer.12.attention.self.key.bias": "pytorch_model-00003-of-00006.bin",
84
+ "bert.encoder.layer.12.attention.self.key.weight": "pytorch_model-00003-of-00006.bin",
85
+ "bert.encoder.layer.12.attention.self.query.bias": "pytorch_model-00003-of-00006.bin",
86
+ "bert.encoder.layer.12.attention.self.query.weight": "pytorch_model-00003-of-00006.bin",
87
+ "bert.encoder.layer.12.attention.self.value.bias": "pytorch_model-00003-of-00006.bin",
88
+ "bert.encoder.layer.12.attention.self.value.weight": "pytorch_model-00003-of-00006.bin",
89
+ "bert.encoder.layer.12.ln.bias": "pytorch_model-00003-of-00006.bin",
90
+ "bert.encoder.layer.12.ln.weight": "pytorch_model-00003-of-00006.bin",
91
+ "bert.encoder.layer.12.mlp.down_proj.bias": "pytorch_model-00003-of-00006.bin",
92
+ "bert.encoder.layer.12.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
93
+ "bert.encoder.layer.12.mlp.gate_proj.bias": "pytorch_model-00003-of-00006.bin",
94
+ "bert.encoder.layer.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
95
+ "bert.encoder.layer.12.mlp.up_proj.bias": "pytorch_model-00003-of-00006.bin",
96
+ "bert.encoder.layer.12.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
97
+ "bert.encoder.layer.13.attention.ln.bias": "pytorch_model-00003-of-00006.bin",
98
+ "bert.encoder.layer.13.attention.ln.weight": "pytorch_model-00003-of-00006.bin",
99
+ "bert.encoder.layer.13.attention.output.dense.bias": "pytorch_model-00003-of-00006.bin",
100
+ "bert.encoder.layer.13.attention.output.dense.weight": "pytorch_model-00003-of-00006.bin",
101
+ "bert.encoder.layer.13.attention.self.key.bias": "pytorch_model-00003-of-00006.bin",
102
+ "bert.encoder.layer.13.attention.self.key.weight": "pytorch_model-00003-of-00006.bin",
103
+ "bert.encoder.layer.13.attention.self.query.bias": "pytorch_model-00003-of-00006.bin",
104
+ "bert.encoder.layer.13.attention.self.query.weight": "pytorch_model-00003-of-00006.bin",
105
+ "bert.encoder.layer.13.attention.self.value.bias": "pytorch_model-00003-of-00006.bin",
106
+ "bert.encoder.layer.13.attention.self.value.weight": "pytorch_model-00003-of-00006.bin",
107
+ "bert.encoder.layer.13.ln.bias": "pytorch_model-00003-of-00006.bin",
108
+ "bert.encoder.layer.13.ln.weight": "pytorch_model-00003-of-00006.bin",
109
+ "bert.encoder.layer.13.mlp.down_proj.bias": "pytorch_model-00003-of-00006.bin",
110
+ "bert.encoder.layer.13.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
111
+ "bert.encoder.layer.13.mlp.gate_proj.bias": "pytorch_model-00003-of-00006.bin",
112
+ "bert.encoder.layer.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
113
+ "bert.encoder.layer.13.mlp.up_proj.bias": "pytorch_model-00003-of-00006.bin",
114
+ "bert.encoder.layer.13.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
115
+ "bert.encoder.layer.14.attention.ln.bias": "pytorch_model-00003-of-00006.bin",
116
+ "bert.encoder.layer.14.attention.ln.weight": "pytorch_model-00003-of-00006.bin",
117
+ "bert.encoder.layer.14.attention.output.dense.bias": "pytorch_model-00003-of-00006.bin",
118
+ "bert.encoder.layer.14.attention.output.dense.weight": "pytorch_model-00003-of-00006.bin",
119
+ "bert.encoder.layer.14.attention.self.key.bias": "pytorch_model-00003-of-00006.bin",
120
+ "bert.encoder.layer.14.attention.self.key.weight": "pytorch_model-00003-of-00006.bin",
121
+ "bert.encoder.layer.14.attention.self.query.bias": "pytorch_model-00003-of-00006.bin",
122
+ "bert.encoder.layer.14.attention.self.query.weight": "pytorch_model-00003-of-00006.bin",
123
+ "bert.encoder.layer.14.attention.self.value.bias": "pytorch_model-00003-of-00006.bin",
124
+ "bert.encoder.layer.14.attention.self.value.weight": "pytorch_model-00003-of-00006.bin",
125
+ "bert.encoder.layer.14.ln.bias": "pytorch_model-00003-of-00006.bin",
126
+ "bert.encoder.layer.14.ln.weight": "pytorch_model-00003-of-00006.bin",
127
+ "bert.encoder.layer.14.mlp.down_proj.bias": "pytorch_model-00003-of-00006.bin",
128
+ "bert.encoder.layer.14.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
129
+ "bert.encoder.layer.14.mlp.gate_proj.bias": "pytorch_model-00003-of-00006.bin",
130
+ "bert.encoder.layer.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
131
+ "bert.encoder.layer.14.mlp.up_proj.bias": "pytorch_model-00003-of-00006.bin",
132
+ "bert.encoder.layer.14.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
133
+ "bert.encoder.layer.15.attention.ln.bias": "pytorch_model-00003-of-00006.bin",
134
+ "bert.encoder.layer.15.attention.ln.weight": "pytorch_model-00003-of-00006.bin",
135
+ "bert.encoder.layer.15.attention.output.dense.bias": "pytorch_model-00003-of-00006.bin",
136
+ "bert.encoder.layer.15.attention.output.dense.weight": "pytorch_model-00003-of-00006.bin",
137
+ "bert.encoder.layer.15.attention.self.key.bias": "pytorch_model-00003-of-00006.bin",
138
+ "bert.encoder.layer.15.attention.self.key.weight": "pytorch_model-00003-of-00006.bin",
139
+ "bert.encoder.layer.15.attention.self.query.bias": "pytorch_model-00003-of-00006.bin",
140
+ "bert.encoder.layer.15.attention.self.query.weight": "pytorch_model-00003-of-00006.bin",
141
+ "bert.encoder.layer.15.attention.self.value.bias": "pytorch_model-00003-of-00006.bin",
142
+ "bert.encoder.layer.15.attention.self.value.weight": "pytorch_model-00003-of-00006.bin",
143
+ "bert.encoder.layer.15.ln.bias": "pytorch_model-00003-of-00006.bin",
144
+ "bert.encoder.layer.15.ln.weight": "pytorch_model-00003-of-00006.bin",
145
+ "bert.encoder.layer.15.mlp.down_proj.bias": "pytorch_model-00003-of-00006.bin",
146
+ "bert.encoder.layer.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
147
+ "bert.encoder.layer.15.mlp.gate_proj.bias": "pytorch_model-00003-of-00006.bin",
148
+ "bert.encoder.layer.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
149
+ "bert.encoder.layer.15.mlp.up_proj.bias": "pytorch_model-00003-of-00006.bin",
150
+ "bert.encoder.layer.15.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
151
+ "bert.encoder.layer.16.attention.ln.bias": "pytorch_model-00003-of-00006.bin",
152
+ "bert.encoder.layer.16.attention.ln.weight": "pytorch_model-00003-of-00006.bin",
153
+ "bert.encoder.layer.16.attention.output.dense.bias": "pytorch_model-00004-of-00006.bin",
154
+ "bert.encoder.layer.16.attention.output.dense.weight": "pytorch_model-00004-of-00006.bin",
155
+ "bert.encoder.layer.16.attention.self.key.bias": "pytorch_model-00003-of-00006.bin",
156
+ "bert.encoder.layer.16.attention.self.key.weight": "pytorch_model-00003-of-00006.bin",
157
+ "bert.encoder.layer.16.attention.self.query.bias": "pytorch_model-00003-of-00006.bin",
158
+ "bert.encoder.layer.16.attention.self.query.weight": "pytorch_model-00003-of-00006.bin",
159
+ "bert.encoder.layer.16.attention.self.value.bias": "pytorch_model-00003-of-00006.bin",
160
+ "bert.encoder.layer.16.attention.self.value.weight": "pytorch_model-00003-of-00006.bin",
161
+ "bert.encoder.layer.16.ln.bias": "pytorch_model-00004-of-00006.bin",
162
+ "bert.encoder.layer.16.ln.weight": "pytorch_model-00004-of-00006.bin",
163
+ "bert.encoder.layer.16.mlp.down_proj.bias": "pytorch_model-00004-of-00006.bin",
164
+ "bert.encoder.layer.16.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
165
+ "bert.encoder.layer.16.mlp.gate_proj.bias": "pytorch_model-00004-of-00006.bin",
166
+ "bert.encoder.layer.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
167
+ "bert.encoder.layer.16.mlp.up_proj.bias": "pytorch_model-00004-of-00006.bin",
168
+ "bert.encoder.layer.16.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
169
+ "bert.encoder.layer.17.attention.ln.bias": "pytorch_model-00004-of-00006.bin",
170
+ "bert.encoder.layer.17.attention.ln.weight": "pytorch_model-00004-of-00006.bin",
171
+ "bert.encoder.layer.17.attention.output.dense.bias": "pytorch_model-00004-of-00006.bin",
172
+ "bert.encoder.layer.17.attention.output.dense.weight": "pytorch_model-00004-of-00006.bin",
173
+ "bert.encoder.layer.17.attention.self.key.bias": "pytorch_model-00004-of-00006.bin",
174
+ "bert.encoder.layer.17.attention.self.key.weight": "pytorch_model-00004-of-00006.bin",
175
+ "bert.encoder.layer.17.attention.self.query.bias": "pytorch_model-00004-of-00006.bin",
176
+ "bert.encoder.layer.17.attention.self.query.weight": "pytorch_model-00004-of-00006.bin",
177
+ "bert.encoder.layer.17.attention.self.value.bias": "pytorch_model-00004-of-00006.bin",
178
+ "bert.encoder.layer.17.attention.self.value.weight": "pytorch_model-00004-of-00006.bin",
179
+ "bert.encoder.layer.17.ln.bias": "pytorch_model-00004-of-00006.bin",
180
+ "bert.encoder.layer.17.ln.weight": "pytorch_model-00004-of-00006.bin",
181
+ "bert.encoder.layer.17.mlp.down_proj.bias": "pytorch_model-00004-of-00006.bin",
182
+ "bert.encoder.layer.17.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
183
+ "bert.encoder.layer.17.mlp.gate_proj.bias": "pytorch_model-00004-of-00006.bin",
184
+ "bert.encoder.layer.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
185
+ "bert.encoder.layer.17.mlp.up_proj.bias": "pytorch_model-00004-of-00006.bin",
186
+ "bert.encoder.layer.17.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
187
+ "bert.encoder.layer.18.attention.ln.bias": "pytorch_model-00004-of-00006.bin",
188
+ "bert.encoder.layer.18.attention.ln.weight": "pytorch_model-00004-of-00006.bin",
189
+ "bert.encoder.layer.18.attention.output.dense.bias": "pytorch_model-00004-of-00006.bin",
190
+ "bert.encoder.layer.18.attention.output.dense.weight": "pytorch_model-00004-of-00006.bin",
191
+ "bert.encoder.layer.18.attention.self.key.bias": "pytorch_model-00004-of-00006.bin",
192
+ "bert.encoder.layer.18.attention.self.key.weight": "pytorch_model-00004-of-00006.bin",
193
+ "bert.encoder.layer.18.attention.self.query.bias": "pytorch_model-00004-of-00006.bin",
194
+ "bert.encoder.layer.18.attention.self.query.weight": "pytorch_model-00004-of-00006.bin",
195
+ "bert.encoder.layer.18.attention.self.value.bias": "pytorch_model-00004-of-00006.bin",
196
+ "bert.encoder.layer.18.attention.self.value.weight": "pytorch_model-00004-of-00006.bin",
197
+ "bert.encoder.layer.18.ln.bias": "pytorch_model-00004-of-00006.bin",
198
+ "bert.encoder.layer.18.ln.weight": "pytorch_model-00004-of-00006.bin",
199
+ "bert.encoder.layer.18.mlp.down_proj.bias": "pytorch_model-00004-of-00006.bin",
200
+ "bert.encoder.layer.18.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
201
+ "bert.encoder.layer.18.mlp.gate_proj.bias": "pytorch_model-00004-of-00006.bin",
202
+ "bert.encoder.layer.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
203
+ "bert.encoder.layer.18.mlp.up_proj.bias": "pytorch_model-00004-of-00006.bin",
204
+ "bert.encoder.layer.18.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
205
+ "bert.encoder.layer.19.attention.ln.bias": "pytorch_model-00004-of-00006.bin",
206
+ "bert.encoder.layer.19.attention.ln.weight": "pytorch_model-00004-of-00006.bin",
207
+ "bert.encoder.layer.19.attention.output.dense.bias": "pytorch_model-00004-of-00006.bin",
208
+ "bert.encoder.layer.19.attention.output.dense.weight": "pytorch_model-00004-of-00006.bin",
209
+ "bert.encoder.layer.19.attention.self.key.bias": "pytorch_model-00004-of-00006.bin",
210
+ "bert.encoder.layer.19.attention.self.key.weight": "pytorch_model-00004-of-00006.bin",
211
+ "bert.encoder.layer.19.attention.self.query.bias": "pytorch_model-00004-of-00006.bin",
212
+ "bert.encoder.layer.19.attention.self.query.weight": "pytorch_model-00004-of-00006.bin",
213
+ "bert.encoder.layer.19.attention.self.value.bias": "pytorch_model-00004-of-00006.bin",
214
+ "bert.encoder.layer.19.attention.self.value.weight": "pytorch_model-00004-of-00006.bin",
215
+ "bert.encoder.layer.19.ln.bias": "pytorch_model-00004-of-00006.bin",
216
+ "bert.encoder.layer.19.ln.weight": "pytorch_model-00004-of-00006.bin",
217
+ "bert.encoder.layer.19.mlp.down_proj.bias": "pytorch_model-00004-of-00006.bin",
218
+ "bert.encoder.layer.19.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
219
+ "bert.encoder.layer.19.mlp.gate_proj.bias": "pytorch_model-00004-of-00006.bin",
220
+ "bert.encoder.layer.19.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
221
+ "bert.encoder.layer.19.mlp.up_proj.bias": "pytorch_model-00004-of-00006.bin",
222
+ "bert.encoder.layer.19.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
223
+ "bert.encoder.layer.2.attention.ln.bias": "pytorch_model-00001-of-00006.bin",
224
+ "bert.encoder.layer.2.attention.ln.weight": "pytorch_model-00001-of-00006.bin",
225
+ "bert.encoder.layer.2.attention.output.dense.bias": "pytorch_model-00001-of-00006.bin",
226
+ "bert.encoder.layer.2.attention.output.dense.weight": "pytorch_model-00001-of-00006.bin",
227
+ "bert.encoder.layer.2.attention.self.key.bias": "pytorch_model-00001-of-00006.bin",
228
+ "bert.encoder.layer.2.attention.self.key.weight": "pytorch_model-00001-of-00006.bin",
229
+ "bert.encoder.layer.2.attention.self.query.bias": "pytorch_model-00001-of-00006.bin",
230
+ "bert.encoder.layer.2.attention.self.query.weight": "pytorch_model-00001-of-00006.bin",
231
+ "bert.encoder.layer.2.attention.self.value.bias": "pytorch_model-00001-of-00006.bin",
232
+ "bert.encoder.layer.2.attention.self.value.weight": "pytorch_model-00001-of-00006.bin",
233
+ "bert.encoder.layer.2.ln.bias": "pytorch_model-00001-of-00006.bin",
234
+ "bert.encoder.layer.2.ln.weight": "pytorch_model-00001-of-00006.bin",
235
+ "bert.encoder.layer.2.mlp.down_proj.bias": "pytorch_model-00001-of-00006.bin",
236
+ "bert.encoder.layer.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
237
+ "bert.encoder.layer.2.mlp.gate_proj.bias": "pytorch_model-00001-of-00006.bin",
238
+ "bert.encoder.layer.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
239
+ "bert.encoder.layer.2.mlp.up_proj.bias": "pytorch_model-00001-of-00006.bin",
240
+ "bert.encoder.layer.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
241
+ "bert.encoder.layer.20.attention.ln.bias": "pytorch_model-00004-of-00006.bin",
242
+ "bert.encoder.layer.20.attention.ln.weight": "pytorch_model-00004-of-00006.bin",
243
+ "bert.encoder.layer.20.attention.output.dense.bias": "pytorch_model-00004-of-00006.bin",
244
+ "bert.encoder.layer.20.attention.output.dense.weight": "pytorch_model-00004-of-00006.bin",
245
+ "bert.encoder.layer.20.attention.self.key.bias": "pytorch_model-00004-of-00006.bin",
246
+ "bert.encoder.layer.20.attention.self.key.weight": "pytorch_model-00004-of-00006.bin",
247
+ "bert.encoder.layer.20.attention.self.query.bias": "pytorch_model-00004-of-00006.bin",
248
+ "bert.encoder.layer.20.attention.self.query.weight": "pytorch_model-00004-of-00006.bin",
249
+ "bert.encoder.layer.20.attention.self.value.bias": "pytorch_model-00004-of-00006.bin",
250
+ "bert.encoder.layer.20.attention.self.value.weight": "pytorch_model-00004-of-00006.bin",
251
+ "bert.encoder.layer.20.ln.bias": "pytorch_model-00004-of-00006.bin",
252
+ "bert.encoder.layer.20.ln.weight": "pytorch_model-00004-of-00006.bin",
253
+ "bert.encoder.layer.20.mlp.down_proj.bias": "pytorch_model-00004-of-00006.bin",
254
+ "bert.encoder.layer.20.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
255
+ "bert.encoder.layer.20.mlp.gate_proj.bias": "pytorch_model-00004-of-00006.bin",
256
+ "bert.encoder.layer.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
257
+ "bert.encoder.layer.20.mlp.up_proj.bias": "pytorch_model-00004-of-00006.bin",
258
+ "bert.encoder.layer.20.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
259
+ "bert.encoder.layer.21.attention.ln.bias": "pytorch_model-00004-of-00006.bin",
260
+ "bert.encoder.layer.21.attention.ln.weight": "pytorch_model-00004-of-00006.bin",
261
+ "bert.encoder.layer.21.attention.output.dense.bias": "pytorch_model-00004-of-00006.bin",
262
+ "bert.encoder.layer.21.attention.output.dense.weight": "pytorch_model-00004-of-00006.bin",
263
+ "bert.encoder.layer.21.attention.self.key.bias": "pytorch_model-00004-of-00006.bin",
264
+ "bert.encoder.layer.21.attention.self.key.weight": "pytorch_model-00004-of-00006.bin",
265
+ "bert.encoder.layer.21.attention.self.query.bias": "pytorch_model-00004-of-00006.bin",
266
+ "bert.encoder.layer.21.attention.self.query.weight": "pytorch_model-00004-of-00006.bin",
267
+ "bert.encoder.layer.21.attention.self.value.bias": "pytorch_model-00004-of-00006.bin",
268
+ "bert.encoder.layer.21.attention.self.value.weight": "pytorch_model-00004-of-00006.bin",
269
+ "bert.encoder.layer.21.ln.bias": "pytorch_model-00004-of-00006.bin",
270
+ "bert.encoder.layer.21.ln.weight": "pytorch_model-00004-of-00006.bin",
271
+ "bert.encoder.layer.21.mlp.down_proj.bias": "pytorch_model-00005-of-00006.bin",
272
+ "bert.encoder.layer.21.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
273
+ "bert.encoder.layer.21.mlp.gate_proj.bias": "pytorch_model-00005-of-00006.bin",
274
+ "bert.encoder.layer.21.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
275
+ "bert.encoder.layer.21.mlp.up_proj.bias": "pytorch_model-00004-of-00006.bin",
276
+ "bert.encoder.layer.21.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
277
+ "bert.encoder.layer.22.attention.ln.bias": "pytorch_model-00005-of-00006.bin",
278
+ "bert.encoder.layer.22.attention.ln.weight": "pytorch_model-00005-of-00006.bin",
279
+ "bert.encoder.layer.22.attention.output.dense.bias": "pytorch_model-00005-of-00006.bin",
280
+ "bert.encoder.layer.22.attention.output.dense.weight": "pytorch_model-00005-of-00006.bin",
281
+ "bert.encoder.layer.22.attention.self.key.bias": "pytorch_model-00005-of-00006.bin",
282
+ "bert.encoder.layer.22.attention.self.key.weight": "pytorch_model-00005-of-00006.bin",
283
+ "bert.encoder.layer.22.attention.self.query.bias": "pytorch_model-00005-of-00006.bin",
284
+ "bert.encoder.layer.22.attention.self.query.weight": "pytorch_model-00005-of-00006.bin",
285
+ "bert.encoder.layer.22.attention.self.value.bias": "pytorch_model-00005-of-00006.bin",
286
+ "bert.encoder.layer.22.attention.self.value.weight": "pytorch_model-00005-of-00006.bin",
287
+ "bert.encoder.layer.22.ln.bias": "pytorch_model-00005-of-00006.bin",
288
+ "bert.encoder.layer.22.ln.weight": "pytorch_model-00005-of-00006.bin",
289
+ "bert.encoder.layer.22.mlp.down_proj.bias": "pytorch_model-00005-of-00006.bin",
290
+ "bert.encoder.layer.22.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
291
+ "bert.encoder.layer.22.mlp.gate_proj.bias": "pytorch_model-00005-of-00006.bin",
292
+ "bert.encoder.layer.22.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
293
+ "bert.encoder.layer.22.mlp.up_proj.bias": "pytorch_model-00005-of-00006.bin",
294
+ "bert.encoder.layer.22.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
295
+ "bert.encoder.layer.23.attention.ln.bias": "pytorch_model-00005-of-00006.bin",
296
+ "bert.encoder.layer.23.attention.ln.weight": "pytorch_model-00005-of-00006.bin",
297
+ "bert.encoder.layer.23.attention.output.dense.bias": "pytorch_model-00005-of-00006.bin",
298
+ "bert.encoder.layer.23.attention.output.dense.weight": "pytorch_model-00005-of-00006.bin",
299
+ "bert.encoder.layer.23.attention.self.key.bias": "pytorch_model-00005-of-00006.bin",
300
+ "bert.encoder.layer.23.attention.self.key.weight": "pytorch_model-00005-of-00006.bin",
301
+ "bert.encoder.layer.23.attention.self.query.bias": "pytorch_model-00005-of-00006.bin",
302
+ "bert.encoder.layer.23.attention.self.query.weight": "pytorch_model-00005-of-00006.bin",
303
+ "bert.encoder.layer.23.attention.self.value.bias": "pytorch_model-00005-of-00006.bin",
304
+ "bert.encoder.layer.23.attention.self.value.weight": "pytorch_model-00005-of-00006.bin",
305
+ "bert.encoder.layer.23.ln.bias": "pytorch_model-00005-of-00006.bin",
306
+ "bert.encoder.layer.23.ln.weight": "pytorch_model-00005-of-00006.bin",
307
+ "bert.encoder.layer.23.mlp.down_proj.bias": "pytorch_model-00005-of-00006.bin",
308
+ "bert.encoder.layer.23.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
309
+ "bert.encoder.layer.23.mlp.gate_proj.bias": "pytorch_model-00005-of-00006.bin",
310
+ "bert.encoder.layer.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
311
+ "bert.encoder.layer.23.mlp.up_proj.bias": "pytorch_model-00005-of-00006.bin",
312
+ "bert.encoder.layer.23.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
313
+ "bert.encoder.layer.24.attention.ln.bias": "pytorch_model-00005-of-00006.bin",
314
+ "bert.encoder.layer.24.attention.ln.weight": "pytorch_model-00005-of-00006.bin",
315
+ "bert.encoder.layer.24.attention.output.dense.bias": "pytorch_model-00005-of-00006.bin",
316
+ "bert.encoder.layer.24.attention.output.dense.weight": "pytorch_model-00005-of-00006.bin",
317
+ "bert.encoder.layer.24.attention.self.key.bias": "pytorch_model-00005-of-00006.bin",
318
+ "bert.encoder.layer.24.attention.self.key.weight": "pytorch_model-00005-of-00006.bin",
319
+ "bert.encoder.layer.24.attention.self.query.bias": "pytorch_model-00005-of-00006.bin",
320
+ "bert.encoder.layer.24.attention.self.query.weight": "pytorch_model-00005-of-00006.bin",
321
+ "bert.encoder.layer.24.attention.self.value.bias": "pytorch_model-00005-of-00006.bin",
322
+ "bert.encoder.layer.24.attention.self.value.weight": "pytorch_model-00005-of-00006.bin",
323
+ "bert.encoder.layer.24.ln.bias": "pytorch_model-00005-of-00006.bin",
324
+ "bert.encoder.layer.24.ln.weight": "pytorch_model-00005-of-00006.bin",
325
+ "bert.encoder.layer.24.mlp.down_proj.bias": "pytorch_model-00005-of-00006.bin",
326
+ "bert.encoder.layer.24.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
327
+ "bert.encoder.layer.24.mlp.gate_proj.bias": "pytorch_model-00005-of-00006.bin",
328
+ "bert.encoder.layer.24.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
329
+ "bert.encoder.layer.24.mlp.up_proj.bias": "pytorch_model-00005-of-00006.bin",
330
+ "bert.encoder.layer.24.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
331
+ "bert.encoder.layer.25.attention.ln.bias": "pytorch_model-00005-of-00006.bin",
332
+ "bert.encoder.layer.25.attention.ln.weight": "pytorch_model-00005-of-00006.bin",
333
+ "bert.encoder.layer.25.attention.output.dense.bias": "pytorch_model-00005-of-00006.bin",
334
+ "bert.encoder.layer.25.attention.output.dense.weight": "pytorch_model-00005-of-00006.bin",
335
+ "bert.encoder.layer.25.attention.self.key.bias": "pytorch_model-00005-of-00006.bin",
336
+ "bert.encoder.layer.25.attention.self.key.weight": "pytorch_model-00005-of-00006.bin",
337
+ "bert.encoder.layer.25.attention.self.query.bias": "pytorch_model-00005-of-00006.bin",
338
+ "bert.encoder.layer.25.attention.self.query.weight": "pytorch_model-00005-of-00006.bin",
339
+ "bert.encoder.layer.25.attention.self.value.bias": "pytorch_model-00005-of-00006.bin",
340
+ "bert.encoder.layer.25.attention.self.value.weight": "pytorch_model-00005-of-00006.bin",
341
+ "bert.encoder.layer.25.ln.bias": "pytorch_model-00005-of-00006.bin",
342
+ "bert.encoder.layer.25.ln.weight": "pytorch_model-00005-of-00006.bin",
343
+ "bert.encoder.layer.25.mlp.down_proj.bias": "pytorch_model-00005-of-00006.bin",
344
+ "bert.encoder.layer.25.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
345
+ "bert.encoder.layer.25.mlp.gate_proj.bias": "pytorch_model-00005-of-00006.bin",
346
+ "bert.encoder.layer.25.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
347
+ "bert.encoder.layer.25.mlp.up_proj.bias": "pytorch_model-00005-of-00006.bin",
348
+ "bert.encoder.layer.25.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
349
+ "bert.encoder.layer.26.attention.ln.bias": "pytorch_model-00005-of-00006.bin",
350
+ "bert.encoder.layer.26.attention.ln.weight": "pytorch_model-00005-of-00006.bin",
351
+ "bert.encoder.layer.26.attention.output.dense.bias": "pytorch_model-00005-of-00006.bin",
352
+ "bert.encoder.layer.26.attention.output.dense.weight": "pytorch_model-00005-of-00006.bin",
353
+ "bert.encoder.layer.26.attention.self.key.bias": "pytorch_model-00005-of-00006.bin",
354
+ "bert.encoder.layer.26.attention.self.key.weight": "pytorch_model-00005-of-00006.bin",
355
+ "bert.encoder.layer.26.attention.self.query.bias": "pytorch_model-00005-of-00006.bin",
356
+ "bert.encoder.layer.26.attention.self.query.weight": "pytorch_model-00005-of-00006.bin",
357
+ "bert.encoder.layer.26.attention.self.value.bias": "pytorch_model-00005-of-00006.bin",
358
+ "bert.encoder.layer.26.attention.self.value.weight": "pytorch_model-00005-of-00006.bin",
359
+ "bert.encoder.layer.26.ln.bias": "pytorch_model-00005-of-00006.bin",
360
+ "bert.encoder.layer.26.ln.weight": "pytorch_model-00005-of-00006.bin",
361
+ "bert.encoder.layer.26.mlp.down_proj.bias": "pytorch_model-00005-of-00006.bin",
362
+ "bert.encoder.layer.26.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
363
+ "bert.encoder.layer.26.mlp.gate_proj.bias": "pytorch_model-00005-of-00006.bin",
364
+ "bert.encoder.layer.26.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
365
+ "bert.encoder.layer.26.mlp.up_proj.bias": "pytorch_model-00005-of-00006.bin",
366
+ "bert.encoder.layer.26.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
367
+ "bert.encoder.layer.27.attention.ln.bias": "pytorch_model-00005-of-00006.bin",
368
+ "bert.encoder.layer.27.attention.ln.weight": "pytorch_model-00005-of-00006.bin",
369
+ "bert.encoder.layer.27.attention.output.dense.bias": "pytorch_model-00006-of-00006.bin",
370
+ "bert.encoder.layer.27.attention.output.dense.weight": "pytorch_model-00006-of-00006.bin",
371
+ "bert.encoder.layer.27.attention.self.key.bias": "pytorch_model-00006-of-00006.bin",
372
+ "bert.encoder.layer.27.attention.self.key.weight": "pytorch_model-00006-of-00006.bin",
373
+ "bert.encoder.layer.27.attention.self.query.bias": "pytorch_model-00006-of-00006.bin",
374
+ "bert.encoder.layer.27.attention.self.query.weight": "pytorch_model-00006-of-00006.bin",
375
+ "bert.encoder.layer.27.attention.self.value.bias": "pytorch_model-00006-of-00006.bin",
376
+ "bert.encoder.layer.27.attention.self.value.weight": "pytorch_model-00006-of-00006.bin",
377
+ "bert.encoder.layer.27.ln.bias": "pytorch_model-00006-of-00006.bin",
378
+ "bert.encoder.layer.27.ln.weight": "pytorch_model-00006-of-00006.bin",
379
+ "bert.encoder.layer.27.mlp.down_proj.bias": "pytorch_model-00006-of-00006.bin",
380
+ "bert.encoder.layer.27.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
381
+ "bert.encoder.layer.27.mlp.gate_proj.bias": "pytorch_model-00006-of-00006.bin",
382
+ "bert.encoder.layer.27.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
383
+ "bert.encoder.layer.27.mlp.up_proj.bias": "pytorch_model-00006-of-00006.bin",
384
+ "bert.encoder.layer.27.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
385
+ "bert.encoder.layer.28.attention.ln.bias": "pytorch_model-00006-of-00006.bin",
386
+ "bert.encoder.layer.28.attention.ln.weight": "pytorch_model-00006-of-00006.bin",
387
+ "bert.encoder.layer.28.attention.output.dense.bias": "pytorch_model-00006-of-00006.bin",
388
+ "bert.encoder.layer.28.attention.output.dense.weight": "pytorch_model-00006-of-00006.bin",
389
+ "bert.encoder.layer.28.attention.self.key.bias": "pytorch_model-00006-of-00006.bin",
390
+ "bert.encoder.layer.28.attention.self.key.weight": "pytorch_model-00006-of-00006.bin",
391
+ "bert.encoder.layer.28.attention.self.query.bias": "pytorch_model-00006-of-00006.bin",
392
+ "bert.encoder.layer.28.attention.self.query.weight": "pytorch_model-00006-of-00006.bin",
393
+ "bert.encoder.layer.28.attention.self.value.bias": "pytorch_model-00006-of-00006.bin",
394
+ "bert.encoder.layer.28.attention.self.value.weight": "pytorch_model-00006-of-00006.bin",
395
+ "bert.encoder.layer.28.ln.bias": "pytorch_model-00006-of-00006.bin",
396
+ "bert.encoder.layer.28.ln.weight": "pytorch_model-00006-of-00006.bin",
397
+ "bert.encoder.layer.28.mlp.down_proj.bias": "pytorch_model-00006-of-00006.bin",
398
+ "bert.encoder.layer.28.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
399
+ "bert.encoder.layer.28.mlp.gate_proj.bias": "pytorch_model-00006-of-00006.bin",
400
+ "bert.encoder.layer.28.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
401
+ "bert.encoder.layer.28.mlp.up_proj.bias": "pytorch_model-00006-of-00006.bin",
402
+ "bert.encoder.layer.28.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
403
+ "bert.encoder.layer.29.attention.ln.bias": "pytorch_model-00006-of-00006.bin",
404
+ "bert.encoder.layer.29.attention.ln.weight": "pytorch_model-00006-of-00006.bin",
405
+ "bert.encoder.layer.29.attention.output.dense.bias": "pytorch_model-00006-of-00006.bin",
406
+ "bert.encoder.layer.29.attention.output.dense.weight": "pytorch_model-00006-of-00006.bin",
407
+ "bert.encoder.layer.29.attention.self.key.bias": "pytorch_model-00006-of-00006.bin",
408
+ "bert.encoder.layer.29.attention.self.key.weight": "pytorch_model-00006-of-00006.bin",
409
+ "bert.encoder.layer.29.attention.self.query.bias": "pytorch_model-00006-of-00006.bin",
410
+ "bert.encoder.layer.29.attention.self.query.weight": "pytorch_model-00006-of-00006.bin",
411
+ "bert.encoder.layer.29.attention.self.value.bias": "pytorch_model-00006-of-00006.bin",
412
+ "bert.encoder.layer.29.attention.self.value.weight": "pytorch_model-00006-of-00006.bin",
413
+ "bert.encoder.layer.29.ln.bias": "pytorch_model-00006-of-00006.bin",
414
+ "bert.encoder.layer.29.ln.weight": "pytorch_model-00006-of-00006.bin",
415
+ "bert.encoder.layer.29.mlp.down_proj.bias": "pytorch_model-00006-of-00006.bin",
416
+ "bert.encoder.layer.29.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
417
+ "bert.encoder.layer.29.mlp.gate_proj.bias": "pytorch_model-00006-of-00006.bin",
418
+ "bert.encoder.layer.29.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
419
+ "bert.encoder.layer.29.mlp.up_proj.bias": "pytorch_model-00006-of-00006.bin",
420
+ "bert.encoder.layer.29.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
421
+ "bert.encoder.layer.3.attention.ln.bias": "pytorch_model-00001-of-00006.bin",
422
+ "bert.encoder.layer.3.attention.ln.weight": "pytorch_model-00001-of-00006.bin",
423
+ "bert.encoder.layer.3.attention.output.dense.bias": "pytorch_model-00001-of-00006.bin",
424
+ "bert.encoder.layer.3.attention.output.dense.weight": "pytorch_model-00001-of-00006.bin",
425
+ "bert.encoder.layer.3.attention.self.key.bias": "pytorch_model-00001-of-00006.bin",
426
+ "bert.encoder.layer.3.attention.self.key.weight": "pytorch_model-00001-of-00006.bin",
427
+ "bert.encoder.layer.3.attention.self.query.bias": "pytorch_model-00001-of-00006.bin",
428
+ "bert.encoder.layer.3.attention.self.query.weight": "pytorch_model-00001-of-00006.bin",
429
+ "bert.encoder.layer.3.attention.self.value.bias": "pytorch_model-00001-of-00006.bin",
430
+ "bert.encoder.layer.3.attention.self.value.weight": "pytorch_model-00001-of-00006.bin",
431
+ "bert.encoder.layer.3.ln.bias": "pytorch_model-00001-of-00006.bin",
432
+ "bert.encoder.layer.3.ln.weight": "pytorch_model-00001-of-00006.bin",
433
+ "bert.encoder.layer.3.mlp.down_proj.bias": "pytorch_model-00001-of-00006.bin",
434
+ "bert.encoder.layer.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
435
+ "bert.encoder.layer.3.mlp.gate_proj.bias": "pytorch_model-00001-of-00006.bin",
436
+ "bert.encoder.layer.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
437
+ "bert.encoder.layer.3.mlp.up_proj.bias": "pytorch_model-00001-of-00006.bin",
438
+ "bert.encoder.layer.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
439
+ "bert.encoder.layer.30.attention.ln.bias": "pytorch_model-00006-of-00006.bin",
440
+ "bert.encoder.layer.30.attention.ln.weight": "pytorch_model-00006-of-00006.bin",
441
+ "bert.encoder.layer.30.attention.output.dense.bias": "pytorch_model-00006-of-00006.bin",
442
+ "bert.encoder.layer.30.attention.output.dense.weight": "pytorch_model-00006-of-00006.bin",
443
+ "bert.encoder.layer.30.attention.self.key.bias": "pytorch_model-00006-of-00006.bin",
444
+ "bert.encoder.layer.30.attention.self.key.weight": "pytorch_model-00006-of-00006.bin",
445
+ "bert.encoder.layer.30.attention.self.query.bias": "pytorch_model-00006-of-00006.bin",
446
+ "bert.encoder.layer.30.attention.self.query.weight": "pytorch_model-00006-of-00006.bin",
447
+ "bert.encoder.layer.30.attention.self.value.bias": "pytorch_model-00006-of-00006.bin",
448
+ "bert.encoder.layer.30.attention.self.value.weight": "pytorch_model-00006-of-00006.bin",
449
+ "bert.encoder.layer.30.ln.bias": "pytorch_model-00006-of-00006.bin",
450
+ "bert.encoder.layer.30.ln.weight": "pytorch_model-00006-of-00006.bin",
451
+ "bert.encoder.layer.30.mlp.down_proj.bias": "pytorch_model-00006-of-00006.bin",
452
+ "bert.encoder.layer.30.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
453
+ "bert.encoder.layer.30.mlp.gate_proj.bias": "pytorch_model-00006-of-00006.bin",
454
+ "bert.encoder.layer.30.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
455
+ "bert.encoder.layer.30.mlp.up_proj.bias": "pytorch_model-00006-of-00006.bin",
456
+ "bert.encoder.layer.30.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
457
+ "bert.encoder.layer.31.attention.ln.bias": "pytorch_model-00006-of-00006.bin",
458
+ "bert.encoder.layer.31.attention.ln.weight": "pytorch_model-00006-of-00006.bin",
459
+ "bert.encoder.layer.31.attention.output.dense.bias": "pytorch_model-00006-of-00006.bin",
460
+ "bert.encoder.layer.31.attention.output.dense.weight": "pytorch_model-00006-of-00006.bin",
461
+ "bert.encoder.layer.31.attention.self.key.bias": "pytorch_model-00006-of-00006.bin",
462
+ "bert.encoder.layer.31.attention.self.key.weight": "pytorch_model-00006-of-00006.bin",
463
+ "bert.encoder.layer.31.attention.self.query.bias": "pytorch_model-00006-of-00006.bin",
464
+ "bert.encoder.layer.31.attention.self.query.weight": "pytorch_model-00006-of-00006.bin",
465
+ "bert.encoder.layer.31.attention.self.value.bias": "pytorch_model-00006-of-00006.bin",
466
+ "bert.encoder.layer.31.attention.self.value.weight": "pytorch_model-00006-of-00006.bin",
467
+ "bert.encoder.layer.31.ln.bias": "pytorch_model-00006-of-00006.bin",
468
+ "bert.encoder.layer.31.ln.weight": "pytorch_model-00006-of-00006.bin",
469
+ "bert.encoder.layer.31.mlp.down_proj.bias": "pytorch_model-00006-of-00006.bin",
470
+ "bert.encoder.layer.31.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
471
+ "bert.encoder.layer.31.mlp.gate_proj.bias": "pytorch_model-00006-of-00006.bin",
472
+ "bert.encoder.layer.31.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
473
+ "bert.encoder.layer.31.mlp.up_proj.bias": "pytorch_model-00006-of-00006.bin",
474
+ "bert.encoder.layer.31.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
475
+ "bert.encoder.layer.4.attention.ln.bias": "pytorch_model-00001-of-00006.bin",
476
+ "bert.encoder.layer.4.attention.ln.weight": "pytorch_model-00001-of-00006.bin",
477
+ "bert.encoder.layer.4.attention.output.dense.bias": "pytorch_model-00001-of-00006.bin",
478
+ "bert.encoder.layer.4.attention.output.dense.weight": "pytorch_model-00001-of-00006.bin",
479
+ "bert.encoder.layer.4.attention.self.key.bias": "pytorch_model-00001-of-00006.bin",
480
+ "bert.encoder.layer.4.attention.self.key.weight": "pytorch_model-00001-of-00006.bin",
481
+ "bert.encoder.layer.4.attention.self.query.bias": "pytorch_model-00001-of-00006.bin",
482
+ "bert.encoder.layer.4.attention.self.query.weight": "pytorch_model-00001-of-00006.bin",
483
+ "bert.encoder.layer.4.attention.self.value.bias": "pytorch_model-00001-of-00006.bin",
484
+ "bert.encoder.layer.4.attention.self.value.weight": "pytorch_model-00001-of-00006.bin",
485
+ "bert.encoder.layer.4.ln.bias": "pytorch_model-00001-of-00006.bin",
486
+ "bert.encoder.layer.4.ln.weight": "pytorch_model-00001-of-00006.bin",
487
+ "bert.encoder.layer.4.mlp.down_proj.bias": "pytorch_model-00001-of-00006.bin",
488
+ "bert.encoder.layer.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
489
+ "bert.encoder.layer.4.mlp.gate_proj.bias": "pytorch_model-00001-of-00006.bin",
490
+ "bert.encoder.layer.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
491
+ "bert.encoder.layer.4.mlp.up_proj.bias": "pytorch_model-00001-of-00006.bin",
492
+ "bert.encoder.layer.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
493
+ "bert.encoder.layer.5.attention.ln.bias": "pytorch_model-00001-of-00006.bin",
494
+ "bert.encoder.layer.5.attention.ln.weight": "pytorch_model-00001-of-00006.bin",
495
+ "bert.encoder.layer.5.attention.output.dense.bias": "pytorch_model-00001-of-00006.bin",
496
+ "bert.encoder.layer.5.attention.output.dense.weight": "pytorch_model-00001-of-00006.bin",
497
+ "bert.encoder.layer.5.attention.self.key.bias": "pytorch_model-00001-of-00006.bin",
498
+ "bert.encoder.layer.5.attention.self.key.weight": "pytorch_model-00001-of-00006.bin",
499
+ "bert.encoder.layer.5.attention.self.query.bias": "pytorch_model-00001-of-00006.bin",
500
+ "bert.encoder.layer.5.attention.self.query.weight": "pytorch_model-00001-of-00006.bin",
501
+ "bert.encoder.layer.5.attention.self.value.bias": "pytorch_model-00001-of-00006.bin",
502
+ "bert.encoder.layer.5.attention.self.value.weight": "pytorch_model-00001-of-00006.bin",
503
+ "bert.encoder.layer.5.ln.bias": "pytorch_model-00001-of-00006.bin",
504
+ "bert.encoder.layer.5.ln.weight": "pytorch_model-00001-of-00006.bin",
505
+ "bert.encoder.layer.5.mlp.down_proj.bias": "pytorch_model-00002-of-00006.bin",
506
+ "bert.encoder.layer.5.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
507
+ "bert.encoder.layer.5.mlp.gate_proj.bias": "pytorch_model-00002-of-00006.bin",
508
+ "bert.encoder.layer.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
509
+ "bert.encoder.layer.5.mlp.up_proj.bias": "pytorch_model-00002-of-00006.bin",
510
+ "bert.encoder.layer.5.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
511
+ "bert.encoder.layer.6.attention.ln.bias": "pytorch_model-00002-of-00006.bin",
512
+ "bert.encoder.layer.6.attention.ln.weight": "pytorch_model-00002-of-00006.bin",
513
+ "bert.encoder.layer.6.attention.output.dense.bias": "pytorch_model-00002-of-00006.bin",
514
+ "bert.encoder.layer.6.attention.output.dense.weight": "pytorch_model-00002-of-00006.bin",
515
+ "bert.encoder.layer.6.attention.self.key.bias": "pytorch_model-00002-of-00006.bin",
516
+ "bert.encoder.layer.6.attention.self.key.weight": "pytorch_model-00002-of-00006.bin",
517
+ "bert.encoder.layer.6.attention.self.query.bias": "pytorch_model-00002-of-00006.bin",
518
+ "bert.encoder.layer.6.attention.self.query.weight": "pytorch_model-00002-of-00006.bin",
519
+ "bert.encoder.layer.6.attention.self.value.bias": "pytorch_model-00002-of-00006.bin",
520
+ "bert.encoder.layer.6.attention.self.value.weight": "pytorch_model-00002-of-00006.bin",
521
+ "bert.encoder.layer.6.ln.bias": "pytorch_model-00002-of-00006.bin",
522
+ "bert.encoder.layer.6.ln.weight": "pytorch_model-00002-of-00006.bin",
523
+ "bert.encoder.layer.6.mlp.down_proj.bias": "pytorch_model-00002-of-00006.bin",
524
+ "bert.encoder.layer.6.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
525
+ "bert.encoder.layer.6.mlp.gate_proj.bias": "pytorch_model-00002-of-00006.bin",
526
+ "bert.encoder.layer.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
527
+ "bert.encoder.layer.6.mlp.up_proj.bias": "pytorch_model-00002-of-00006.bin",
528
+ "bert.encoder.layer.6.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
529
+ "bert.encoder.layer.7.attention.ln.bias": "pytorch_model-00002-of-00006.bin",
530
+ "bert.encoder.layer.7.attention.ln.weight": "pytorch_model-00002-of-00006.bin",
531
+ "bert.encoder.layer.7.attention.output.dense.bias": "pytorch_model-00002-of-00006.bin",
532
+ "bert.encoder.layer.7.attention.output.dense.weight": "pytorch_model-00002-of-00006.bin",
533
+ "bert.encoder.layer.7.attention.self.key.bias": "pytorch_model-00002-of-00006.bin",
534
+ "bert.encoder.layer.7.attention.self.key.weight": "pytorch_model-00002-of-00006.bin",
535
+ "bert.encoder.layer.7.attention.self.query.bias": "pytorch_model-00002-of-00006.bin",
536
+ "bert.encoder.layer.7.attention.self.query.weight": "pytorch_model-00002-of-00006.bin",
537
+ "bert.encoder.layer.7.attention.self.value.bias": "pytorch_model-00002-of-00006.bin",
538
+ "bert.encoder.layer.7.attention.self.value.weight": "pytorch_model-00002-of-00006.bin",
539
+ "bert.encoder.layer.7.ln.bias": "pytorch_model-00002-of-00006.bin",
540
+ "bert.encoder.layer.7.ln.weight": "pytorch_model-00002-of-00006.bin",
541
+ "bert.encoder.layer.7.mlp.down_proj.bias": "pytorch_model-00002-of-00006.bin",
542
+ "bert.encoder.layer.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
543
+ "bert.encoder.layer.7.mlp.gate_proj.bias": "pytorch_model-00002-of-00006.bin",
544
+ "bert.encoder.layer.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
545
+ "bert.encoder.layer.7.mlp.up_proj.bias": "pytorch_model-00002-of-00006.bin",
546
+ "bert.encoder.layer.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
547
+ "bert.encoder.layer.8.attention.ln.bias": "pytorch_model-00002-of-00006.bin",
548
+ "bert.encoder.layer.8.attention.ln.weight": "pytorch_model-00002-of-00006.bin",
549
+ "bert.encoder.layer.8.attention.output.dense.bias": "pytorch_model-00002-of-00006.bin",
550
+ "bert.encoder.layer.8.attention.output.dense.weight": "pytorch_model-00002-of-00006.bin",
551
+ "bert.encoder.layer.8.attention.self.key.bias": "pytorch_model-00002-of-00006.bin",
552
+ "bert.encoder.layer.8.attention.self.key.weight": "pytorch_model-00002-of-00006.bin",
553
+ "bert.encoder.layer.8.attention.self.query.bias": "pytorch_model-00002-of-00006.bin",
554
+ "bert.encoder.layer.8.attention.self.query.weight": "pytorch_model-00002-of-00006.bin",
555
+ "bert.encoder.layer.8.attention.self.value.bias": "pytorch_model-00002-of-00006.bin",
556
+ "bert.encoder.layer.8.attention.self.value.weight": "pytorch_model-00002-of-00006.bin",
557
+ "bert.encoder.layer.8.ln.bias": "pytorch_model-00002-of-00006.bin",
558
+ "bert.encoder.layer.8.ln.weight": "pytorch_model-00002-of-00006.bin",
559
+ "bert.encoder.layer.8.mlp.down_proj.bias": "pytorch_model-00002-of-00006.bin",
560
+ "bert.encoder.layer.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
561
+ "bert.encoder.layer.8.mlp.gate_proj.bias": "pytorch_model-00002-of-00006.bin",
562
+ "bert.encoder.layer.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
563
+ "bert.encoder.layer.8.mlp.up_proj.bias": "pytorch_model-00002-of-00006.bin",
564
+ "bert.encoder.layer.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
565
+ "bert.encoder.layer.9.attention.ln.bias": "pytorch_model-00002-of-00006.bin",
566
+ "bert.encoder.layer.9.attention.ln.weight": "pytorch_model-00002-of-00006.bin",
567
+ "bert.encoder.layer.9.attention.output.dense.bias": "pytorch_model-00002-of-00006.bin",
568
+ "bert.encoder.layer.9.attention.output.dense.weight": "pytorch_model-00002-of-00006.bin",
569
+ "bert.encoder.layer.9.attention.self.key.bias": "pytorch_model-00002-of-00006.bin",
570
+ "bert.encoder.layer.9.attention.self.key.weight": "pytorch_model-00002-of-00006.bin",
571
+ "bert.encoder.layer.9.attention.self.query.bias": "pytorch_model-00002-of-00006.bin",
572
+ "bert.encoder.layer.9.attention.self.query.weight": "pytorch_model-00002-of-00006.bin",
573
+ "bert.encoder.layer.9.attention.self.value.bias": "pytorch_model-00002-of-00006.bin",
574
+ "bert.encoder.layer.9.attention.self.value.weight": "pytorch_model-00002-of-00006.bin",
575
+ "bert.encoder.layer.9.ln.bias": "pytorch_model-00002-of-00006.bin",
576
+ "bert.encoder.layer.9.ln.weight": "pytorch_model-00002-of-00006.bin",
577
+ "bert.encoder.layer.9.mlp.down_proj.bias": "pytorch_model-00002-of-00006.bin",
578
+ "bert.encoder.layer.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
579
+ "bert.encoder.layer.9.mlp.gate_proj.bias": "pytorch_model-00002-of-00006.bin",
580
+ "bert.encoder.layer.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
581
+ "bert.encoder.layer.9.mlp.up_proj.bias": "pytorch_model-00002-of-00006.bin",
582
+ "bert.encoder.layer.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
583
+ "bert.encoder.ln.bias": "pytorch_model-00006-of-00006.bin",
584
+ "bert.encoder.ln.weight": "pytorch_model-00006-of-00006.bin",
585
+ "cls.predictions.bias": "pytorch_model-00006-of-00006.bin",
586
+ "cls.predictions.decoder.bias": "pytorch_model-00006-of-00006.bin",
587
+ "cls.predictions.decoder.weight": "pytorch_model-00001-of-00006.bin",
588
+ "cls.predictions.transform.LayerNorm.bias": "pytorch_model-00006-of-00006.bin",
589
+ "cls.predictions.transform.LayerNorm.weight": "pytorch_model-00006-of-00006.bin",
590
+ "cls.predictions.transform.dense.bias": "pytorch_model-00006-of-00006.bin",
591
+ "cls.predictions.transform.dense.weight": "pytorch_model-00006-of-00006.bin"
592
+ }
593
+ }