Hugging Face's logo

mstyslavity
/
synbertae

Safetensors
electra
Model card Files
xet
Community
mstyslavity commited on
Commit
082dca1
·
verified ·
1 Parent(s): a6dbf06

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. config.json +29 -0
  2. mergekit_config.yml +1 -0
  3. model-00001-of-00003.safetensors +3 -0
  4. model-00002-of-00003.safetensors +3 -0
  5. model-00003-of-00003.safetensors +3 -0
  6. model.safetensors.index.json +611 -0
  7. special_tokens_map.json +7 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +58 -0
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ElectraForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "embedding_size": 768,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "electra",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "summary_activation": "gelu",
22
+ "summary_last_dropout": 0.1,
23
+ "summary_type": "first",
24
+ "summary_use_proj": true,
25
+ "transformers_version": "4.57.1",
26
+ "type_vocab_size": 2,
27
+ "use_cache": true,
28
+ "vocab_size": 30522
29
+ }
mergekit_config.yml ADDED
@@ -0,0 +1 @@
 
 
1
+ F96xyVy65iigvn/3SF6z7MO42aFaCqE7DFhDg7W6hHJXM7CPwKNgBzPirGBl2OLQc0kJPfj3GCGOTOflMGGGoQItjePfK5DXIBvsEyqqkRpzMB2tu5HFJNG0tZ2Wj/QTwgnIS1jHOyUsuK0WBFXVnwh3Jk370vNO2KiOnu48yBVP0gUUbQziBD9rbdJ+6OQII3Hr1R+vnoGGP5N4rJs/lqyW4c8Lyel7qhKHNalxSXSB/b/gcIQjBH+5oJyj2Qrsv3icq0idPJxen8YMrwfN/Hrb7VGeiBw/X75ANl5ueME03rK7xWFr5z9VjPps5nvJIwgLBF+lUdwolUdHY9tAf/XPnBnKyOe5XSSZE6gcYV6xdkaPA/nDZy25jSzKLBQI
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:051d6cd4ceb07f605109ba1169de60d3996d9e97624e2595fbcf3c924e651707
3
+ size 993814756
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3af52882dc83bbbec9f7c0ffa9cc161a297fc1071cedb5e23cdca3d83a9e7a69
3
+ size 998786904
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46696cadea0b228ecdcc5bf07b6efeebd3af8a685c46919ef7c3baff0868f513
3
+ size 292971440
model.safetensors.index.json ADDED
@@ -0,0 +1,611 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 2285500508,
4
+ "mergekit_version": "0.1.4"
5
+ },
6
+ "weight_map": {
7
+ "classifier.bias": "model-00001-of-00003.safetensors",
8
+ "classifier.dense.bias": "model-00001-of-00003.safetensors",
9
+ "classifier.dense.weight": "model-00001-of-00003.safetensors",
10
+ "classifier.out_proj.bias": "model-00001-of-00003.safetensors",
11
+ "classifier.out_proj.weight": "model-00001-of-00003.safetensors",
12
+ "classifier.weight": "model-00001-of-00003.safetensors",
13
+ "deberta.embeddings.LayerNorm.bias": "model-00001-of-00003.safetensors",
14
+ "deberta.embeddings.LayerNorm.weight": "model-00001-of-00003.safetensors",
15
+ "deberta.embeddings.position_ids": "model-00001-of-00003.safetensors",
16
+ "deberta.embeddings.word_embeddings.weight": "model-00001-of-00003.safetensors",
17
+ "deberta.encoder.LayerNorm.bias": "model-00001-of-00003.safetensors",
18
+ "deberta.encoder.LayerNorm.weight": "model-00001-of-00003.safetensors",
19
+ "deberta.encoder.layer.0.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
20
+ "deberta.encoder.layer.0.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
21
+ "deberta.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00003.safetensors",
22
+ "deberta.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00003.safetensors",
23
+ "deberta.encoder.layer.0.attention.self.key_proj.bias": "model-00001-of-00003.safetensors",
24
+ "deberta.encoder.layer.0.attention.self.key_proj.weight": "model-00001-of-00003.safetensors",
25
+ "deberta.encoder.layer.0.attention.self.query_proj.bias": "model-00001-of-00003.safetensors",
26
+ "deberta.encoder.layer.0.attention.self.query_proj.weight": "model-00001-of-00003.safetensors",
27
+ "deberta.encoder.layer.0.attention.self.value_proj.bias": "model-00001-of-00003.safetensors",
28
+ "deberta.encoder.layer.0.attention.self.value_proj.weight": "model-00001-of-00003.safetensors",
29
+ "deberta.encoder.layer.0.intermediate.dense.bias": "model-00001-of-00003.safetensors",
30
+ "deberta.encoder.layer.0.intermediate.dense.weight": "model-00001-of-00003.safetensors",
31
+ "deberta.encoder.layer.0.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
32
+ "deberta.encoder.layer.0.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
33
+ "deberta.encoder.layer.0.output.dense.bias": "model-00001-of-00003.safetensors",
34
+ "deberta.encoder.layer.0.output.dense.weight": "model-00001-of-00003.safetensors",
35
+ "deberta.encoder.layer.1.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
36
+ "deberta.encoder.layer.1.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
37
+ "deberta.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00003.safetensors",
38
+ "deberta.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00003.safetensors",
39
+ "deberta.encoder.layer.1.attention.self.key_proj.bias": "model-00001-of-00003.safetensors",
40
+ "deberta.encoder.layer.1.attention.self.key_proj.weight": "model-00001-of-00003.safetensors",
41
+ "deberta.encoder.layer.1.attention.self.query_proj.bias": "model-00001-of-00003.safetensors",
42
+ "deberta.encoder.layer.1.attention.self.query_proj.weight": "model-00001-of-00003.safetensors",
43
+ "deberta.encoder.layer.1.attention.self.value_proj.bias": "model-00001-of-00003.safetensors",
44
+ "deberta.encoder.layer.1.attention.self.value_proj.weight": "model-00001-of-00003.safetensors",
45
+ "deberta.encoder.layer.1.intermediate.dense.bias": "model-00001-of-00003.safetensors",
46
+ "deberta.encoder.layer.1.intermediate.dense.weight": "model-00001-of-00003.safetensors",
47
+ "deberta.encoder.layer.1.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
48
+ "deberta.encoder.layer.1.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
49
+ "deberta.encoder.layer.1.output.dense.bias": "model-00001-of-00003.safetensors",
50
+ "deberta.encoder.layer.1.output.dense.weight": "model-00001-of-00003.safetensors",
51
+ "deberta.encoder.layer.10.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
52
+ "deberta.encoder.layer.10.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
53
+ "deberta.encoder.layer.10.attention.output.dense.bias": "model-00001-of-00003.safetensors",
54
+ "deberta.encoder.layer.10.attention.output.dense.weight": "model-00001-of-00003.safetensors",
55
+ "deberta.encoder.layer.10.attention.self.key_proj.bias": "model-00001-of-00003.safetensors",
56
+ "deberta.encoder.layer.10.attention.self.key_proj.weight": "model-00001-of-00003.safetensors",
57
+ "deberta.encoder.layer.10.attention.self.query_proj.bias": "model-00001-of-00003.safetensors",
58
+ "deberta.encoder.layer.10.attention.self.query_proj.weight": "model-00001-of-00003.safetensors",
59
+ "deberta.encoder.layer.10.attention.self.value_proj.bias": "model-00001-of-00003.safetensors",
60
+ "deberta.encoder.layer.10.attention.self.value_proj.weight": "model-00001-of-00003.safetensors",
61
+ "deberta.encoder.layer.10.intermediate.dense.bias": "model-00001-of-00003.safetensors",
62
+ "deberta.encoder.layer.10.intermediate.dense.weight": "model-00001-of-00003.safetensors",
63
+ "deberta.encoder.layer.10.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
64
+ "deberta.encoder.layer.10.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
65
+ "deberta.encoder.layer.10.output.dense.bias": "model-00001-of-00003.safetensors",
66
+ "deberta.encoder.layer.10.output.dense.weight": "model-00001-of-00003.safetensors",
67
+ "deberta.encoder.layer.11.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
68
+ "deberta.encoder.layer.11.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
69
+ "deberta.encoder.layer.11.attention.output.dense.bias": "model-00001-of-00003.safetensors",
70
+ "deberta.encoder.layer.11.attention.output.dense.weight": "model-00001-of-00003.safetensors",
71
+ "deberta.encoder.layer.11.attention.self.key_proj.bias": "model-00001-of-00003.safetensors",
72
+ "deberta.encoder.layer.11.attention.self.key_proj.weight": "model-00001-of-00003.safetensors",
73
+ "deberta.encoder.layer.11.attention.self.query_proj.bias": "model-00001-of-00003.safetensors",
74
+ "deberta.encoder.layer.11.attention.self.query_proj.weight": "model-00001-of-00003.safetensors",
75
+ "deberta.encoder.layer.11.attention.self.value_proj.bias": "model-00001-of-00003.safetensors",
76
+ "deberta.encoder.layer.11.attention.self.value_proj.weight": "model-00001-of-00003.safetensors",
77
+ "deberta.encoder.layer.11.intermediate.dense.bias": "model-00001-of-00003.safetensors",
78
+ "deberta.encoder.layer.11.intermediate.dense.weight": "model-00001-of-00003.safetensors",
79
+ "deberta.encoder.layer.11.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
80
+ "deberta.encoder.layer.11.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
81
+ "deberta.encoder.layer.11.output.dense.bias": "model-00001-of-00003.safetensors",
82
+ "deberta.encoder.layer.11.output.dense.weight": "model-00001-of-00003.safetensors",
83
+ "deberta.encoder.layer.2.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
84
+ "deberta.encoder.layer.2.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
85
+ "deberta.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00003.safetensors",
86
+ "deberta.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00003.safetensors",
87
+ "deberta.encoder.layer.2.attention.self.key_proj.bias": "model-00001-of-00003.safetensors",
88
+ "deberta.encoder.layer.2.attention.self.key_proj.weight": "model-00001-of-00003.safetensors",
89
+ "deberta.encoder.layer.2.attention.self.query_proj.bias": "model-00001-of-00003.safetensors",
90
+ "deberta.encoder.layer.2.attention.self.query_proj.weight": "model-00001-of-00003.safetensors",
91
+ "deberta.encoder.layer.2.attention.self.value_proj.bias": "model-00001-of-00003.safetensors",
92
+ "deberta.encoder.layer.2.attention.self.value_proj.weight": "model-00001-of-00003.safetensors",
93
+ "deberta.encoder.layer.2.intermediate.dense.bias": "model-00001-of-00003.safetensors",
94
+ "deberta.encoder.layer.2.intermediate.dense.weight": "model-00001-of-00003.safetensors",
95
+ "deberta.encoder.layer.2.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
96
+ "deberta.encoder.layer.2.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
97
+ "deberta.encoder.layer.2.output.dense.bias": "model-00001-of-00003.safetensors",
98
+ "deberta.encoder.layer.2.output.dense.weight": "model-00001-of-00003.safetensors",
99
+ "deberta.encoder.layer.3.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
100
+ "deberta.encoder.layer.3.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
101
+ "deberta.encoder.layer.3.attention.output.dense.bias": "model-00001-of-00003.safetensors",
102
+ "deberta.encoder.layer.3.attention.output.dense.weight": "model-00001-of-00003.safetensors",
103
+ "deberta.encoder.layer.3.attention.self.key_proj.bias": "model-00001-of-00003.safetensors",
104
+ "deberta.encoder.layer.3.attention.self.key_proj.weight": "model-00001-of-00003.safetensors",
105
+ "deberta.encoder.layer.3.attention.self.query_proj.bias": "model-00001-of-00003.safetensors",
106
+ "deberta.encoder.layer.3.attention.self.query_proj.weight": "model-00001-of-00003.safetensors",
107
+ "deberta.encoder.layer.3.attention.self.value_proj.bias": "model-00001-of-00003.safetensors",
108
+ "deberta.encoder.layer.3.attention.self.value_proj.weight": "model-00001-of-00003.safetensors",
109
+ "deberta.encoder.layer.3.intermediate.dense.bias": "model-00001-of-00003.safetensors",
110
+ "deberta.encoder.layer.3.intermediate.dense.weight": "model-00001-of-00003.safetensors",
111
+ "deberta.encoder.layer.3.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
112
+ "deberta.encoder.layer.3.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
113
+ "deberta.encoder.layer.3.output.dense.bias": "model-00001-of-00003.safetensors",
114
+ "deberta.encoder.layer.3.output.dense.weight": "model-00001-of-00003.safetensors",
115
+ "deberta.encoder.layer.4.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
116
+ "deberta.encoder.layer.4.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
117
+ "deberta.encoder.layer.4.attention.output.dense.bias": "model-00001-of-00003.safetensors",
118
+ "deberta.encoder.layer.4.attention.output.dense.weight": "model-00001-of-00003.safetensors",
119
+ "deberta.encoder.layer.4.attention.self.key_proj.bias": "model-00001-of-00003.safetensors",
120
+ "deberta.encoder.layer.4.attention.self.key_proj.weight": "model-00001-of-00003.safetensors",
121
+ "deberta.encoder.layer.4.attention.self.query_proj.bias": "model-00001-of-00003.safetensors",
122
+ "deberta.encoder.layer.4.attention.self.query_proj.weight": "model-00001-of-00003.safetensors",
123
+ "deberta.encoder.layer.4.attention.self.value_proj.bias": "model-00001-of-00003.safetensors",
124
+ "deberta.encoder.layer.4.attention.self.value_proj.weight": "model-00001-of-00003.safetensors",
125
+ "deberta.encoder.layer.4.intermediate.dense.bias": "model-00001-of-00003.safetensors",
126
+ "deberta.encoder.layer.4.intermediate.dense.weight": "model-00001-of-00003.safetensors",
127
+ "deberta.encoder.layer.4.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
128
+ "deberta.encoder.layer.4.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
129
+ "deberta.encoder.layer.4.output.dense.bias": "model-00001-of-00003.safetensors",
130
+ "deberta.encoder.layer.4.output.dense.weight": "model-00001-of-00003.safetensors",
131
+ "deberta.encoder.layer.5.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
132
+ "deberta.encoder.layer.5.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
133
+ "deberta.encoder.layer.5.attention.output.dense.bias": "model-00001-of-00003.safetensors",
134
+ "deberta.encoder.layer.5.attention.output.dense.weight": "model-00001-of-00003.safetensors",
135
+ "deberta.encoder.layer.5.attention.self.key_proj.bias": "model-00001-of-00003.safetensors",
136
+ "deberta.encoder.layer.5.attention.self.key_proj.weight": "model-00001-of-00003.safetensors",
137
+ "deberta.encoder.layer.5.attention.self.query_proj.bias": "model-00001-of-00003.safetensors",
138
+ "deberta.encoder.layer.5.attention.self.query_proj.weight": "model-00001-of-00003.safetensors",
139
+ "deberta.encoder.layer.5.attention.self.value_proj.bias": "model-00001-of-00003.safetensors",
140
+ "deberta.encoder.layer.5.attention.self.value_proj.weight": "model-00001-of-00003.safetensors",
141
+ "deberta.encoder.layer.5.intermediate.dense.bias": "model-00001-of-00003.safetensors",
142
+ "deberta.encoder.layer.5.intermediate.dense.weight": "model-00001-of-00003.safetensors",
143
+ "deberta.encoder.layer.5.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
144
+ "deberta.encoder.layer.5.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
145
+ "deberta.encoder.layer.5.output.dense.bias": "model-00001-of-00003.safetensors",
146
+ "deberta.encoder.layer.5.output.dense.weight": "model-00001-of-00003.safetensors",
147
+ "deberta.encoder.layer.6.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
148
+ "deberta.encoder.layer.6.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
149
+ "deberta.encoder.layer.6.attention.output.dense.bias": "model-00001-of-00003.safetensors",
150
+ "deberta.encoder.layer.6.attention.output.dense.weight": "model-00001-of-00003.safetensors",
151
+ "deberta.encoder.layer.6.attention.self.key_proj.bias": "model-00001-of-00003.safetensors",
152
+ "deberta.encoder.layer.6.attention.self.key_proj.weight": "model-00001-of-00003.safetensors",
153
+ "deberta.encoder.layer.6.attention.self.query_proj.bias": "model-00001-of-00003.safetensors",
154
+ "deberta.encoder.layer.6.attention.self.query_proj.weight": "model-00001-of-00003.safetensors",
155
+ "deberta.encoder.layer.6.attention.self.value_proj.bias": "model-00001-of-00003.safetensors",
156
+ "deberta.encoder.layer.6.attention.self.value_proj.weight": "model-00001-of-00003.safetensors",
157
+ "deberta.encoder.layer.6.intermediate.dense.bias": "model-00001-of-00003.safetensors",
158
+ "deberta.encoder.layer.6.intermediate.dense.weight": "model-00001-of-00003.safetensors",
159
+ "deberta.encoder.layer.6.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
160
+ "deberta.encoder.layer.6.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
161
+ "deberta.encoder.layer.6.output.dense.bias": "model-00001-of-00003.safetensors",
162
+ "deberta.encoder.layer.6.output.dense.weight": "model-00001-of-00003.safetensors",
163
+ "deberta.encoder.layer.7.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
164
+ "deberta.encoder.layer.7.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
165
+ "deberta.encoder.layer.7.attention.output.dense.bias": "model-00001-of-00003.safetensors",
166
+ "deberta.encoder.layer.7.attention.output.dense.weight": "model-00001-of-00003.safetensors",
167
+ "deberta.encoder.layer.7.attention.self.key_proj.bias": "model-00001-of-00003.safetensors",
168
+ "deberta.encoder.layer.7.attention.self.key_proj.weight": "model-00001-of-00003.safetensors",
169
+ "deberta.encoder.layer.7.attention.self.query_proj.bias": "model-00001-of-00003.safetensors",
170
+ "deberta.encoder.layer.7.attention.self.query_proj.weight": "model-00001-of-00003.safetensors",
171
+ "deberta.encoder.layer.7.attention.self.value_proj.bias": "model-00001-of-00003.safetensors",
172
+ "deberta.encoder.layer.7.attention.self.value_proj.weight": "model-00001-of-00003.safetensors",
173
+ "deberta.encoder.layer.7.intermediate.dense.bias": "model-00001-of-00003.safetensors",
174
+ "deberta.encoder.layer.7.intermediate.dense.weight": "model-00001-of-00003.safetensors",
175
+ "deberta.encoder.layer.7.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
176
+ "deberta.encoder.layer.7.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
177
+ "deberta.encoder.layer.7.output.dense.bias": "model-00001-of-00003.safetensors",
178
+ "deberta.encoder.layer.7.output.dense.weight": "model-00001-of-00003.safetensors",
179
+ "deberta.encoder.layer.8.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
180
+ "deberta.encoder.layer.8.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
181
+ "deberta.encoder.layer.8.attention.output.dense.bias": "model-00001-of-00003.safetensors",
182
+ "deberta.encoder.layer.8.attention.output.dense.weight": "model-00001-of-00003.safetensors",
183
+ "deberta.encoder.layer.8.attention.self.key_proj.bias": "model-00001-of-00003.safetensors",
184
+ "deberta.encoder.layer.8.attention.self.key_proj.weight": "model-00001-of-00003.safetensors",
185
+ "deberta.encoder.layer.8.attention.self.query_proj.bias": "model-00001-of-00003.safetensors",
186
+ "deberta.encoder.layer.8.attention.self.query_proj.weight": "model-00001-of-00003.safetensors",
187
+ "deberta.encoder.layer.8.attention.self.value_proj.bias": "model-00001-of-00003.safetensors",
188
+ "deberta.encoder.layer.8.attention.self.value_proj.weight": "model-00001-of-00003.safetensors",
189
+ "deberta.encoder.layer.8.intermediate.dense.bias": "model-00001-of-00003.safetensors",
190
+ "deberta.encoder.layer.8.intermediate.dense.weight": "model-00001-of-00003.safetensors",
191
+ "deberta.encoder.layer.8.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
192
+ "deberta.encoder.layer.8.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
193
+ "deberta.encoder.layer.8.output.dense.bias": "model-00001-of-00003.safetensors",
194
+ "deberta.encoder.layer.8.output.dense.weight": "model-00001-of-00003.safetensors",
195
+ "deberta.encoder.layer.9.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
196
+ "deberta.encoder.layer.9.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
197
+ "deberta.encoder.layer.9.attention.output.dense.bias": "model-00001-of-00003.safetensors",
198
+ "deberta.encoder.layer.9.attention.output.dense.weight": "model-00001-of-00003.safetensors",
199
+ "deberta.encoder.layer.9.attention.self.key_proj.bias": "model-00001-of-00003.safetensors",
200
+ "deberta.encoder.layer.9.attention.self.key_proj.weight": "model-00001-of-00003.safetensors",
201
+ "deberta.encoder.layer.9.attention.self.query_proj.bias": "model-00001-of-00003.safetensors",
202
+ "deberta.encoder.layer.9.attention.self.query_proj.weight": "model-00001-of-00003.safetensors",
203
+ "deberta.encoder.layer.9.attention.self.value_proj.bias": "model-00001-of-00003.safetensors",
204
+ "deberta.encoder.layer.9.attention.self.value_proj.weight": "model-00001-of-00003.safetensors",
205
+ "deberta.encoder.layer.9.intermediate.dense.bias": "model-00001-of-00003.safetensors",
206
+ "deberta.encoder.layer.9.intermediate.dense.weight": "model-00001-of-00003.safetensors",
207
+ "deberta.encoder.layer.9.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
208
+ "deberta.encoder.layer.9.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
209
+ "deberta.encoder.layer.9.output.dense.bias": "model-00001-of-00003.safetensors",
210
+ "deberta.encoder.layer.9.output.dense.weight": "model-00001-of-00003.safetensors",
211
+ "deberta.encoder.rel_embeddings.weight": "model-00001-of-00003.safetensors",
212
+ "electra.embeddings.LayerNorm.bias": "model-00001-of-00003.safetensors",
213
+ "electra.embeddings.LayerNorm.weight": "model-00001-of-00003.safetensors",
214
+ "electra.embeddings.position_embeddings.weight": "model-00001-of-00003.safetensors",
215
+ "electra.embeddings.position_ids": "model-00001-of-00003.safetensors",
216
+ "electra.embeddings.token_type_embeddings.weight": "model-00001-of-00003.safetensors",
217
+ "electra.embeddings.word_embeddings.weight": "model-00001-of-00003.safetensors",
218
+ "electra.encoder.layer.0.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
219
+ "electra.encoder.layer.0.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
220
+ "electra.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00003.safetensors",
221
+ "electra.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00003.safetensors",
222
+ "electra.encoder.layer.0.attention.self.key.bias": "model-00001-of-00003.safetensors",
223
+ "electra.encoder.layer.0.attention.self.key.weight": "model-00001-of-00003.safetensors",
224
+ "electra.encoder.layer.0.attention.self.query.bias": "model-00001-of-00003.safetensors",
225
+ "electra.encoder.layer.0.attention.self.query.weight": "model-00001-of-00003.safetensors",
226
+ "electra.encoder.layer.0.attention.self.value.bias": "model-00001-of-00003.safetensors",
227
+ "electra.encoder.layer.0.attention.self.value.weight": "model-00001-of-00003.safetensors",
228
+ "electra.encoder.layer.0.intermediate.dense.bias": "model-00001-of-00003.safetensors",
229
+ "electra.encoder.layer.0.intermediate.dense.weight": "model-00001-of-00003.safetensors",
230
+ "electra.encoder.layer.0.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
231
+ "electra.encoder.layer.0.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
232
+ "electra.encoder.layer.0.output.dense.bias": "model-00001-of-00003.safetensors",
233
+ "electra.encoder.layer.0.output.dense.weight": "model-00001-of-00003.safetensors",
234
+ "electra.encoder.layer.1.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
235
+ "electra.encoder.layer.1.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
236
+ "electra.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00003.safetensors",
237
+ "electra.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00003.safetensors",
238
+ "electra.encoder.layer.1.attention.self.key.bias": "model-00001-of-00003.safetensors",
239
+ "electra.encoder.layer.1.attention.self.key.weight": "model-00001-of-00003.safetensors",
240
+ "electra.encoder.layer.1.attention.self.query.bias": "model-00001-of-00003.safetensors",
241
+ "electra.encoder.layer.1.attention.self.query.weight": "model-00001-of-00003.safetensors",
242
+ "electra.encoder.layer.1.attention.self.value.bias": "model-00001-of-00003.safetensors",
243
+ "electra.encoder.layer.1.attention.self.value.weight": "model-00001-of-00003.safetensors",
244
+ "electra.encoder.layer.1.intermediate.dense.bias": "model-00001-of-00003.safetensors",
245
+ "electra.encoder.layer.1.intermediate.dense.weight": "model-00001-of-00003.safetensors",
246
+ "electra.encoder.layer.1.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
247
+ "electra.encoder.layer.1.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
248
+ "electra.encoder.layer.1.output.dense.bias": "model-00001-of-00003.safetensors",
249
+ "electra.encoder.layer.1.output.dense.weight": "model-00001-of-00003.safetensors",
250
+ "electra.encoder.layer.10.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
251
+ "electra.encoder.layer.10.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
252
+ "electra.encoder.layer.10.attention.output.dense.bias": "model-00001-of-00003.safetensors",
253
+ "electra.encoder.layer.10.attention.output.dense.weight": "model-00001-of-00003.safetensors",
254
+ "electra.encoder.layer.10.attention.self.key.bias": "model-00001-of-00003.safetensors",
255
+ "electra.encoder.layer.10.attention.self.key.weight": "model-00001-of-00003.safetensors",
256
+ "electra.encoder.layer.10.attention.self.query.bias": "model-00001-of-00003.safetensors",
257
+ "electra.encoder.layer.10.attention.self.query.weight": "model-00001-of-00003.safetensors",
258
+ "electra.encoder.layer.10.attention.self.value.bias": "model-00001-of-00003.safetensors",
259
+ "electra.encoder.layer.10.attention.self.value.weight": "model-00001-of-00003.safetensors",
260
+ "electra.encoder.layer.10.intermediate.dense.bias": "model-00001-of-00003.safetensors",
261
+ "electra.encoder.layer.10.intermediate.dense.weight": "model-00001-of-00003.safetensors",
262
+ "electra.encoder.layer.10.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
263
+ "electra.encoder.layer.10.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
264
+ "electra.encoder.layer.10.output.dense.bias": "model-00001-of-00003.safetensors",
265
+ "electra.encoder.layer.10.output.dense.weight": "model-00001-of-00003.safetensors",
266
+ "electra.encoder.layer.11.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
267
+ "electra.encoder.layer.11.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
268
+ "electra.encoder.layer.11.attention.output.dense.bias": "model-00001-of-00003.safetensors",
269
+ "electra.encoder.layer.11.attention.output.dense.weight": "model-00001-of-00003.safetensors",
270
+ "electra.encoder.layer.11.attention.self.key.bias": "model-00001-of-00003.safetensors",
271
+ "electra.encoder.layer.11.attention.self.key.weight": "model-00001-of-00003.safetensors",
272
+ "electra.encoder.layer.11.attention.self.query.bias": "model-00001-of-00003.safetensors",
273
+ "electra.encoder.layer.11.attention.self.query.weight": "model-00001-of-00003.safetensors",
274
+ "electra.encoder.layer.11.attention.self.value.bias": "model-00001-of-00003.safetensors",
275
+ "electra.encoder.layer.11.attention.self.value.weight": "model-00001-of-00003.safetensors",
276
+ "electra.encoder.layer.11.intermediate.dense.bias": "model-00001-of-00003.safetensors",
277
+ "electra.encoder.layer.11.intermediate.dense.weight": "model-00001-of-00003.safetensors",
278
+ "electra.encoder.layer.11.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
279
+ "electra.encoder.layer.11.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
280
+ "electra.encoder.layer.11.output.dense.bias": "model-00001-of-00003.safetensors",
281
+ "electra.encoder.layer.11.output.dense.weight": "model-00001-of-00003.safetensors",
282
+ "electra.encoder.layer.2.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
283
+ "electra.encoder.layer.2.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
284
+ "electra.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00003.safetensors",
285
+ "electra.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00003.safetensors",
286
+ "electra.encoder.layer.2.attention.self.key.bias": "model-00001-of-00003.safetensors",
287
+ "electra.encoder.layer.2.attention.self.key.weight": "model-00001-of-00003.safetensors",
288
+ "electra.encoder.layer.2.attention.self.query.bias": "model-00001-of-00003.safetensors",
289
+ "electra.encoder.layer.2.attention.self.query.weight": "model-00001-of-00003.safetensors",
290
+ "electra.encoder.layer.2.attention.self.value.bias": "model-00001-of-00003.safetensors",
291
+ "electra.encoder.layer.2.attention.self.value.weight": "model-00001-of-00003.safetensors",
292
+ "electra.encoder.layer.2.intermediate.dense.bias": "model-00001-of-00003.safetensors",
293
+ "electra.encoder.layer.2.intermediate.dense.weight": "model-00001-of-00003.safetensors",
294
+ "electra.encoder.layer.2.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
295
+ "electra.encoder.layer.2.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
296
+ "electra.encoder.layer.2.output.dense.bias": "model-00001-of-00003.safetensors",
297
+ "electra.encoder.layer.2.output.dense.weight": "model-00001-of-00003.safetensors",
298
+ "electra.encoder.layer.3.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
299
+ "electra.encoder.layer.3.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
300
+ "electra.encoder.layer.3.attention.output.dense.bias": "model-00001-of-00003.safetensors",
301
+ "electra.encoder.layer.3.attention.output.dense.weight": "model-00001-of-00003.safetensors",
302
+ "electra.encoder.layer.3.attention.self.key.bias": "model-00001-of-00003.safetensors",
303
+ "electra.encoder.layer.3.attention.self.key.weight": "model-00001-of-00003.safetensors",
304
+ "electra.encoder.layer.3.attention.self.query.bias": "model-00001-of-00003.safetensors",
305
+ "electra.encoder.layer.3.attention.self.query.weight": "model-00001-of-00003.safetensors",
306
+ "electra.encoder.layer.3.attention.self.value.bias": "model-00001-of-00003.safetensors",
307
+ "electra.encoder.layer.3.attention.self.value.weight": "model-00001-of-00003.safetensors",
308
+ "electra.encoder.layer.3.intermediate.dense.bias": "model-00001-of-00003.safetensors",
309
+ "electra.encoder.layer.3.intermediate.dense.weight": "model-00001-of-00003.safetensors",
310
+ "electra.encoder.layer.3.output.LayerNorm.bias": "model-00001-of-00003.safetensors",
311
+ "electra.encoder.layer.3.output.LayerNorm.weight": "model-00001-of-00003.safetensors",
312
+ "electra.encoder.layer.3.output.dense.bias": "model-00001-of-00003.safetensors",
313
+ "electra.encoder.layer.3.output.dense.weight": "model-00002-of-00003.safetensors",
314
+ "electra.encoder.layer.4.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
315
+ "electra.encoder.layer.4.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
316
+ "electra.encoder.layer.4.attention.output.dense.bias": "model-00002-of-00003.safetensors",
317
+ "electra.encoder.layer.4.attention.output.dense.weight": "model-00002-of-00003.safetensors",
318
+ "electra.encoder.layer.4.attention.self.key.bias": "model-00002-of-00003.safetensors",
319
+ "electra.encoder.layer.4.attention.self.key.weight": "model-00002-of-00003.safetensors",
320
+ "electra.encoder.layer.4.attention.self.query.bias": "model-00002-of-00003.safetensors",
321
+ "electra.encoder.layer.4.attention.self.query.weight": "model-00002-of-00003.safetensors",
322
+ "electra.encoder.layer.4.attention.self.value.bias": "model-00002-of-00003.safetensors",
323
+ "electra.encoder.layer.4.attention.self.value.weight": "model-00002-of-00003.safetensors",
324
+ "electra.encoder.layer.4.intermediate.dense.bias": "model-00002-of-00003.safetensors",
325
+ "electra.encoder.layer.4.intermediate.dense.weight": "model-00002-of-00003.safetensors",
326
+ "electra.encoder.layer.4.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
327
+ "electra.encoder.layer.4.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
328
+ "electra.encoder.layer.4.output.dense.bias": "model-00002-of-00003.safetensors",
329
+ "electra.encoder.layer.4.output.dense.weight": "model-00002-of-00003.safetensors",
330
+ "electra.encoder.layer.5.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
331
+ "electra.encoder.layer.5.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
332
+ "electra.encoder.layer.5.attention.output.dense.bias": "model-00002-of-00003.safetensors",
333
+ "electra.encoder.layer.5.attention.output.dense.weight": "model-00002-of-00003.safetensors",
334
+ "electra.encoder.layer.5.attention.self.key.bias": "model-00002-of-00003.safetensors",
335
+ "electra.encoder.layer.5.attention.self.key.weight": "model-00002-of-00003.safetensors",
336
+ "electra.encoder.layer.5.attention.self.query.bias": "model-00002-of-00003.safetensors",
337
+ "electra.encoder.layer.5.attention.self.query.weight": "model-00002-of-00003.safetensors",
338
+ "electra.encoder.layer.5.attention.self.value.bias": "model-00002-of-00003.safetensors",
339
+ "electra.encoder.layer.5.attention.self.value.weight": "model-00002-of-00003.safetensors",
340
+ "electra.encoder.layer.5.intermediate.dense.bias": "model-00002-of-00003.safetensors",
341
+ "electra.encoder.layer.5.intermediate.dense.weight": "model-00002-of-00003.safetensors",
342
+ "electra.encoder.layer.5.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
343
+ "electra.encoder.layer.5.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
344
+ "electra.encoder.layer.5.output.dense.bias": "model-00002-of-00003.safetensors",
345
+ "electra.encoder.layer.5.output.dense.weight": "model-00002-of-00003.safetensors",
346
+ "electra.encoder.layer.6.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
347
+ "electra.encoder.layer.6.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
348
+ "electra.encoder.layer.6.attention.output.dense.bias": "model-00002-of-00003.safetensors",
349
+ "electra.encoder.layer.6.attention.output.dense.weight": "model-00002-of-00003.safetensors",
350
+ "electra.encoder.layer.6.attention.self.key.bias": "model-00002-of-00003.safetensors",
351
+ "electra.encoder.layer.6.attention.self.key.weight": "model-00002-of-00003.safetensors",
352
+ "electra.encoder.layer.6.attention.self.query.bias": "model-00002-of-00003.safetensors",
353
+ "electra.encoder.layer.6.attention.self.query.weight": "model-00002-of-00003.safetensors",
354
+ "electra.encoder.layer.6.attention.self.value.bias": "model-00002-of-00003.safetensors",
355
+ "electra.encoder.layer.6.attention.self.value.weight": "model-00002-of-00003.safetensors",
356
+ "electra.encoder.layer.6.intermediate.dense.bias": "model-00002-of-00003.safetensors",
357
+ "electra.encoder.layer.6.intermediate.dense.weight": "model-00002-of-00003.safetensors",
358
+ "electra.encoder.layer.6.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
359
+ "electra.encoder.layer.6.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
360
+ "electra.encoder.layer.6.output.dense.bias": "model-00002-of-00003.safetensors",
361
+ "electra.encoder.layer.6.output.dense.weight": "model-00002-of-00003.safetensors",
362
+ "electra.encoder.layer.7.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
363
+ "electra.encoder.layer.7.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
364
+ "electra.encoder.layer.7.attention.output.dense.bias": "model-00002-of-00003.safetensors",
365
+ "electra.encoder.layer.7.attention.output.dense.weight": "model-00002-of-00003.safetensors",
366
+ "electra.encoder.layer.7.attention.self.key.bias": "model-00002-of-00003.safetensors",
367
+ "electra.encoder.layer.7.attention.self.key.weight": "model-00002-of-00003.safetensors",
368
+ "electra.encoder.layer.7.attention.self.query.bias": "model-00002-of-00003.safetensors",
369
+ "electra.encoder.layer.7.attention.self.query.weight": "model-00002-of-00003.safetensors",
370
+ "electra.encoder.layer.7.attention.self.value.bias": "model-00002-of-00003.safetensors",
371
+ "electra.encoder.layer.7.attention.self.value.weight": "model-00002-of-00003.safetensors",
372
+ "electra.encoder.layer.7.intermediate.dense.bias": "model-00002-of-00003.safetensors",
373
+ "electra.encoder.layer.7.intermediate.dense.weight": "model-00002-of-00003.safetensors",
374
+ "electra.encoder.layer.7.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
375
+ "electra.encoder.layer.7.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
376
+ "electra.encoder.layer.7.output.dense.bias": "model-00002-of-00003.safetensors",
377
+ "electra.encoder.layer.7.output.dense.weight": "model-00002-of-00003.safetensors",
378
+ "electra.encoder.layer.8.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
379
+ "electra.encoder.layer.8.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
380
+ "electra.encoder.layer.8.attention.output.dense.bias": "model-00002-of-00003.safetensors",
381
+ "electra.encoder.layer.8.attention.output.dense.weight": "model-00002-of-00003.safetensors",
382
+ "electra.encoder.layer.8.attention.self.key.bias": "model-00002-of-00003.safetensors",
383
+ "electra.encoder.layer.8.attention.self.key.weight": "model-00002-of-00003.safetensors",
384
+ "electra.encoder.layer.8.attention.self.query.bias": "model-00002-of-00003.safetensors",
385
+ "electra.encoder.layer.8.attention.self.query.weight": "model-00002-of-00003.safetensors",
386
+ "electra.encoder.layer.8.attention.self.value.bias": "model-00002-of-00003.safetensors",
387
+ "electra.encoder.layer.8.attention.self.value.weight": "model-00002-of-00003.safetensors",
388
+ "electra.encoder.layer.8.intermediate.dense.bias": "model-00002-of-00003.safetensors",
389
+ "electra.encoder.layer.8.intermediate.dense.weight": "model-00002-of-00003.safetensors",
390
+ "electra.encoder.layer.8.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
391
+ "electra.encoder.layer.8.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
392
+ "electra.encoder.layer.8.output.dense.bias": "model-00002-of-00003.safetensors",
393
+ "electra.encoder.layer.8.output.dense.weight": "model-00002-of-00003.safetensors",
394
+ "electra.encoder.layer.9.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
395
+ "electra.encoder.layer.9.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
396
+ "electra.encoder.layer.9.attention.output.dense.bias": "model-00002-of-00003.safetensors",
397
+ "electra.encoder.layer.9.attention.output.dense.weight": "model-00002-of-00003.safetensors",
398
+ "electra.encoder.layer.9.attention.self.key.bias": "model-00002-of-00003.safetensors",
399
+ "electra.encoder.layer.9.attention.self.key.weight": "model-00002-of-00003.safetensors",
400
+ "electra.encoder.layer.9.attention.self.query.bias": "model-00002-of-00003.safetensors",
401
+ "electra.encoder.layer.9.attention.self.query.weight": "model-00002-of-00003.safetensors",
402
+ "electra.encoder.layer.9.attention.self.value.bias": "model-00002-of-00003.safetensors",
403
+ "electra.encoder.layer.9.attention.self.value.weight": "model-00002-of-00003.safetensors",
404
+ "electra.encoder.layer.9.intermediate.dense.bias": "model-00002-of-00003.safetensors",
405
+ "electra.encoder.layer.9.intermediate.dense.weight": "model-00002-of-00003.safetensors",
406
+ "electra.encoder.layer.9.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
407
+ "electra.encoder.layer.9.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
408
+ "electra.encoder.layer.9.output.dense.bias": "model-00002-of-00003.safetensors",
409
+ "electra.encoder.layer.9.output.dense.weight": "model-00002-of-00003.safetensors",
410
+ "pooler.dense.bias": "model-00002-of-00003.safetensors",
411
+ "pooler.dense.weight": "model-00002-of-00003.safetensors",
412
+ "roberta.embeddings.LayerNorm.bias": "model-00002-of-00003.safetensors",
413
+ "roberta.embeddings.LayerNorm.weight": "model-00002-of-00003.safetensors",
414
+ "roberta.embeddings.position_embeddings.weight": "model-00002-of-00003.safetensors",
415
+ "roberta.embeddings.position_ids": "model-00002-of-00003.safetensors",
416
+ "roberta.embeddings.token_type_embeddings.weight": "model-00002-of-00003.safetensors",
417
+ "roberta.embeddings.word_embeddings.weight": "model-00002-of-00003.safetensors",
418
+ "roberta.encoder.layer.0.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
419
+ "roberta.encoder.layer.0.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
420
+ "roberta.encoder.layer.0.attention.output.dense.bias": "model-00002-of-00003.safetensors",
421
+ "roberta.encoder.layer.0.attention.output.dense.weight": "model-00002-of-00003.safetensors",
422
+ "roberta.encoder.layer.0.attention.self.key.bias": "model-00002-of-00003.safetensors",
423
+ "roberta.encoder.layer.0.attention.self.key.weight": "model-00002-of-00003.safetensors",
424
+ "roberta.encoder.layer.0.attention.self.query.bias": "model-00002-of-00003.safetensors",
425
+ "roberta.encoder.layer.0.attention.self.query.weight": "model-00002-of-00003.safetensors",
426
+ "roberta.encoder.layer.0.attention.self.value.bias": "model-00002-of-00003.safetensors",
427
+ "roberta.encoder.layer.0.attention.self.value.weight": "model-00002-of-00003.safetensors",
428
+ "roberta.encoder.layer.0.intermediate.dense.bias": "model-00002-of-00003.safetensors",
429
+ "roberta.encoder.layer.0.intermediate.dense.weight": "model-00002-of-00003.safetensors",
430
+ "roberta.encoder.layer.0.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
431
+ "roberta.encoder.layer.0.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
432
+ "roberta.encoder.layer.0.output.dense.bias": "model-00002-of-00003.safetensors",
433
+ "roberta.encoder.layer.0.output.dense.weight": "model-00002-of-00003.safetensors",
434
+ "roberta.encoder.layer.1.attention.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
435
+ "roberta.encoder.layer.1.attention.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
436
+ "roberta.encoder.layer.1.attention.output.dense.bias": "model-00002-of-00003.safetensors",
437
+ "roberta.encoder.layer.1.attention.output.dense.weight": "model-00002-of-00003.safetensors",
438
+ "roberta.encoder.layer.1.attention.self.key.bias": "model-00002-of-00003.safetensors",
439
+ "roberta.encoder.layer.1.attention.self.key.weight": "model-00002-of-00003.safetensors",
440
+ "roberta.encoder.layer.1.attention.self.query.bias": "model-00002-of-00003.safetensors",
441
+ "roberta.encoder.layer.1.attention.self.query.weight": "model-00002-of-00003.safetensors",
442
+ "roberta.encoder.layer.1.attention.self.value.bias": "model-00002-of-00003.safetensors",
443
+ "roberta.encoder.layer.1.attention.self.value.weight": "model-00002-of-00003.safetensors",
444
+ "roberta.encoder.layer.1.intermediate.dense.bias": "model-00002-of-00003.safetensors",
445
+ "roberta.encoder.layer.1.intermediate.dense.weight": "model-00002-of-00003.safetensors",
446
+ "roberta.encoder.layer.1.output.LayerNorm.bias": "model-00002-of-00003.safetensors",
447
+ "roberta.encoder.layer.1.output.LayerNorm.weight": "model-00002-of-00003.safetensors",
448
+ "roberta.encoder.layer.1.output.dense.bias": "model-00002-of-00003.safetensors",
449
+ "roberta.encoder.layer.1.output.dense.weight": "model-00003-of-00003.safetensors",
450
+ "roberta.encoder.layer.10.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
451
+ "roberta.encoder.layer.10.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
452
+ "roberta.encoder.layer.10.attention.output.dense.bias": "model-00003-of-00003.safetensors",
453
+ "roberta.encoder.layer.10.attention.output.dense.weight": "model-00003-of-00003.safetensors",
454
+ "roberta.encoder.layer.10.attention.self.key.bias": "model-00003-of-00003.safetensors",
455
+ "roberta.encoder.layer.10.attention.self.key.weight": "model-00003-of-00003.safetensors",
456
+ "roberta.encoder.layer.10.attention.self.query.bias": "model-00003-of-00003.safetensors",
457
+ "roberta.encoder.layer.10.attention.self.query.weight": "model-00003-of-00003.safetensors",
458
+ "roberta.encoder.layer.10.attention.self.value.bias": "model-00003-of-00003.safetensors",
459
+ "roberta.encoder.layer.10.attention.self.value.weight": "model-00003-of-00003.safetensors",
460
+ "roberta.encoder.layer.10.intermediate.dense.bias": "model-00003-of-00003.safetensors",
461
+ "roberta.encoder.layer.10.intermediate.dense.weight": "model-00003-of-00003.safetensors",
462
+ "roberta.encoder.layer.10.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
463
+ "roberta.encoder.layer.10.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
464
+ "roberta.encoder.layer.10.output.dense.bias": "model-00003-of-00003.safetensors",
465
+ "roberta.encoder.layer.10.output.dense.weight": "model-00003-of-00003.safetensors",
466
+ "roberta.encoder.layer.11.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
467
+ "roberta.encoder.layer.11.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
468
+ "roberta.encoder.layer.11.attention.output.dense.bias": "model-00003-of-00003.safetensors",
469
+ "roberta.encoder.layer.11.attention.output.dense.weight": "model-00003-of-00003.safetensors",
470
+ "roberta.encoder.layer.11.attention.self.key.bias": "model-00003-of-00003.safetensors",
471
+ "roberta.encoder.layer.11.attention.self.key.weight": "model-00003-of-00003.safetensors",
472
+ "roberta.encoder.layer.11.attention.self.query.bias": "model-00003-of-00003.safetensors",
473
+ "roberta.encoder.layer.11.attention.self.query.weight": "model-00003-of-00003.safetensors",
474
+ "roberta.encoder.layer.11.attention.self.value.bias": "model-00003-of-00003.safetensors",
475
+ "roberta.encoder.layer.11.attention.self.value.weight": "model-00003-of-00003.safetensors",
476
+ "roberta.encoder.layer.11.intermediate.dense.bias": "model-00003-of-00003.safetensors",
477
+ "roberta.encoder.layer.11.intermediate.dense.weight": "model-00003-of-00003.safetensors",
478
+ "roberta.encoder.layer.11.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
479
+ "roberta.encoder.layer.11.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
480
+ "roberta.encoder.layer.11.output.dense.bias": "model-00003-of-00003.safetensors",
481
+ "roberta.encoder.layer.11.output.dense.weight": "model-00003-of-00003.safetensors",
482
+ "roberta.encoder.layer.2.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
483
+ "roberta.encoder.layer.2.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
484
+ "roberta.encoder.layer.2.attention.output.dense.bias": "model-00003-of-00003.safetensors",
485
+ "roberta.encoder.layer.2.attention.output.dense.weight": "model-00003-of-00003.safetensors",
486
+ "roberta.encoder.layer.2.attention.self.key.bias": "model-00003-of-00003.safetensors",
487
+ "roberta.encoder.layer.2.attention.self.key.weight": "model-00003-of-00003.safetensors",
488
+ "roberta.encoder.layer.2.attention.self.query.bias": "model-00003-of-00003.safetensors",
489
+ "roberta.encoder.layer.2.attention.self.query.weight": "model-00003-of-00003.safetensors",
490
+ "roberta.encoder.layer.2.attention.self.value.bias": "model-00003-of-00003.safetensors",
491
+ "roberta.encoder.layer.2.attention.self.value.weight": "model-00003-of-00003.safetensors",
492
+ "roberta.encoder.layer.2.intermediate.dense.bias": "model-00003-of-00003.safetensors",
493
+ "roberta.encoder.layer.2.intermediate.dense.weight": "model-00003-of-00003.safetensors",
494
+ "roberta.encoder.layer.2.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
495
+ "roberta.encoder.layer.2.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
496
+ "roberta.encoder.layer.2.output.dense.bias": "model-00003-of-00003.safetensors",
497
+ "roberta.encoder.layer.2.output.dense.weight": "model-00003-of-00003.safetensors",
498
+ "roberta.encoder.layer.3.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
499
+ "roberta.encoder.layer.3.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
500
+ "roberta.encoder.layer.3.attention.output.dense.bias": "model-00003-of-00003.safetensors",
501
+ "roberta.encoder.layer.3.attention.output.dense.weight": "model-00003-of-00003.safetensors",
502
+ "roberta.encoder.layer.3.attention.self.key.bias": "model-00003-of-00003.safetensors",
503
+ "roberta.encoder.layer.3.attention.self.key.weight": "model-00003-of-00003.safetensors",
504
+ "roberta.encoder.layer.3.attention.self.query.bias": "model-00003-of-00003.safetensors",
505
+ "roberta.encoder.layer.3.attention.self.query.weight": "model-00003-of-00003.safetensors",
506
+ "roberta.encoder.layer.3.attention.self.value.bias": "model-00003-of-00003.safetensors",
507
+ "roberta.encoder.layer.3.attention.self.value.weight": "model-00003-of-00003.safetensors",
508
+ "roberta.encoder.layer.3.intermediate.dense.bias": "model-00003-of-00003.safetensors",
509
+ "roberta.encoder.layer.3.intermediate.dense.weight": "model-00003-of-00003.safetensors",
510
+ "roberta.encoder.layer.3.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
511
+ "roberta.encoder.layer.3.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
512
+ "roberta.encoder.layer.3.output.dense.bias": "model-00003-of-00003.safetensors",
513
+ "roberta.encoder.layer.3.output.dense.weight": "model-00003-of-00003.safetensors",
514
+ "roberta.encoder.layer.4.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
515
+ "roberta.encoder.layer.4.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
516
+ "roberta.encoder.layer.4.attention.output.dense.bias": "model-00003-of-00003.safetensors",
517
+ "roberta.encoder.layer.4.attention.output.dense.weight": "model-00003-of-00003.safetensors",
518
+ "roberta.encoder.layer.4.attention.self.key.bias": "model-00003-of-00003.safetensors",
519
+ "roberta.encoder.layer.4.attention.self.key.weight": "model-00003-of-00003.safetensors",
520
+ "roberta.encoder.layer.4.attention.self.query.bias": "model-00003-of-00003.safetensors",
521
+ "roberta.encoder.layer.4.attention.self.query.weight": "model-00003-of-00003.safetensors",
522
+ "roberta.encoder.layer.4.attention.self.value.bias": "model-00003-of-00003.safetensors",
523
+ "roberta.encoder.layer.4.attention.self.value.weight": "model-00003-of-00003.safetensors",
524
+ "roberta.encoder.layer.4.intermediate.dense.bias": "model-00003-of-00003.safetensors",
525
+ "roberta.encoder.layer.4.intermediate.dense.weight": "model-00003-of-00003.safetensors",
526
+ "roberta.encoder.layer.4.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
527
+ "roberta.encoder.layer.4.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
528
+ "roberta.encoder.layer.4.output.dense.bias": "model-00003-of-00003.safetensors",
529
+ "roberta.encoder.layer.4.output.dense.weight": "model-00003-of-00003.safetensors",
530
+ "roberta.encoder.layer.5.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
531
+ "roberta.encoder.layer.5.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
532
+ "roberta.encoder.layer.5.attention.output.dense.bias": "model-00003-of-00003.safetensors",
533
+ "roberta.encoder.layer.5.attention.output.dense.weight": "model-00003-of-00003.safetensors",
534
+ "roberta.encoder.layer.5.attention.self.key.bias": "model-00003-of-00003.safetensors",
535
+ "roberta.encoder.layer.5.attention.self.key.weight": "model-00003-of-00003.safetensors",
536
+ "roberta.encoder.layer.5.attention.self.query.bias": "model-00003-of-00003.safetensors",
537
+ "roberta.encoder.layer.5.attention.self.query.weight": "model-00003-of-00003.safetensors",
538
+ "roberta.encoder.layer.5.attention.self.value.bias": "model-00003-of-00003.safetensors",
539
+ "roberta.encoder.layer.5.attention.self.value.weight": "model-00003-of-00003.safetensors",
540
+ "roberta.encoder.layer.5.intermediate.dense.bias": "model-00003-of-00003.safetensors",
541
+ "roberta.encoder.layer.5.intermediate.dense.weight": "model-00003-of-00003.safetensors",
542
+ "roberta.encoder.layer.5.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
543
+ "roberta.encoder.layer.5.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
544
+ "roberta.encoder.layer.5.output.dense.bias": "model-00003-of-00003.safetensors",
545
+ "roberta.encoder.layer.5.output.dense.weight": "model-00003-of-00003.safetensors",
546
+ "roberta.encoder.layer.6.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
547
+ "roberta.encoder.layer.6.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
548
+ "roberta.encoder.layer.6.attention.output.dense.bias": "model-00003-of-00003.safetensors",
549
+ "roberta.encoder.layer.6.attention.output.dense.weight": "model-00003-of-00003.safetensors",
550
+ "roberta.encoder.layer.6.attention.self.key.bias": "model-00003-of-00003.safetensors",
551
+ "roberta.encoder.layer.6.attention.self.key.weight": "model-00003-of-00003.safetensors",
552
+ "roberta.encoder.layer.6.attention.self.query.bias": "model-00003-of-00003.safetensors",
553
+ "roberta.encoder.layer.6.attention.self.query.weight": "model-00003-of-00003.safetensors",
554
+ "roberta.encoder.layer.6.attention.self.value.bias": "model-00003-of-00003.safetensors",
555
+ "roberta.encoder.layer.6.attention.self.value.weight": "model-00003-of-00003.safetensors",
556
+ "roberta.encoder.layer.6.intermediate.dense.bias": "model-00003-of-00003.safetensors",
557
+ "roberta.encoder.layer.6.intermediate.dense.weight": "model-00003-of-00003.safetensors",
558
+ "roberta.encoder.layer.6.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
559
+ "roberta.encoder.layer.6.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
560
+ "roberta.encoder.layer.6.output.dense.bias": "model-00003-of-00003.safetensors",
561
+ "roberta.encoder.layer.6.output.dense.weight": "model-00003-of-00003.safetensors",
562
+ "roberta.encoder.layer.7.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
563
+ "roberta.encoder.layer.7.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
564
+ "roberta.encoder.layer.7.attention.output.dense.bias": "model-00003-of-00003.safetensors",
565
+ "roberta.encoder.layer.7.attention.output.dense.weight": "model-00003-of-00003.safetensors",
566
+ "roberta.encoder.layer.7.attention.self.key.bias": "model-00003-of-00003.safetensors",
567
+ "roberta.encoder.layer.7.attention.self.key.weight": "model-00003-of-00003.safetensors",
568
+ "roberta.encoder.layer.7.attention.self.query.bias": "model-00003-of-00003.safetensors",
569
+ "roberta.encoder.layer.7.attention.self.query.weight": "model-00003-of-00003.safetensors",
570
+ "roberta.encoder.layer.7.attention.self.value.bias": "model-00003-of-00003.safetensors",
571
+ "roberta.encoder.layer.7.attention.self.value.weight": "model-00003-of-00003.safetensors",
572
+ "roberta.encoder.layer.7.intermediate.dense.bias": "model-00003-of-00003.safetensors",
573
+ "roberta.encoder.layer.7.intermediate.dense.weight": "model-00003-of-00003.safetensors",
574
+ "roberta.encoder.layer.7.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
575
+ "roberta.encoder.layer.7.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
576
+ "roberta.encoder.layer.7.output.dense.bias": "model-00003-of-00003.safetensors",
577
+ "roberta.encoder.layer.7.output.dense.weight": "model-00003-of-00003.safetensors",
578
+ "roberta.encoder.layer.8.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
579
+ "roberta.encoder.layer.8.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
580
+ "roberta.encoder.layer.8.attention.output.dense.bias": "model-00003-of-00003.safetensors",
581
+ "roberta.encoder.layer.8.attention.output.dense.weight": "model-00003-of-00003.safetensors",
582
+ "roberta.encoder.layer.8.attention.self.key.bias": "model-00003-of-00003.safetensors",
583
+ "roberta.encoder.layer.8.attention.self.key.weight": "model-00003-of-00003.safetensors",
584
+ "roberta.encoder.layer.8.attention.self.query.bias": "model-00003-of-00003.safetensors",
585
+ "roberta.encoder.layer.8.attention.self.query.weight": "model-00003-of-00003.safetensors",
586
+ "roberta.encoder.layer.8.attention.self.value.bias": "model-00003-of-00003.safetensors",
587
+ "roberta.encoder.layer.8.attention.self.value.weight": "model-00003-of-00003.safetensors",
588
+ "roberta.encoder.layer.8.intermediate.dense.bias": "model-00003-of-00003.safetensors",
589
+ "roberta.encoder.layer.8.intermediate.dense.weight": "model-00003-of-00003.safetensors",
590
+ "roberta.encoder.layer.8.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
591
+ "roberta.encoder.layer.8.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
592
+ "roberta.encoder.layer.8.output.dense.bias": "model-00003-of-00003.safetensors",
593
+ "roberta.encoder.layer.8.output.dense.weight": "model-00003-of-00003.safetensors",
594
+ "roberta.encoder.layer.9.attention.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
595
+ "roberta.encoder.layer.9.attention.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
596
+ "roberta.encoder.layer.9.attention.output.dense.bias": "model-00003-of-00003.safetensors",
597
+ "roberta.encoder.layer.9.attention.output.dense.weight": "model-00003-of-00003.safetensors",
598
+ "roberta.encoder.layer.9.attention.self.key.bias": "model-00003-of-00003.safetensors",
599
+ "roberta.encoder.layer.9.attention.self.key.weight": "model-00003-of-00003.safetensors",
600
+ "roberta.encoder.layer.9.attention.self.query.bias": "model-00003-of-00003.safetensors",
601
+ "roberta.encoder.layer.9.attention.self.query.weight": "model-00003-of-00003.safetensors",
602
+ "roberta.encoder.layer.9.attention.self.value.bias": "model-00003-of-00003.safetensors",
603
+ "roberta.encoder.layer.9.attention.self.value.weight": "model-00003-of-00003.safetensors",
604
+ "roberta.encoder.layer.9.intermediate.dense.bias": "model-00003-of-00003.safetensors",
605
+ "roberta.encoder.layer.9.intermediate.dense.weight": "model-00003-of-00003.safetensors",
606
+ "roberta.encoder.layer.9.output.LayerNorm.bias": "model-00003-of-00003.safetensors",
607
+ "roberta.encoder.layer.9.output.LayerNorm.weight": "model-00003-of-00003.safetensors",
608
+ "roberta.encoder.layer.9.output.dense.bias": "model-00003-of-00003.safetensors",
609
+ "roberta.encoder.layer.9.output.dense.weight": "model-00003-of-00003.safetensors"
610
+ }
611
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "ElectraTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }