Adding `safetensors` variant of this model

#1
by SFconvertbot - opened
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aa4934afaba9848ea231fb420b4d88d0698a25d9b1ec420b35d60c8b132d0d6
3
+ size 994321960
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95276d67b051ca0c5710a9ca6fc2c3f6e813bb7851e27eb3c996652ce60580a1
3
+ size 990373064
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54aaad6f6959a7e73da8defc53d0b4c8649feabfa8a35d313a065fb0d77689dd
3
+ size 990389704
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09bf953d03d8a4c420d500fa2eb4275be1162ab3b18d1b3d0bdd4954c88b3585
3
+ size 990389760
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e7de5967310dee76f0d6400ae83baa4db72df81889508c0e0351ffcf81af05a
3
+ size 990389752
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c459603cedba11419871a1997366619791a8a06e6814433882063aa2d1c85b17
3
+ size 948411248
model.safetensors.index.json ADDED
@@ -0,0 +1,405 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5904482288
4
+ },
5
+ "weight_map": {
6
+ "cls.predictions.bias": "model-00006-of-00006.safetensors",
7
+ "cls.predictions.decoder.bias": "model-00006-of-00006.safetensors",
8
+ "cls.predictions.decoder.weight": "model-00006-of-00006.safetensors",
9
+ "cls.predictions.transform.LayerNorm.bias": "model-00006-of-00006.safetensors",
10
+ "cls.predictions.transform.LayerNorm.weight": "model-00006-of-00006.safetensors",
11
+ "cls.predictions.transform.dense.bias": "model-00006-of-00006.safetensors",
12
+ "cls.predictions.transform.dense.weight": "model-00006-of-00006.safetensors",
13
+ "deberta.embeddings.LayerNorm.bias": "model-00001-of-00006.safetensors",
14
+ "deberta.embeddings.LayerNorm.weight": "model-00001-of-00006.safetensors",
15
+ "deberta.embeddings.position_ids": "model-00001-of-00006.safetensors",
16
+ "deberta.embeddings.word_embeddings.weight": "model-00001-of-00006.safetensors",
17
+ "deberta.encoder.LayerNorm.bias": "model-00006-of-00006.safetensors",
18
+ "deberta.encoder.LayerNorm.weight": "model-00006-of-00006.safetensors",
19
+ "deberta.encoder.layer.0.attention.output.LayerNorm.bias": "model-00001-of-00006.safetensors",
20
+ "deberta.encoder.layer.0.attention.output.LayerNorm.weight": "model-00001-of-00006.safetensors",
21
+ "deberta.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00006.safetensors",
22
+ "deberta.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00006.safetensors",
23
+ "deberta.encoder.layer.0.attention.self.key_proj.bias": "model-00001-of-00006.safetensors",
24
+ "deberta.encoder.layer.0.attention.self.key_proj.weight": "model-00001-of-00006.safetensors",
25
+ "deberta.encoder.layer.0.attention.self.query_proj.bias": "model-00001-of-00006.safetensors",
26
+ "deberta.encoder.layer.0.attention.self.query_proj.weight": "model-00001-of-00006.safetensors",
27
+ "deberta.encoder.layer.0.attention.self.value_proj.bias": "model-00001-of-00006.safetensors",
28
+ "deberta.encoder.layer.0.attention.self.value_proj.weight": "model-00001-of-00006.safetensors",
29
+ "deberta.encoder.layer.0.intermediate.dense.bias": "model-00001-of-00006.safetensors",
30
+ "deberta.encoder.layer.0.intermediate.dense.weight": "model-00001-of-00006.safetensors",
31
+ "deberta.encoder.layer.0.output.LayerNorm.bias": "model-00001-of-00006.safetensors",
32
+ "deberta.encoder.layer.0.output.LayerNorm.weight": "model-00001-of-00006.safetensors",
33
+ "deberta.encoder.layer.0.output.dense.bias": "model-00001-of-00006.safetensors",
34
+ "deberta.encoder.layer.0.output.dense.weight": "model-00001-of-00006.safetensors",
35
+ "deberta.encoder.layer.1.attention.output.LayerNorm.bias": "model-00001-of-00006.safetensors",
36
+ "deberta.encoder.layer.1.attention.output.LayerNorm.weight": "model-00001-of-00006.safetensors",
37
+ "deberta.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00006.safetensors",
38
+ "deberta.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00006.safetensors",
39
+ "deberta.encoder.layer.1.attention.self.key_proj.bias": "model-00001-of-00006.safetensors",
40
+ "deberta.encoder.layer.1.attention.self.key_proj.weight": "model-00001-of-00006.safetensors",
41
+ "deberta.encoder.layer.1.attention.self.query_proj.bias": "model-00001-of-00006.safetensors",
42
+ "deberta.encoder.layer.1.attention.self.query_proj.weight": "model-00001-of-00006.safetensors",
43
+ "deberta.encoder.layer.1.attention.self.value_proj.bias": "model-00001-of-00006.safetensors",
44
+ "deberta.encoder.layer.1.attention.self.value_proj.weight": "model-00001-of-00006.safetensors",
45
+ "deberta.encoder.layer.1.intermediate.dense.bias": "model-00001-of-00006.safetensors",
46
+ "deberta.encoder.layer.1.intermediate.dense.weight": "model-00001-of-00006.safetensors",
47
+ "deberta.encoder.layer.1.output.LayerNorm.bias": "model-00001-of-00006.safetensors",
48
+ "deberta.encoder.layer.1.output.LayerNorm.weight": "model-00001-of-00006.safetensors",
49
+ "deberta.encoder.layer.1.output.dense.bias": "model-00001-of-00006.safetensors",
50
+ "deberta.encoder.layer.1.output.dense.weight": "model-00001-of-00006.safetensors",
51
+ "deberta.encoder.layer.10.attention.output.LayerNorm.bias": "model-00003-of-00006.safetensors",
52
+ "deberta.encoder.layer.10.attention.output.LayerNorm.weight": "model-00003-of-00006.safetensors",
53
+ "deberta.encoder.layer.10.attention.output.dense.bias": "model-00003-of-00006.safetensors",
54
+ "deberta.encoder.layer.10.attention.output.dense.weight": "model-00003-of-00006.safetensors",
55
+ "deberta.encoder.layer.10.attention.self.key_proj.bias": "model-00003-of-00006.safetensors",
56
+ "deberta.encoder.layer.10.attention.self.key_proj.weight": "model-00003-of-00006.safetensors",
57
+ "deberta.encoder.layer.10.attention.self.query_proj.bias": "model-00003-of-00006.safetensors",
58
+ "deberta.encoder.layer.10.attention.self.query_proj.weight": "model-00003-of-00006.safetensors",
59
+ "deberta.encoder.layer.10.attention.self.value_proj.bias": "model-00003-of-00006.safetensors",
60
+ "deberta.encoder.layer.10.attention.self.value_proj.weight": "model-00003-of-00006.safetensors",
61
+ "deberta.encoder.layer.10.intermediate.dense.bias": "model-00003-of-00006.safetensors",
62
+ "deberta.encoder.layer.10.intermediate.dense.weight": "model-00003-of-00006.safetensors",
63
+ "deberta.encoder.layer.10.output.LayerNorm.bias": "model-00003-of-00006.safetensors",
64
+ "deberta.encoder.layer.10.output.LayerNorm.weight": "model-00003-of-00006.safetensors",
65
+ "deberta.encoder.layer.10.output.dense.bias": "model-00003-of-00006.safetensors",
66
+ "deberta.encoder.layer.10.output.dense.weight": "model-00003-of-00006.safetensors",
67
+ "deberta.encoder.layer.11.attention.output.LayerNorm.bias": "model-00003-of-00006.safetensors",
68
+ "deberta.encoder.layer.11.attention.output.LayerNorm.weight": "model-00003-of-00006.safetensors",
69
+ "deberta.encoder.layer.11.attention.output.dense.bias": "model-00003-of-00006.safetensors",
70
+ "deberta.encoder.layer.11.attention.output.dense.weight": "model-00003-of-00006.safetensors",
71
+ "deberta.encoder.layer.11.attention.self.key_proj.bias": "model-00003-of-00006.safetensors",
72
+ "deberta.encoder.layer.11.attention.self.key_proj.weight": "model-00003-of-00006.safetensors",
73
+ "deberta.encoder.layer.11.attention.self.query_proj.bias": "model-00003-of-00006.safetensors",
74
+ "deberta.encoder.layer.11.attention.self.query_proj.weight": "model-00003-of-00006.safetensors",
75
+ "deberta.encoder.layer.11.attention.self.value_proj.bias": "model-00003-of-00006.safetensors",
76
+ "deberta.encoder.layer.11.attention.self.value_proj.weight": "model-00003-of-00006.safetensors",
77
+ "deberta.encoder.layer.11.intermediate.dense.bias": "model-00003-of-00006.safetensors",
78
+ "deberta.encoder.layer.11.intermediate.dense.weight": "model-00003-of-00006.safetensors",
79
+ "deberta.encoder.layer.11.output.LayerNorm.bias": "model-00003-of-00006.safetensors",
80
+ "deberta.encoder.layer.11.output.LayerNorm.weight": "model-00003-of-00006.safetensors",
81
+ "deberta.encoder.layer.11.output.dense.bias": "model-00003-of-00006.safetensors",
82
+ "deberta.encoder.layer.11.output.dense.weight": "model-00003-of-00006.safetensors",
83
+ "deberta.encoder.layer.12.attention.output.LayerNorm.bias": "model-00004-of-00006.safetensors",
84
+ "deberta.encoder.layer.12.attention.output.LayerNorm.weight": "model-00004-of-00006.safetensors",
85
+ "deberta.encoder.layer.12.attention.output.dense.bias": "model-00004-of-00006.safetensors",
86
+ "deberta.encoder.layer.12.attention.output.dense.weight": "model-00004-of-00006.safetensors",
87
+ "deberta.encoder.layer.12.attention.self.key_proj.bias": "model-00003-of-00006.safetensors",
88
+ "deberta.encoder.layer.12.attention.self.key_proj.weight": "model-00003-of-00006.safetensors",
89
+ "deberta.encoder.layer.12.attention.self.query_proj.bias": "model-00003-of-00006.safetensors",
90
+ "deberta.encoder.layer.12.attention.self.query_proj.weight": "model-00003-of-00006.safetensors",
91
+ "deberta.encoder.layer.12.attention.self.value_proj.bias": "model-00004-of-00006.safetensors",
92
+ "deberta.encoder.layer.12.attention.self.value_proj.weight": "model-00004-of-00006.safetensors",
93
+ "deberta.encoder.layer.12.intermediate.dense.bias": "model-00004-of-00006.safetensors",
94
+ "deberta.encoder.layer.12.intermediate.dense.weight": "model-00004-of-00006.safetensors",
95
+ "deberta.encoder.layer.12.output.LayerNorm.bias": "model-00004-of-00006.safetensors",
96
+ "deberta.encoder.layer.12.output.LayerNorm.weight": "model-00004-of-00006.safetensors",
97
+ "deberta.encoder.layer.12.output.dense.bias": "model-00004-of-00006.safetensors",
98
+ "deberta.encoder.layer.12.output.dense.weight": "model-00004-of-00006.safetensors",
99
+ "deberta.encoder.layer.13.attention.output.LayerNorm.bias": "model-00004-of-00006.safetensors",
100
+ "deberta.encoder.layer.13.attention.output.LayerNorm.weight": "model-00004-of-00006.safetensors",
101
+ "deberta.encoder.layer.13.attention.output.dense.bias": "model-00004-of-00006.safetensors",
102
+ "deberta.encoder.layer.13.attention.output.dense.weight": "model-00004-of-00006.safetensors",
103
+ "deberta.encoder.layer.13.attention.self.key_proj.bias": "model-00004-of-00006.safetensors",
104
+ "deberta.encoder.layer.13.attention.self.key_proj.weight": "model-00004-of-00006.safetensors",
105
+ "deberta.encoder.layer.13.attention.self.query_proj.bias": "model-00004-of-00006.safetensors",
106
+ "deberta.encoder.layer.13.attention.self.query_proj.weight": "model-00004-of-00006.safetensors",
107
+ "deberta.encoder.layer.13.attention.self.value_proj.bias": "model-00004-of-00006.safetensors",
108
+ "deberta.encoder.layer.13.attention.self.value_proj.weight": "model-00004-of-00006.safetensors",
109
+ "deberta.encoder.layer.13.intermediate.dense.bias": "model-00004-of-00006.safetensors",
110
+ "deberta.encoder.layer.13.intermediate.dense.weight": "model-00004-of-00006.safetensors",
111
+ "deberta.encoder.layer.13.output.LayerNorm.bias": "model-00004-of-00006.safetensors",
112
+ "deberta.encoder.layer.13.output.LayerNorm.weight": "model-00004-of-00006.safetensors",
113
+ "deberta.encoder.layer.13.output.dense.bias": "model-00004-of-00006.safetensors",
114
+ "deberta.encoder.layer.13.output.dense.weight": "model-00004-of-00006.safetensors",
115
+ "deberta.encoder.layer.14.attention.output.LayerNorm.bias": "model-00004-of-00006.safetensors",
116
+ "deberta.encoder.layer.14.attention.output.LayerNorm.weight": "model-00004-of-00006.safetensors",
117
+ "deberta.encoder.layer.14.attention.output.dense.bias": "model-00004-of-00006.safetensors",
118
+ "deberta.encoder.layer.14.attention.output.dense.weight": "model-00004-of-00006.safetensors",
119
+ "deberta.encoder.layer.14.attention.self.key_proj.bias": "model-00004-of-00006.safetensors",
120
+ "deberta.encoder.layer.14.attention.self.key_proj.weight": "model-00004-of-00006.safetensors",
121
+ "deberta.encoder.layer.14.attention.self.query_proj.bias": "model-00004-of-00006.safetensors",
122
+ "deberta.encoder.layer.14.attention.self.query_proj.weight": "model-00004-of-00006.safetensors",
123
+ "deberta.encoder.layer.14.attention.self.value_proj.bias": "model-00004-of-00006.safetensors",
124
+ "deberta.encoder.layer.14.attention.self.value_proj.weight": "model-00004-of-00006.safetensors",
125
+ "deberta.encoder.layer.14.intermediate.dense.bias": "model-00004-of-00006.safetensors",
126
+ "deberta.encoder.layer.14.intermediate.dense.weight": "model-00004-of-00006.safetensors",
127
+ "deberta.encoder.layer.14.output.LayerNorm.bias": "model-00004-of-00006.safetensors",
128
+ "deberta.encoder.layer.14.output.LayerNorm.weight": "model-00004-of-00006.safetensors",
129
+ "deberta.encoder.layer.14.output.dense.bias": "model-00004-of-00006.safetensors",
130
+ "deberta.encoder.layer.14.output.dense.weight": "model-00004-of-00006.safetensors",
131
+ "deberta.encoder.layer.15.attention.output.LayerNorm.bias": "model-00004-of-00006.safetensors",
132
+ "deberta.encoder.layer.15.attention.output.LayerNorm.weight": "model-00004-of-00006.safetensors",
133
+ "deberta.encoder.layer.15.attention.output.dense.bias": "model-00004-of-00006.safetensors",
134
+ "deberta.encoder.layer.15.attention.output.dense.weight": "model-00004-of-00006.safetensors",
135
+ "deberta.encoder.layer.15.attention.self.key_proj.bias": "model-00004-of-00006.safetensors",
136
+ "deberta.encoder.layer.15.attention.self.key_proj.weight": "model-00004-of-00006.safetensors",
137
+ "deberta.encoder.layer.15.attention.self.query_proj.bias": "model-00004-of-00006.safetensors",
138
+ "deberta.encoder.layer.15.attention.self.query_proj.weight": "model-00004-of-00006.safetensors",
139
+ "deberta.encoder.layer.15.attention.self.value_proj.bias": "model-00004-of-00006.safetensors",
140
+ "deberta.encoder.layer.15.attention.self.value_proj.weight": "model-00004-of-00006.safetensors",
141
+ "deberta.encoder.layer.15.intermediate.dense.bias": "model-00004-of-00006.safetensors",
142
+ "deberta.encoder.layer.15.intermediate.dense.weight": "model-00004-of-00006.safetensors",
143
+ "deberta.encoder.layer.15.output.LayerNorm.bias": "model-00004-of-00006.safetensors",
144
+ "deberta.encoder.layer.15.output.LayerNorm.weight": "model-00004-of-00006.safetensors",
145
+ "deberta.encoder.layer.15.output.dense.bias": "model-00004-of-00006.safetensors",
146
+ "deberta.encoder.layer.15.output.dense.weight": "model-00004-of-00006.safetensors",
147
+ "deberta.encoder.layer.16.attention.output.LayerNorm.bias": "model-00004-of-00006.safetensors",
148
+ "deberta.encoder.layer.16.attention.output.LayerNorm.weight": "model-00004-of-00006.safetensors",
149
+ "deberta.encoder.layer.16.attention.output.dense.bias": "model-00004-of-00006.safetensors",
150
+ "deberta.encoder.layer.16.attention.output.dense.weight": "model-00004-of-00006.safetensors",
151
+ "deberta.encoder.layer.16.attention.self.key_proj.bias": "model-00004-of-00006.safetensors",
152
+ "deberta.encoder.layer.16.attention.self.key_proj.weight": "model-00004-of-00006.safetensors",
153
+ "deberta.encoder.layer.16.attention.self.query_proj.bias": "model-00004-of-00006.safetensors",
154
+ "deberta.encoder.layer.16.attention.self.query_proj.weight": "model-00004-of-00006.safetensors",
155
+ "deberta.encoder.layer.16.attention.self.value_proj.bias": "model-00004-of-00006.safetensors",
156
+ "deberta.encoder.layer.16.attention.self.value_proj.weight": "model-00004-of-00006.safetensors",
157
+ "deberta.encoder.layer.16.intermediate.dense.bias": "model-00004-of-00006.safetensors",
158
+ "deberta.encoder.layer.16.intermediate.dense.weight": "model-00004-of-00006.safetensors",
159
+ "deberta.encoder.layer.16.output.LayerNorm.bias": "model-00004-of-00006.safetensors",
160
+ "deberta.encoder.layer.16.output.LayerNorm.weight": "model-00004-of-00006.safetensors",
161
+ "deberta.encoder.layer.16.output.dense.bias": "model-00004-of-00006.safetensors",
162
+ "deberta.encoder.layer.16.output.dense.weight": "model-00004-of-00006.safetensors",
163
+ "deberta.encoder.layer.17.attention.output.LayerNorm.bias": "model-00005-of-00006.safetensors",
164
+ "deberta.encoder.layer.17.attention.output.LayerNorm.weight": "model-00005-of-00006.safetensors",
165
+ "deberta.encoder.layer.17.attention.output.dense.bias": "model-00005-of-00006.safetensors",
166
+ "deberta.encoder.layer.17.attention.output.dense.weight": "model-00005-of-00006.safetensors",
167
+ "deberta.encoder.layer.17.attention.self.key_proj.bias": "model-00005-of-00006.safetensors",
168
+ "deberta.encoder.layer.17.attention.self.key_proj.weight": "model-00005-of-00006.safetensors",
169
+ "deberta.encoder.layer.17.attention.self.query_proj.bias": "model-00004-of-00006.safetensors",
170
+ "deberta.encoder.layer.17.attention.self.query_proj.weight": "model-00004-of-00006.safetensors",
171
+ "deberta.encoder.layer.17.attention.self.value_proj.bias": "model-00005-of-00006.safetensors",
172
+ "deberta.encoder.layer.17.attention.self.value_proj.weight": "model-00005-of-00006.safetensors",
173
+ "deberta.encoder.layer.17.intermediate.dense.bias": "model-00005-of-00006.safetensors",
174
+ "deberta.encoder.layer.17.intermediate.dense.weight": "model-00005-of-00006.safetensors",
175
+ "deberta.encoder.layer.17.output.LayerNorm.bias": "model-00005-of-00006.safetensors",
176
+ "deberta.encoder.layer.17.output.LayerNorm.weight": "model-00005-of-00006.safetensors",
177
+ "deberta.encoder.layer.17.output.dense.bias": "model-00005-of-00006.safetensors",
178
+ "deberta.encoder.layer.17.output.dense.weight": "model-00005-of-00006.safetensors",
179
+ "deberta.encoder.layer.18.attention.output.LayerNorm.bias": "model-00005-of-00006.safetensors",
180
+ "deberta.encoder.layer.18.attention.output.LayerNorm.weight": "model-00005-of-00006.safetensors",
181
+ "deberta.encoder.layer.18.attention.output.dense.bias": "model-00005-of-00006.safetensors",
182
+ "deberta.encoder.layer.18.attention.output.dense.weight": "model-00005-of-00006.safetensors",
183
+ "deberta.encoder.layer.18.attention.self.key_proj.bias": "model-00005-of-00006.safetensors",
184
+ "deberta.encoder.layer.18.attention.self.key_proj.weight": "model-00005-of-00006.safetensors",
185
+ "deberta.encoder.layer.18.attention.self.query_proj.bias": "model-00005-of-00006.safetensors",
186
+ "deberta.encoder.layer.18.attention.self.query_proj.weight": "model-00005-of-00006.safetensors",
187
+ "deberta.encoder.layer.18.attention.self.value_proj.bias": "model-00005-of-00006.safetensors",
188
+ "deberta.encoder.layer.18.attention.self.value_proj.weight": "model-00005-of-00006.safetensors",
189
+ "deberta.encoder.layer.18.intermediate.dense.bias": "model-00005-of-00006.safetensors",
190
+ "deberta.encoder.layer.18.intermediate.dense.weight": "model-00005-of-00006.safetensors",
191
+ "deberta.encoder.layer.18.output.LayerNorm.bias": "model-00005-of-00006.safetensors",
192
+ "deberta.encoder.layer.18.output.LayerNorm.weight": "model-00005-of-00006.safetensors",
193
+ "deberta.encoder.layer.18.output.dense.bias": "model-00005-of-00006.safetensors",
194
+ "deberta.encoder.layer.18.output.dense.weight": "model-00005-of-00006.safetensors",
195
+ "deberta.encoder.layer.19.attention.output.LayerNorm.bias": "model-00005-of-00006.safetensors",
196
+ "deberta.encoder.layer.19.attention.output.LayerNorm.weight": "model-00005-of-00006.safetensors",
197
+ "deberta.encoder.layer.19.attention.output.dense.bias": "model-00005-of-00006.safetensors",
198
+ "deberta.encoder.layer.19.attention.output.dense.weight": "model-00005-of-00006.safetensors",
199
+ "deberta.encoder.layer.19.attention.self.key_proj.bias": "model-00005-of-00006.safetensors",
200
+ "deberta.encoder.layer.19.attention.self.key_proj.weight": "model-00005-of-00006.safetensors",
201
+ "deberta.encoder.layer.19.attention.self.query_proj.bias": "model-00005-of-00006.safetensors",
202
+ "deberta.encoder.layer.19.attention.self.query_proj.weight": "model-00005-of-00006.safetensors",
203
+ "deberta.encoder.layer.19.attention.self.value_proj.bias": "model-00005-of-00006.safetensors",
204
+ "deberta.encoder.layer.19.attention.self.value_proj.weight": "model-00005-of-00006.safetensors",
205
+ "deberta.encoder.layer.19.intermediate.dense.bias": "model-00005-of-00006.safetensors",
206
+ "deberta.encoder.layer.19.intermediate.dense.weight": "model-00005-of-00006.safetensors",
207
+ "deberta.encoder.layer.19.output.LayerNorm.bias": "model-00005-of-00006.safetensors",
208
+ "deberta.encoder.layer.19.output.LayerNorm.weight": "model-00005-of-00006.safetensors",
209
+ "deberta.encoder.layer.19.output.dense.bias": "model-00005-of-00006.safetensors",
210
+ "deberta.encoder.layer.19.output.dense.weight": "model-00005-of-00006.safetensors",
211
+ "deberta.encoder.layer.2.attention.output.LayerNorm.bias": "model-00001-of-00006.safetensors",
212
+ "deberta.encoder.layer.2.attention.output.LayerNorm.weight": "model-00001-of-00006.safetensors",
213
+ "deberta.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00006.safetensors",
214
+ "deberta.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00006.safetensors",
215
+ "deberta.encoder.layer.2.attention.self.key_proj.bias": "model-00001-of-00006.safetensors",
216
+ "deberta.encoder.layer.2.attention.self.key_proj.weight": "model-00001-of-00006.safetensors",
217
+ "deberta.encoder.layer.2.attention.self.query_proj.bias": "model-00001-of-00006.safetensors",
218
+ "deberta.encoder.layer.2.attention.self.query_proj.weight": "model-00001-of-00006.safetensors",
219
+ "deberta.encoder.layer.2.attention.self.value_proj.bias": "model-00001-of-00006.safetensors",
220
+ "deberta.encoder.layer.2.attention.self.value_proj.weight": "model-00001-of-00006.safetensors",
221
+ "deberta.encoder.layer.2.intermediate.dense.bias": "model-00002-of-00006.safetensors",
222
+ "deberta.encoder.layer.2.intermediate.dense.weight": "model-00002-of-00006.safetensors",
223
+ "deberta.encoder.layer.2.output.LayerNorm.bias": "model-00002-of-00006.safetensors",
224
+ "deberta.encoder.layer.2.output.LayerNorm.weight": "model-00002-of-00006.safetensors",
225
+ "deberta.encoder.layer.2.output.dense.bias": "model-00002-of-00006.safetensors",
226
+ "deberta.encoder.layer.2.output.dense.weight": "model-00002-of-00006.safetensors",
227
+ "deberta.encoder.layer.20.attention.output.LayerNorm.bias": "model-00005-of-00006.safetensors",
228
+ "deberta.encoder.layer.20.attention.output.LayerNorm.weight": "model-00005-of-00006.safetensors",
229
+ "deberta.encoder.layer.20.attention.output.dense.bias": "model-00005-of-00006.safetensors",
230
+ "deberta.encoder.layer.20.attention.output.dense.weight": "model-00005-of-00006.safetensors",
231
+ "deberta.encoder.layer.20.attention.self.key_proj.bias": "model-00005-of-00006.safetensors",
232
+ "deberta.encoder.layer.20.attention.self.key_proj.weight": "model-00005-of-00006.safetensors",
233
+ "deberta.encoder.layer.20.attention.self.query_proj.bias": "model-00005-of-00006.safetensors",
234
+ "deberta.encoder.layer.20.attention.self.query_proj.weight": "model-00005-of-00006.safetensors",
235
+ "deberta.encoder.layer.20.attention.self.value_proj.bias": "model-00005-of-00006.safetensors",
236
+ "deberta.encoder.layer.20.attention.self.value_proj.weight": "model-00005-of-00006.safetensors",
237
+ "deberta.encoder.layer.20.intermediate.dense.bias": "model-00005-of-00006.safetensors",
238
+ "deberta.encoder.layer.20.intermediate.dense.weight": "model-00005-of-00006.safetensors",
239
+ "deberta.encoder.layer.20.output.LayerNorm.bias": "model-00005-of-00006.safetensors",
240
+ "deberta.encoder.layer.20.output.LayerNorm.weight": "model-00005-of-00006.safetensors",
241
+ "deberta.encoder.layer.20.output.dense.bias": "model-00005-of-00006.safetensors",
242
+ "deberta.encoder.layer.20.output.dense.weight": "model-00005-of-00006.safetensors",
243
+ "deberta.encoder.layer.21.attention.output.LayerNorm.bias": "model-00005-of-00006.safetensors",
244
+ "deberta.encoder.layer.21.attention.output.LayerNorm.weight": "model-00005-of-00006.safetensors",
245
+ "deberta.encoder.layer.21.attention.output.dense.bias": "model-00005-of-00006.safetensors",
246
+ "deberta.encoder.layer.21.attention.output.dense.weight": "model-00005-of-00006.safetensors",
247
+ "deberta.encoder.layer.21.attention.self.key_proj.bias": "model-00005-of-00006.safetensors",
248
+ "deberta.encoder.layer.21.attention.self.key_proj.weight": "model-00005-of-00006.safetensors",
249
+ "deberta.encoder.layer.21.attention.self.query_proj.bias": "model-00005-of-00006.safetensors",
250
+ "deberta.encoder.layer.21.attention.self.query_proj.weight": "model-00005-of-00006.safetensors",
251
+ "deberta.encoder.layer.21.attention.self.value_proj.bias": "model-00005-of-00006.safetensors",
252
+ "deberta.encoder.layer.21.attention.self.value_proj.weight": "model-00005-of-00006.safetensors",
253
+ "deberta.encoder.layer.21.intermediate.dense.bias": "model-00005-of-00006.safetensors",
254
+ "deberta.encoder.layer.21.intermediate.dense.weight": "model-00005-of-00006.safetensors",
255
+ "deberta.encoder.layer.21.output.LayerNorm.bias": "model-00005-of-00006.safetensors",
256
+ "deberta.encoder.layer.21.output.LayerNorm.weight": "model-00005-of-00006.safetensors",
257
+ "deberta.encoder.layer.21.output.dense.bias": "model-00005-of-00006.safetensors",
258
+ "deberta.encoder.layer.21.output.dense.weight": "model-00005-of-00006.safetensors",
259
+ "deberta.encoder.layer.22.attention.output.LayerNorm.bias": "model-00006-of-00006.safetensors",
260
+ "deberta.encoder.layer.22.attention.output.LayerNorm.weight": "model-00006-of-00006.safetensors",
261
+ "deberta.encoder.layer.22.attention.output.dense.bias": "model-00006-of-00006.safetensors",
262
+ "deberta.encoder.layer.22.attention.output.dense.weight": "model-00006-of-00006.safetensors",
263
+ "deberta.encoder.layer.22.attention.self.key_proj.bias": "model-00006-of-00006.safetensors",
264
+ "deberta.encoder.layer.22.attention.self.key_proj.weight": "model-00006-of-00006.safetensors",
265
+ "deberta.encoder.layer.22.attention.self.query_proj.bias": "model-00006-of-00006.safetensors",
266
+ "deberta.encoder.layer.22.attention.self.query_proj.weight": "model-00006-of-00006.safetensors",
267
+ "deberta.encoder.layer.22.attention.self.value_proj.bias": "model-00006-of-00006.safetensors",
268
+ "deberta.encoder.layer.22.attention.self.value_proj.weight": "model-00006-of-00006.safetensors",
269
+ "deberta.encoder.layer.22.intermediate.dense.bias": "model-00006-of-00006.safetensors",
270
+ "deberta.encoder.layer.22.intermediate.dense.weight": "model-00006-of-00006.safetensors",
271
+ "deberta.encoder.layer.22.output.LayerNorm.bias": "model-00006-of-00006.safetensors",
272
+ "deberta.encoder.layer.22.output.LayerNorm.weight": "model-00006-of-00006.safetensors",
273
+ "deberta.encoder.layer.22.output.dense.bias": "model-00006-of-00006.safetensors",
274
+ "deberta.encoder.layer.22.output.dense.weight": "model-00006-of-00006.safetensors",
275
+ "deberta.encoder.layer.23.attention.output.LayerNorm.bias": "model-00006-of-00006.safetensors",
276
+ "deberta.encoder.layer.23.attention.output.LayerNorm.weight": "model-00006-of-00006.safetensors",
277
+ "deberta.encoder.layer.23.attention.output.dense.bias": "model-00006-of-00006.safetensors",
278
+ "deberta.encoder.layer.23.attention.output.dense.weight": "model-00006-of-00006.safetensors",
279
+ "deberta.encoder.layer.23.attention.self.key_proj.bias": "model-00006-of-00006.safetensors",
280
+ "deberta.encoder.layer.23.attention.self.key_proj.weight": "model-00006-of-00006.safetensors",
281
+ "deberta.encoder.layer.23.attention.self.query_proj.bias": "model-00006-of-00006.safetensors",
282
+ "deberta.encoder.layer.23.attention.self.query_proj.weight": "model-00006-of-00006.safetensors",
283
+ "deberta.encoder.layer.23.attention.self.value_proj.bias": "model-00006-of-00006.safetensors",
284
+ "deberta.encoder.layer.23.attention.self.value_proj.weight": "model-00006-of-00006.safetensors",
285
+ "deberta.encoder.layer.23.intermediate.dense.bias": "model-00006-of-00006.safetensors",
286
+ "deberta.encoder.layer.23.intermediate.dense.weight": "model-00006-of-00006.safetensors",
287
+ "deberta.encoder.layer.23.output.LayerNorm.bias": "model-00006-of-00006.safetensors",
288
+ "deberta.encoder.layer.23.output.LayerNorm.weight": "model-00006-of-00006.safetensors",
289
+ "deberta.encoder.layer.23.output.dense.bias": "model-00006-of-00006.safetensors",
290
+ "deberta.encoder.layer.23.output.dense.weight": "model-00006-of-00006.safetensors",
291
+ "deberta.encoder.layer.3.attention.output.LayerNorm.bias": "model-00002-of-00006.safetensors",
292
+ "deberta.encoder.layer.3.attention.output.LayerNorm.weight": "model-00002-of-00006.safetensors",
293
+ "deberta.encoder.layer.3.attention.output.dense.bias": "model-00002-of-00006.safetensors",
294
+ "deberta.encoder.layer.3.attention.output.dense.weight": "model-00002-of-00006.safetensors",
295
+ "deberta.encoder.layer.3.attention.self.key_proj.bias": "model-00002-of-00006.safetensors",
296
+ "deberta.encoder.layer.3.attention.self.key_proj.weight": "model-00002-of-00006.safetensors",
297
+ "deberta.encoder.layer.3.attention.self.query_proj.bias": "model-00002-of-00006.safetensors",
298
+ "deberta.encoder.layer.3.attention.self.query_proj.weight": "model-00002-of-00006.safetensors",
299
+ "deberta.encoder.layer.3.attention.self.value_proj.bias": "model-00002-of-00006.safetensors",
300
+ "deberta.encoder.layer.3.attention.self.value_proj.weight": "model-00002-of-00006.safetensors",
301
+ "deberta.encoder.layer.3.intermediate.dense.bias": "model-00002-of-00006.safetensors",
302
+ "deberta.encoder.layer.3.intermediate.dense.weight": "model-00002-of-00006.safetensors",
303
+ "deberta.encoder.layer.3.output.LayerNorm.bias": "model-00002-of-00006.safetensors",
304
+ "deberta.encoder.layer.3.output.LayerNorm.weight": "model-00002-of-00006.safetensors",
305
+ "deberta.encoder.layer.3.output.dense.bias": "model-00002-of-00006.safetensors",
306
+ "deberta.encoder.layer.3.output.dense.weight": "model-00002-of-00006.safetensors",
307
+ "deberta.encoder.layer.4.attention.output.LayerNorm.bias": "model-00002-of-00006.safetensors",
308
+ "deberta.encoder.layer.4.attention.output.LayerNorm.weight": "model-00002-of-00006.safetensors",
309
+ "deberta.encoder.layer.4.attention.output.dense.bias": "model-00002-of-00006.safetensors",
310
+ "deberta.encoder.layer.4.attention.output.dense.weight": "model-00002-of-00006.safetensors",
311
+ "deberta.encoder.layer.4.attention.self.key_proj.bias": "model-00002-of-00006.safetensors",
312
+ "deberta.encoder.layer.4.attention.self.key_proj.weight": "model-00002-of-00006.safetensors",
313
+ "deberta.encoder.layer.4.attention.self.query_proj.bias": "model-00002-of-00006.safetensors",
314
+ "deberta.encoder.layer.4.attention.self.query_proj.weight": "model-00002-of-00006.safetensors",
315
+ "deberta.encoder.layer.4.attention.self.value_proj.bias": "model-00002-of-00006.safetensors",
316
+ "deberta.encoder.layer.4.attention.self.value_proj.weight": "model-00002-of-00006.safetensors",
317
+ "deberta.encoder.layer.4.intermediate.dense.bias": "model-00002-of-00006.safetensors",
318
+ "deberta.encoder.layer.4.intermediate.dense.weight": "model-00002-of-00006.safetensors",
319
+ "deberta.encoder.layer.4.output.LayerNorm.bias": "model-00002-of-00006.safetensors",
320
+ "deberta.encoder.layer.4.output.LayerNorm.weight": "model-00002-of-00006.safetensors",
321
+ "deberta.encoder.layer.4.output.dense.bias": "model-00002-of-00006.safetensors",
322
+ "deberta.encoder.layer.4.output.dense.weight": "model-00002-of-00006.safetensors",
323
+ "deberta.encoder.layer.5.attention.output.LayerNorm.bias": "model-00002-of-00006.safetensors",
324
+ "deberta.encoder.layer.5.attention.output.LayerNorm.weight": "model-00002-of-00006.safetensors",
325
+ "deberta.encoder.layer.5.attention.output.dense.bias": "model-00002-of-00006.safetensors",
326
+ "deberta.encoder.layer.5.attention.output.dense.weight": "model-00002-of-00006.safetensors",
327
+ "deberta.encoder.layer.5.attention.self.key_proj.bias": "model-00002-of-00006.safetensors",
328
+ "deberta.encoder.layer.5.attention.self.key_proj.weight": "model-00002-of-00006.safetensors",
329
+ "deberta.encoder.layer.5.attention.self.query_proj.bias": "model-00002-of-00006.safetensors",
330
+ "deberta.encoder.layer.5.attention.self.query_proj.weight": "model-00002-of-00006.safetensors",
331
+ "deberta.encoder.layer.5.attention.self.value_proj.bias": "model-00002-of-00006.safetensors",
332
+ "deberta.encoder.layer.5.attention.self.value_proj.weight": "model-00002-of-00006.safetensors",
333
+ "deberta.encoder.layer.5.intermediate.dense.bias": "model-00002-of-00006.safetensors",
334
+ "deberta.encoder.layer.5.intermediate.dense.weight": "model-00002-of-00006.safetensors",
335
+ "deberta.encoder.layer.5.output.LayerNorm.bias": "model-00002-of-00006.safetensors",
336
+ "deberta.encoder.layer.5.output.LayerNorm.weight": "model-00002-of-00006.safetensors",
337
+ "deberta.encoder.layer.5.output.dense.bias": "model-00002-of-00006.safetensors",
338
+ "deberta.encoder.layer.5.output.dense.weight": "model-00002-of-00006.safetensors",
339
+ "deberta.encoder.layer.6.attention.output.LayerNorm.bias": "model-00002-of-00006.safetensors",
340
+ "deberta.encoder.layer.6.attention.output.LayerNorm.weight": "model-00002-of-00006.safetensors",
341
+ "deberta.encoder.layer.6.attention.output.dense.bias": "model-00002-of-00006.safetensors",
342
+ "deberta.encoder.layer.6.attention.output.dense.weight": "model-00002-of-00006.safetensors",
343
+ "deberta.encoder.layer.6.attention.self.key_proj.bias": "model-00002-of-00006.safetensors",
344
+ "deberta.encoder.layer.6.attention.self.key_proj.weight": "model-00002-of-00006.safetensors",
345
+ "deberta.encoder.layer.6.attention.self.query_proj.bias": "model-00002-of-00006.safetensors",
346
+ "deberta.encoder.layer.6.attention.self.query_proj.weight": "model-00002-of-00006.safetensors",
347
+ "deberta.encoder.layer.6.attention.self.value_proj.bias": "model-00002-of-00006.safetensors",
348
+ "deberta.encoder.layer.6.attention.self.value_proj.weight": "model-00002-of-00006.safetensors",
349
+ "deberta.encoder.layer.6.intermediate.dense.bias": "model-00002-of-00006.safetensors",
350
+ "deberta.encoder.layer.6.intermediate.dense.weight": "model-00002-of-00006.safetensors",
351
+ "deberta.encoder.layer.6.output.LayerNorm.bias": "model-00002-of-00006.safetensors",
352
+ "deberta.encoder.layer.6.output.LayerNorm.weight": "model-00002-of-00006.safetensors",
353
+ "deberta.encoder.layer.6.output.dense.bias": "model-00002-of-00006.safetensors",
354
+ "deberta.encoder.layer.6.output.dense.weight": "model-00002-of-00006.safetensors",
355
+ "deberta.encoder.layer.7.attention.output.LayerNorm.bias": "model-00003-of-00006.safetensors",
356
+ "deberta.encoder.layer.7.attention.output.LayerNorm.weight": "model-00003-of-00006.safetensors",
357
+ "deberta.encoder.layer.7.attention.output.dense.bias": "model-00003-of-00006.safetensors",
358
+ "deberta.encoder.layer.7.attention.output.dense.weight": "model-00003-of-00006.safetensors",
359
+ "deberta.encoder.layer.7.attention.self.key_proj.bias": "model-00002-of-00006.safetensors",
360
+ "deberta.encoder.layer.7.attention.self.key_proj.weight": "model-00002-of-00006.safetensors",
361
+ "deberta.encoder.layer.7.attention.self.query_proj.bias": "model-00002-of-00006.safetensors",
362
+ "deberta.encoder.layer.7.attention.self.query_proj.weight": "model-00002-of-00006.safetensors",
363
+ "deberta.encoder.layer.7.attention.self.value_proj.bias": "model-00002-of-00006.safetensors",
364
+ "deberta.encoder.layer.7.attention.self.value_proj.weight": "model-00002-of-00006.safetensors",
365
+ "deberta.encoder.layer.7.intermediate.dense.bias": "model-00003-of-00006.safetensors",
366
+ "deberta.encoder.layer.7.intermediate.dense.weight": "model-00003-of-00006.safetensors",
367
+ "deberta.encoder.layer.7.output.LayerNorm.bias": "model-00003-of-00006.safetensors",
368
+ "deberta.encoder.layer.7.output.LayerNorm.weight": "model-00003-of-00006.safetensors",
369
+ "deberta.encoder.layer.7.output.dense.bias": "model-00003-of-00006.safetensors",
370
+ "deberta.encoder.layer.7.output.dense.weight": "model-00003-of-00006.safetensors",
371
+ "deberta.encoder.layer.8.attention.output.LayerNorm.bias": "model-00003-of-00006.safetensors",
372
+ "deberta.encoder.layer.8.attention.output.LayerNorm.weight": "model-00003-of-00006.safetensors",
373
+ "deberta.encoder.layer.8.attention.output.dense.bias": "model-00003-of-00006.safetensors",
374
+ "deberta.encoder.layer.8.attention.output.dense.weight": "model-00003-of-00006.safetensors",
375
+ "deberta.encoder.layer.8.attention.self.key_proj.bias": "model-00003-of-00006.safetensors",
376
+ "deberta.encoder.layer.8.attention.self.key_proj.weight": "model-00003-of-00006.safetensors",
377
+ "deberta.encoder.layer.8.attention.self.query_proj.bias": "model-00003-of-00006.safetensors",
378
+ "deberta.encoder.layer.8.attention.self.query_proj.weight": "model-00003-of-00006.safetensors",
379
+ "deberta.encoder.layer.8.attention.self.value_proj.bias": "model-00003-of-00006.safetensors",
380
+ "deberta.encoder.layer.8.attention.self.value_proj.weight": "model-00003-of-00006.safetensors",
381
+ "deberta.encoder.layer.8.intermediate.dense.bias": "model-00003-of-00006.safetensors",
382
+ "deberta.encoder.layer.8.intermediate.dense.weight": "model-00003-of-00006.safetensors",
383
+ "deberta.encoder.layer.8.output.LayerNorm.bias": "model-00003-of-00006.safetensors",
384
+ "deberta.encoder.layer.8.output.LayerNorm.weight": "model-00003-of-00006.safetensors",
385
+ "deberta.encoder.layer.8.output.dense.bias": "model-00003-of-00006.safetensors",
386
+ "deberta.encoder.layer.8.output.dense.weight": "model-00003-of-00006.safetensors",
387
+ "deberta.encoder.layer.9.attention.output.LayerNorm.bias": "model-00003-of-00006.safetensors",
388
+ "deberta.encoder.layer.9.attention.output.LayerNorm.weight": "model-00003-of-00006.safetensors",
389
+ "deberta.encoder.layer.9.attention.output.dense.bias": "model-00003-of-00006.safetensors",
390
+ "deberta.encoder.layer.9.attention.output.dense.weight": "model-00003-of-00006.safetensors",
391
+ "deberta.encoder.layer.9.attention.self.key_proj.bias": "model-00003-of-00006.safetensors",
392
+ "deberta.encoder.layer.9.attention.self.key_proj.weight": "model-00003-of-00006.safetensors",
393
+ "deberta.encoder.layer.9.attention.self.query_proj.bias": "model-00003-of-00006.safetensors",
394
+ "deberta.encoder.layer.9.attention.self.query_proj.weight": "model-00003-of-00006.safetensors",
395
+ "deberta.encoder.layer.9.attention.self.value_proj.bias": "model-00003-of-00006.safetensors",
396
+ "deberta.encoder.layer.9.attention.self.value_proj.weight": "model-00003-of-00006.safetensors",
397
+ "deberta.encoder.layer.9.intermediate.dense.bias": "model-00003-of-00006.safetensors",
398
+ "deberta.encoder.layer.9.intermediate.dense.weight": "model-00003-of-00006.safetensors",
399
+ "deberta.encoder.layer.9.output.LayerNorm.bias": "model-00003-of-00006.safetensors",
400
+ "deberta.encoder.layer.9.output.LayerNorm.weight": "model-00003-of-00006.safetensors",
401
+ "deberta.encoder.layer.9.output.dense.bias": "model-00003-of-00006.safetensors",
402
+ "deberta.encoder.layer.9.output.dense.weight": "model-00003-of-00006.safetensors",
403
+ "deberta.encoder.rel_embeddings.weight": "model-00006-of-00006.safetensors"
404
+ }
405
+ }