tliu commited on
Commit
62204fb
1 Parent(s): 208cbf2
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c883de63a5f1ce8c385e3328fba3c90d96279d2cdd280e81c3513489b1ff1806
3
+ size 9969676874
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dcce0096e4e6b901c7aa063fd98e69d2e7890b0ed9e41992c8dbcefb1311d94
3
+ size 1227711692
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,578 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 11197177232
4
+ },
5
+ "weight_map": {
6
+ "action_head.0.bias": "pytorch_model-00002-of-00002.bin",
7
+ "action_head.0.weight": "pytorch_model-00002-of-00002.bin",
8
+ "action_head.3.bias": "pytorch_model-00002-of-00002.bin",
9
+ "action_head.3.weight": "pytorch_model-00002-of-00002.bin",
10
+ "lr_scorer.0.bias": "pytorch_model-00002-of-00002.bin",
11
+ "lr_scorer.0.weight": "pytorch_model-00002-of-00002.bin",
12
+ "lr_scorer.3.bias": "pytorch_model-00002-of-00002.bin",
13
+ "lr_scorer.3.weight": "pytorch_model-00002-of-00002.bin",
14
+ "rr_scorer.0.bias": "pytorch_model-00002-of-00002.bin",
15
+ "rr_scorer.0.weight": "pytorch_model-00002-of-00002.bin",
16
+ "rr_scorer.3.bias": "pytorch_model-00002-of-00002.bin",
17
+ "rr_scorer.3.weight": "pytorch_model-00002-of-00002.bin",
18
+ "t5.decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
19
+ "t5.decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
20
+ "t5.decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
21
+ "t5.decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin",
22
+ "t5.decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
23
+ "t5.decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
24
+ "t5.decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
25
+ "t5.decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
26
+ "t5.decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
27
+ "t5.decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
28
+ "t5.decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
29
+ "t5.decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
30
+ "t5.decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
31
+ "t5.decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
32
+ "t5.decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
33
+ "t5.decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
34
+ "t5.decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
35
+ "t5.decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
36
+ "t5.decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
37
+ "t5.decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
38
+ "t5.decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
39
+ "t5.decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
40
+ "t5.decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
41
+ "t5.decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
42
+ "t5.decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
43
+ "t5.decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
44
+ "t5.decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
45
+ "t5.decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
46
+ "t5.decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
47
+ "t5.decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
48
+ "t5.decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
49
+ "t5.decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
50
+ "t5.decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
51
+ "t5.decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
52
+ "t5.decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
53
+ "t5.decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
54
+ "t5.decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
55
+ "t5.decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
56
+ "t5.decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
57
+ "t5.decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
58
+ "t5.decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
59
+ "t5.decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
60
+ "t5.decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
61
+ "t5.decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
62
+ "t5.decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
63
+ "t5.decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
64
+ "t5.decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
65
+ "t5.decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
66
+ "t5.decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
67
+ "t5.decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
68
+ "t5.decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
69
+ "t5.decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
70
+ "t5.decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
71
+ "t5.decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
72
+ "t5.decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
73
+ "t5.decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
74
+ "t5.decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
75
+ "t5.decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
76
+ "t5.decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
77
+ "t5.decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
78
+ "t5.decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
79
+ "t5.decoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
80
+ "t5.decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
81
+ "t5.decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
82
+ "t5.decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
83
+ "t5.decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
84
+ "t5.decoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
85
+ "t5.decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
86
+ "t5.decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
87
+ "t5.decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
88
+ "t5.decoder.block.12.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
89
+ "t5.decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
90
+ "t5.decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
91
+ "t5.decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
92
+ "t5.decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
93
+ "t5.decoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
94
+ "t5.decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
95
+ "t5.decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
96
+ "t5.decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
97
+ "t5.decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
98
+ "t5.decoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
99
+ "t5.decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
100
+ "t5.decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
101
+ "t5.decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
102
+ "t5.decoder.block.13.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
103
+ "t5.decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
104
+ "t5.decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
105
+ "t5.decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
106
+ "t5.decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
107
+ "t5.decoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
108
+ "t5.decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
109
+ "t5.decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
110
+ "t5.decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
111
+ "t5.decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
112
+ "t5.decoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
113
+ "t5.decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
114
+ "t5.decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
115
+ "t5.decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
116
+ "t5.decoder.block.14.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
117
+ "t5.decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
118
+ "t5.decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
119
+ "t5.decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
120
+ "t5.decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
121
+ "t5.decoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
122
+ "t5.decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
123
+ "t5.decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
124
+ "t5.decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
125
+ "t5.decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
126
+ "t5.decoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
127
+ "t5.decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
128
+ "t5.decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
129
+ "t5.decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
130
+ "t5.decoder.block.15.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
131
+ "t5.decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
132
+ "t5.decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
133
+ "t5.decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
134
+ "t5.decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
135
+ "t5.decoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
136
+ "t5.decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
137
+ "t5.decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
138
+ "t5.decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
139
+ "t5.decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
140
+ "t5.decoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
141
+ "t5.decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
142
+ "t5.decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
143
+ "t5.decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
144
+ "t5.decoder.block.16.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
145
+ "t5.decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
146
+ "t5.decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
147
+ "t5.decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
148
+ "t5.decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
149
+ "t5.decoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
150
+ "t5.decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
151
+ "t5.decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
152
+ "t5.decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
153
+ "t5.decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
154
+ "t5.decoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
155
+ "t5.decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
156
+ "t5.decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
157
+ "t5.decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
158
+ "t5.decoder.block.17.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
159
+ "t5.decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
160
+ "t5.decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
161
+ "t5.decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
162
+ "t5.decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
163
+ "t5.decoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
164
+ "t5.decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
165
+ "t5.decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
166
+ "t5.decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
167
+ "t5.decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
168
+ "t5.decoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
169
+ "t5.decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
170
+ "t5.decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
171
+ "t5.decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
172
+ "t5.decoder.block.18.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
173
+ "t5.decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
174
+ "t5.decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
175
+ "t5.decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
176
+ "t5.decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
177
+ "t5.decoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
178
+ "t5.decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
179
+ "t5.decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
180
+ "t5.decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
181
+ "t5.decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
182
+ "t5.decoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
183
+ "t5.decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
184
+ "t5.decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
185
+ "t5.decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
186
+ "t5.decoder.block.19.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
187
+ "t5.decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
188
+ "t5.decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
189
+ "t5.decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
190
+ "t5.decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
191
+ "t5.decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
192
+ "t5.decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
193
+ "t5.decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
194
+ "t5.decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
195
+ "t5.decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
196
+ "t5.decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
197
+ "t5.decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
198
+ "t5.decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
199
+ "t5.decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
200
+ "t5.decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
201
+ "t5.decoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
202
+ "t5.decoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
203
+ "t5.decoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
204
+ "t5.decoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
205
+ "t5.decoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
206
+ "t5.decoder.block.20.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
207
+ "t5.decoder.block.20.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
208
+ "t5.decoder.block.20.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
209
+ "t5.decoder.block.20.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
210
+ "t5.decoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
211
+ "t5.decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
212
+ "t5.decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
213
+ "t5.decoder.block.20.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
214
+ "t5.decoder.block.20.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
215
+ "t5.decoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
216
+ "t5.decoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
217
+ "t5.decoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
218
+ "t5.decoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
219
+ "t5.decoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
220
+ "t5.decoder.block.21.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
221
+ "t5.decoder.block.21.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
222
+ "t5.decoder.block.21.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
223
+ "t5.decoder.block.21.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
224
+ "t5.decoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
225
+ "t5.decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
226
+ "t5.decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
227
+ "t5.decoder.block.21.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
228
+ "t5.decoder.block.21.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
229
+ "t5.decoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
230
+ "t5.decoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
231
+ "t5.decoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
232
+ "t5.decoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
233
+ "t5.decoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
234
+ "t5.decoder.block.22.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
235
+ "t5.decoder.block.22.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
236
+ "t5.decoder.block.22.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
237
+ "t5.decoder.block.22.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
238
+ "t5.decoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
239
+ "t5.decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
240
+ "t5.decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
241
+ "t5.decoder.block.22.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
242
+ "t5.decoder.block.22.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
243
+ "t5.decoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
244
+ "t5.decoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
245
+ "t5.decoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
246
+ "t5.decoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
247
+ "t5.decoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
248
+ "t5.decoder.block.23.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
249
+ "t5.decoder.block.23.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
250
+ "t5.decoder.block.23.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
251
+ "t5.decoder.block.23.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
252
+ "t5.decoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
253
+ "t5.decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
254
+ "t5.decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
255
+ "t5.decoder.block.23.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
256
+ "t5.decoder.block.23.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
257
+ "t5.decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
258
+ "t5.decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
259
+ "t5.decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
260
+ "t5.decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
261
+ "t5.decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
262
+ "t5.decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
263
+ "t5.decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
264
+ "t5.decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
265
+ "t5.decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
266
+ "t5.decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
267
+ "t5.decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
268
+ "t5.decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
269
+ "t5.decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
270
+ "t5.decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
271
+ "t5.decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
272
+ "t5.decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
273
+ "t5.decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
274
+ "t5.decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
275
+ "t5.decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
276
+ "t5.decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
277
+ "t5.decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
278
+ "t5.decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
279
+ "t5.decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
280
+ "t5.decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
281
+ "t5.decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
282
+ "t5.decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
283
+ "t5.decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
284
+ "t5.decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
285
+ "t5.decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
286
+ "t5.decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
287
+ "t5.decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
288
+ "t5.decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
289
+ "t5.decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
290
+ "t5.decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
291
+ "t5.decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
292
+ "t5.decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
293
+ "t5.decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
294
+ "t5.decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
295
+ "t5.decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
296
+ "t5.decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
297
+ "t5.decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
298
+ "t5.decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
299
+ "t5.decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
300
+ "t5.decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
301
+ "t5.decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
302
+ "t5.decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
303
+ "t5.decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
304
+ "t5.decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
305
+ "t5.decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
306
+ "t5.decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
307
+ "t5.decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
308
+ "t5.decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
309
+ "t5.decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
310
+ "t5.decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
311
+ "t5.decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
312
+ "t5.decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
313
+ "t5.decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
314
+ "t5.decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
315
+ "t5.decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
316
+ "t5.decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
317
+ "t5.decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
318
+ "t5.decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
319
+ "t5.decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
320
+ "t5.decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
321
+ "t5.decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
322
+ "t5.decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
323
+ "t5.decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
324
+ "t5.decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
325
+ "t5.decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
326
+ "t5.decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
327
+ "t5.decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
328
+ "t5.decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
329
+ "t5.decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
330
+ "t5.decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
331
+ "t5.decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
332
+ "t5.decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
333
+ "t5.decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
334
+ "t5.decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
335
+ "t5.decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
336
+ "t5.decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
337
+ "t5.decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
338
+ "t5.decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
339
+ "t5.decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
340
+ "t5.decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
341
+ "t5.decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
342
+ "t5.decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
343
+ "t5.decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
344
+ "t5.decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
345
+ "t5.decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
346
+ "t5.decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
347
+ "t5.decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
348
+ "t5.decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
349
+ "t5.decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
350
+ "t5.decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
351
+ "t5.decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
352
+ "t5.decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
353
+ "t5.decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
354
+ "t5.decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
355
+ "t5.decoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
356
+ "t5.decoder.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
357
+ "t5.encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
358
+ "t5.encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
359
+ "t5.encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
360
+ "t5.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin",
361
+ "t5.encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
362
+ "t5.encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
363
+ "t5.encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
364
+ "t5.encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
365
+ "t5.encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
366
+ "t5.encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
367
+ "t5.encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
368
+ "t5.encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
369
+ "t5.encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
370
+ "t5.encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
371
+ "t5.encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
372
+ "t5.encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
373
+ "t5.encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
374
+ "t5.encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
375
+ "t5.encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
376
+ "t5.encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
377
+ "t5.encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
378
+ "t5.encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
379
+ "t5.encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
380
+ "t5.encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
381
+ "t5.encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
382
+ "t5.encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
383
+ "t5.encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
384
+ "t5.encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
385
+ "t5.encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
386
+ "t5.encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
387
+ "t5.encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
388
+ "t5.encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
389
+ "t5.encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
390
+ "t5.encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
391
+ "t5.encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
392
+ "t5.encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
393
+ "t5.encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
394
+ "t5.encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
395
+ "t5.encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
396
+ "t5.encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
397
+ "t5.encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
398
+ "t5.encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
399
+ "t5.encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
400
+ "t5.encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
401
+ "t5.encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
402
+ "t5.encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
403
+ "t5.encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
404
+ "t5.encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
405
+ "t5.encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
406
+ "t5.encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
407
+ "t5.encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
408
+ "t5.encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
409
+ "t5.encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
410
+ "t5.encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
411
+ "t5.encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
412
+ "t5.encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
413
+ "t5.encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
414
+ "t5.encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
415
+ "t5.encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
416
+ "t5.encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
417
+ "t5.encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
418
+ "t5.encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
419
+ "t5.encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
420
+ "t5.encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
421
+ "t5.encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
422
+ "t5.encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
423
+ "t5.encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
424
+ "t5.encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
425
+ "t5.encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
426
+ "t5.encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
427
+ "t5.encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
428
+ "t5.encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
429
+ "t5.encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
430
+ "t5.encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
431
+ "t5.encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
432
+ "t5.encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
433
+ "t5.encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
434
+ "t5.encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
435
+ "t5.encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
436
+ "t5.encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
437
+ "t5.encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
438
+ "t5.encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
439
+ "t5.encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
440
+ "t5.encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
441
+ "t5.encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
442
+ "t5.encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
443
+ "t5.encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
444
+ "t5.encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
445
+ "t5.encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
446
+ "t5.encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
447
+ "t5.encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
448
+ "t5.encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
449
+ "t5.encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
450
+ "t5.encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
451
+ "t5.encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
452
+ "t5.encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
453
+ "t5.encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
454
+ "t5.encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
455
+ "t5.encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
456
+ "t5.encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
457
+ "t5.encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
458
+ "t5.encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
459
+ "t5.encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
460
+ "t5.encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
461
+ "t5.encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
462
+ "t5.encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
463
+ "t5.encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
464
+ "t5.encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
465
+ "t5.encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
466
+ "t5.encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
467
+ "t5.encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
468
+ "t5.encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
469
+ "t5.encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
470
+ "t5.encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
471
+ "t5.encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
472
+ "t5.encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
473
+ "t5.encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
474
+ "t5.encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
475
+ "t5.encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
476
+ "t5.encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
477
+ "t5.encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
478
+ "t5.encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
479
+ "t5.encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
480
+ "t5.encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
481
+ "t5.encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
482
+ "t5.encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
483
+ "t5.encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
484
+ "t5.encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
485
+ "t5.encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
486
+ "t5.encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
487
+ "t5.encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
488
+ "t5.encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
489
+ "t5.encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
490
+ "t5.encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
491
+ "t5.encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
492
+ "t5.encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
493
+ "t5.encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
494
+ "t5.encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
495
+ "t5.encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
496
+ "t5.encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
497
+ "t5.encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
498
+ "t5.encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
499
+ "t5.encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
500
+ "t5.encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
501
+ "t5.encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
502
+ "t5.encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
503
+ "t5.encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
504
+ "t5.encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
505
+ "t5.encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
506
+ "t5.encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
507
+ "t5.encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
508
+ "t5.encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
509
+ "t5.encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
510
+ "t5.encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
511
+ "t5.encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
512
+ "t5.encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
513
+ "t5.encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
514
+ "t5.encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
515
+ "t5.encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
516
+ "t5.encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
517
+ "t5.encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
518
+ "t5.encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
519
+ "t5.encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
520
+ "t5.encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
521
+ "t5.encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
522
+ "t5.encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
523
+ "t5.encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
524
+ "t5.encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
525
+ "t5.encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
526
+ "t5.encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
527
+ "t5.encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
528
+ "t5.encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
529
+ "t5.encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
530
+ "t5.encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
531
+ "t5.encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
532
+ "t5.encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
533
+ "t5.encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
534
+ "t5.encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
535
+ "t5.encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
536
+ "t5.encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
537
+ "t5.encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
538
+ "t5.encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
539
+ "t5.encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
540
+ "t5.encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
541
+ "t5.encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
542
+ "t5.encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
543
+ "t5.encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
544
+ "t5.encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
545
+ "t5.encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
546
+ "t5.encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
547
+ "t5.encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
548
+ "t5.encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
549
+ "t5.encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
550
+ "t5.encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
551
+ "t5.encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
552
+ "t5.encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
553
+ "t5.encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
554
+ "t5.encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
555
+ "t5.encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
556
+ "t5.encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
557
+ "t5.encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
558
+ "t5.encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
559
+ "t5.encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
560
+ "t5.encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
561
+ "t5.encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
562
+ "t5.encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
563
+ "t5.encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
564
+ "t5.encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
565
+ "t5.encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
566
+ "t5.encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
567
+ "t5.encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
568
+ "t5.encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
569
+ "t5.encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
570
+ "t5.encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
571
+ "t5.encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
572
+ "t5.encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
573
+ "t5.encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
574
+ "t5.encoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
575
+ "t5.encoder.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
576
+ "t5.shared.weight": "pytorch_model-00001-of-00002.bin"
577
+ }
578
+ }