ybelkada commited on
Commit
e79e151
1 Parent(s): b0871c5

add sharded weights

Browse files
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5WithLMHeadModel"
4
+ ],
5
+ "d_ff": 16384,
6
+ "d_kv": 128,
7
+ "d_model": 1024,
8
+ "decoder_start_token_id": 0,
9
+ "dropout_rate": 0.1,
10
+ "eos_token_id": 1,
11
+ "initializer_factor": 1.0,
12
+ "is_encoder_decoder": true,
13
+ "layer_norm_epsilon": 1e-06,
14
+ "model_type": "t5",
15
+ "n_positions": 512,
16
+ "num_heads": 32,
17
+ "num_layers": 24,
18
+ "output_past": true,
19
+ "pad_token_id": 0,
20
+ "relative_attention_num_buckets": 32,
21
+ "task_specific_params": {
22
+ "summarization": {
23
+ "early_stopping": true,
24
+ "length_penalty": 2.0,
25
+ "max_length": 200,
26
+ "min_length": 30,
27
+ "no_repeat_ngram_size": 3,
28
+ "num_beams": 4,
29
+ "prefix": "summarize: "
30
+ },
31
+ "translation_en_to_de": {
32
+ "early_stopping": true,
33
+ "max_length": 300,
34
+ "num_beams": 4,
35
+ "prefix": "translate English to German: "
36
+ },
37
+ "translation_en_to_fr": {
38
+ "early_stopping": true,
39
+ "max_length": 300,
40
+ "num_beams": 4,
41
+ "prefix": "translate English to French: "
42
+ },
43
+ "translation_en_to_ro": {
44
+ "early_stopping": true,
45
+ "max_length": 300,
46
+ "num_beams": 4,
47
+ "prefix": "translate English to Romanian: "
48
+ }
49
+ },
50
+ "vocab_size": 32128
51
+ }
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,517 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 11406397440
4
+ },
5
+ "weight_map": {
6
+ "decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model_00002-of-00005.bin",
7
+ "decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model_00002-of-00005.bin",
8
+ "decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model_00002-of-00005.bin",
9
+ "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model_00002-of-00005.bin",
10
+ "decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model_00002-of-00005.bin",
11
+ "decoder.block.0.layer.0.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
12
+ "decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model_00002-of-00005.bin",
13
+ "decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model_00003-of-00005.bin",
14
+ "decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model_00002-of-00005.bin",
15
+ "decoder.block.0.layer.1.EncDecAttention.relative_attention_bias.weight": "pytorch_model_00003-of-00005.bin",
16
+ "decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model_00002-of-00005.bin",
17
+ "decoder.block.0.layer.1.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
18
+ "decoder.block.0.layer.2.DenseReluDense.wi.weight": "pytorch_model_00003-of-00005.bin",
19
+ "decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model_00003-of-00005.bin",
20
+ "decoder.block.0.layer.2.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
21
+ "decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model_00003-of-00005.bin",
22
+ "decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model_00003-of-00005.bin",
23
+ "decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model_00003-of-00005.bin",
24
+ "decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model_00003-of-00005.bin",
25
+ "decoder.block.1.layer.0.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
26
+ "decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model_00003-of-00005.bin",
27
+ "decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model_00003-of-00005.bin",
28
+ "decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model_00003-of-00005.bin",
29
+ "decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model_00003-of-00005.bin",
30
+ "decoder.block.1.layer.1.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
31
+ "decoder.block.1.layer.2.DenseReluDense.wi.weight": "pytorch_model_00003-of-00005.bin",
32
+ "decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model_00003-of-00005.bin",
33
+ "decoder.block.1.layer.2.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
34
+ "decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model_00004-of-00005.bin",
35
+ "decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model_00004-of-00005.bin",
36
+ "decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model_00004-of-00005.bin",
37
+ "decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model_00004-of-00005.bin",
38
+ "decoder.block.10.layer.0.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
39
+ "decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model_00004-of-00005.bin",
40
+ "decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model_00004-of-00005.bin",
41
+ "decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model_00004-of-00005.bin",
42
+ "decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model_00004-of-00005.bin",
43
+ "decoder.block.10.layer.1.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
44
+ "decoder.block.10.layer.2.DenseReluDense.wi.weight": "pytorch_model_00004-of-00005.bin",
45
+ "decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model_00004-of-00005.bin",
46
+ "decoder.block.10.layer.2.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
47
+ "decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model_00004-of-00005.bin",
48
+ "decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model_00004-of-00005.bin",
49
+ "decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model_00004-of-00005.bin",
50
+ "decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model_00004-of-00005.bin",
51
+ "decoder.block.11.layer.0.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
52
+ "decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model_00004-of-00005.bin",
53
+ "decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model_00004-of-00005.bin",
54
+ "decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model_00004-of-00005.bin",
55
+ "decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model_00004-of-00005.bin",
56
+ "decoder.block.11.layer.1.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
57
+ "decoder.block.11.layer.2.DenseReluDense.wi.weight": "pytorch_model_00004-of-00005.bin",
58
+ "decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model_00004-of-00005.bin",
59
+ "decoder.block.11.layer.2.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
60
+ "decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model_00004-of-00005.bin",
61
+ "decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model_00004-of-00005.bin",
62
+ "decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model_00004-of-00005.bin",
63
+ "decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model_00004-of-00005.bin",
64
+ "decoder.block.12.layer.0.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
65
+ "decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model_00004-of-00005.bin",
66
+ "decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model_00004-of-00005.bin",
67
+ "decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model_00004-of-00005.bin",
68
+ "decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model_00004-of-00005.bin",
69
+ "decoder.block.12.layer.1.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
70
+ "decoder.block.12.layer.2.DenseReluDense.wi.weight": "pytorch_model_00004-of-00005.bin",
71
+ "decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model_00004-of-00005.bin",
72
+ "decoder.block.12.layer.2.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
73
+ "decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model_00004-of-00005.bin",
74
+ "decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model_00004-of-00005.bin",
75
+ "decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model_00004-of-00005.bin",
76
+ "decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model_00004-of-00005.bin",
77
+ "decoder.block.13.layer.0.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
78
+ "decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model_00004-of-00005.bin",
79
+ "decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model_00004-of-00005.bin",
80
+ "decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model_00004-of-00005.bin",
81
+ "decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model_00004-of-00005.bin",
82
+ "decoder.block.13.layer.1.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
83
+ "decoder.block.13.layer.2.DenseReluDense.wi.weight": "pytorch_model_00004-of-00005.bin",
84
+ "decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model_00004-of-00005.bin",
85
+ "decoder.block.13.layer.2.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
86
+ "decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model_00004-of-00005.bin",
87
+ "decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model_00004-of-00005.bin",
88
+ "decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model_00004-of-00005.bin",
89
+ "decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model_00004-of-00005.bin",
90
+ "decoder.block.14.layer.0.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
91
+ "decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model_00004-of-00005.bin",
92
+ "decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model_00004-of-00005.bin",
93
+ "decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model_00004-of-00005.bin",
94
+ "decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model_00004-of-00005.bin",
95
+ "decoder.block.14.layer.1.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
96
+ "decoder.block.14.layer.2.DenseReluDense.wi.weight": "pytorch_model_00004-of-00005.bin",
97
+ "decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model_00004-of-00005.bin",
98
+ "decoder.block.14.layer.2.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
99
+ "decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model_00004-of-00005.bin",
100
+ "decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model_00004-of-00005.bin",
101
+ "decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model_00004-of-00005.bin",
102
+ "decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model_00004-of-00005.bin",
103
+ "decoder.block.15.layer.0.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
104
+ "decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model_00004-of-00005.bin",
105
+ "decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model_00004-of-00005.bin",
106
+ "decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model_00004-of-00005.bin",
107
+ "decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model_00004-of-00005.bin",
108
+ "decoder.block.15.layer.1.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
109
+ "decoder.block.15.layer.2.DenseReluDense.wi.weight": "pytorch_model_00004-of-00005.bin",
110
+ "decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model_00004-of-00005.bin",
111
+ "decoder.block.15.layer.2.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
112
+ "decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model_00004-of-00005.bin",
113
+ "decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model_00005-of-00005.bin",
114
+ "decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model_00004-of-00005.bin",
115
+ "decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model_00004-of-00005.bin",
116
+ "decoder.block.16.layer.0.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
117
+ "decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model_00005-of-00005.bin",
118
+ "decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model_00005-of-00005.bin",
119
+ "decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model_00005-of-00005.bin",
120
+ "decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model_00005-of-00005.bin",
121
+ "decoder.block.16.layer.1.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
122
+ "decoder.block.16.layer.2.DenseReluDense.wi.weight": "pytorch_model_00005-of-00005.bin",
123
+ "decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model_00005-of-00005.bin",
124
+ "decoder.block.16.layer.2.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
125
+ "decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model_00005-of-00005.bin",
126
+ "decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model_00005-of-00005.bin",
127
+ "decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model_00005-of-00005.bin",
128
+ "decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model_00005-of-00005.bin",
129
+ "decoder.block.17.layer.0.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
130
+ "decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model_00005-of-00005.bin",
131
+ "decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model_00005-of-00005.bin",
132
+ "decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model_00005-of-00005.bin",
133
+ "decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model_00005-of-00005.bin",
134
+ "decoder.block.17.layer.1.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
135
+ "decoder.block.17.layer.2.DenseReluDense.wi.weight": "pytorch_model_00005-of-00005.bin",
136
+ "decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model_00005-of-00005.bin",
137
+ "decoder.block.17.layer.2.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
138
+ "decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model_00005-of-00005.bin",
139
+ "decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model_00005-of-00005.bin",
140
+ "decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model_00005-of-00005.bin",
141
+ "decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model_00005-of-00005.bin",
142
+ "decoder.block.18.layer.0.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
143
+ "decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model_00005-of-00005.bin",
144
+ "decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model_00005-of-00005.bin",
145
+ "decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model_00005-of-00005.bin",
146
+ "decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model_00005-of-00005.bin",
147
+ "decoder.block.18.layer.1.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
148
+ "decoder.block.18.layer.2.DenseReluDense.wi.weight": "pytorch_model_00005-of-00005.bin",
149
+ "decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model_00005-of-00005.bin",
150
+ "decoder.block.18.layer.2.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
151
+ "decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model_00005-of-00005.bin",
152
+ "decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model_00005-of-00005.bin",
153
+ "decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model_00005-of-00005.bin",
154
+ "decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model_00005-of-00005.bin",
155
+ "decoder.block.19.layer.0.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
156
+ "decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model_00005-of-00005.bin",
157
+ "decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model_00005-of-00005.bin",
158
+ "decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model_00005-of-00005.bin",
159
+ "decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model_00005-of-00005.bin",
160
+ "decoder.block.19.layer.1.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
161
+ "decoder.block.19.layer.2.DenseReluDense.wi.weight": "pytorch_model_00005-of-00005.bin",
162
+ "decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model_00005-of-00005.bin",
163
+ "decoder.block.19.layer.2.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
164
+ "decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model_00003-of-00005.bin",
165
+ "decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model_00003-of-00005.bin",
166
+ "decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model_00003-of-00005.bin",
167
+ "decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model_00003-of-00005.bin",
168
+ "decoder.block.2.layer.0.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
169
+ "decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model_00003-of-00005.bin",
170
+ "decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model_00003-of-00005.bin",
171
+ "decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model_00003-of-00005.bin",
172
+ "decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model_00003-of-00005.bin",
173
+ "decoder.block.2.layer.1.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
174
+ "decoder.block.2.layer.2.DenseReluDense.wi.weight": "pytorch_model_00003-of-00005.bin",
175
+ "decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model_00003-of-00005.bin",
176
+ "decoder.block.2.layer.2.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
177
+ "decoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model_00005-of-00005.bin",
178
+ "decoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model_00005-of-00005.bin",
179
+ "decoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model_00005-of-00005.bin",
180
+ "decoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model_00005-of-00005.bin",
181
+ "decoder.block.20.layer.0.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
182
+ "decoder.block.20.layer.1.EncDecAttention.k.weight": "pytorch_model_00005-of-00005.bin",
183
+ "decoder.block.20.layer.1.EncDecAttention.o.weight": "pytorch_model_00005-of-00005.bin",
184
+ "decoder.block.20.layer.1.EncDecAttention.q.weight": "pytorch_model_00005-of-00005.bin",
185
+ "decoder.block.20.layer.1.EncDecAttention.v.weight": "pytorch_model_00005-of-00005.bin",
186
+ "decoder.block.20.layer.1.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
187
+ "decoder.block.20.layer.2.DenseReluDense.wi.weight": "pytorch_model_00005-of-00005.bin",
188
+ "decoder.block.20.layer.2.DenseReluDense.wo.weight": "pytorch_model_00005-of-00005.bin",
189
+ "decoder.block.20.layer.2.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
190
+ "decoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model_00005-of-00005.bin",
191
+ "decoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model_00005-of-00005.bin",
192
+ "decoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model_00005-of-00005.bin",
193
+ "decoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model_00005-of-00005.bin",
194
+ "decoder.block.21.layer.0.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
195
+ "decoder.block.21.layer.1.EncDecAttention.k.weight": "pytorch_model_00005-of-00005.bin",
196
+ "decoder.block.21.layer.1.EncDecAttention.o.weight": "pytorch_model_00005-of-00005.bin",
197
+ "decoder.block.21.layer.1.EncDecAttention.q.weight": "pytorch_model_00005-of-00005.bin",
198
+ "decoder.block.21.layer.1.EncDecAttention.v.weight": "pytorch_model_00005-of-00005.bin",
199
+ "decoder.block.21.layer.1.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
200
+ "decoder.block.21.layer.2.DenseReluDense.wi.weight": "pytorch_model_00005-of-00005.bin",
201
+ "decoder.block.21.layer.2.DenseReluDense.wo.weight": "pytorch_model_00005-of-00005.bin",
202
+ "decoder.block.21.layer.2.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
203
+ "decoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model_00005-of-00005.bin",
204
+ "decoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model_00005-of-00005.bin",
205
+ "decoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model_00005-of-00005.bin",
206
+ "decoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model_00005-of-00005.bin",
207
+ "decoder.block.22.layer.0.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
208
+ "decoder.block.22.layer.1.EncDecAttention.k.weight": "pytorch_model_00005-of-00005.bin",
209
+ "decoder.block.22.layer.1.EncDecAttention.o.weight": "pytorch_model_00005-of-00005.bin",
210
+ "decoder.block.22.layer.1.EncDecAttention.q.weight": "pytorch_model_00005-of-00005.bin",
211
+ "decoder.block.22.layer.1.EncDecAttention.v.weight": "pytorch_model_00005-of-00005.bin",
212
+ "decoder.block.22.layer.1.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
213
+ "decoder.block.22.layer.2.DenseReluDense.wi.weight": "pytorch_model_00005-of-00005.bin",
214
+ "decoder.block.22.layer.2.DenseReluDense.wo.weight": "pytorch_model_00005-of-00005.bin",
215
+ "decoder.block.22.layer.2.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
216
+ "decoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model_00005-of-00005.bin",
217
+ "decoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model_00005-of-00005.bin",
218
+ "decoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model_00005-of-00005.bin",
219
+ "decoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model_00005-of-00005.bin",
220
+ "decoder.block.23.layer.0.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
221
+ "decoder.block.23.layer.1.EncDecAttention.k.weight": "pytorch_model_00005-of-00005.bin",
222
+ "decoder.block.23.layer.1.EncDecAttention.o.weight": "pytorch_model_00005-of-00005.bin",
223
+ "decoder.block.23.layer.1.EncDecAttention.q.weight": "pytorch_model_00005-of-00005.bin",
224
+ "decoder.block.23.layer.1.EncDecAttention.v.weight": "pytorch_model_00005-of-00005.bin",
225
+ "decoder.block.23.layer.1.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
226
+ "decoder.block.23.layer.2.DenseReluDense.wi.weight": "pytorch_model_00005-of-00005.bin",
227
+ "decoder.block.23.layer.2.DenseReluDense.wo.weight": "pytorch_model_00005-of-00005.bin",
228
+ "decoder.block.23.layer.2.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
229
+ "decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model_00003-of-00005.bin",
230
+ "decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model_00003-of-00005.bin",
231
+ "decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model_00003-of-00005.bin",
232
+ "decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model_00003-of-00005.bin",
233
+ "decoder.block.3.layer.0.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
234
+ "decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model_00003-of-00005.bin",
235
+ "decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model_00003-of-00005.bin",
236
+ "decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model_00003-of-00005.bin",
237
+ "decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model_00003-of-00005.bin",
238
+ "decoder.block.3.layer.1.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
239
+ "decoder.block.3.layer.2.DenseReluDense.wi.weight": "pytorch_model_00003-of-00005.bin",
240
+ "decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model_00003-of-00005.bin",
241
+ "decoder.block.3.layer.2.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
242
+ "decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model_00003-of-00005.bin",
243
+ "decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model_00003-of-00005.bin",
244
+ "decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model_00003-of-00005.bin",
245
+ "decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model_00003-of-00005.bin",
246
+ "decoder.block.4.layer.0.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
247
+ "decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model_00003-of-00005.bin",
248
+ "decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model_00003-of-00005.bin",
249
+ "decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model_00003-of-00005.bin",
250
+ "decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model_00003-of-00005.bin",
251
+ "decoder.block.4.layer.1.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
252
+ "decoder.block.4.layer.2.DenseReluDense.wi.weight": "pytorch_model_00003-of-00005.bin",
253
+ "decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model_00003-of-00005.bin",
254
+ "decoder.block.4.layer.2.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
255
+ "decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model_00003-of-00005.bin",
256
+ "decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model_00003-of-00005.bin",
257
+ "decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model_00003-of-00005.bin",
258
+ "decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model_00003-of-00005.bin",
259
+ "decoder.block.5.layer.0.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
260
+ "decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model_00003-of-00005.bin",
261
+ "decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model_00003-of-00005.bin",
262
+ "decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model_00003-of-00005.bin",
263
+ "decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model_00003-of-00005.bin",
264
+ "decoder.block.5.layer.1.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
265
+ "decoder.block.5.layer.2.DenseReluDense.wi.weight": "pytorch_model_00003-of-00005.bin",
266
+ "decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model_00003-of-00005.bin",
267
+ "decoder.block.5.layer.2.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
268
+ "decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model_00003-of-00005.bin",
269
+ "decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model_00003-of-00005.bin",
270
+ "decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model_00003-of-00005.bin",
271
+ "decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model_00003-of-00005.bin",
272
+ "decoder.block.6.layer.0.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
273
+ "decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model_00003-of-00005.bin",
274
+ "decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model_00003-of-00005.bin",
275
+ "decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model_00003-of-00005.bin",
276
+ "decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model_00003-of-00005.bin",
277
+ "decoder.block.6.layer.1.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
278
+ "decoder.block.6.layer.2.DenseReluDense.wi.weight": "pytorch_model_00003-of-00005.bin",
279
+ "decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model_00003-of-00005.bin",
280
+ "decoder.block.6.layer.2.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
281
+ "decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model_00003-of-00005.bin",
282
+ "decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model_00003-of-00005.bin",
283
+ "decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model_00003-of-00005.bin",
284
+ "decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model_00003-of-00005.bin",
285
+ "decoder.block.7.layer.0.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
286
+ "decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model_00003-of-00005.bin",
287
+ "decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model_00003-of-00005.bin",
288
+ "decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model_00003-of-00005.bin",
289
+ "decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model_00003-of-00005.bin",
290
+ "decoder.block.7.layer.1.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
291
+ "decoder.block.7.layer.2.DenseReluDense.wi.weight": "pytorch_model_00003-of-00005.bin",
292
+ "decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model_00003-of-00005.bin",
293
+ "decoder.block.7.layer.2.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
294
+ "decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model_00003-of-00005.bin",
295
+ "decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model_00003-of-00005.bin",
296
+ "decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model_00003-of-00005.bin",
297
+ "decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model_00003-of-00005.bin",
298
+ "decoder.block.8.layer.0.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
299
+ "decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model_00004-of-00005.bin",
300
+ "decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model_00004-of-00005.bin",
301
+ "decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model_00004-of-00005.bin",
302
+ "decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model_00004-of-00005.bin",
303
+ "decoder.block.8.layer.1.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
304
+ "decoder.block.8.layer.2.DenseReluDense.wi.weight": "pytorch_model_00004-of-00005.bin",
305
+ "decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model_00004-of-00005.bin",
306
+ "decoder.block.8.layer.2.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
307
+ "decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model_00004-of-00005.bin",
308
+ "decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model_00004-of-00005.bin",
309
+ "decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model_00004-of-00005.bin",
310
+ "decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model_00004-of-00005.bin",
311
+ "decoder.block.9.layer.0.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
312
+ "decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model_00004-of-00005.bin",
313
+ "decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model_00004-of-00005.bin",
314
+ "decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model_00004-of-00005.bin",
315
+ "decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model_00004-of-00005.bin",
316
+ "decoder.block.9.layer.1.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
317
+ "decoder.block.9.layer.2.DenseReluDense.wi.weight": "pytorch_model_00004-of-00005.bin",
318
+ "decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model_00004-of-00005.bin",
319
+ "decoder.block.9.layer.2.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
320
+ "decoder.final_layer_norm.weight": "pytorch_model_00005-of-00005.bin",
321
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model_00001-of-00005.bin",
322
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model_00001-of-00005.bin",
323
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model_00001-of-00005.bin",
324
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model_00001-of-00005.bin",
325
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model_00001-of-00005.bin",
326
+ "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
327
+ "encoder.block.0.layer.1.DenseReluDense.wi.weight": "pytorch_model_00001-of-00005.bin",
328
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model_00001-of-00005.bin",
329
+ "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
330
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model_00001-of-00005.bin",
331
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model_00001-of-00005.bin",
332
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model_00001-of-00005.bin",
333
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model_00001-of-00005.bin",
334
+ "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
335
+ "encoder.block.1.layer.1.DenseReluDense.wi.weight": "pytorch_model_00001-of-00005.bin",
336
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model_00001-of-00005.bin",
337
+ "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
338
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model_00001-of-00005.bin",
339
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model_00001-of-00005.bin",
340
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model_00001-of-00005.bin",
341
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model_00001-of-00005.bin",
342
+ "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
343
+ "encoder.block.10.layer.1.DenseReluDense.wi.weight": "pytorch_model_00001-of-00005.bin",
344
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model_00001-of-00005.bin",
345
+ "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
346
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model_00001-of-00005.bin",
347
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model_00001-of-00005.bin",
348
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model_00001-of-00005.bin",
349
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model_00001-of-00005.bin",
350
+ "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
351
+ "encoder.block.11.layer.1.DenseReluDense.wi.weight": "pytorch_model_00001-of-00005.bin",
352
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model_00001-of-00005.bin",
353
+ "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
354
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model_00001-of-00005.bin",
355
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model_00001-of-00005.bin",
356
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model_00001-of-00005.bin",
357
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model_00001-of-00005.bin",
358
+ "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
359
+ "encoder.block.12.layer.1.DenseReluDense.wi.weight": "pytorch_model_00002-of-00005.bin",
360
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model_00002-of-00005.bin",
361
+ "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
362
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model_00002-of-00005.bin",
363
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model_00002-of-00005.bin",
364
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model_00002-of-00005.bin",
365
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model_00002-of-00005.bin",
366
+ "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
367
+ "encoder.block.13.layer.1.DenseReluDense.wi.weight": "pytorch_model_00002-of-00005.bin",
368
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model_00002-of-00005.bin",
369
+ "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
370
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model_00002-of-00005.bin",
371
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model_00002-of-00005.bin",
372
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model_00002-of-00005.bin",
373
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model_00002-of-00005.bin",
374
+ "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
375
+ "encoder.block.14.layer.1.DenseReluDense.wi.weight": "pytorch_model_00002-of-00005.bin",
376
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model_00002-of-00005.bin",
377
+ "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
378
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model_00002-of-00005.bin",
379
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model_00002-of-00005.bin",
380
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model_00002-of-00005.bin",
381
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model_00002-of-00005.bin",
382
+ "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
383
+ "encoder.block.15.layer.1.DenseReluDense.wi.weight": "pytorch_model_00002-of-00005.bin",
384
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model_00002-of-00005.bin",
385
+ "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
386
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model_00002-of-00005.bin",
387
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model_00002-of-00005.bin",
388
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model_00002-of-00005.bin",
389
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model_00002-of-00005.bin",
390
+ "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
391
+ "encoder.block.16.layer.1.DenseReluDense.wi.weight": "pytorch_model_00002-of-00005.bin",
392
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model_00002-of-00005.bin",
393
+ "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
394
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model_00002-of-00005.bin",
395
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model_00002-of-00005.bin",
396
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model_00002-of-00005.bin",
397
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model_00002-of-00005.bin",
398
+ "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
399
+ "encoder.block.17.layer.1.DenseReluDense.wi.weight": "pytorch_model_00002-of-00005.bin",
400
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model_00002-of-00005.bin",
401
+ "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
402
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model_00002-of-00005.bin",
403
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model_00002-of-00005.bin",
404
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model_00002-of-00005.bin",
405
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model_00002-of-00005.bin",
406
+ "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
407
+ "encoder.block.18.layer.1.DenseReluDense.wi.weight": "pytorch_model_00002-of-00005.bin",
408
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model_00002-of-00005.bin",
409
+ "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
410
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model_00002-of-00005.bin",
411
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model_00002-of-00005.bin",
412
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model_00002-of-00005.bin",
413
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model_00002-of-00005.bin",
414
+ "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
415
+ "encoder.block.19.layer.1.DenseReluDense.wi.weight": "pytorch_model_00002-of-00005.bin",
416
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model_00002-of-00005.bin",
417
+ "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
418
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model_00001-of-00005.bin",
419
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model_00001-of-00005.bin",
420
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model_00001-of-00005.bin",
421
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model_00001-of-00005.bin",
422
+ "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
423
+ "encoder.block.2.layer.1.DenseReluDense.wi.weight": "pytorch_model_00001-of-00005.bin",
424
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model_00001-of-00005.bin",
425
+ "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
426
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model_00002-of-00005.bin",
427
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model_00002-of-00005.bin",
428
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model_00002-of-00005.bin",
429
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model_00002-of-00005.bin",
430
+ "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
431
+ "encoder.block.20.layer.1.DenseReluDense.wi.weight": "pytorch_model_00002-of-00005.bin",
432
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model_00002-of-00005.bin",
433
+ "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
434
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model_00002-of-00005.bin",
435
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model_00002-of-00005.bin",
436
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model_00002-of-00005.bin",
437
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model_00002-of-00005.bin",
438
+ "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
439
+ "encoder.block.21.layer.1.DenseReluDense.wi.weight": "pytorch_model_00002-of-00005.bin",
440
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model_00002-of-00005.bin",
441
+ "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
442
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model_00002-of-00005.bin",
443
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model_00002-of-00005.bin",
444
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model_00002-of-00005.bin",
445
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model_00002-of-00005.bin",
446
+ "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
447
+ "encoder.block.22.layer.1.DenseReluDense.wi.weight": "pytorch_model_00002-of-00005.bin",
448
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model_00002-of-00005.bin",
449
+ "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
450
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model_00002-of-00005.bin",
451
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model_00002-of-00005.bin",
452
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model_00002-of-00005.bin",
453
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model_00002-of-00005.bin",
454
+ "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
455
+ "encoder.block.23.layer.1.DenseReluDense.wi.weight": "pytorch_model_00002-of-00005.bin",
456
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model_00002-of-00005.bin",
457
+ "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
458
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model_00001-of-00005.bin",
459
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model_00001-of-00005.bin",
460
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model_00001-of-00005.bin",
461
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model_00001-of-00005.bin",
462
+ "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
463
+ "encoder.block.3.layer.1.DenseReluDense.wi.weight": "pytorch_model_00001-of-00005.bin",
464
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model_00001-of-00005.bin",
465
+ "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
466
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model_00001-of-00005.bin",
467
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model_00001-of-00005.bin",
468
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model_00001-of-00005.bin",
469
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model_00001-of-00005.bin",
470
+ "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
471
+ "encoder.block.4.layer.1.DenseReluDense.wi.weight": "pytorch_model_00001-of-00005.bin",
472
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model_00001-of-00005.bin",
473
+ "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
474
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model_00001-of-00005.bin",
475
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model_00001-of-00005.bin",
476
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model_00001-of-00005.bin",
477
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model_00001-of-00005.bin",
478
+ "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
479
+ "encoder.block.5.layer.1.DenseReluDense.wi.weight": "pytorch_model_00001-of-00005.bin",
480
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model_00001-of-00005.bin",
481
+ "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
482
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model_00001-of-00005.bin",
483
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model_00001-of-00005.bin",
484
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model_00001-of-00005.bin",
485
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model_00001-of-00005.bin",
486
+ "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
487
+ "encoder.block.6.layer.1.DenseReluDense.wi.weight": "pytorch_model_00001-of-00005.bin",
488
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model_00001-of-00005.bin",
489
+ "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
490
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model_00001-of-00005.bin",
491
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model_00001-of-00005.bin",
492
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model_00001-of-00005.bin",
493
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model_00001-of-00005.bin",
494
+ "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
495
+ "encoder.block.7.layer.1.DenseReluDense.wi.weight": "pytorch_model_00001-of-00005.bin",
496
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model_00001-of-00005.bin",
497
+ "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
498
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model_00001-of-00005.bin",
499
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model_00001-of-00005.bin",
500
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model_00001-of-00005.bin",
501
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model_00001-of-00005.bin",
502
+ "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
503
+ "encoder.block.8.layer.1.DenseReluDense.wi.weight": "pytorch_model_00001-of-00005.bin",
504
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model_00001-of-00005.bin",
505
+ "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
506
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model_00001-of-00005.bin",
507
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model_00001-of-00005.bin",
508
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model_00001-of-00005.bin",
509
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model_00001-of-00005.bin",
510
+ "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
511
+ "encoder.block.9.layer.1.DenseReluDense.wi.weight": "pytorch_model_00001-of-00005.bin",
512
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model_00001-of-00005.bin",
513
+ "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
514
+ "encoder.final_layer_norm.weight": "pytorch_model_00002-of-00005.bin",
515
+ "shared.weight": "pytorch_model_00001-of-00005.bin"
516
+ }
517
+ }
pytorch_model.index.json ADDED
@@ -0,0 +1,517 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 11406397440
4
+ },
5
+ "weight_map": {
6
+ "decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model_00002-of-00005.bin",
7
+ "decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model_00002-of-00005.bin",
8
+ "decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model_00002-of-00005.bin",
9
+ "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model_00002-of-00005.bin",
10
+ "decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model_00002-of-00005.bin",
11
+ "decoder.block.0.layer.0.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
12
+ "decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model_00002-of-00005.bin",
13
+ "decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model_00003-of-00005.bin",
14
+ "decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model_00002-of-00005.bin",
15
+ "decoder.block.0.layer.1.EncDecAttention.relative_attention_bias.weight": "pytorch_model_00003-of-00005.bin",
16
+ "decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model_00002-of-00005.bin",
17
+ "decoder.block.0.layer.1.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
18
+ "decoder.block.0.layer.2.DenseReluDense.wi.weight": "pytorch_model_00003-of-00005.bin",
19
+ "decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model_00003-of-00005.bin",
20
+ "decoder.block.0.layer.2.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
21
+ "decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model_00003-of-00005.bin",
22
+ "decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model_00003-of-00005.bin",
23
+ "decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model_00003-of-00005.bin",
24
+ "decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model_00003-of-00005.bin",
25
+ "decoder.block.1.layer.0.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
26
+ "decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model_00003-of-00005.bin",
27
+ "decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model_00003-of-00005.bin",
28
+ "decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model_00003-of-00005.bin",
29
+ "decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model_00003-of-00005.bin",
30
+ "decoder.block.1.layer.1.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
31
+ "decoder.block.1.layer.2.DenseReluDense.wi.weight": "pytorch_model_00003-of-00005.bin",
32
+ "decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model_00003-of-00005.bin",
33
+ "decoder.block.1.layer.2.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
34
+ "decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model_00004-of-00005.bin",
35
+ "decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model_00004-of-00005.bin",
36
+ "decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model_00004-of-00005.bin",
37
+ "decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model_00004-of-00005.bin",
38
+ "decoder.block.10.layer.0.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
39
+ "decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model_00004-of-00005.bin",
40
+ "decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model_00004-of-00005.bin",
41
+ "decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model_00004-of-00005.bin",
42
+ "decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model_00004-of-00005.bin",
43
+ "decoder.block.10.layer.1.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
44
+ "decoder.block.10.layer.2.DenseReluDense.wi.weight": "pytorch_model_00004-of-00005.bin",
45
+ "decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model_00004-of-00005.bin",
46
+ "decoder.block.10.layer.2.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
47
+ "decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model_00004-of-00005.bin",
48
+ "decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model_00004-of-00005.bin",
49
+ "decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model_00004-of-00005.bin",
50
+ "decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model_00004-of-00005.bin",
51
+ "decoder.block.11.layer.0.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
52
+ "decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model_00004-of-00005.bin",
53
+ "decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model_00004-of-00005.bin",
54
+ "decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model_00004-of-00005.bin",
55
+ "decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model_00004-of-00005.bin",
56
+ "decoder.block.11.layer.1.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
57
+ "decoder.block.11.layer.2.DenseReluDense.wi.weight": "pytorch_model_00004-of-00005.bin",
58
+ "decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model_00004-of-00005.bin",
59
+ "decoder.block.11.layer.2.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
60
+ "decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model_00004-of-00005.bin",
61
+ "decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model_00004-of-00005.bin",
62
+ "decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model_00004-of-00005.bin",
63
+ "decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model_00004-of-00005.bin",
64
+ "decoder.block.12.layer.0.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
65
+ "decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model_00004-of-00005.bin",
66
+ "decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model_00004-of-00005.bin",
67
+ "decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model_00004-of-00005.bin",
68
+ "decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model_00004-of-00005.bin",
69
+ "decoder.block.12.layer.1.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
70
+ "decoder.block.12.layer.2.DenseReluDense.wi.weight": "pytorch_model_00004-of-00005.bin",
71
+ "decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model_00004-of-00005.bin",
72
+ "decoder.block.12.layer.2.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
73
+ "decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model_00004-of-00005.bin",
74
+ "decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model_00004-of-00005.bin",
75
+ "decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model_00004-of-00005.bin",
76
+ "decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model_00004-of-00005.bin",
77
+ "decoder.block.13.layer.0.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
78
+ "decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model_00004-of-00005.bin",
79
+ "decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model_00004-of-00005.bin",
80
+ "decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model_00004-of-00005.bin",
81
+ "decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model_00004-of-00005.bin",
82
+ "decoder.block.13.layer.1.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
83
+ "decoder.block.13.layer.2.DenseReluDense.wi.weight": "pytorch_model_00004-of-00005.bin",
84
+ "decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model_00004-of-00005.bin",
85
+ "decoder.block.13.layer.2.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
86
+ "decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model_00004-of-00005.bin",
87
+ "decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model_00004-of-00005.bin",
88
+ "decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model_00004-of-00005.bin",
89
+ "decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model_00004-of-00005.bin",
90
+ "decoder.block.14.layer.0.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
91
+ "decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model_00004-of-00005.bin",
92
+ "decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model_00004-of-00005.bin",
93
+ "decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model_00004-of-00005.bin",
94
+ "decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model_00004-of-00005.bin",
95
+ "decoder.block.14.layer.1.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
96
+ "decoder.block.14.layer.2.DenseReluDense.wi.weight": "pytorch_model_00004-of-00005.bin",
97
+ "decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model_00004-of-00005.bin",
98
+ "decoder.block.14.layer.2.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
99
+ "decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model_00004-of-00005.bin",
100
+ "decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model_00004-of-00005.bin",
101
+ "decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model_00004-of-00005.bin",
102
+ "decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model_00004-of-00005.bin",
103
+ "decoder.block.15.layer.0.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
104
+ "decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model_00004-of-00005.bin",
105
+ "decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model_00004-of-00005.bin",
106
+ "decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model_00004-of-00005.bin",
107
+ "decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model_00004-of-00005.bin",
108
+ "decoder.block.15.layer.1.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
109
+ "decoder.block.15.layer.2.DenseReluDense.wi.weight": "pytorch_model_00004-of-00005.bin",
110
+ "decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model_00004-of-00005.bin",
111
+ "decoder.block.15.layer.2.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
112
+ "decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model_00004-of-00005.bin",
113
+ "decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model_00005-of-00005.bin",
114
+ "decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model_00004-of-00005.bin",
115
+ "decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model_00004-of-00005.bin",
116
+ "decoder.block.16.layer.0.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
117
+ "decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model_00005-of-00005.bin",
118
+ "decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model_00005-of-00005.bin",
119
+ "decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model_00005-of-00005.bin",
120
+ "decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model_00005-of-00005.bin",
121
+ "decoder.block.16.layer.1.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
122
+ "decoder.block.16.layer.2.DenseReluDense.wi.weight": "pytorch_model_00005-of-00005.bin",
123
+ "decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model_00005-of-00005.bin",
124
+ "decoder.block.16.layer.2.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
125
+ "decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model_00005-of-00005.bin",
126
+ "decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model_00005-of-00005.bin",
127
+ "decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model_00005-of-00005.bin",
128
+ "decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model_00005-of-00005.bin",
129
+ "decoder.block.17.layer.0.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
130
+ "decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model_00005-of-00005.bin",
131
+ "decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model_00005-of-00005.bin",
132
+ "decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model_00005-of-00005.bin",
133
+ "decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model_00005-of-00005.bin",
134
+ "decoder.block.17.layer.1.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
135
+ "decoder.block.17.layer.2.DenseReluDense.wi.weight": "pytorch_model_00005-of-00005.bin",
136
+ "decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model_00005-of-00005.bin",
137
+ "decoder.block.17.layer.2.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
138
+ "decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model_00005-of-00005.bin",
139
+ "decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model_00005-of-00005.bin",
140
+ "decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model_00005-of-00005.bin",
141
+ "decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model_00005-of-00005.bin",
142
+ "decoder.block.18.layer.0.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
143
+ "decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model_00005-of-00005.bin",
144
+ "decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model_00005-of-00005.bin",
145
+ "decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model_00005-of-00005.bin",
146
+ "decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model_00005-of-00005.bin",
147
+ "decoder.block.18.layer.1.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
148
+ "decoder.block.18.layer.2.DenseReluDense.wi.weight": "pytorch_model_00005-of-00005.bin",
149
+ "decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model_00005-of-00005.bin",
150
+ "decoder.block.18.layer.2.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
151
+ "decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model_00005-of-00005.bin",
152
+ "decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model_00005-of-00005.bin",
153
+ "decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model_00005-of-00005.bin",
154
+ "decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model_00005-of-00005.bin",
155
+ "decoder.block.19.layer.0.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
156
+ "decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model_00005-of-00005.bin",
157
+ "decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model_00005-of-00005.bin",
158
+ "decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model_00005-of-00005.bin",
159
+ "decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model_00005-of-00005.bin",
160
+ "decoder.block.19.layer.1.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
161
+ "decoder.block.19.layer.2.DenseReluDense.wi.weight": "pytorch_model_00005-of-00005.bin",
162
+ "decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model_00005-of-00005.bin",
163
+ "decoder.block.19.layer.2.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
164
+ "decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model_00003-of-00005.bin",
165
+ "decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model_00003-of-00005.bin",
166
+ "decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model_00003-of-00005.bin",
167
+ "decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model_00003-of-00005.bin",
168
+ "decoder.block.2.layer.0.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
169
+ "decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model_00003-of-00005.bin",
170
+ "decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model_00003-of-00005.bin",
171
+ "decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model_00003-of-00005.bin",
172
+ "decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model_00003-of-00005.bin",
173
+ "decoder.block.2.layer.1.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
174
+ "decoder.block.2.layer.2.DenseReluDense.wi.weight": "pytorch_model_00003-of-00005.bin",
175
+ "decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model_00003-of-00005.bin",
176
+ "decoder.block.2.layer.2.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
177
+ "decoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model_00005-of-00005.bin",
178
+ "decoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model_00005-of-00005.bin",
179
+ "decoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model_00005-of-00005.bin",
180
+ "decoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model_00005-of-00005.bin",
181
+ "decoder.block.20.layer.0.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
182
+ "decoder.block.20.layer.1.EncDecAttention.k.weight": "pytorch_model_00005-of-00005.bin",
183
+ "decoder.block.20.layer.1.EncDecAttention.o.weight": "pytorch_model_00005-of-00005.bin",
184
+ "decoder.block.20.layer.1.EncDecAttention.q.weight": "pytorch_model_00005-of-00005.bin",
185
+ "decoder.block.20.layer.1.EncDecAttention.v.weight": "pytorch_model_00005-of-00005.bin",
186
+ "decoder.block.20.layer.1.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
187
+ "decoder.block.20.layer.2.DenseReluDense.wi.weight": "pytorch_model_00005-of-00005.bin",
188
+ "decoder.block.20.layer.2.DenseReluDense.wo.weight": "pytorch_model_00005-of-00005.bin",
189
+ "decoder.block.20.layer.2.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
190
+ "decoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model_00005-of-00005.bin",
191
+ "decoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model_00005-of-00005.bin",
192
+ "decoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model_00005-of-00005.bin",
193
+ "decoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model_00005-of-00005.bin",
194
+ "decoder.block.21.layer.0.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
195
+ "decoder.block.21.layer.1.EncDecAttention.k.weight": "pytorch_model_00005-of-00005.bin",
196
+ "decoder.block.21.layer.1.EncDecAttention.o.weight": "pytorch_model_00005-of-00005.bin",
197
+ "decoder.block.21.layer.1.EncDecAttention.q.weight": "pytorch_model_00005-of-00005.bin",
198
+ "decoder.block.21.layer.1.EncDecAttention.v.weight": "pytorch_model_00005-of-00005.bin",
199
+ "decoder.block.21.layer.1.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
200
+ "decoder.block.21.layer.2.DenseReluDense.wi.weight": "pytorch_model_00005-of-00005.bin",
201
+ "decoder.block.21.layer.2.DenseReluDense.wo.weight": "pytorch_model_00005-of-00005.bin",
202
+ "decoder.block.21.layer.2.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
203
+ "decoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model_00005-of-00005.bin",
204
+ "decoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model_00005-of-00005.bin",
205
+ "decoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model_00005-of-00005.bin",
206
+ "decoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model_00005-of-00005.bin",
207
+ "decoder.block.22.layer.0.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
208
+ "decoder.block.22.layer.1.EncDecAttention.k.weight": "pytorch_model_00005-of-00005.bin",
209
+ "decoder.block.22.layer.1.EncDecAttention.o.weight": "pytorch_model_00005-of-00005.bin",
210
+ "decoder.block.22.layer.1.EncDecAttention.q.weight": "pytorch_model_00005-of-00005.bin",
211
+ "decoder.block.22.layer.1.EncDecAttention.v.weight": "pytorch_model_00005-of-00005.bin",
212
+ "decoder.block.22.layer.1.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
213
+ "decoder.block.22.layer.2.DenseReluDense.wi.weight": "pytorch_model_00005-of-00005.bin",
214
+ "decoder.block.22.layer.2.DenseReluDense.wo.weight": "pytorch_model_00005-of-00005.bin",
215
+ "decoder.block.22.layer.2.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
216
+ "decoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model_00005-of-00005.bin",
217
+ "decoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model_00005-of-00005.bin",
218
+ "decoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model_00005-of-00005.bin",
219
+ "decoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model_00005-of-00005.bin",
220
+ "decoder.block.23.layer.0.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
221
+ "decoder.block.23.layer.1.EncDecAttention.k.weight": "pytorch_model_00005-of-00005.bin",
222
+ "decoder.block.23.layer.1.EncDecAttention.o.weight": "pytorch_model_00005-of-00005.bin",
223
+ "decoder.block.23.layer.1.EncDecAttention.q.weight": "pytorch_model_00005-of-00005.bin",
224
+ "decoder.block.23.layer.1.EncDecAttention.v.weight": "pytorch_model_00005-of-00005.bin",
225
+ "decoder.block.23.layer.1.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
226
+ "decoder.block.23.layer.2.DenseReluDense.wi.weight": "pytorch_model_00005-of-00005.bin",
227
+ "decoder.block.23.layer.2.DenseReluDense.wo.weight": "pytorch_model_00005-of-00005.bin",
228
+ "decoder.block.23.layer.2.layer_norm.weight": "pytorch_model_00005-of-00005.bin",
229
+ "decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model_00003-of-00005.bin",
230
+ "decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model_00003-of-00005.bin",
231
+ "decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model_00003-of-00005.bin",
232
+ "decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model_00003-of-00005.bin",
233
+ "decoder.block.3.layer.0.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
234
+ "decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model_00003-of-00005.bin",
235
+ "decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model_00003-of-00005.bin",
236
+ "decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model_00003-of-00005.bin",
237
+ "decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model_00003-of-00005.bin",
238
+ "decoder.block.3.layer.1.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
239
+ "decoder.block.3.layer.2.DenseReluDense.wi.weight": "pytorch_model_00003-of-00005.bin",
240
+ "decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model_00003-of-00005.bin",
241
+ "decoder.block.3.layer.2.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
242
+ "decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model_00003-of-00005.bin",
243
+ "decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model_00003-of-00005.bin",
244
+ "decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model_00003-of-00005.bin",
245
+ "decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model_00003-of-00005.bin",
246
+ "decoder.block.4.layer.0.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
247
+ "decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model_00003-of-00005.bin",
248
+ "decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model_00003-of-00005.bin",
249
+ "decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model_00003-of-00005.bin",
250
+ "decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model_00003-of-00005.bin",
251
+ "decoder.block.4.layer.1.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
252
+ "decoder.block.4.layer.2.DenseReluDense.wi.weight": "pytorch_model_00003-of-00005.bin",
253
+ "decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model_00003-of-00005.bin",
254
+ "decoder.block.4.layer.2.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
255
+ "decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model_00003-of-00005.bin",
256
+ "decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model_00003-of-00005.bin",
257
+ "decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model_00003-of-00005.bin",
258
+ "decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model_00003-of-00005.bin",
259
+ "decoder.block.5.layer.0.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
260
+ "decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model_00003-of-00005.bin",
261
+ "decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model_00003-of-00005.bin",
262
+ "decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model_00003-of-00005.bin",
263
+ "decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model_00003-of-00005.bin",
264
+ "decoder.block.5.layer.1.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
265
+ "decoder.block.5.layer.2.DenseReluDense.wi.weight": "pytorch_model_00003-of-00005.bin",
266
+ "decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model_00003-of-00005.bin",
267
+ "decoder.block.5.layer.2.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
268
+ "decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model_00003-of-00005.bin",
269
+ "decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model_00003-of-00005.bin",
270
+ "decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model_00003-of-00005.bin",
271
+ "decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model_00003-of-00005.bin",
272
+ "decoder.block.6.layer.0.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
273
+ "decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model_00003-of-00005.bin",
274
+ "decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model_00003-of-00005.bin",
275
+ "decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model_00003-of-00005.bin",
276
+ "decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model_00003-of-00005.bin",
277
+ "decoder.block.6.layer.1.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
278
+ "decoder.block.6.layer.2.DenseReluDense.wi.weight": "pytorch_model_00003-of-00005.bin",
279
+ "decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model_00003-of-00005.bin",
280
+ "decoder.block.6.layer.2.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
281
+ "decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model_00003-of-00005.bin",
282
+ "decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model_00003-of-00005.bin",
283
+ "decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model_00003-of-00005.bin",
284
+ "decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model_00003-of-00005.bin",
285
+ "decoder.block.7.layer.0.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
286
+ "decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model_00003-of-00005.bin",
287
+ "decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model_00003-of-00005.bin",
288
+ "decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model_00003-of-00005.bin",
289
+ "decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model_00003-of-00005.bin",
290
+ "decoder.block.7.layer.1.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
291
+ "decoder.block.7.layer.2.DenseReluDense.wi.weight": "pytorch_model_00003-of-00005.bin",
292
+ "decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model_00003-of-00005.bin",
293
+ "decoder.block.7.layer.2.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
294
+ "decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model_00003-of-00005.bin",
295
+ "decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model_00003-of-00005.bin",
296
+ "decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model_00003-of-00005.bin",
297
+ "decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model_00003-of-00005.bin",
298
+ "decoder.block.8.layer.0.layer_norm.weight": "pytorch_model_00003-of-00005.bin",
299
+ "decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model_00004-of-00005.bin",
300
+ "decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model_00004-of-00005.bin",
301
+ "decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model_00004-of-00005.bin",
302
+ "decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model_00004-of-00005.bin",
303
+ "decoder.block.8.layer.1.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
304
+ "decoder.block.8.layer.2.DenseReluDense.wi.weight": "pytorch_model_00004-of-00005.bin",
305
+ "decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model_00004-of-00005.bin",
306
+ "decoder.block.8.layer.2.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
307
+ "decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model_00004-of-00005.bin",
308
+ "decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model_00004-of-00005.bin",
309
+ "decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model_00004-of-00005.bin",
310
+ "decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model_00004-of-00005.bin",
311
+ "decoder.block.9.layer.0.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
312
+ "decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model_00004-of-00005.bin",
313
+ "decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model_00004-of-00005.bin",
314
+ "decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model_00004-of-00005.bin",
315
+ "decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model_00004-of-00005.bin",
316
+ "decoder.block.9.layer.1.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
317
+ "decoder.block.9.layer.2.DenseReluDense.wi.weight": "pytorch_model_00004-of-00005.bin",
318
+ "decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model_00004-of-00005.bin",
319
+ "decoder.block.9.layer.2.layer_norm.weight": "pytorch_model_00004-of-00005.bin",
320
+ "decoder.final_layer_norm.weight": "pytorch_model_00005-of-00005.bin",
321
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model_00001-of-00005.bin",
322
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model_00001-of-00005.bin",
323
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model_00001-of-00005.bin",
324
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model_00001-of-00005.bin",
325
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model_00001-of-00005.bin",
326
+ "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
327
+ "encoder.block.0.layer.1.DenseReluDense.wi.weight": "pytorch_model_00001-of-00005.bin",
328
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model_00001-of-00005.bin",
329
+ "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
330
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model_00001-of-00005.bin",
331
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model_00001-of-00005.bin",
332
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model_00001-of-00005.bin",
333
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model_00001-of-00005.bin",
334
+ "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
335
+ "encoder.block.1.layer.1.DenseReluDense.wi.weight": "pytorch_model_00001-of-00005.bin",
336
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model_00001-of-00005.bin",
337
+ "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
338
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model_00001-of-00005.bin",
339
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model_00001-of-00005.bin",
340
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model_00001-of-00005.bin",
341
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model_00001-of-00005.bin",
342
+ "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
343
+ "encoder.block.10.layer.1.DenseReluDense.wi.weight": "pytorch_model_00001-of-00005.bin",
344
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model_00001-of-00005.bin",
345
+ "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
346
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model_00001-of-00005.bin",
347
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model_00001-of-00005.bin",
348
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model_00001-of-00005.bin",
349
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model_00001-of-00005.bin",
350
+ "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
351
+ "encoder.block.11.layer.1.DenseReluDense.wi.weight": "pytorch_model_00001-of-00005.bin",
352
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model_00001-of-00005.bin",
353
+ "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
354
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model_00001-of-00005.bin",
355
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model_00001-of-00005.bin",
356
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model_00001-of-00005.bin",
357
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model_00001-of-00005.bin",
358
+ "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
359
+ "encoder.block.12.layer.1.DenseReluDense.wi.weight": "pytorch_model_00002-of-00005.bin",
360
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model_00002-of-00005.bin",
361
+ "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
362
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model_00002-of-00005.bin",
363
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model_00002-of-00005.bin",
364
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model_00002-of-00005.bin",
365
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model_00002-of-00005.bin",
366
+ "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
367
+ "encoder.block.13.layer.1.DenseReluDense.wi.weight": "pytorch_model_00002-of-00005.bin",
368
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model_00002-of-00005.bin",
369
+ "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
370
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model_00002-of-00005.bin",
371
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model_00002-of-00005.bin",
372
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model_00002-of-00005.bin",
373
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model_00002-of-00005.bin",
374
+ "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
375
+ "encoder.block.14.layer.1.DenseReluDense.wi.weight": "pytorch_model_00002-of-00005.bin",
376
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model_00002-of-00005.bin",
377
+ "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
378
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model_00002-of-00005.bin",
379
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model_00002-of-00005.bin",
380
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model_00002-of-00005.bin",
381
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model_00002-of-00005.bin",
382
+ "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
383
+ "encoder.block.15.layer.1.DenseReluDense.wi.weight": "pytorch_model_00002-of-00005.bin",
384
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model_00002-of-00005.bin",
385
+ "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
386
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model_00002-of-00005.bin",
387
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model_00002-of-00005.bin",
388
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model_00002-of-00005.bin",
389
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model_00002-of-00005.bin",
390
+ "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
391
+ "encoder.block.16.layer.1.DenseReluDense.wi.weight": "pytorch_model_00002-of-00005.bin",
392
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model_00002-of-00005.bin",
393
+ "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
394
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model_00002-of-00005.bin",
395
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model_00002-of-00005.bin",
396
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model_00002-of-00005.bin",
397
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model_00002-of-00005.bin",
398
+ "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
399
+ "encoder.block.17.layer.1.DenseReluDense.wi.weight": "pytorch_model_00002-of-00005.bin",
400
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model_00002-of-00005.bin",
401
+ "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
402
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model_00002-of-00005.bin",
403
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model_00002-of-00005.bin",
404
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model_00002-of-00005.bin",
405
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model_00002-of-00005.bin",
406
+ "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
407
+ "encoder.block.18.layer.1.DenseReluDense.wi.weight": "pytorch_model_00002-of-00005.bin",
408
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model_00002-of-00005.bin",
409
+ "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
410
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model_00002-of-00005.bin",
411
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model_00002-of-00005.bin",
412
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model_00002-of-00005.bin",
413
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model_00002-of-00005.bin",
414
+ "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
415
+ "encoder.block.19.layer.1.DenseReluDense.wi.weight": "pytorch_model_00002-of-00005.bin",
416
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model_00002-of-00005.bin",
417
+ "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
418
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model_00001-of-00005.bin",
419
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model_00001-of-00005.bin",
420
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model_00001-of-00005.bin",
421
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model_00001-of-00005.bin",
422
+ "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
423
+ "encoder.block.2.layer.1.DenseReluDense.wi.weight": "pytorch_model_00001-of-00005.bin",
424
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model_00001-of-00005.bin",
425
+ "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
426
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model_00002-of-00005.bin",
427
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model_00002-of-00005.bin",
428
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model_00002-of-00005.bin",
429
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model_00002-of-00005.bin",
430
+ "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
431
+ "encoder.block.20.layer.1.DenseReluDense.wi.weight": "pytorch_model_00002-of-00005.bin",
432
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model_00002-of-00005.bin",
433
+ "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
434
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model_00002-of-00005.bin",
435
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model_00002-of-00005.bin",
436
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model_00002-of-00005.bin",
437
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model_00002-of-00005.bin",
438
+ "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
439
+ "encoder.block.21.layer.1.DenseReluDense.wi.weight": "pytorch_model_00002-of-00005.bin",
440
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model_00002-of-00005.bin",
441
+ "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
442
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model_00002-of-00005.bin",
443
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model_00002-of-00005.bin",
444
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model_00002-of-00005.bin",
445
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model_00002-of-00005.bin",
446
+ "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
447
+ "encoder.block.22.layer.1.DenseReluDense.wi.weight": "pytorch_model_00002-of-00005.bin",
448
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model_00002-of-00005.bin",
449
+ "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
450
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model_00002-of-00005.bin",
451
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model_00002-of-00005.bin",
452
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model_00002-of-00005.bin",
453
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model_00002-of-00005.bin",
454
+ "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
455
+ "encoder.block.23.layer.1.DenseReluDense.wi.weight": "pytorch_model_00002-of-00005.bin",
456
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model_00002-of-00005.bin",
457
+ "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model_00002-of-00005.bin",
458
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model_00001-of-00005.bin",
459
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model_00001-of-00005.bin",
460
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model_00001-of-00005.bin",
461
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model_00001-of-00005.bin",
462
+ "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
463
+ "encoder.block.3.layer.1.DenseReluDense.wi.weight": "pytorch_model_00001-of-00005.bin",
464
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model_00001-of-00005.bin",
465
+ "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
466
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model_00001-of-00005.bin",
467
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model_00001-of-00005.bin",
468
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model_00001-of-00005.bin",
469
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model_00001-of-00005.bin",
470
+ "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
471
+ "encoder.block.4.layer.1.DenseReluDense.wi.weight": "pytorch_model_00001-of-00005.bin",
472
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model_00001-of-00005.bin",
473
+ "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
474
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model_00001-of-00005.bin",
475
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model_00001-of-00005.bin",
476
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model_00001-of-00005.bin",
477
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model_00001-of-00005.bin",
478
+ "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
479
+ "encoder.block.5.layer.1.DenseReluDense.wi.weight": "pytorch_model_00001-of-00005.bin",
480
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model_00001-of-00005.bin",
481
+ "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
482
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model_00001-of-00005.bin",
483
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model_00001-of-00005.bin",
484
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model_00001-of-00005.bin",
485
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model_00001-of-00005.bin",
486
+ "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
487
+ "encoder.block.6.layer.1.DenseReluDense.wi.weight": "pytorch_model_00001-of-00005.bin",
488
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model_00001-of-00005.bin",
489
+ "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
490
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model_00001-of-00005.bin",
491
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model_00001-of-00005.bin",
492
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model_00001-of-00005.bin",
493
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model_00001-of-00005.bin",
494
+ "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
495
+ "encoder.block.7.layer.1.DenseReluDense.wi.weight": "pytorch_model_00001-of-00005.bin",
496
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model_00001-of-00005.bin",
497
+ "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
498
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model_00001-of-00005.bin",
499
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model_00001-of-00005.bin",
500
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model_00001-of-00005.bin",
501
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model_00001-of-00005.bin",
502
+ "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
503
+ "encoder.block.8.layer.1.DenseReluDense.wi.weight": "pytorch_model_00001-of-00005.bin",
504
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model_00001-of-00005.bin",
505
+ "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
506
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model_00001-of-00005.bin",
507
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model_00001-of-00005.bin",
508
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model_00001-of-00005.bin",
509
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model_00001-of-00005.bin",
510
+ "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
511
+ "encoder.block.9.layer.1.DenseReluDense.wi.weight": "pytorch_model_00001-of-00005.bin",
512
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model_00001-of-00005.bin",
513
+ "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model_00001-of-00005.bin",
514
+ "encoder.final_layer_norm.weight": "pytorch_model_00002-of-00005.bin",
515
+ "shared.weight": "pytorch_model_00001-of-00005.bin"
516
+ }
517
+ }
pytorch_model_00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91aad0623deeac7e05eed8186462f1c8e40ad6d7b9f05398ea56ac76833ddbff
3
+ size 3218775427
pytorch_model_00001-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4426c155ce5020d56d10f8460db2e04295888df9271ad2c2d64b9ef9fdc72097
3
+ size 2614758837
pytorch_model_00002-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d25f1a956afc4b256b44b307dab80bc6d2169ecadd32e3497ef5c57008157969
3
+ size 2885856707
pytorch_model_00002-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e5c762de05e517e7c13bd86c89f67d6cdd3927261548e655c6b4a9b4e8d282f
3
+ size 2466393589
pytorch_model_00003-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cb7b8165efe9816ab1df70e9eab5dd4e60bc0885844042206d6a00f7fe8c488
3
+ size 2650959299
pytorch_model_00003-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97f5368d7a43426aee8e790fd5ae59d005913cd83417c39dc0a8fc1d42666a05
3
+ size 2097286581
pytorch_model_00004-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afcd94314d734503cc5feef35eeeb4cbe77e673ea9f0d5931f5f393669dbd603
3
+ size 2650959427
pytorch_model_00004-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86c661d37b3b946ab5896a2b7766ae71b53645c2ff22feab279ba104de0b9b49
3
+ size 2130832949
pytorch_model_00005-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5f8836f8823a54741158f620c5849a4700aa6abdccad7d6b9c94001e6581135
3
+ size 9191
pytorch_model_00005-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:348f572c43e4d756d75b55d90335232db5125105c1308967ebb4ebd8e80d5461
3
+ size 2097286645
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff