AntoineBlanot commited on
Commit
5d3ab1b
1 Parent(s): ca46dc3

Upload T5ForClassification

Browse files
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "philschmid/flan-t5-xxl-sharded-fp16",
3
+ "architectures": [
4
+ "T5ForClassification"
5
+ ],
6
+ "d_ff": 10240,
7
+ "d_kv": 64,
8
+ "d_model": 4096,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gelu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_class": 3,
20
+ "num_decoder_layers": 1,
21
+ "num_heads": 64,
22
+ "num_layers": 24,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.27.2",
30
+ "use_cache": false,
31
+ "vocab_size": 32128
32
+ }
pytorch_model-00001-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90c839bf4cd4b4404765612591f07393dfa5c990a45ee0d3a2da54bc832ad162
3
+ size 4452442307
pytorch_model-00002-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a31d7a149dafa0150b3f6b1a07ef8c95f2096d35d781bb3e10af61cde503b7c
3
+ size 4999843701
pytorch_model-00003-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23a0d2d645b760d32915bf87a23ebbc63ffe27461476ead5f14596b5fc95a26b
3
+ size 4966288621
pytorch_model-00004-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49abd0ef104b9e9de7ec4a69af8f4af6a8c620bed032dcd388928e212fa77251
3
+ size 4630743525
pytorch_model-00005-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea05e2d61117b83f4cc778d9974116049677e94b767b9f7117969dd0634a333f
3
+ size 1566701779
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 21142323200
4
+ },
5
+ "weight_map": {
6
+ "decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00005.bin",
7
+ "decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00005.bin",
8
+ "decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00005.bin",
9
+ "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00005-of-00005.bin",
10
+ "decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00005.bin",
11
+ "decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
12
+ "decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00005.bin",
13
+ "decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00005.bin",
14
+ "decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00005.bin",
15
+ "decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00005.bin",
16
+ "decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
17
+ "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00005.bin",
18
+ "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00005.bin",
19
+ "decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00005.bin",
20
+ "decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
21
+ "decoder.embed_tokens.weight": "pytorch_model-00005-of-00005.bin",
22
+ "decoder.final_layer_norm.weight": "pytorch_model-00005-of-00005.bin",
23
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
24
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
25
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
26
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00005.bin",
27
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
28
+ "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
29
+ "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
30
+ "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
31
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
32
+ "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
33
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
34
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
35
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
36
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
37
+ "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
38
+ "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
39
+ "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
40
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
41
+ "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
42
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
43
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
44
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
45
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
46
+ "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
47
+ "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00005.bin",
48
+ "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00005.bin",
49
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
50
+ "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
51
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
52
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
53
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
54
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
55
+ "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
56
+ "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00005.bin",
57
+ "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00005.bin",
58
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
59
+ "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
60
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
61
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
62
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
63
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
64
+ "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
65
+ "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00005.bin",
66
+ "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00005.bin",
67
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
68
+ "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
69
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
70
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
71
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
72
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
73
+ "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
74
+ "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00005.bin",
75
+ "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00005.bin",
76
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
77
+ "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
78
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
79
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
80
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
81
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
82
+ "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
83
+ "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00005.bin",
84
+ "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00005.bin",
85
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
86
+ "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
87
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
88
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
89
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
90
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
91
+ "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
92
+ "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00005.bin",
93
+ "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00005.bin",
94
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
95
+ "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
96
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
97
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
98
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
99
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
100
+ "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
101
+ "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00005.bin",
102
+ "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00005.bin",
103
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
104
+ "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
105
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
106
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
107
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
108
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
109
+ "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
110
+ "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00005.bin",
111
+ "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00005.bin",
112
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
113
+ "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
114
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
115
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
116
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
117
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
118
+ "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
119
+ "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00005.bin",
120
+ "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00005.bin",
121
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
122
+ "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
123
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
124
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
125
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
126
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
127
+ "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
128
+ "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00005.bin",
129
+ "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00005.bin",
130
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
131
+ "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
132
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
133
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
134
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
135
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
136
+ "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
137
+ "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
138
+ "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
139
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
140
+ "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
141
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
142
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
143
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
144
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
145
+ "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
146
+ "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00005.bin",
147
+ "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00005.bin",
148
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
149
+ "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
150
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
151
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
152
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
153
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
154
+ "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
155
+ "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00005.bin",
156
+ "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00005.bin",
157
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
158
+ "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
159
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
160
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
161
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
162
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
163
+ "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
164
+ "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00005.bin",
165
+ "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00005.bin",
166
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
167
+ "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
168
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
169
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
170
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
171
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
172
+ "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
173
+ "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00005.bin",
174
+ "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00005.bin",
175
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
176
+ "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
177
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
178
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
179
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
180
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
181
+ "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
182
+ "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
183
+ "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
184
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
185
+ "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
186
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
187
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
188
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
189
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
190
+ "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
191
+ "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
192
+ "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
193
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
194
+ "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
195
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
196
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
197
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
198
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
199
+ "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
200
+ "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00005.bin",
201
+ "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00005.bin",
202
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
203
+ "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
204
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
205
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
206
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
207
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
208
+ "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
209
+ "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00005.bin",
210
+ "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00005.bin",
211
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
212
+ "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
213
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
214
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
215
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
216
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
217
+ "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
218
+ "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00005.bin",
219
+ "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00005.bin",
220
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
221
+ "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
222
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
223
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
224
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
225
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
226
+ "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
227
+ "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00005.bin",
228
+ "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00005.bin",
229
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
230
+ "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
231
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
232
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
233
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
234
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
235
+ "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
236
+ "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00005.bin",
237
+ "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00005.bin",
238
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
239
+ "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
240
+ "encoder.embed_tokens.weight": "pytorch_model-00001-of-00005.bin",
241
+ "encoder.final_layer_norm.weight": "pytorch_model-00004-of-00005.bin",
242
+ "head.weight": "pytorch_model-00005-of-00005.bin",
243
+ "shared.weight": "pytorch_model-00001-of-00005.bin"
244
+ }
245
+ }