Hugging Face's logo

jbochi
/
madlad400-3b-mt

Translation
Transformers
Safetensors
GGUF
JAX
419 languages
t5
text2text-generation
text-generation-inference
Inference Endpoints
Model card Files Community
17
jbochi commited on
Commit
bb876df
•
1 Parent(s): 2b63016

It works!

Browse files
Files changed (12) hide show
  1. added_tokens.json +103 -0
  2. config.json +28 -31
  3. flax_model.msgpack +0 -3
  4. generation_config.json +1 -1
  5. model.safetensors +2 -2
  6. pytorch_model-00001-of-00002.bin +0 -3
  7. pytorch_model-00002-of-00002.bin +0 -3
  8. pytorch_model.bin.index.json +0 -751
  9. special_tokens_map.json +21 -3
  10. spiece.model +2 -2
  11. tokenizer.json +2 -2
  12. tokenizer_config.json +826 -0
added_tokens.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<extra_id_0>": 256099,
3
+ "<extra_id_10>": 256089,
4
+ "<extra_id_11>": 256088,
5
+ "<extra_id_12>": 256087,
6
+ "<extra_id_13>": 256086,
7
+ "<extra_id_14>": 256085,
8
+ "<extra_id_15>": 256084,
9
+ "<extra_id_16>": 256083,
10
+ "<extra_id_17>": 256082,
11
+ "<extra_id_18>": 256081,
12
+ "<extra_id_19>": 256080,
13
+ "<extra_id_1>": 256098,
14
+ "<extra_id_20>": 256079,
15
+ "<extra_id_21>": 256078,
16
+ "<extra_id_22>": 256077,
17
+ "<extra_id_23>": 256076,
18
+ "<extra_id_24>": 256075,
19
+ "<extra_id_25>": 256074,
20
+ "<extra_id_26>": 256073,
21
+ "<extra_id_27>": 256072,
22
+ "<extra_id_28>": 256071,
23
+ "<extra_id_29>": 256070,
24
+ "<extra_id_2>": 256097,
25
+ "<extra_id_30>": 256069,
26
+ "<extra_id_31>": 256068,
27
+ "<extra_id_32>": 256067,
28
+ "<extra_id_33>": 256066,
29
+ "<extra_id_34>": 256065,
30
+ "<extra_id_35>": 256064,
31
+ "<extra_id_36>": 256063,
32
+ "<extra_id_37>": 256062,
33
+ "<extra_id_38>": 256061,
34
+ "<extra_id_39>": 256060,
35
+ "<extra_id_3>": 256096,
36
+ "<extra_id_40>": 256059,
37
+ "<extra_id_41>": 256058,
38
+ "<extra_id_42>": 256057,
39
+ "<extra_id_43>": 256056,
40
+ "<extra_id_44>": 256055,
41
+ "<extra_id_45>": 256054,
42
+ "<extra_id_46>": 256053,
43
+ "<extra_id_47>": 256052,
44
+ "<extra_id_48>": 256051,
45
+ "<extra_id_49>": 256050,
46
+ "<extra_id_4>": 256095,
47
+ "<extra_id_50>": 256049,
48
+ "<extra_id_51>": 256048,
49
+ "<extra_id_52>": 256047,
50
+ "<extra_id_53>": 256046,
51
+ "<extra_id_54>": 256045,
52
+ "<extra_id_55>": 256044,
53
+ "<extra_id_56>": 256043,
54
+ "<extra_id_57>": 256042,
55
+ "<extra_id_58>": 256041,
56
+ "<extra_id_59>": 256040,
57
+ "<extra_id_5>": 256094,
58
+ "<extra_id_60>": 256039,
59
+ "<extra_id_61>": 256038,
60
+ "<extra_id_62>": 256037,
61
+ "<extra_id_63>": 256036,
62
+ "<extra_id_64>": 256035,
63
+ "<extra_id_65>": 256034,
64
+ "<extra_id_66>": 256033,
65
+ "<extra_id_67>": 256032,
66
+ "<extra_id_68>": 256031,
67
+ "<extra_id_69>": 256030,
68
+ "<extra_id_6>": 256093,
69
+ "<extra_id_70>": 256029,
70
+ "<extra_id_71>": 256028,
71
+ "<extra_id_72>": 256027,
72
+ "<extra_id_73>": 256026,
73
+ "<extra_id_74>": 256025,
74
+ "<extra_id_75>": 256024,
75
+ "<extra_id_76>": 256023,
76
+ "<extra_id_77>": 256022,
77
+ "<extra_id_78>": 256021,
78
+ "<extra_id_79>": 256020,
79
+ "<extra_id_7>": 256092,
80
+ "<extra_id_80>": 256019,
81
+ "<extra_id_81>": 256018,
82
+ "<extra_id_82>": 256017,
83
+ "<extra_id_83>": 256016,
84
+ "<extra_id_84>": 256015,
85
+ "<extra_id_85>": 256014,
86
+ "<extra_id_86>": 256013,
87
+ "<extra_id_87>": 256012,
88
+ "<extra_id_88>": 256011,
89
+ "<extra_id_89>": 256010,
90
+ "<extra_id_8>": 256091,
91
+ "<extra_id_90>": 256009,
92
+ "<extra_id_91>": 256008,
93
+ "<extra_id_92>": 256007,
94
+ "<extra_id_93>": 256006,
95
+ "<extra_id_94>": 256005,
96
+ "<extra_id_95>": 256004,
97
+ "<extra_id_96>": 256003,
98
+ "<extra_id_97>": 256002,
99
+ "<extra_id_98>": 256001,
100
+ "<extra_id_99>": 256000,
101
+ "<extra_id_9>": 256090,
102
+ "<pad>": 256100
103
+ }
config.json CHANGED
@@ -1,32 +1,29 @@
1
  {
2
- "architectures": [
3
- "T5ForConditionalGeneration"
4
- ],
5
- "classifier_dropout": 0.0,
6
- "d_ff": 8192,
7
- "d_kv": 128,
8
- "d_model": 1024,
9
- "decoder_start_token_id": 1,
10
- "dense_act_fn": "gelu_new",
11
- "dropout_rate": 0.1,
12
- "eos_token_id": 2,
13
- "feed_forward_proj": "gated-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_positions": 512,
20
- "num_decoder_layers": 32,
21
- "num_heads": 16,
22
- "num_layers": 32,
23
- "output_past": true,
24
- "pad_token_id": 1,
25
- "relative_attention_max_distance": 128,
26
- "relative_attention_num_buckets": 32,
27
- "task_specific_params": {},
28
- "tie_word_embeddings": false,
29
- "transformers_version": "4.33.2",
30
- "use_cache": true,
31
- "vocab_size": 256000
32
- }
 
1
  {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "d_ff": 8192,
6
+ "d_kv": 128,
7
+ "d_model": 1024,
8
+ "dropout_rate": 0.1,
9
+ "decoder_start_token_id": 1,
10
+ "pad_token_id": 1,
11
+ "eos_token_id": 2,
12
+ "feed_forward_proj": "gated-gelu",
13
+ "initializer_factor": 1.0,
14
+ "is_encoder_decoder": true,
15
+ "layer_norm_epsilon": 1e-06,
16
+ "model_type": "t5",
17
+ "n_positions": 512,
18
+ "num_decoder_layers": 32,
19
+ "num_heads": 16,
20
+ "num_layers": 32,
21
+ "output_past": true,
22
+ "relative_attention_max_distance": 128,
23
+ "relative_attention_num_buckets": 32,
24
+ "task_specific_params": {},
25
+ "tie_word_embeddings": false,
26
+ "transformers_version": "4.23.1",
27
+ "use_cache": true,
28
+ "vocab_size": 256000
29
+ }
 
 
 
flax_model.msgpack DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9dc94c6dc47a8e24d50b810d3ece0ae3b78b66ef310d053557b4ffe8ad6b1b77
3
- size 11761528083
 
 
 
 
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "decoder_start_token_id": 1,
4
  "eos_token_id": 2,
5
  "pad_token_id": 1,
6
- "transformers_version": "4.33.2"
7
  }
 
3
  "decoder_start_token_id": 1,
4
  "eos_token_id": 2,
5
  "pad_token_id": 1,
6
+ "transformers_version": "4.35.0"
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ddca188b8a3db3666eae1b7176f9bbd20a6b378efc3dbc2a823564c5b9d8e7c
3
- size 12810163832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66ff5f8fcaf92291da486fdfbd4d5233cec90e1359348a56e3172c978b3a76d4
3
+ size 11761587872
pytorch_model-00001-of-00002.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a28403955d7d7699a5745c2b6e4f02eee8962d85d5e4b98e509329c72b9f607
3
- size 9974907514
 
 
 
 
pytorch_model-00002-of-00002.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3368d731cf5b286d309f44ccae713abdc074ac71668b0a13ba533968f4ad6972
3
- size 1786851801
 
 
 
 
pytorch_model.bin.index.json DELETED
@@ -1,751 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 11761496064
4
- },
5
- "weight_map": {
6
- "decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
7
- "decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
8
- "decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
9
- "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin",
10
- "decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
11
- "decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
12
- "decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
13
- "decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
14
- "decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
15
- "decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
16
- "decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
17
- "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
18
- "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
19
- "decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
20
- "decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
21
- "decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
22
- "decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
23
- "decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
24
- "decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
25
- "decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
26
- "decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
27
- "decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
28
- "decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
29
- "decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
30
- "decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
31
- "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
32
- "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
33
- "decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
34
- "decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
35
- "decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
36
- "decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
37
- "decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
38
- "decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
39
- "decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
40
- "decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
41
- "decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
42
- "decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
43
- "decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
44
- "decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
45
- "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
46
- "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
47
- "decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
48
- "decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
49
- "decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
50
- "decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
51
- "decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
52
- "decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
53
- "decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
54
- "decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
55
- "decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
56
- "decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
57
- "decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
58
- "decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
59
- "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
60
- "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
61
- "decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
62
- "decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
63
- "decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
64
- "decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
65
- "decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
66
- "decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
67
- "decoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
68
- "decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
69
- "decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
70
- "decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
71
- "decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
72
- "decoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
73
- "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
74
- "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
75
- "decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
76
- "decoder.block.12.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
77
- "decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
78
- "decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
79
- "decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
80
- "decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
81
- "decoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
82
- "decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
83
- "decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
84
- "decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
85
- "decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
86
- "decoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
87
- "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
88
- "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
89
- "decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
90
- "decoder.block.13.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
91
- "decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
92
- "decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
93
- "decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
94
- "decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
95
- "decoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
96
- "decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
97
- "decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
98
- "decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
99
- "decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
100
- "decoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
101
- "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
102
- "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
103
- "decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
104
- "decoder.block.14.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
105
- "decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
106
- "decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
107
- "decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
108
- "decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
109
- "decoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
110
- "decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
111
- "decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
112
- "decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
113
- "decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
114
- "decoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
115
- "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
116
- "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
117
- "decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
118
- "decoder.block.15.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
119
- "decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
120
- "decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
121
- "decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
122
- "decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
123
- "decoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
124
- "decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
125
- "decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
126
- "decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
127
- "decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
128
- "decoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
129
- "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
130
- "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
131
- "decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
132
- "decoder.block.16.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
133
- "decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
134
- "decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
135
- "decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
136
- "decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
137
- "decoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
138
- "decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
139
- "decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
140
- "decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
141
- "decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
142
- "decoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
143
- "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
144
- "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
145
- "decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
146
- "decoder.block.17.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
147
- "decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
148
- "decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
149
- "decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
150
- "decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
151
- "decoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
152
- "decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
153
- "decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
154
- "decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
155
- "decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
156
- "decoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
157
- "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
158
- "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
159
- "decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
160
- "decoder.block.18.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
161
- "decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
162
- "decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
163
- "decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
164
- "decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
165
- "decoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
166
- "decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
167
- "decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
168
- "decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
169
- "decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
170
- "decoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
171
- "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
172
- "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
173
- "decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
174
- "decoder.block.19.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
175
- "decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
176
- "decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
177
- "decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
178
- "decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
179
- "decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
180
- "decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
181
- "decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
182
- "decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
183
- "decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
184
- "decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
185
- "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
186
- "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
187
- "decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
188
- "decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
189
- "decoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
190
- "decoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
191
- "decoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
192
- "decoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
193
- "decoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
194
- "decoder.block.20.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
195
- "decoder.block.20.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
196
- "decoder.block.20.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
197
- "decoder.block.20.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
198
- "decoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
199
- "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
200
- "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
201
- "decoder.block.20.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
202
- "decoder.block.20.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
203
- "decoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
204
- "decoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
205
- "decoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
206
- "decoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
207
- "decoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
208
- "decoder.block.21.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
209
- "decoder.block.21.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
210
- "decoder.block.21.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
211
- "decoder.block.21.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
212
- "decoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
213
- "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
214
- "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
215
- "decoder.block.21.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
216
- "decoder.block.21.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
217
- "decoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
218
- "decoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
219
- "decoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
220
- "decoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
221
- "decoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
222
- "decoder.block.22.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
223
- "decoder.block.22.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
224
- "decoder.block.22.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
225
- "decoder.block.22.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
226
- "decoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
227
- "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
228
- "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
229
- "decoder.block.22.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
230
- "decoder.block.22.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
231
- "decoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
232
- "decoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
233
- "decoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
234
- "decoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
235
- "decoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
236
- "decoder.block.23.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
237
- "decoder.block.23.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
238
- "decoder.block.23.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
239
- "decoder.block.23.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
240
- "decoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
241
- "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
242
- "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
243
- "decoder.block.23.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
244
- "decoder.block.23.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
245
- "decoder.block.24.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
246
- "decoder.block.24.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
247
- "decoder.block.24.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
248
- "decoder.block.24.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
249
- "decoder.block.24.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
250
- "decoder.block.24.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
251
- "decoder.block.24.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
252
- "decoder.block.24.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
253
- "decoder.block.24.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
254
- "decoder.block.24.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
255
- "decoder.block.24.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
256
- "decoder.block.24.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
257
- "decoder.block.24.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
258
- "decoder.block.24.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
259
- "decoder.block.25.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
260
- "decoder.block.25.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
261
- "decoder.block.25.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
262
- "decoder.block.25.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
263
- "decoder.block.25.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
264
- "decoder.block.25.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
265
- "decoder.block.25.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
266
- "decoder.block.25.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
267
- "decoder.block.25.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
268
- "decoder.block.25.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
269
- "decoder.block.25.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
270
- "decoder.block.25.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
271
- "decoder.block.25.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
272
- "decoder.block.25.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
273
- "decoder.block.26.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
274
- "decoder.block.26.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
275
- "decoder.block.26.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
276
- "decoder.block.26.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
277
- "decoder.block.26.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
278
- "decoder.block.26.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
279
- "decoder.block.26.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
280
- "decoder.block.26.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
281
- "decoder.block.26.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
282
- "decoder.block.26.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
283
- "decoder.block.26.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
284
- "decoder.block.26.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
285
- "decoder.block.26.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
286
- "decoder.block.26.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
287
- "decoder.block.27.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
288
- "decoder.block.27.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
289
- "decoder.block.27.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
290
- "decoder.block.27.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
291
- "decoder.block.27.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
292
- "decoder.block.27.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
293
- "decoder.block.27.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
294
- "decoder.block.27.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
295
- "decoder.block.27.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
296
- "decoder.block.27.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
297
- "decoder.block.27.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
298
- "decoder.block.27.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
299
- "decoder.block.27.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
300
- "decoder.block.27.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
301
- "decoder.block.28.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
302
- "decoder.block.28.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
303
- "decoder.block.28.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
304
- "decoder.block.28.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
305
- "decoder.block.28.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
306
- "decoder.block.28.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
307
- "decoder.block.28.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
308
- "decoder.block.28.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
309
- "decoder.block.28.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
310
- "decoder.block.28.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
311
- "decoder.block.28.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
312
- "decoder.block.28.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
313
- "decoder.block.28.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
314
- "decoder.block.28.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
315
- "decoder.block.29.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
316
- "decoder.block.29.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
317
- "decoder.block.29.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
318
- "decoder.block.29.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
319
- "decoder.block.29.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
320
- "decoder.block.29.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
321
- "decoder.block.29.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
322
- "decoder.block.29.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
323
- "decoder.block.29.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
324
- "decoder.block.29.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
325
- "decoder.block.29.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
326
- "decoder.block.29.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
327
- "decoder.block.29.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
328
- "decoder.block.29.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
329
- "decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
330
- "decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
331
- "decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
332
- "decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
333
- "decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
334
- "decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
335
- "decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
336
- "decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
337
- "decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
338
- "decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
339
- "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
340
- "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
341
- "decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
342
- "decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
343
- "decoder.block.30.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
344
- "decoder.block.30.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
345
- "decoder.block.30.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
346
- "decoder.block.30.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
347
- "decoder.block.30.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
348
- "decoder.block.30.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
349
- "decoder.block.30.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
350
- "decoder.block.30.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
351
- "decoder.block.30.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
352
- "decoder.block.30.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
353
- "decoder.block.30.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
354
- "decoder.block.30.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
355
- "decoder.block.30.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
356
- "decoder.block.30.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
357
- "decoder.block.31.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
358
- "decoder.block.31.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
359
- "decoder.block.31.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
360
- "decoder.block.31.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
361
- "decoder.block.31.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
362
- "decoder.block.31.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
363
- "decoder.block.31.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
364
- "decoder.block.31.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
365
- "decoder.block.31.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
366
- "decoder.block.31.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
367
- "decoder.block.31.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
368
- "decoder.block.31.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
369
- "decoder.block.31.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
370
- "decoder.block.31.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
371
- "decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
372
- "decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
373
- "decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
374
- "decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
375
- "decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
376
- "decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
377
- "decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
378
- "decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
379
- "decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
380
- "decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
381
- "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
382
- "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
383
- "decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
384
- "decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
385
- "decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
386
- "decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
387
- "decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
388
- "decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
389
- "decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
390
- "decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
391
- "decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
392
- "decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
393
- "decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
394
- "decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
395
- "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
396
- "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
397
- "decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
398
- "decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
399
- "decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
400
- "decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
401
- "decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
402
- "decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
403
- "decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
404
- "decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
405
- "decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
406
- "decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
407
- "decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
408
- "decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
409
- "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
410
- "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
411
- "decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
412
- "decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
413
- "decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
414
- "decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
415
- "decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
416
- "decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
417
- "decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
418
- "decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
419
- "decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
420
- "decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
421
- "decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
422
- "decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
423
- "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
424
- "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
425
- "decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
426
- "decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
427
- "decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
428
- "decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
429
- "decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
430
- "decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
431
- "decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
432
- "decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
433
- "decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
434
- "decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
435
- "decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
436
- "decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
437
- "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
438
- "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
439
- "decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
440
- "decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
441
- "decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
442
- "decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
443
- "decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
444
- "decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
445
- "decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
446
- "decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
447
- "decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
448
- "decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
449
- "decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
450
- "decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
451
- "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
452
- "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
453
- "decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
454
- "decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
455
- "decoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
456
- "decoder.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
457
- "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
458
- "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
459
- "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
460
- "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin",
461
- "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
462
- "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
463
- "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
464
- "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
465
- "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
466
- "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
467
- "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
468
- "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
469
- "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
470
- "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
471
- "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
472
- "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
473
- "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
474
- "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
475
- "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
476
- "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
477
- "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
478
- "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
479
- "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
480
- "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
481
- "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
482
- "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
483
- "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
484
- "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
485
- "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
486
- "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
487
- "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
488
- "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
489
- "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
490
- "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
491
- "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
492
- "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
493
- "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
494
- "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
495
- "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
496
- "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
497
- "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
498
- "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
499
- "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
500
- "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
501
- "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
502
- "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
503
- "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
504
- "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
505
- "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
506
- "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
507
- "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
508
- "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
509
- "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
510
- "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
511
- "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
512
- "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
513
- "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
514
- "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
515
- "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
516
- "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
517
- "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
518
- "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
519
- "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
520
- "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
521
- "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
522
- "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
523
- "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
524
- "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
525
- "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
526
- "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
527
- "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
528
- "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
529
- "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
530
- "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
531
- "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
532
- "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
533
- "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
534
- "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
535
- "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
536
- "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
537
- "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
538
- "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
539
- "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
540
- "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
541
- "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
542
- "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
543
- "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
544
- "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
545
- "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
546
- "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
547
- "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
548
- "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
549
- "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
550
- "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
551
- "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
552
- "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
553
- "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
554
- "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
555
- "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
556
- "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
557
- "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
558
- "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
559
- "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
560
- "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
561
- "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
562
- "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
563
- "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
564
- "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
565
- "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
566
- "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
567
- "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
568
- "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
569
- "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
570
- "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
571
- "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
572
- "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
573
- "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
574
- "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
575
- "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
576
- "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
577
- "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
578
- "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
579
- "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
580
- "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
581
- "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
582
- "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
583
- "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
584
- "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
585
- "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
586
- "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
587
- "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
588
- "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
589
- "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
590
- "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
591
- "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
592
- "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
593
- "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
594
- "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
595
- "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
596
- "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
597
- "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
598
- "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
599
- "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
600
- "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
601
- "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
602
- "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
603
- "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
604
- "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
605
- "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
606
- "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
607
- "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
608
- "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
609
- "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
610
- "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
611
- "encoder.block.24.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
612
- "encoder.block.24.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
613
- "encoder.block.24.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
614
- "encoder.block.24.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
615
- "encoder.block.24.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
616
- "encoder.block.24.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
617
- "encoder.block.24.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
618
- "encoder.block.24.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
619
- "encoder.block.24.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
620
- "encoder.block.25.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
621
- "encoder.block.25.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
622
- "encoder.block.25.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
623
- "encoder.block.25.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
624
- "encoder.block.25.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
625
- "encoder.block.25.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
626
- "encoder.block.25.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
627
- "encoder.block.25.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
628
- "encoder.block.25.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
629
- "encoder.block.26.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
630
- "encoder.block.26.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
631
- "encoder.block.26.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
632
- "encoder.block.26.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
633
- "encoder.block.26.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
634
- "encoder.block.26.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
635
- "encoder.block.26.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
636
- "encoder.block.26.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
637
- "encoder.block.26.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
638
- "encoder.block.27.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
639
- "encoder.block.27.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
640
- "encoder.block.27.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
641
- "encoder.block.27.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
642
- "encoder.block.27.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
643
- "encoder.block.27.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
644
- "encoder.block.27.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
645
- "encoder.block.27.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
646
- "encoder.block.27.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
647
- "encoder.block.28.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
648
- "encoder.block.28.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
649
- "encoder.block.28.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
650
- "encoder.block.28.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
651
- "encoder.block.28.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
652
- "encoder.block.28.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
653
- "encoder.block.28.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
654
- "encoder.block.28.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
655
- "encoder.block.28.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
656
- "encoder.block.29.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
657
- "encoder.block.29.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
658
- "encoder.block.29.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
659
- "encoder.block.29.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
660
- "encoder.block.29.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
661
- "encoder.block.29.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
662
- "encoder.block.29.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
663
- "encoder.block.29.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
664
- "encoder.block.29.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
665
- "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
666
- "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
667
- "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
668
- "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
669
- "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
670
- "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
671
- "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
672
- "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
673
- "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
674
- "encoder.block.30.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
675
- "encoder.block.30.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
676
- "encoder.block.30.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
677
- "encoder.block.30.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
678
- "encoder.block.30.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
679
- "encoder.block.30.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
680
- "encoder.block.30.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
681
- "encoder.block.30.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
682
- "encoder.block.30.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
683
- "encoder.block.31.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
684
- "encoder.block.31.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
685
- "encoder.block.31.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
686
- "encoder.block.31.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
687
- "encoder.block.31.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
688
- "encoder.block.31.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
689
- "encoder.block.31.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
690
- "encoder.block.31.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
691
- "encoder.block.31.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
692
- "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
693
- "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
694
- "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
695
- "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
696
- "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
697
- "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
698
- "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
699
- "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
700
- "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
701
- "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
702
- "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
703
- "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
704
- "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
705
- "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
706
- "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
707
- "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
708
- "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
709
- "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
710
- "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
711
- "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
712
- "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
713
- "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
714
- "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
715
- "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
716
- "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
717
- "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
718
- "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
719
- "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
720
- "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
721
- "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
722
- "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
723
- "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
724
- "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
725
- "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
726
- "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
727
- "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
728
- "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
729
- "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
730
- "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
731
- "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
732
- "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
733
- "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
734
- "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
735
- "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
736
- "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
737
- "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
738
- "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
739
- "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
740
- "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
741
- "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
742
- "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
743
- "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
744
- "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
745
- "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
746
- "encoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
747
- "encoder.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
748
- "lm_head.weight": "pytorch_model-00002-of-00002.bin",
749
- "shared.weight": "pytorch_model-00001-of-00002.bin"
750
- }
751
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
special_tokens_map.json CHANGED
@@ -101,7 +101,25 @@
101
  "<extra_id_98>",
102
  "<extra_id_99>"
103
  ],
104
- "eos_token": "</s>",
105
- "pad_token": "<pad>",
106
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
107
  }
 
101
  "<extra_id_98>",
102
  "<extra_id_99>"
103
  ],
104
+ "eos_token": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
  }
spiece.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df65ad942bf9646454eaaff5bdb08e155b6b4e105ae8e2dac96d0ebb2e455073
3
- size 2148928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef11ac9a22c7503492f56d48dce53be20e339b63605983e9f27d2cd0e0f3922c
3
+ size 4427844
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15aa9b3cbcf2ec220c6044f898e27fd302067a336df5369ec55a8f385f849d3b
3
- size 8236606
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ceb4f73d0ecf9131e8fbf80b7b5261c202f85b69d3b24f822bf59249b16cccc
3
+ size 16634421
tokenizer_config.json CHANGED
@@ -1,4 +1,830 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "additional_special_tokens": [
3
  "<extra_id_0>",
4
  "<extra_id_1>",
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "2": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "256000": {
20
+ "content": "<extra_id_99>",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": true,
25
+ "special": true
26
+ },
27
+ "256001": {
28
+ "content": "<extra_id_98>",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": true,
33
+ "special": true
34
+ },
35
+ "256002": {
36
+ "content": "<extra_id_97>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": true,
41
+ "special": true
42
+ },
43
+ "256003": {
44
+ "content": "<extra_id_96>",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": true,
49
+ "special": true
50
+ },
51
+ "256004": {
52
+ "content": "<extra_id_95>",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": true,
57
+ "special": true
58
+ },
59
+ "256005": {
60
+ "content": "<extra_id_94>",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": true,
65
+ "special": true
66
+ },
67
+ "256006": {
68
+ "content": "<extra_id_93>",
69
+ "lstrip": true,
70
+ "normalized": false,
71
+ "rstrip": true,
72
+ "single_word": true,
73
+ "special": true
74
+ },
75
+ "256007": {
76
+ "content": "<extra_id_92>",
77
+ "lstrip": true,
78
+ "normalized": false,
79
+ "rstrip": true,
80
+ "single_word": true,
81
+ "special": true
82
+ },
83
+ "256008": {
84
+ "content": "<extra_id_91>",
85
+ "lstrip": true,
86
+ "normalized": false,
87
+ "rstrip": true,
88
+ "single_word": true,
89
+ "special": true
90
+ },
91
+ "256009": {
92
+ "content": "<extra_id_90>",
93
+ "lstrip": true,
94
+ "normalized": false,
95
+ "rstrip": true,
96
+ "single_word": true,
97
+ "special": true
98
+ },
99
+ "256010": {
100
+ "content": "<extra_id_89>",
101
+ "lstrip": true,
102
+ "normalized": false,
103
+ "rstrip": true,
104
+ "single_word": true,
105
+ "special": true
106
+ },
107
+ "256011": {
108
+ "content": "<extra_id_88>",
109
+ "lstrip": true,
110
+ "normalized": false,
111
+ "rstrip": true,
112
+ "single_word": true,
113
+ "special": true
114
+ },
115
+ "256012": {
116
+ "content": "<extra_id_87>",
117
+ "lstrip": true,
118
+ "normalized": false,
119
+ "rstrip": true,
120
+ "single_word": true,
121
+ "special": true
122
+ },
123
+ "256013": {
124
+ "content": "<extra_id_86>",
125
+ "lstrip": true,
126
+ "normalized": false,
127
+ "rstrip": true,
128
+ "single_word": true,
129
+ "special": true
130
+ },
131
+ "256014": {
132
+ "content": "<extra_id_85>",
133
+ "lstrip": true,
134
+ "normalized": false,
135
+ "rstrip": true,
136
+ "single_word": true,
137
+ "special": true
138
+ },
139
+ "256015": {
140
+ "content": "<extra_id_84>",
141
+ "lstrip": true,
142
+ "normalized": false,
143
+ "rstrip": true,
144
+ "single_word": true,
145
+ "special": true
146
+ },
147
+ "256016": {
148
+ "content": "<extra_id_83>",
149
+ "lstrip": true,
150
+ "normalized": false,
151
+ "rstrip": true,
152
+ "single_word": true,
153
+ "special": true
154
+ },
155
+ "256017": {
156
+ "content": "<extra_id_82>",
157
+ "lstrip": true,
158
+ "normalized": false,
159
+ "rstrip": true,
160
+ "single_word": true,
161
+ "special": true
162
+ },
163
+ "256018": {
164
+ "content": "<extra_id_81>",
165
+ "lstrip": true,
166
+ "normalized": false,
167
+ "rstrip": true,
168
+ "single_word": true,
169
+ "special": true
170
+ },
171
+ "256019": {
172
+ "content": "<extra_id_80>",
173
+ "lstrip": true,
174
+ "normalized": false,
175
+ "rstrip": true,
176
+ "single_word": true,
177
+ "special": true
178
+ },
179
+ "256020": {
180
+ "content": "<extra_id_79>",
181
+ "lstrip": true,
182
+ "normalized": false,
183
+ "rstrip": true,
184
+ "single_word": true,
185
+ "special": true
186
+ },
187
+ "256021": {
188
+ "content": "<extra_id_78>",
189
+ "lstrip": true,
190
+ "normalized": false,
191
+ "rstrip": true,
192
+ "single_word": true,
193
+ "special": true
194
+ },
195
+ "256022": {
196
+ "content": "<extra_id_77>",
197
+ "lstrip": true,
198
+ "normalized": false,
199
+ "rstrip": true,
200
+ "single_word": true,
201
+ "special": true
202
+ },
203
+ "256023": {
204
+ "content": "<extra_id_76>",
205
+ "lstrip": true,
206
+ "normalized": false,
207
+ "rstrip": true,
208
+ "single_word": true,
209
+ "special": true
210
+ },
211
+ "256024": {
212
+ "content": "<extra_id_75>",
213
+ "lstrip": true,
214
+ "normalized": false,
215
+ "rstrip": true,
216
+ "single_word": true,
217
+ "special": true
218
+ },
219
+ "256025": {
220
+ "content": "<extra_id_74>",
221
+ "lstrip": true,
222
+ "normalized": false,
223
+ "rstrip": true,
224
+ "single_word": true,
225
+ "special": true
226
+ },
227
+ "256026": {
228
+ "content": "<extra_id_73>",
229
+ "lstrip": true,
230
+ "normalized": false,
231
+ "rstrip": true,
232
+ "single_word": true,
233
+ "special": true
234
+ },
235
+ "256027": {
236
+ "content": "<extra_id_72>",
237
+ "lstrip": true,
238
+ "normalized": false,
239
+ "rstrip": true,
240
+ "single_word": true,
241
+ "special": true
242
+ },
243
+ "256028": {
244
+ "content": "<extra_id_71>",
245
+ "lstrip": true,
246
+ "normalized": false,
247
+ "rstrip": true,
248
+ "single_word": true,
249
+ "special": true
250
+ },
251
+ "256029": {
252
+ "content": "<extra_id_70>",
253
+ "lstrip": true,
254
+ "normalized": false,
255
+ "rstrip": true,
256
+ "single_word": true,
257
+ "special": true
258
+ },
259
+ "256030": {
260
+ "content": "<extra_id_69>",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": true,
264
+ "single_word": true,
265
+ "special": true
266
+ },
267
+ "256031": {
268
+ "content": "<extra_id_68>",
269
+ "lstrip": true,
270
+ "normalized": false,
271
+ "rstrip": true,
272
+ "single_word": true,
273
+ "special": true
274
+ },
275
+ "256032": {
276
+ "content": "<extra_id_67>",
277
+ "lstrip": true,
278
+ "normalized": false,
279
+ "rstrip": true,
280
+ "single_word": true,
281
+ "special": true
282
+ },
283
+ "256033": {
284
+ "content": "<extra_id_66>",
285
+ "lstrip": true,
286
+ "normalized": false,
287
+ "rstrip": true,
288
+ "single_word": true,
289
+ "special": true
290
+ },
291
+ "256034": {
292
+ "content": "<extra_id_65>",
293
+ "lstrip": true,
294
+ "normalized": false,
295
+ "rstrip": true,
296
+ "single_word": true,
297
+ "special": true
298
+ },
299
+ "256035": {
300
+ "content": "<extra_id_64>",
301
+ "lstrip": true,
302
+ "normalized": false,
303
+ "rstrip": true,
304
+ "single_word": true,
305
+ "special": true
306
+ },
307
+ "256036": {
308
+ "content": "<extra_id_63>",
309
+ "lstrip": true,
310
+ "normalized": false,
311
+ "rstrip": true,
312
+ "single_word": true,
313
+ "special": true
314
+ },
315
+ "256037": {
316
+ "content": "<extra_id_62>",
317
+ "lstrip": true,
318
+ "normalized": false,
319
+ "rstrip": true,
320
+ "single_word": true,
321
+ "special": true
322
+ },
323
+ "256038": {
324
+ "content": "<extra_id_61>",
325
+ "lstrip": true,
326
+ "normalized": false,
327
+ "rstrip": true,
328
+ "single_word": true,
329
+ "special": true
330
+ },
331
+ "256039": {
332
+ "content": "<extra_id_60>",
333
+ "lstrip": true,
334
+ "normalized": false,
335
+ "rstrip": true,
336
+ "single_word": true,
337
+ "special": true
338
+ },
339
+ "256040": {
340
+ "content": "<extra_id_59>",
341
+ "lstrip": true,
342
+ "normalized": false,
343
+ "rstrip": true,
344
+ "single_word": true,
345
+ "special": true
346
+ },
347
+ "256041": {
348
+ "content": "<extra_id_58>",
349
+ "lstrip": true,
350
+ "normalized": false,
351
+ "rstrip": true,
352
+ "single_word": true,
353
+ "special": true
354
+ },
355
+ "256042": {
356
+ "content": "<extra_id_57>",
357
+ "lstrip": true,
358
+ "normalized": false,
359
+ "rstrip": true,
360
+ "single_word": true,
361
+ "special": true
362
+ },
363
+ "256043": {
364
+ "content": "<extra_id_56>",
365
+ "lstrip": true,
366
+ "normalized": false,
367
+ "rstrip": true,
368
+ "single_word": true,
369
+ "special": true
370
+ },
371
+ "256044": {
372
+ "content": "<extra_id_55>",
373
+ "lstrip": true,
374
+ "normalized": false,
375
+ "rstrip": true,
376
+ "single_word": true,
377
+ "special": true
378
+ },
379
+ "256045": {
380
+ "content": "<extra_id_54>",
381
+ "lstrip": true,
382
+ "normalized": false,
383
+ "rstrip": true,
384
+ "single_word": true,
385
+ "special": true
386
+ },
387
+ "256046": {
388
+ "content": "<extra_id_53>",
389
+ "lstrip": true,
390
+ "normalized": false,
391
+ "rstrip": true,
392
+ "single_word": true,
393
+ "special": true
394
+ },
395
+ "256047": {
396
+ "content": "<extra_id_52>",
397
+ "lstrip": true,
398
+ "normalized": false,
399
+ "rstrip": true,
400
+ "single_word": true,
401
+ "special": true
402
+ },
403
+ "256048": {
404
+ "content": "<extra_id_51>",
405
+ "lstrip": true,
406
+ "normalized": false,
407
+ "rstrip": true,
408
+ "single_word": true,
409
+ "special": true
410
+ },
411
+ "256049": {
412
+ "content": "<extra_id_50>",
413
+ "lstrip": true,
414
+ "normalized": false,
415
+ "rstrip": true,
416
+ "single_word": true,
417
+ "special": true
418
+ },
419
+ "256050": {
420
+ "content": "<extra_id_49>",
421
+ "lstrip": true,
422
+ "normalized": false,
423
+ "rstrip": true,
424
+ "single_word": true,
425
+ "special": true
426
+ },
427
+ "256051": {
428
+ "content": "<extra_id_48>",
429
+ "lstrip": true,
430
+ "normalized": false,
431
+ "rstrip": true,
432
+ "single_word": true,
433
+ "special": true
434
+ },
435
+ "256052": {
436
+ "content": "<extra_id_47>",
437
+ "lstrip": true,
438
+ "normalized": false,
439
+ "rstrip": true,
440
+ "single_word": true,
441
+ "special": true
442
+ },
443
+ "256053": {
444
+ "content": "<extra_id_46>",
445
+ "lstrip": true,
446
+ "normalized": false,
447
+ "rstrip": true,
448
+ "single_word": true,
449
+ "special": true
450
+ },
451
+ "256054": {
452
+ "content": "<extra_id_45>",
453
+ "lstrip": true,
454
+ "normalized": false,
455
+ "rstrip": true,
456
+ "single_word": true,
457
+ "special": true
458
+ },
459
+ "256055": {
460
+ "content": "<extra_id_44>",
461
+ "lstrip": true,
462
+ "normalized": false,
463
+ "rstrip": true,
464
+ "single_word": true,
465
+ "special": true
466
+ },
467
+ "256056": {
468
+ "content": "<extra_id_43>",
469
+ "lstrip": true,
470
+ "normalized": false,
471
+ "rstrip": true,
472
+ "single_word": true,
473
+ "special": true
474
+ },
475
+ "256057": {
476
+ "content": "<extra_id_42>",
477
+ "lstrip": true,
478
+ "normalized": false,
479
+ "rstrip": true,
480
+ "single_word": true,
481
+ "special": true
482
+ },
483
+ "256058": {
484
+ "content": "<extra_id_41>",
485
+ "lstrip": true,
486
+ "normalized": false,
487
+ "rstrip": true,
488
+ "single_word": true,
489
+ "special": true
490
+ },
491
+ "256059": {
492
+ "content": "<extra_id_40>",
493
+ "lstrip": true,
494
+ "normalized": false,
495
+ "rstrip": true,
496
+ "single_word": true,
497
+ "special": true
498
+ },
499
+ "256060": {
500
+ "content": "<extra_id_39>",
501
+ "lstrip": true,
502
+ "normalized": false,
503
+ "rstrip": true,
504
+ "single_word": true,
505
+ "special": true
506
+ },
507
+ "256061": {
508
+ "content": "<extra_id_38>",
509
+ "lstrip": true,
510
+ "normalized": false,
511
+ "rstrip": true,
512
+ "single_word": true,
513
+ "special": true
514
+ },
515
+ "256062": {
516
+ "content": "<extra_id_37>",
517
+ "lstrip": true,
518
+ "normalized": false,
519
+ "rstrip": true,
520
+ "single_word": true,
521
+ "special": true
522
+ },
523
+ "256063": {
524
+ "content": "<extra_id_36>",
525
+ "lstrip": true,
526
+ "normalized": false,
527
+ "rstrip": true,
528
+ "single_word": true,
529
+ "special": true
530
+ },
531
+ "256064": {
532
+ "content": "<extra_id_35>",
533
+ "lstrip": true,
534
+ "normalized": false,
535
+ "rstrip": true,
536
+ "single_word": true,
537
+ "special": true
538
+ },
539
+ "256065": {
540
+ "content": "<extra_id_34>",
541
+ "lstrip": true,
542
+ "normalized": false,
543
+ "rstrip": true,
544
+ "single_word": true,
545
+ "special": true
546
+ },
547
+ "256066": {
548
+ "content": "<extra_id_33>",
549
+ "lstrip": true,
550
+ "normalized": false,
551
+ "rstrip": true,
552
+ "single_word": true,
553
+ "special": true
554
+ },
555
+ "256067": {
556
+ "content": "<extra_id_32>",
557
+ "lstrip": true,
558
+ "normalized": false,
559
+ "rstrip": true,
560
+ "single_word": true,
561
+ "special": true
562
+ },
563
+ "256068": {
564
+ "content": "<extra_id_31>",
565
+ "lstrip": true,
566
+ "normalized": false,
567
+ "rstrip": true,
568
+ "single_word": true,
569
+ "special": true
570
+ },
571
+ "256069": {
572
+ "content": "<extra_id_30>",
573
+ "lstrip": true,
574
+ "normalized": false,
575
+ "rstrip": true,
576
+ "single_word": true,
577
+ "special": true
578
+ },
579
+ "256070": {
580
+ "content": "<extra_id_29>",
581
+ "lstrip": true,
582
+ "normalized": false,
583
+ "rstrip": true,
584
+ "single_word": true,
585
+ "special": true
586
+ },
587
+ "256071": {
588
+ "content": "<extra_id_28>",
589
+ "lstrip": true,
590
+ "normalized": false,
591
+ "rstrip": true,
592
+ "single_word": true,
593
+ "special": true
594
+ },
595
+ "256072": {
596
+ "content": "<extra_id_27>",
597
+ "lstrip": true,
598
+ "normalized": false,
599
+ "rstrip": true,
600
+ "single_word": true,
601
+ "special": true
602
+ },
603
+ "256073": {
604
+ "content": "<extra_id_26>",
605
+ "lstrip": true,
606
+ "normalized": false,
607
+ "rstrip": true,
608
+ "single_word": true,
609
+ "special": true
610
+ },
611
+ "256074": {
612
+ "content": "<extra_id_25>",
613
+ "lstrip": true,
614
+ "normalized": false,
615
+ "rstrip": true,
616
+ "single_word": true,
617
+ "special": true
618
+ },
619
+ "256075": {
620
+ "content": "<extra_id_24>",
621
+ "lstrip": true,
622
+ "normalized": false,
623
+ "rstrip": true,
624
+ "single_word": true,
625
+ "special": true
626
+ },
627
+ "256076": {
628
+ "content": "<extra_id_23>",
629
+ "lstrip": true,
630
+ "normalized": false,
631
+ "rstrip": true,
632
+ "single_word": true,
633
+ "special": true
634
+ },
635
+ "256077": {
636
+ "content": "<extra_id_22>",
637
+ "lstrip": true,
638
+ "normalized": false,
639
+ "rstrip": true,
640
+ "single_word": true,
641
+ "special": true
642
+ },
643
+ "256078": {
644
+ "content": "<extra_id_21>",
645
+ "lstrip": true,
646
+ "normalized": false,
647
+ "rstrip": true,
648
+ "single_word": true,
649
+ "special": true
650
+ },
651
+ "256079": {
652
+ "content": "<extra_id_20>",
653
+ "lstrip": true,
654
+ "normalized": false,
655
+ "rstrip": true,
656
+ "single_word": true,
657
+ "special": true
658
+ },
659
+ "256080": {
660
+ "content": "<extra_id_19>",
661
+ "lstrip": true,
662
+ "normalized": false,
663
+ "rstrip": true,
664
+ "single_word": true,
665
+ "special": true
666
+ },
667
+ "256081": {
668
+ "content": "<extra_id_18>",
669
+ "lstrip": true,
670
+ "normalized": false,
671
+ "rstrip": true,
672
+ "single_word": true,
673
+ "special": true
674
+ },
675
+ "256082": {
676
+ "content": "<extra_id_17>",
677
+ "lstrip": true,
678
+ "normalized": false,
679
+ "rstrip": true,
680
+ "single_word": true,
681
+ "special": true
682
+ },
683
+ "256083": {
684
+ "content": "<extra_id_16>",
685
+ "lstrip": true,
686
+ "normalized": false,
687
+ "rstrip": true,
688
+ "single_word": true,
689
+ "special": true
690
+ },
691
+ "256084": {
692
+ "content": "<extra_id_15>",
693
+ "lstrip": true,
694
+ "normalized": false,
695
+ "rstrip": true,
696
+ "single_word": true,
697
+ "special": true
698
+ },
699
+ "256085": {
700
+ "content": "<extra_id_14>",
701
+ "lstrip": true,
702
+ "normalized": false,
703
+ "rstrip": true,
704
+ "single_word": true,
705
+ "special": true
706
+ },
707
+ "256086": {
708
+ "content": "<extra_id_13>",
709
+ "lstrip": true,
710
+ "normalized": false,
711
+ "rstrip": true,
712
+ "single_word": true,
713
+ "special": true
714
+ },
715
+ "256087": {
716
+ "content": "<extra_id_12>",
717
+ "lstrip": true,
718
+ "normalized": false,
719
+ "rstrip": true,
720
+ "single_word": true,
721
+ "special": true
722
+ },
723
+ "256088": {
724
+ "content": "<extra_id_11>",
725
+ "lstrip": true,
726
+ "normalized": false,
727
+ "rstrip": true,
728
+ "single_word": true,
729
+ "special": true
730
+ },
731
+ "256089": {
732
+ "content": "<extra_id_10>",
733
+ "lstrip": true,
734
+ "normalized": false,
735
+ "rstrip": true,
736
+ "single_word": true,
737
+ "special": true
738
+ },
739
+ "256090": {
740
+ "content": "<extra_id_9>",
741
+ "lstrip": true,
742
+ "normalized": false,
743
+ "rstrip": true,
744
+ "single_word": true,
745
+ "special": true
746
+ },
747
+ "256091": {
748
+ "content": "<extra_id_8>",
749
+ "lstrip": true,
750
+ "normalized": false,
751
+ "rstrip": true,
752
+ "single_word": true,
753
+ "special": true
754
+ },
755
+ "256092": {
756
+ "content": "<extra_id_7>",
757
+ "lstrip": true,
758
+ "normalized": false,
759
+ "rstrip": true,
760
+ "single_word": true,
761
+ "special": true
762
+ },
763
+ "256093": {
764
+ "content": "<extra_id_6>",
765
+ "lstrip": true,
766
+ "normalized": false,
767
+ "rstrip": true,
768
+ "single_word": true,
769
+ "special": true
770
+ },
771
+ "256094": {
772
+ "content": "<extra_id_5>",
773
+ "lstrip": true,
774
+ "normalized": false,
775
+ "rstrip": true,
776
+ "single_word": true,
777
+ "special": true
778
+ },
779
+ "256095": {
780
+ "content": "<extra_id_4>",
781
+ "lstrip": true,
782
+ "normalized": false,
783
+ "rstrip": true,
784
+ "single_word": true,
785
+ "special": true
786
+ },
787
+ "256096": {
788
+ "content": "<extra_id_3>",
789
+ "lstrip": true,
790
+ "normalized": false,
791
+ "rstrip": true,
792
+ "single_word": true,
793
+ "special": true
794
+ },
795
+ "256097": {
796
+ "content": "<extra_id_2>",
797
+ "lstrip": true,
798
+ "normalized": false,
799
+ "rstrip": true,
800
+ "single_word": true,
801
+ "special": true
802
+ },
803
+ "256098": {
804
+ "content": "<extra_id_1>",
805
+ "lstrip": true,
806
+ "normalized": false,
807
+ "rstrip": true,
808
+ "single_word": true,
809
+ "special": true
810
+ },
811
+ "256099": {
812
+ "content": "<extra_id_0>",
813
+ "lstrip": true,
814
+ "normalized": false,
815
+ "rstrip": true,
816
+ "single_word": true,
817
+ "special": true
818
+ },
819
+ "256100": {
820
+ "content": "<pad>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ }
827
+ },
828
  "additional_special_tokens": [
829
  "<extra_id_0>",
830
  "<extra_id_1>",