cnmoro commited on
Commit
89b9809
·
1 Parent(s): a25d900

Upload 9 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|NLG|>": 50260,
3
+ "<|NLU|>": 50259,
4
+ "<|beginoftext|>": 50257,
5
+ "<|extra_id_0|>": 50261,
6
+ "<|extra_id_10|>": 50271,
7
+ "<|extra_id_11|>": 50272,
8
+ "<|extra_id_12|>": 50273,
9
+ "<|extra_id_13|>": 50274,
10
+ "<|extra_id_14|>": 50275,
11
+ "<|extra_id_15|>": 50276,
12
+ "<|extra_id_16|>": 50277,
13
+ "<|extra_id_17|>": 50278,
14
+ "<|extra_id_18|>": 50279,
15
+ "<|extra_id_19|>": 50280,
16
+ "<|extra_id_1|>": 50262,
17
+ "<|extra_id_20|>": 50281,
18
+ "<|extra_id_21|>": 50282,
19
+ "<|extra_id_22|>": 50283,
20
+ "<|extra_id_23|>": 50284,
21
+ "<|extra_id_24|>": 50285,
22
+ "<|extra_id_25|>": 50286,
23
+ "<|extra_id_26|>": 50287,
24
+ "<|extra_id_27|>": 50288,
25
+ "<|extra_id_28|>": 50289,
26
+ "<|extra_id_29|>": 50290,
27
+ "<|extra_id_2|>": 50263,
28
+ "<|extra_id_30|>": 50291,
29
+ "<|extra_id_31|>": 50292,
30
+ "<|extra_id_32|>": 50293,
31
+ "<|extra_id_33|>": 50294,
32
+ "<|extra_id_34|>": 50295,
33
+ "<|extra_id_35|>": 50296,
34
+ "<|extra_id_36|>": 50297,
35
+ "<|extra_id_37|>": 50298,
36
+ "<|extra_id_38|>": 50299,
37
+ "<|extra_id_39|>": 50300,
38
+ "<|extra_id_3|>": 50264,
39
+ "<|extra_id_40|>": 50301,
40
+ "<|extra_id_41|>": 50302,
41
+ "<|extra_id_42|>": 50303,
42
+ "<|extra_id_43|>": 50304,
43
+ "<|extra_id_44|>": 50305,
44
+ "<|extra_id_45|>": 50306,
45
+ "<|extra_id_46|>": 50307,
46
+ "<|extra_id_47|>": 50308,
47
+ "<|extra_id_48|>": 50309,
48
+ "<|extra_id_49|>": 50310,
49
+ "<|extra_id_4|>": 50265,
50
+ "<|extra_id_50|>": 50311,
51
+ "<|extra_id_51|>": 50312,
52
+ "<|extra_id_52|>": 50313,
53
+ "<|extra_id_53|>": 50314,
54
+ "<|extra_id_54|>": 50315,
55
+ "<|extra_id_55|>": 50316,
56
+ "<|extra_id_56|>": 50317,
57
+ "<|extra_id_57|>": 50318,
58
+ "<|extra_id_58|>": 50319,
59
+ "<|extra_id_59|>": 50320,
60
+ "<|extra_id_5|>": 50266,
61
+ "<|extra_id_60|>": 50321,
62
+ "<|extra_id_61|>": 50322,
63
+ "<|extra_id_62|>": 50323,
64
+ "<|extra_id_63|>": 50324,
65
+ "<|extra_id_64|>": 50325,
66
+ "<|extra_id_65|>": 50326,
67
+ "<|extra_id_66|>": 50327,
68
+ "<|extra_id_67|>": 50328,
69
+ "<|extra_id_68|>": 50329,
70
+ "<|extra_id_69|>": 50330,
71
+ "<|extra_id_6|>": 50267,
72
+ "<|extra_id_70|>": 50331,
73
+ "<|extra_id_71|>": 50332,
74
+ "<|extra_id_72|>": 50333,
75
+ "<|extra_id_73|>": 50334,
76
+ "<|extra_id_74|>": 50335,
77
+ "<|extra_id_75|>": 50336,
78
+ "<|extra_id_76|>": 50337,
79
+ "<|extra_id_77|>": 50338,
80
+ "<|extra_id_78|>": 50339,
81
+ "<|extra_id_79|>": 50340,
82
+ "<|extra_id_7|>": 50268,
83
+ "<|extra_id_80|>": 50341,
84
+ "<|extra_id_81|>": 50342,
85
+ "<|extra_id_82|>": 50343,
86
+ "<|extra_id_83|>": 50344,
87
+ "<|extra_id_84|>": 50345,
88
+ "<|extra_id_85|>": 50346,
89
+ "<|extra_id_86|>": 50347,
90
+ "<|extra_id_87|>": 50348,
91
+ "<|extra_id_88|>": 50349,
92
+ "<|extra_id_89|>": 50350,
93
+ "<|extra_id_8|>": 50269,
94
+ "<|extra_id_90|>": 50351,
95
+ "<|extra_id_91|>": 50352,
96
+ "<|extra_id_92|>": 50353,
97
+ "<|extra_id_93|>": 50354,
98
+ "<|extra_id_94|>": 50355,
99
+ "<|extra_id_95|>": 50356,
100
+ "<|extra_id_96|>": 50357,
101
+ "<|extra_id_97|>": 50358,
102
+ "<|extra_id_98|>": 50359,
103
+ "<|extra_id_99|>": 50360,
104
+ "<|extra_id_9|>": 50270,
105
+ "<|unk|>": 50258
106
+ }
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tgsc/ult5-pt-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "bos_token_id": 50257,
7
+ "classifier_dropout": 0.0,
8
+ "d_ff": 2048,
9
+ "d_kv": 64,
10
+ "d_model": 512,
11
+ "decoder_start_token_id": 0,
12
+ "dense_act_fn": "silu",
13
+ "dropout_rate": 0.1,
14
+ "eos_token_id": 1,
15
+ "feed_forward_proj": "gated-silu",
16
+ "initializer_factor": 1.0,
17
+ "is_encoder_decoder": true,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "model_type": "t5",
21
+ "n_positions": 1024,
22
+ "num_decoder_layers": 6,
23
+ "num_heads": 8,
24
+ "num_layers": 6,
25
+ "output_past": true,
26
+ "pad_token_id": 0,
27
+ "relative_attention_max_distance": 128,
28
+ "relative_attention_num_buckets": 32,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.34.1",
37
+ "use_cache": true,
38
+ "vocab_size": 50361
39
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50257,
4
+ "decoder_start_token_id": 0,
5
+ "eos_token_id": 1,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.34.1"
8
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0173200311798d0c82df1461ea8aa0759ad22afa36f4f9f569b346530e511516
3
+ size 329749190
special_tokens_map.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|pad|>",
4
+ "<|endoftext|>",
5
+ "<|NLU|>",
6
+ "<|NLG|>",
7
+ "<|extra_id_0|>",
8
+ "<|extra_id_1|>",
9
+ "<|extra_id_2|>",
10
+ "<|extra_id_3|>",
11
+ "<|extra_id_4|>",
12
+ "<|extra_id_5|>",
13
+ "<|extra_id_6|>",
14
+ "<|extra_id_7|>",
15
+ "<|extra_id_8|>",
16
+ "<|extra_id_9|>",
17
+ "<|extra_id_10|>",
18
+ "<|extra_id_11|>",
19
+ "<|extra_id_12|>",
20
+ "<|extra_id_13|>",
21
+ "<|extra_id_14|>",
22
+ "<|extra_id_15|>",
23
+ "<|extra_id_16|>",
24
+ "<|extra_id_17|>",
25
+ "<|extra_id_18|>",
26
+ "<|extra_id_19|>",
27
+ "<|extra_id_20|>",
28
+ "<|extra_id_21|>",
29
+ "<|extra_id_22|>",
30
+ "<|extra_id_23|>",
31
+ "<|extra_id_24|>",
32
+ "<|extra_id_25|>",
33
+ "<|extra_id_26|>",
34
+ "<|extra_id_27|>",
35
+ "<|extra_id_28|>",
36
+ "<|extra_id_29|>",
37
+ "<|extra_id_30|>",
38
+ "<|extra_id_31|>",
39
+ "<|extra_id_32|>",
40
+ "<|extra_id_33|>",
41
+ "<|extra_id_34|>",
42
+ "<|extra_id_35|>",
43
+ "<|extra_id_36|>",
44
+ "<|extra_id_37|>",
45
+ "<|extra_id_38|>",
46
+ "<|extra_id_39|>",
47
+ "<|extra_id_40|>",
48
+ "<|extra_id_41|>",
49
+ "<|extra_id_42|>",
50
+ "<|extra_id_43|>",
51
+ "<|extra_id_44|>",
52
+ "<|extra_id_45|>",
53
+ "<|extra_id_46|>",
54
+ "<|extra_id_47|>",
55
+ "<|extra_id_48|>",
56
+ "<|extra_id_49|>",
57
+ "<|extra_id_50|>",
58
+ "<|extra_id_51|>",
59
+ "<|extra_id_52|>",
60
+ "<|extra_id_53|>",
61
+ "<|extra_id_54|>",
62
+ "<|extra_id_55|>",
63
+ "<|extra_id_56|>",
64
+ "<|extra_id_57|>",
65
+ "<|extra_id_58|>",
66
+ "<|extra_id_59|>",
67
+ "<|extra_id_60|>",
68
+ "<|extra_id_61|>",
69
+ "<|extra_id_62|>",
70
+ "<|extra_id_63|>",
71
+ "<|extra_id_64|>",
72
+ "<|extra_id_65|>",
73
+ "<|extra_id_66|>",
74
+ "<|extra_id_67|>",
75
+ "<|extra_id_68|>",
76
+ "<|extra_id_69|>",
77
+ "<|extra_id_70|>",
78
+ "<|extra_id_71|>",
79
+ "<|extra_id_72|>",
80
+ "<|extra_id_73|>",
81
+ "<|extra_id_74|>",
82
+ "<|extra_id_75|>",
83
+ "<|extra_id_76|>",
84
+ "<|extra_id_77|>",
85
+ "<|extra_id_78|>",
86
+ "<|extra_id_79|>",
87
+ "<|extra_id_80|>",
88
+ "<|extra_id_81|>",
89
+ "<|extra_id_82|>",
90
+ "<|extra_id_83|>",
91
+ "<|extra_id_84|>",
92
+ "<|extra_id_85|>",
93
+ "<|extra_id_86|>",
94
+ "<|extra_id_87|>",
95
+ "<|extra_id_88|>",
96
+ "<|extra_id_89|>",
97
+ "<|extra_id_90|>",
98
+ "<|extra_id_91|>",
99
+ "<|extra_id_92|>",
100
+ "<|extra_id_93|>",
101
+ "<|extra_id_94|>",
102
+ "<|extra_id_95|>",
103
+ "<|extra_id_96|>",
104
+ "<|extra_id_97|>",
105
+ "<|extra_id_98|>",
106
+ "<|extra_id_99|>"
107
+ ],
108
+ "bos_token": "<|beginoftext|>",
109
+ "eos_token": "<|endoftext|>",
110
+ "pad_token": "<|pad|>",
111
+ "unk_token": "<|unk|>"
112
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,966 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|pad|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50257": {
21
+ "content": "<|beginoftext|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "50258": {
29
+ "content": "<|unk|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50259": {
37
+ "content": "<|NLU|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "50260": {
45
+ "content": "<|NLG|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "50261": {
53
+ "content": "<|extra_id_0|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "50262": {
61
+ "content": "<|extra_id_1|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "50263": {
69
+ "content": "<|extra_id_2|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "50264": {
77
+ "content": "<|extra_id_3|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "50265": {
85
+ "content": "<|extra_id_4|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "50266": {
93
+ "content": "<|extra_id_5|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "50267": {
101
+ "content": "<|extra_id_6|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "50268": {
109
+ "content": "<|extra_id_7|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "50269": {
117
+ "content": "<|extra_id_8|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "50270": {
125
+ "content": "<|extra_id_9|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "50271": {
133
+ "content": "<|extra_id_10|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "50272": {
141
+ "content": "<|extra_id_11|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "50273": {
149
+ "content": "<|extra_id_12|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "50274": {
157
+ "content": "<|extra_id_13|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "50275": {
165
+ "content": "<|extra_id_14|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "50276": {
173
+ "content": "<|extra_id_15|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "50277": {
181
+ "content": "<|extra_id_16|>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "50278": {
189
+ "content": "<|extra_id_17|>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "50279": {
197
+ "content": "<|extra_id_18|>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "50280": {
205
+ "content": "<|extra_id_19|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "50281": {
213
+ "content": "<|extra_id_20|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "50282": {
221
+ "content": "<|extra_id_21|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "50283": {
229
+ "content": "<|extra_id_22|>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "50284": {
237
+ "content": "<|extra_id_23|>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "50285": {
245
+ "content": "<|extra_id_24|>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "50286": {
253
+ "content": "<|extra_id_25|>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "50287": {
261
+ "content": "<|extra_id_26|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "50288": {
269
+ "content": "<|extra_id_27|>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "50289": {
277
+ "content": "<|extra_id_28|>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "50290": {
285
+ "content": "<|extra_id_29|>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "50291": {
293
+ "content": "<|extra_id_30|>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "50292": {
301
+ "content": "<|extra_id_31|>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "50293": {
309
+ "content": "<|extra_id_32|>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "50294": {
317
+ "content": "<|extra_id_33|>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "50295": {
325
+ "content": "<|extra_id_34|>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "50296": {
333
+ "content": "<|extra_id_35|>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "50297": {
341
+ "content": "<|extra_id_36|>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "50298": {
349
+ "content": "<|extra_id_37|>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "50299": {
357
+ "content": "<|extra_id_38|>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "50300": {
365
+ "content": "<|extra_id_39|>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "50301": {
373
+ "content": "<|extra_id_40|>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "50302": {
381
+ "content": "<|extra_id_41|>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "50303": {
389
+ "content": "<|extra_id_42|>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "50304": {
397
+ "content": "<|extra_id_43|>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "50305": {
405
+ "content": "<|extra_id_44|>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "50306": {
413
+ "content": "<|extra_id_45|>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "50307": {
421
+ "content": "<|extra_id_46|>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "50308": {
429
+ "content": "<|extra_id_47|>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "50309": {
437
+ "content": "<|extra_id_48|>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "50310": {
445
+ "content": "<|extra_id_49|>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "50311": {
453
+ "content": "<|extra_id_50|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "50312": {
461
+ "content": "<|extra_id_51|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "50313": {
469
+ "content": "<|extra_id_52|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "50314": {
477
+ "content": "<|extra_id_53|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "50315": {
485
+ "content": "<|extra_id_54|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "50316": {
493
+ "content": "<|extra_id_55|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "50317": {
501
+ "content": "<|extra_id_56|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "50318": {
509
+ "content": "<|extra_id_57|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "50319": {
517
+ "content": "<|extra_id_58|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "50320": {
525
+ "content": "<|extra_id_59|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "50321": {
533
+ "content": "<|extra_id_60|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "50322": {
541
+ "content": "<|extra_id_61|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "50323": {
549
+ "content": "<|extra_id_62|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "50324": {
557
+ "content": "<|extra_id_63|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "50325": {
565
+ "content": "<|extra_id_64|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "50326": {
573
+ "content": "<|extra_id_65|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "50327": {
581
+ "content": "<|extra_id_66|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "50328": {
589
+ "content": "<|extra_id_67|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "50329": {
597
+ "content": "<|extra_id_68|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "50330": {
605
+ "content": "<|extra_id_69|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "50331": {
613
+ "content": "<|extra_id_70|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "50332": {
621
+ "content": "<|extra_id_71|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "50333": {
629
+ "content": "<|extra_id_72|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "50334": {
637
+ "content": "<|extra_id_73|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "50335": {
645
+ "content": "<|extra_id_74|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "50336": {
653
+ "content": "<|extra_id_75|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "50337": {
661
+ "content": "<|extra_id_76|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "50338": {
669
+ "content": "<|extra_id_77|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "50339": {
677
+ "content": "<|extra_id_78|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "50340": {
685
+ "content": "<|extra_id_79|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "50341": {
693
+ "content": "<|extra_id_80|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "50342": {
701
+ "content": "<|extra_id_81|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "50343": {
709
+ "content": "<|extra_id_82|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "50344": {
717
+ "content": "<|extra_id_83|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "50345": {
725
+ "content": "<|extra_id_84|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "50346": {
733
+ "content": "<|extra_id_85|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "50347": {
741
+ "content": "<|extra_id_86|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "50348": {
749
+ "content": "<|extra_id_87|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "50349": {
757
+ "content": "<|extra_id_88|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "50350": {
765
+ "content": "<|extra_id_89|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "50351": {
773
+ "content": "<|extra_id_90|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "50352": {
781
+ "content": "<|extra_id_91|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "50353": {
789
+ "content": "<|extra_id_92|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "50354": {
797
+ "content": "<|extra_id_93|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "50355": {
805
+ "content": "<|extra_id_94|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "50356": {
813
+ "content": "<|extra_id_95|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "50357": {
821
+ "content": "<|extra_id_96|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "50358": {
829
+ "content": "<|extra_id_97|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "50359": {
837
+ "content": "<|extra_id_98|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "50360": {
845
+ "content": "<|extra_id_99|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ }
852
+ },
853
+ "additional_special_tokens": [
854
+ "<|pad|>",
855
+ "<|endoftext|>",
856
+ "<|NLU|>",
857
+ "<|NLG|>",
858
+ "<|extra_id_0|>",
859
+ "<|extra_id_1|>",
860
+ "<|extra_id_2|>",
861
+ "<|extra_id_3|>",
862
+ "<|extra_id_4|>",
863
+ "<|extra_id_5|>",
864
+ "<|extra_id_6|>",
865
+ "<|extra_id_7|>",
866
+ "<|extra_id_8|>",
867
+ "<|extra_id_9|>",
868
+ "<|extra_id_10|>",
869
+ "<|extra_id_11|>",
870
+ "<|extra_id_12|>",
871
+ "<|extra_id_13|>",
872
+ "<|extra_id_14|>",
873
+ "<|extra_id_15|>",
874
+ "<|extra_id_16|>",
875
+ "<|extra_id_17|>",
876
+ "<|extra_id_18|>",
877
+ "<|extra_id_19|>",
878
+ "<|extra_id_20|>",
879
+ "<|extra_id_21|>",
880
+ "<|extra_id_22|>",
881
+ "<|extra_id_23|>",
882
+ "<|extra_id_24|>",
883
+ "<|extra_id_25|>",
884
+ "<|extra_id_26|>",
885
+ "<|extra_id_27|>",
886
+ "<|extra_id_28|>",
887
+ "<|extra_id_29|>",
888
+ "<|extra_id_30|>",
889
+ "<|extra_id_31|>",
890
+ "<|extra_id_32|>",
891
+ "<|extra_id_33|>",
892
+ "<|extra_id_34|>",
893
+ "<|extra_id_35|>",
894
+ "<|extra_id_36|>",
895
+ "<|extra_id_37|>",
896
+ "<|extra_id_38|>",
897
+ "<|extra_id_39|>",
898
+ "<|extra_id_40|>",
899
+ "<|extra_id_41|>",
900
+ "<|extra_id_42|>",
901
+ "<|extra_id_43|>",
902
+ "<|extra_id_44|>",
903
+ "<|extra_id_45|>",
904
+ "<|extra_id_46|>",
905
+ "<|extra_id_47|>",
906
+ "<|extra_id_48|>",
907
+ "<|extra_id_49|>",
908
+ "<|extra_id_50|>",
909
+ "<|extra_id_51|>",
910
+ "<|extra_id_52|>",
911
+ "<|extra_id_53|>",
912
+ "<|extra_id_54|>",
913
+ "<|extra_id_55|>",
914
+ "<|extra_id_56|>",
915
+ "<|extra_id_57|>",
916
+ "<|extra_id_58|>",
917
+ "<|extra_id_59|>",
918
+ "<|extra_id_60|>",
919
+ "<|extra_id_61|>",
920
+ "<|extra_id_62|>",
921
+ "<|extra_id_63|>",
922
+ "<|extra_id_64|>",
923
+ "<|extra_id_65|>",
924
+ "<|extra_id_66|>",
925
+ "<|extra_id_67|>",
926
+ "<|extra_id_68|>",
927
+ "<|extra_id_69|>",
928
+ "<|extra_id_70|>",
929
+ "<|extra_id_71|>",
930
+ "<|extra_id_72|>",
931
+ "<|extra_id_73|>",
932
+ "<|extra_id_74|>",
933
+ "<|extra_id_75|>",
934
+ "<|extra_id_76|>",
935
+ "<|extra_id_77|>",
936
+ "<|extra_id_78|>",
937
+ "<|extra_id_79|>",
938
+ "<|extra_id_80|>",
939
+ "<|extra_id_81|>",
940
+ "<|extra_id_82|>",
941
+ "<|extra_id_83|>",
942
+ "<|extra_id_84|>",
943
+ "<|extra_id_85|>",
944
+ "<|extra_id_86|>",
945
+ "<|extra_id_87|>",
946
+ "<|extra_id_88|>",
947
+ "<|extra_id_89|>",
948
+ "<|extra_id_90|>",
949
+ "<|extra_id_91|>",
950
+ "<|extra_id_92|>",
951
+ "<|extra_id_93|>",
952
+ "<|extra_id_94|>",
953
+ "<|extra_id_95|>",
954
+ "<|extra_id_96|>",
955
+ "<|extra_id_97|>",
956
+ "<|extra_id_98|>",
957
+ "<|extra_id_99|>"
958
+ ],
959
+ "bos_token": "<|beginoftext|>",
960
+ "clean_up_tokenization_spaces": true,
961
+ "eos_token": "<|endoftext|>",
962
+ "model_max_length": 1024,
963
+ "pad_token": "<|pad|>",
964
+ "tokenizer_class": "GPT2Tokenizer",
965
+ "unk_token": "<|unk|>"
966
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff