Hugging Face's logo

maksim2000153
/
my_new_model

Text2Text Generation
Transformers
PyTorch
t5
Inference Endpoints
text-generation-inference
Model card Files Community
maksim2000153 commited on
Commit
d5f755f
•
1 Parent(s): f5da36b

Upload tokenizer

Browse files
Files changed (6) hide show
  1. added_tokens.json +110 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +21 -104
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +37 -108
  6. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<LM>": 50357,
3
+ "<SC1>": 50358,
4
+ "<SC2>": 50359,
5
+ "<SC3>": 50360,
6
+ "<SC4>": 50361,
7
+ "<SC5>": 50362,
8
+ "<SC6>": 50363,
9
+ "<extra_id_0>": 50257,
10
+ "<extra_id_10>": 50267,
11
+ "<extra_id_11>": 50268,
12
+ "<extra_id_12>": 50269,
13
+ "<extra_id_13>": 50270,
14
+ "<extra_id_14>": 50271,
15
+ "<extra_id_15>": 50272,
16
+ "<extra_id_16>": 50273,
17
+ "<extra_id_17>": 50274,
18
+ "<extra_id_18>": 50275,
19
+ "<extra_id_19>": 50276,
20
+ "<extra_id_1>": 50258,
21
+ "<extra_id_20>": 50277,
22
+ "<extra_id_21>": 50278,
23
+ "<extra_id_22>": 50279,
24
+ "<extra_id_23>": 50280,
25
+ "<extra_id_24>": 50281,
26
+ "<extra_id_25>": 50282,
27
+ "<extra_id_26>": 50283,
28
+ "<extra_id_27>": 50284,
29
+ "<extra_id_28>": 50285,
30
+ "<extra_id_29>": 50286,
31
+ "<extra_id_2>": 50259,
32
+ "<extra_id_30>": 50287,
33
+ "<extra_id_31>": 50288,
34
+ "<extra_id_32>": 50289,
35
+ "<extra_id_33>": 50290,
36
+ "<extra_id_34>": 50291,
37
+ "<extra_id_35>": 50292,
38
+ "<extra_id_36>": 50293,
39
+ "<extra_id_37>": 50294,
40
+ "<extra_id_38>": 50295,
41
+ "<extra_id_39>": 50296,
42
+ "<extra_id_3>": 50260,
43
+ "<extra_id_40>": 50297,
44
+ "<extra_id_41>": 50298,
45
+ "<extra_id_42>": 50299,
46
+ "<extra_id_43>": 50300,
47
+ "<extra_id_44>": 50301,
48
+ "<extra_id_45>": 50302,
49
+ "<extra_id_46>": 50303,
50
+ "<extra_id_47>": 50304,
51
+ "<extra_id_48>": 50305,
52
+ "<extra_id_49>": 50306,
53
+ "<extra_id_4>": 50261,
54
+ "<extra_id_50>": 50307,
55
+ "<extra_id_51>": 50308,
56
+ "<extra_id_52>": 50309,
57
+ "<extra_id_53>": 50310,
58
+ "<extra_id_54>": 50311,
59
+ "<extra_id_55>": 50312,
60
+ "<extra_id_56>": 50313,
61
+ "<extra_id_57>": 50314,
62
+ "<extra_id_58>": 50315,
63
+ "<extra_id_59>": 50316,
64
+ "<extra_id_5>": 50262,
65
+ "<extra_id_60>": 50317,
66
+ "<extra_id_61>": 50318,
67
+ "<extra_id_62>": 50319,
68
+ "<extra_id_63>": 50320,
69
+ "<extra_id_64>": 50321,
70
+ "<extra_id_65>": 50322,
71
+ "<extra_id_66>": 50323,
72
+ "<extra_id_67>": 50324,
73
+ "<extra_id_68>": 50325,
74
+ "<extra_id_69>": 50326,
75
+ "<extra_id_6>": 50263,
76
+ "<extra_id_70>": 50327,
77
+ "<extra_id_71>": 50328,
78
+ "<extra_id_72>": 50329,
79
+ "<extra_id_73>": 50330,
80
+ "<extra_id_74>": 50331,
81
+ "<extra_id_75>": 50332,
82
+ "<extra_id_76>": 50333,
83
+ "<extra_id_77>": 50334,
84
+ "<extra_id_78>": 50335,
85
+ "<extra_id_79>": 50336,
86
+ "<extra_id_7>": 50264,
87
+ "<extra_id_80>": 50337,
88
+ "<extra_id_81>": 50338,
89
+ "<extra_id_82>": 50339,
90
+ "<extra_id_83>": 50340,
91
+ "<extra_id_84>": 50341,
92
+ "<extra_id_85>": 50342,
93
+ "<extra_id_86>": 50343,
94
+ "<extra_id_87>": 50344,
95
+ "<extra_id_88>": 50345,
96
+ "<extra_id_89>": 50346,
97
+ "<extra_id_8>": 50265,
98
+ "<extra_id_90>": 50347,
99
+ "<extra_id_91>": 50348,
100
+ "<extra_id_92>": 50349,
101
+ "<extra_id_93>": 50350,
102
+ "<extra_id_94>": 50351,
103
+ "<extra_id_95>": 50352,
104
+ "<extra_id_96>": 50353,
105
+ "<extra_id_97>": 50354,
106
+ "<extra_id_98>": 50355,
107
+ "<extra_id_99>": 50356,
108
+ "<extra_id_9>": 50266,
109
+ "<|endoftext|>": 50364
110
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,107 +1,24 @@
1
  {
2
- "additional_special_tokens": [
3
- "<extra_id_0>",
4
- "<extra_id_1>",
5
- "<extra_id_2>",
6
- "<extra_id_3>",
7
- "<extra_id_4>",
8
- "<extra_id_5>",
9
- "<extra_id_6>",
10
- "<extra_id_7>",
11
- "<extra_id_8>",
12
- "<extra_id_9>",
13
- "<extra_id_10>",
14
- "<extra_id_11>",
15
- "<extra_id_12>",
16
- "<extra_id_13>",
17
- "<extra_id_14>",
18
- "<extra_id_15>",
19
- "<extra_id_16>",
20
- "<extra_id_17>",
21
- "<extra_id_18>",
22
- "<extra_id_19>",
23
- "<extra_id_20>",
24
- "<extra_id_21>",
25
- "<extra_id_22>",
26
- "<extra_id_23>",
27
- "<extra_id_24>",
28
- "<extra_id_25>",
29
- "<extra_id_26>",
30
- "<extra_id_27>",
31
- "<extra_id_28>",
32
- "<extra_id_29>",
33
- "<extra_id_30>",
34
- "<extra_id_31>",
35
- "<extra_id_32>",
36
- "<extra_id_33>",
37
- "<extra_id_34>",
38
- "<extra_id_35>",
39
- "<extra_id_36>",
40
- "<extra_id_37>",
41
- "<extra_id_38>",
42
- "<extra_id_39>",
43
- "<extra_id_40>",
44
- "<extra_id_41>",
45
- "<extra_id_42>",
46
- "<extra_id_43>",
47
- "<extra_id_44>",
48
- "<extra_id_45>",
49
- "<extra_id_46>",
50
- "<extra_id_47>",
51
- "<extra_id_48>",
52
- "<extra_id_49>",
53
- "<extra_id_50>",
54
- "<extra_id_51>",
55
- "<extra_id_52>",
56
- "<extra_id_53>",
57
- "<extra_id_54>",
58
- "<extra_id_55>",
59
- "<extra_id_56>",
60
- "<extra_id_57>",
61
- "<extra_id_58>",
62
- "<extra_id_59>",
63
- "<extra_id_60>",
64
- "<extra_id_61>",
65
- "<extra_id_62>",
66
- "<extra_id_63>",
67
- "<extra_id_64>",
68
- "<extra_id_65>",
69
- "<extra_id_66>",
70
- "<extra_id_67>",
71
- "<extra_id_68>",
72
- "<extra_id_69>",
73
- "<extra_id_70>",
74
- "<extra_id_71>",
75
- "<extra_id_72>",
76
- "<extra_id_73>",
77
- "<extra_id_74>",
78
- "<extra_id_75>",
79
- "<extra_id_76>",
80
- "<extra_id_77>",
81
- "<extra_id_78>",
82
- "<extra_id_79>",
83
- "<extra_id_80>",
84
- "<extra_id_81>",
85
- "<extra_id_82>",
86
- "<extra_id_83>",
87
- "<extra_id_84>",
88
- "<extra_id_85>",
89
- "<extra_id_86>",
90
- "<extra_id_87>",
91
- "<extra_id_88>",
92
- "<extra_id_89>",
93
- "<extra_id_90>",
94
- "<extra_id_91>",
95
- "<extra_id_92>",
96
- "<extra_id_93>",
97
- "<extra_id_94>",
98
- "<extra_id_95>",
99
- "<extra_id_96>",
100
- "<extra_id_97>",
101
- "<extra_id_98>",
102
- "<extra_id_99>"
103
- ],
104
- "eos_token": "</s>",
105
  "pad_token": "<pad>",
106
- "unk_token": "<unk>"
 
 
 
 
 
 
107
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16
  "pad_token": "<pad>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,111 +1,40 @@
1
  {
2
- "additional_special_tokens": [
3
- "<extra_id_0>",
4
- "<extra_id_1>",
5
- "<extra_id_2>",
6
- "<extra_id_3>",
7
- "<extra_id_4>",
8
- "<extra_id_5>",
9
- "<extra_id_6>",
10
- "<extra_id_7>",
11
- "<extra_id_8>",
12
- "<extra_id_9>",
13
- "<extra_id_10>",
14
- "<extra_id_11>",
15
- "<extra_id_12>",
16
- "<extra_id_13>",
17
- "<extra_id_14>",
18
- "<extra_id_15>",
19
- "<extra_id_16>",
20
- "<extra_id_17>",
21
- "<extra_id_18>",
22
- "<extra_id_19>",
23
- "<extra_id_20>",
24
- "<extra_id_21>",
25
- "<extra_id_22>",
26
- "<extra_id_23>",
27
- "<extra_id_24>",
28
- "<extra_id_25>",
29
- "<extra_id_26>",
30
- "<extra_id_27>",
31
- "<extra_id_28>",
32
- "<extra_id_29>",
33
- "<extra_id_30>",
34
- "<extra_id_31>",
35
- "<extra_id_32>",
36
- "<extra_id_33>",
37
- "<extra_id_34>",
38
- "<extra_id_35>",
39
- "<extra_id_36>",
40
- "<extra_id_37>",
41
- "<extra_id_38>",
42
- "<extra_id_39>",
43
- "<extra_id_40>",
44
- "<extra_id_41>",
45
- "<extra_id_42>",
46
- "<extra_id_43>",
47
- "<extra_id_44>",
48
- "<extra_id_45>",
49
- "<extra_id_46>",
50
- "<extra_id_47>",
51
- "<extra_id_48>",
52
- "<extra_id_49>",
53
- "<extra_id_50>",
54
- "<extra_id_51>",
55
- "<extra_id_52>",
56
- "<extra_id_53>",
57
- "<extra_id_54>",
58
- "<extra_id_55>",
59
- "<extra_id_56>",
60
- "<extra_id_57>",
61
- "<extra_id_58>",
62
- "<extra_id_59>",
63
- "<extra_id_60>",
64
- "<extra_id_61>",
65
- "<extra_id_62>",
66
- "<extra_id_63>",
67
- "<extra_id_64>",
68
- "<extra_id_65>",
69
- "<extra_id_66>",
70
- "<extra_id_67>",
71
- "<extra_id_68>",
72
- "<extra_id_69>",
73
- "<extra_id_70>",
74
- "<extra_id_71>",
75
- "<extra_id_72>",
76
- "<extra_id_73>",
77
- "<extra_id_74>",
78
- "<extra_id_75>",
79
- "<extra_id_76>",
80
- "<extra_id_77>",
81
- "<extra_id_78>",
82
- "<extra_id_79>",
83
- "<extra_id_80>",
84
- "<extra_id_81>",
85
- "<extra_id_82>",
86
- "<extra_id_83>",
87
- "<extra_id_84>",
88
- "<extra_id_85>",
89
- "<extra_id_86>",
90
- "<extra_id_87>",
91
- "<extra_id_88>",
92
- "<extra_id_89>",
93
- "<extra_id_90>",
94
- "<extra_id_91>",
95
- "<extra_id_92>",
96
- "<extra_id_93>",
97
- "<extra_id_94>",
98
- "<extra_id_95>",
99
- "<extra_id_96>",
100
- "<extra_id_97>",
101
- "<extra_id_98>",
102
- "<extra_id_99>"
103
- ],
104
  "clean_up_tokenization_spaces": true,
105
- "eos_token": "</s>",
106
- "extra_ids": 100,
107
- "model_max_length": 512,
108
- "pad_token": "<pad>",
109
- "tokenizer_class": "T5Tokenizer",
110
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
111
  }
 
1
  {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  "clean_up_tokenization_spaces": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": {
24
+ "__type": "AddedToken",
25
+ "content": "<pad>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "tokenizer_class": "GPT2Tokenizer",
32
+ "unk_token": {
33
+ "__type": "AddedToken",
34
+ "content": "<|endoftext|>",
35
+ "lstrip": false,
36
+ "normalized": true,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ }
40
  }
vocab.json ADDED
The diff for this file is too large to render. See raw diff