Hugging Face's logo

Deeokay
/
gpt2-special-tokens-medium2

Text Generation
Transformers
Safetensors
gpt2
text-generation-inference
Inference Endpoints
Model card Files Community
Deeokay commited on
Commit
c0b0974
•
1 Parent(s): be6fb7c

Upload tokenizer

Browse files
Files changed (5) hide show
  1. added_tokens.json +13 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +42 -0
  4. tokenizer_config.json +122 -0
  5. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|BEGIN_ANALYSIS|>": 50260,
3
+ "<|BEGIN_CLASSIFICATION|>": 50266,
4
+ "<|BEGIN_QUERY|>": 50259,
5
+ "<|BEGIN_RESPONSE|>": 50262,
6
+ "<|BEGIN_SENTIMENT|>": 50264,
7
+ "<|END_ANALYSIS|>": 50261,
8
+ "<|END_CLASSIFICATION|>": 50267,
9
+ "<|END_RESPONSE|>": 50263,
10
+ "<|END_SENTIMENT|>": 50265,
11
+ "<|PAD|>": 50258,
12
+ "<|STOP|>": 50257
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|BEGIN_QUERY|>",
4
+ "<|BEGIN_QUERY|>",
5
+ "<|BEGIN_ANALYSIS|>",
6
+ "<|END_ANALYSIS|>",
7
+ "<|BEGIN_RESPONSE|>",
8
+ "<|END_RESPONSE|>",
9
+ "<|BEGIN_SENTIMENT|>",
10
+ "<|END_SENTIMENT|>",
11
+ "<|BEGIN_CLASSIFICATION|>",
12
+ "<|END_CLASSIFICATION|>"
13
+ ],
14
+ "bos_token": {
15
+ "content": "<|STOP|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "eos_token": {
22
+ "content": "<|STOP|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "pad_token": {
29
+ "content": "<|PAD|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "unk_token": {
36
+ "content": "<|endoftext|>",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false
41
+ }
42
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "50257": {
14
+ "content": "<|STOP|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "50258": {
22
+ "content": "<|PAD|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "50259": {
30
+ "content": "<|BEGIN_QUERY|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "50260": {
38
+ "content": "<|BEGIN_ANALYSIS|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "50261": {
46
+ "content": "<|END_ANALYSIS|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "50262": {
54
+ "content": "<|BEGIN_RESPONSE|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "50263": {
62
+ "content": "<|END_RESPONSE|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "50264": {
70
+ "content": "<|BEGIN_SENTIMENT|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "50265": {
78
+ "content": "<|END_SENTIMENT|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "50266": {
86
+ "content": "<|BEGIN_CLASSIFICATION|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "50267": {
94
+ "content": "<|END_CLASSIFICATION|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ }
101
+ },
102
+ "additional_special_tokens": [
103
+ "<|BEGIN_QUERY|>",
104
+ "<|BEGIN_QUERY|>",
105
+ "<|BEGIN_ANALYSIS|>",
106
+ "<|END_ANALYSIS|>",
107
+ "<|BEGIN_RESPONSE|>",
108
+ "<|END_RESPONSE|>",
109
+ "<|BEGIN_SENTIMENT|>",
110
+ "<|END_SENTIMENT|>",
111
+ "<|BEGIN_CLASSIFICATION|>",
112
+ "<|END_CLASSIFICATION|>"
113
+ ],
114
+ "bos_token": "<|STOP|>",
115
+ "clean_up_tokenization_spaces": true,
116
+ "eos_token": "<|STOP|>",
117
+ "errors": "replace",
118
+ "model_max_length": 1024,
119
+ "pad_token": "<|PAD|>",
120
+ "tokenizer_class": "GPT2Tokenizer",
121
+ "unk_token": "<|endoftext|>"
122
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff