Hugging Face's logo

AI4PD
/
ProtGPT3-1.3B

Text Generation
Transformers
Safetensors
mixtral
text-generation-inference
Model card Files
xet
 Community
michele1993 commited on
Commit
d719c04
·
verified ·
1 Parent(s): f867986

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +30 -0
  2. tokenizer.json +143 -0
  3. tokenizer_config.json +73 -0
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|bos|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eos|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|pad|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
@@ -0,0 +1,143 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<|pad|>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<|bos|>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "<|eos|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "[UNK]",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 31,
44
+ "content": "<s>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 32,
53
+ "content": "</s>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 33,
62
+ "content": "<unk>",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ }
69
+ ],
70
+ "normalizer": null,
71
+ "pre_tokenizer": {
72
+ "type": "Split",
73
+ "pattern": {
74
+ "String": ""
75
+ },
76
+ "behavior": "Isolated",
77
+ "invert": false
78
+ },
79
+ "post_processor": {
80
+ "type": "TemplateProcessing",
81
+ "single": [
82
+ {
83
+ "Sequence": {
84
+ "id": "A",
85
+ "type_id": 0
86
+ }
87
+ }
88
+ ],
89
+ "pair": [
90
+ {
91
+ "Sequence": {
92
+ "id": "A",
93
+ "type_id": 0
94
+ }
95
+ },
96
+ {
97
+ "Sequence": {
98
+ "id": "B",
99
+ "type_id": 1
100
+ }
101
+ }
102
+ ],
103
+ "special_tokens": {}
104
+ },
105
+ "decoder": null,
106
+ "model": {
107
+ "type": "WordLevel",
108
+ "vocab": {
109
+ "<|pad|>": 0,
110
+ "<|bos|>": 1,
111
+ "<|eos|>": 2,
112
+ "[UNK]": 3,
113
+ "1": 4,
114
+ "2": 5,
115
+ "A": 6,
116
+ "B": 7,
117
+ "C": 8,
118
+ "D": 9,
119
+ "E": 10,
120
+ "F": 11,
121
+ "G": 12,
122
+ "H": 13,
123
+ "I": 14,
124
+ "K": 15,
125
+ "L": 16,
126
+ "M": 17,
127
+ "N": 18,
128
+ "O": 19,
129
+ "P": 20,
130
+ "Q": 21,
131
+ "R": 22,
132
+ "S": 23,
133
+ "T": 24,
134
+ "U": 25,
135
+ "V": 26,
136
+ "W": 27,
137
+ "X": 28,
138
+ "Y": 29,
139
+ "Z": 30
140
+ },
141
+ "unk_token": "[UNK]"
142
+ }
143
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<|pad|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|bos|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "<|eos|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "3": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "31": {
39
+ "content": "<s>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32": {
47
+ "content": "</s>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "33": {
55
+ "content": "<unk>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ }
62
+ },
63
+ "bos_token": "<|bos|>",
64
+ "clean_up_tokenization_spaces": false,
65
+ "eos_token": "<|eos|>",
66
+ "extra_special_tokens": {},
67
+ "legacy": true,
68
+ "model_max_length": 1025,
69
+ "pad_token": "<|pad|>",
70
+ "tokenizer_class": "LlamaTokenizerFast",
71
+ "unk_token": "<unk>",
72
+ "use_default_system_prompt": false
73
+ }