Hugging Face's logo

Maluong
/
gpt2-chatbot

Text Generation
Transformers
Safetensors
gpt2
text-generation-inference
Model card Files
xet
Community
Maluong commited on
Commit
f72abc6
·
verified ·
1 Parent(s): c93e266

Upload tokenizer

Browse files
Files changed (6) hide show
  1. added_tokens.json +8 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +34 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +107 -0
  6. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<PAD>": 50261,
3
+ "<UNK>": 50262,
4
+ "<|endoftext|>": 50257,
5
+ "<|question|>": 50258,
6
+ "<|response|>": 50259,
7
+ "<|startoftext|>": 50260
8
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|question|>",
4
+ "<|response|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<|startoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<PAD>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<UNK>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<pad>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<mask>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "50257": {
46
+ "content": "<|endoftext|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "50258": {
54
+ "content": "<|question|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "50259": {
62
+ "content": "<|response|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "50260": {
70
+ "content": "<|startoftext|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "50261": {
78
+ "content": "<PAD>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "50262": {
86
+ "content": "<UNK>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ }
93
+ },
94
+ "additional_special_tokens": [
95
+ "<|question|>",
96
+ "<|response|>"
97
+ ],
98
+ "bos_token": "<|startoftext|>",
99
+ "clean_up_tokenization_spaces": false,
100
+ "eos_token": "<|endoftext|>",
101
+ "errors": "replace",
102
+ "extra_special_tokens": {},
103
+ "model_max_length": 1000000000000000019884624838656,
104
+ "pad_token": "<PAD>",
105
+ "tokenizer_class": "GPT2Tokenizer",
106
+ "unk_token": "<UNK>"
107
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff