Hugging Face's logo

diamantrsd
/
cerpengen-500words

Text Generation
Transformers
Safetensors
gpt2
text-generation-inference
Model card Files
xet
Community
diamantrsd commited on
Commit
3d87f63
·
1 Parent(s): 7e03158

Upload tokenizer

Browse files
Files changed (5) hide show
  1. added_tokens.json +8 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +53 -0
  4. tokenizer_config.json +76 -0
  5. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<CLS>": 50261,
3
+ "<CONTENT>": 50262,
4
+ "<pad>": 50259,
5
+ "<|BOS|>": 50258,
6
+ "<|EOS|>": 50257,
7
+ "<|body|>": 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 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<CLS>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<CONTENT>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": {
19
+ "content": "<|BOS|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "eos_token": {
26
+ "content": "<|EOS|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "pad_token": {
33
+ "content": "<pad>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
+ "sep_token": {
40
+ "content": "<|body|>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "unk_token": {
47
+ "content": "<|endoftext|>",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ }
53
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "50257": {
14
+ "content": "<|EOS|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "50258": {
22
+ "content": "<|BOS|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "50259": {
30
+ "content": "<pad>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "50260": {
38
+ "content": "<|body|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "50261": {
46
+ "content": "<CLS>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "50262": {
54
+ "content": "<CONTENT>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ }
61
+ },
62
+ "additional_special_tokens": [
63
+ "<CLS>",
64
+ "<CONTENT>"
65
+ ],
66
+ "bos_token": "<|BOS|>",
67
+ "clean_up_tokenization_spaces": true,
68
+ "eos_token": "<|EOS|>",
69
+ "errors": "replace",
70
+ "max_len": 512,
71
+ "model_max_length": 512,
72
+ "pad_token": "<pad>",
73
+ "sep_token": "<|body|>",
74
+ "tokenizer_class": "GPT2Tokenizer",
75
+ "unk_token": "<|endoftext|>"
76
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff