Hugging Face's logo

leoschneider
/
chess-state-tokenizer

Model card Files
xet
 Community
leoschneider commited on
Commit
0108685
·
verified ·
1 Parent(s): 2e94b95

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +1 -0
  2. tokenizer.json +94 -0
  3. tokenizer_config.json +40 -0
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
tokenizer.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[UNK]",
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": "[SEP]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "[EOS]",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ }
42
+ ],
43
+ "normalizer": null,
44
+ "pre_tokenizer": null,
45
+ "post_processor": null,
46
+ "decoder": null,
47
+ "model": {
48
+ "type": "BPE",
49
+ "dropout": null,
50
+ "unk_token": "[UNK]",
51
+ "continuing_subword_prefix": null,
52
+ "end_of_word_suffix": null,
53
+ "fuse_unk": false,
54
+ "byte_fallback": false,
55
+ "ignore_merges": false,
56
+ "vocab": {
57
+ "[UNK]": 0,
58
+ "[BOS]": 1,
59
+ "[SEP]": 2,
60
+ "[EOS]": 3,
61
+ "a": 4,
62
+ "e": 5,
63
+ "s": 6,
64
+ "t": 7,
65
+ "at": 8,
66
+ "es": 9,
67
+ "st": 10,
68
+ "ates": 11,
69
+ "states": 12
70
+ },
71
+ "merges": [
72
+ [
73
+ "a",
74
+ "t"
75
+ ],
76
+ [
77
+ "e",
78
+ "s"
79
+ ],
80
+ [
81
+ "s",
82
+ "t"
83
+ ],
84
+ [
85
+ "at",
86
+ "es"
87
+ ],
88
+ [
89
+ "st",
90
+ "ates"
91
+ ]
92
+ ]
93
+ }
94
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[BOS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[EOS]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "clean_up_tokenization_spaces": false,
37
+ "extra_special_tokens": {},
38
+ "model_max_length": 1000000000000000019884624838656,
39
+ "tokenizer_class": "PreTrainedTokenizer"
40
+ }