Hugging Face's logo

theartificialis
/
Othello-Synthetic-AutoEncoder-20m-L

Model card Files
xet
Community
theartificialis commited on
Commit
3bf008b
·
verified ·
1 Parent(s): 0c1ad9b

Upload 5 files

Browse files
Files changed (5) hide show
  1. ckpt_iter100000.pt +3 -0
  2. tokenizer/special_tokens_map.json +4 -0
  3. tokenizer/tokenizer.json +89 -0
  4. tokenizer/tokenizer_config.json +18 -0
  5. vocab.json +63 -0
ckpt_iter100000.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:707aebe88e348bed4f12e7156b3d9f3460c244872fb3d70f0d4ddc56d9d5d05f
3
+ size 306736861
tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "pad_token": "<pad>",
3
+ "unk_token": "<pad>"
4
+ }
tokenizer/tokenizer.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "normalizer": null,
17
+ "pre_tokenizer": {
18
+ "type": "Whitespace"
19
+ },
20
+ "post_processor": null,
21
+ "decoder": null,
22
+ "model": {
23
+ "type": "WordLevel",
24
+ "vocab": {
25
+ "<pad>": 0,
26
+ "a1": 1,
27
+ "a2": 2,
28
+ "a3": 3,
29
+ "a4": 4,
30
+ "a5": 5,
31
+ "a6": 6,
32
+ "a7": 7,
33
+ "a8": 8,
34
+ "b1": 9,
35
+ "b2": 10,
36
+ "b3": 11,
37
+ "b4": 12,
38
+ "b5": 13,
39
+ "b6": 14,
40
+ "b7": 15,
41
+ "b8": 16,
42
+ "c1": 17,
43
+ "c2": 18,
44
+ "c3": 19,
45
+ "c4": 20,
46
+ "c5": 21,
47
+ "c6": 22,
48
+ "c7": 23,
49
+ "c8": 24,
50
+ "d1": 25,
51
+ "d2": 26,
52
+ "d3": 27,
53
+ "d6": 28,
54
+ "d7": 29,
55
+ "d8": 30,
56
+ "e1": 31,
57
+ "e2": 32,
58
+ "e3": 33,
59
+ "e6": 34,
60
+ "e7": 35,
61
+ "e8": 36,
62
+ "f1": 37,
63
+ "f2": 38,
64
+ "f3": 39,
65
+ "f4": 40,
66
+ "f5": 41,
67
+ "f6": 42,
68
+ "f7": 43,
69
+ "f8": 44,
70
+ "g1": 45,
71
+ "g2": 46,
72
+ "g3": 47,
73
+ "g4": 48,
74
+ "g5": 49,
75
+ "g6": 50,
76
+ "g7": 51,
77
+ "g8": 52,
78
+ "h1": 53,
79
+ "h2": 54,
80
+ "h3": 55,
81
+ "h4": 56,
82
+ "h5": 57,
83
+ "h6": 58,
84
+ "h7": 59,
85
+ "h8": 60
86
+ },
87
+ "unk_token": "<pad>"
88
+ }
89
+ }
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ }
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "extra_special_tokens": {},
14
+ "model_max_length": 1000000000000000019884624838656,
15
+ "pad_token": "<pad>",
16
+ "tokenizer_class": "PreTrainedTokenizerFast",
17
+ "unk_token": "<pad>"
18
+ }
vocab.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<pad>": 0,
3
+ "a1": 1,
4
+ "a2": 2,
5
+ "a3": 3,
6
+ "a4": 4,
7
+ "a5": 5,
8
+ "a6": 6,
9
+ "a7": 7,
10
+ "a8": 8,
11
+ "b1": 9,
12
+ "b2": 10,
13
+ "b3": 11,
14
+ "b4": 12,
15
+ "b5": 13,
16
+ "b6": 14,
17
+ "b7": 15,
18
+ "b8": 16,
19
+ "c1": 17,
20
+ "c2": 18,
21
+ "c3": 19,
22
+ "c4": 20,
23
+ "c5": 21,
24
+ "c6": 22,
25
+ "c7": 23,
26
+ "c8": 24,
27
+ "d1": 25,
28
+ "d2": 26,
29
+ "d3": 27,
30
+ "d6": 28,
31
+ "d7": 29,
32
+ "d8": 30,
33
+ "e1": 31,
34
+ "e2": 32,
35
+ "e3": 33,
36
+ "e6": 34,
37
+ "e7": 35,
38
+ "e8": 36,
39
+ "f1": 37,
40
+ "f2": 38,
41
+ "f3": 39,
42
+ "f4": 40,
43
+ "f5": 41,
44
+ "f6": 42,
45
+ "f7": 43,
46
+ "f8": 44,
47
+ "g1": 45,
48
+ "g2": 46,
49
+ "g3": 47,
50
+ "g4": 48,
51
+ "g5": 49,
52
+ "g6": 50,
53
+ "g7": 51,
54
+ "g8": 52,
55
+ "h1": 53,
56
+ "h2": 54,
57
+ "h3": 55,
58
+ "h4": 56,
59
+ "h5": 57,
60
+ "h6": 58,
61
+ "h7": 59,
62
+ "h8": 60
63
+ }