Hugging Face's logo

aloeme
/
chuvash_gpt_54_12_768_5epoch

Feature Extraction
Transformers
Safetensors
gpt2
Model card Files
xet
 Community
chuvash_gpt_54_12_768_5epoch
File size: 2,480 Bytes
2a40318
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "[PAD]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "[UNK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "[MASK]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "[EOS]",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 59,
      "content": "<|endoftext|>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Metaspace",
    "replacement": "▁",
    "prepend_scheme": "always",
    "split": true
  },
  "post_processor": null,
  "decoder": {
    "type": "Metaspace",
    "replacement": "▁",
    "prepend_scheme": "always",
    "split": true
  },
  "model": {
    "type": "BPE",
    "dropout": null,
    "unk_token": null,
    "continuing_subword_prefix": null,
    "end_of_word_suffix": null,
    "fuse_unk": false,
    "byte_fallback": false,
    "ignore_merges": false,
    "vocab": {
      "[PAD]": 0,
      "[UNK]": 1,
      "[MASK]": 2,
      "[EOS]": 3,
      "\n": 4,
      "!": 5,
      "\"": 6,
      ",": 7,
      "-": 8,
      ".": 9,
      "0": 10,
      "1": 11,
      "2": 12,
      "3": 13,
      "4": 14,
      "5": 15,
      "6": 16,
      "7": 17,
      "8": 18,
      "9": 19,
      "?": 20,
      "а": 21,
      "б": 22,
      "в": 23,
      "г": 24,
      "д": 25,
      "е": 26,
      "ж": 27,
      "з": 28,
      "и": 29,
      "й": 30,
      "к": 31,
      "л": 32,
      "м": 33,
      "н": 34,
      "о": 35,
      "п": 36,
      "р": 37,
      "с": 38,
      "т": 39,
      "у": 40,
      "ф": 41,
      "х": 42,
      "ц": 43,
      "ч": 44,
      "ш": 45,
      "щ": 46,
      "ъ": 47,
      "ы": 48,
      "ь": 49,
      "э": 50,
      "ю": 51,
      "я": 52,
      "ё": 53,
      "ҫ": 54,
      "ӑ": 55,
      "ӗ": 56,
      "ӳ": 57,
      "▁": 58
    },
    "merges": []
  }
}