timorobrecht/10k_initials_gpu1
02
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 "1": {
12 "content": "<unk>",
13 "lstrip": false,
14 "normalized": false,
15 "rstrip": false,
16 "single_word": false,
17 "special": true
18 },
19 "2": {
20 "content": "<s>",
21 "lstrip": false,
22 "normalized": false,
23 "rstrip": false,
24 "single_word": false,
25 "special": true
26 },
27 "3": {
28 "content": "</s>",
29 "lstrip": false,
30 "normalized": false,
31 "rstrip": false,
32 "single_word": false,
33 "special": true
34 }
35 },
36 "auto_map": {
37 "AutoTokenizer": [
38 "tokenization_pinyin_code.PinyinCodeTokenizer",
39 null
40 ]
41 },
42 "backend": "custom",
43 "bos_token": "<s>",
44 "eos_token": "</s>",
45 "model_max_length": 512,
46 "pad_token": "<pad>",
47 "tokenizer_class": "PinyinCodeTokenizer",
48 "unk_token": "<unk>"
49}
50 