Hugging Face's logo

minpeter
/
tiny-ko-tokenizer-32k-250718

Model card Files
xet
Community
minpeter commited on
Commit
5468cfe
·
verified ·
1 Parent(s): e363d7b

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +5 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +103 -0
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "<|endoftext|>",
3
+ "pad_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "31989": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": false
12
+ },
13
+ "31990": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": false
20
+ },
21
+ "31991": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "31992": {
30
+ "content": "<tool_call>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "31993": {
38
+ "content": "</tool_call>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "31994": {
46
+ "content": "<think>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "31995": {
54
+ "content": "</think>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "31996": {
62
+ "content": "<|unused_special_token_0|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "31997": {
70
+ "content": "<|unused_special_token_1|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "31998": {
78
+ "content": "<|unused_special_token_2|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "31999": {
86
+ "content": "<|unused_special_token_3|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ }
93
+ },
94
+ "bos_token": null,
95
+ "clean_up_tokenization_spaces": false,
96
+ "eos_token": "<|endoftext|>",
97
+ "extra_special_tokens": {},
98
+ "model_max_length": 1000000000000000019884624838656,
99
+ "pad_token": "<|endoftext|>",
100
+ "split_special_tokens": false,
101
+ "tokenizer_class": "PreTrainedTokenizerFast",
102
+ "unk_token": "<|endoftext|>"
103
+ }