Hugging Face's logo

ocisd4
/
llama_tokenizer_ext_zhtw

Model card Files Community
AlexHung29629 commited on
Commit
806da72
·
verified ·
1 Parent(s): a017e9a

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +6 -0
  2. special_tokens_map.json +9 -28
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +43 -34
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<s>": 1,
4
+ "<unk>": 0,
5
+ "<|func_end|>": 36128
6
+ }
special_tokens_map.json CHANGED
@@ -1,30 +1,11 @@
1
  {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": true,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "</s>",
11
- "lstrip": false,
12
- "normalized": true,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": {
17
- "content": "<unk>",
18
- "lstrip": false,
19
- "normalized": true,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "unk_token": {
24
- "content": "<unk>",
25
- "lstrip": false,
26
- "normalized": true,
27
- "rstrip": false,
28
- "single_word": false
29
- }
30
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": "<s>",
8
+ "eos_token": "</s>",
9
+ "pad_token": "<unk>",
10
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,43 +1,52 @@
1
  {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "bos_token": {
5
- "__type": "AddedToken",
6
- "content": "<s>",
7
- "lstrip": false,
8
- "normalized": true,
9
- "rstrip": false,
10
- "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  },
 
 
 
 
 
 
12
  "clean_up_tokenization_spaces": false,
13
- "eos_token": {
14
- "__type": "AddedToken",
15
- "content": "</s>",
16
- "lstrip": false,
17
- "normalized": true,
18
- "rstrip": false,
19
- "single_word": false
20
- },
21
- "legacy": null,
22
  "model_max_length": 1000000000000000019884624838656,
23
- "pad_token": {
24
- "__type": "AddedToken",
25
- "content": "<unk>",
26
- "lstrip": false,
27
- "normalized": true,
28
- "rstrip": false,
29
- "single_word": false
30
- },
31
  "sp_model_kwargs": {},
32
  "spaces_between_special_tokens": false,
33
  "tokenizer_class": "LlamaTokenizer",
34
- "unk_token": {
35
- "__type": "AddedToken",
36
- "content": "<unk>",
37
- "lstrip": false,
38
- "normalized": true,
39
- "rstrip": false,
40
- "single_word": false
41
- },
42
  "use_default_system_prompt": true
43
  }
 
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": "<s>",
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
+ "36128": {
28
+ "content": "<|func_end|>",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": true,
33
+ "special": false
34
+ }
35
  },
36
+ "additional_special_tokens": [
37
+ "<unk>",
38
+ "<s>",
39
+ "</s>"
40
+ ],
41
+ "bos_token": "<s>",
42
  "clean_up_tokenization_spaces": false,
43
+ "eos_token": "</s>",
44
+ "legacy": true,
 
 
 
 
 
 
 
45
  "model_max_length": 1000000000000000019884624838656,
46
+ "pad_token": "<unk>",
 
 
 
 
 
 
 
47
  "sp_model_kwargs": {},
48
  "spaces_between_special_tokens": false,
49
  "tokenizer_class": "LlamaTokenizer",
50
+ "unk_token": "<unk>",
 
 
 
 
 
 
 
51
  "use_default_system_prompt": true
52
  }