codelion commited on
Commit
21c6fcf
β€’
1 Parent(s): 650aede

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +11 -22
  2. tokenizer.json +10 -10
  3. tokenizer_config.json +61 -24
special_tokens_map.json CHANGED
@@ -1,30 +1,19 @@
1
  {
2
  "additional_special_tokens": [
 
 
 
 
 
 
 
 
3
  "▁<PRE>",
4
  "▁<MID>",
5
  "▁<SUF>",
6
  "▁<EOT>"
7
  ],
8
- "bos_token": {
9
- "content": "<s>",
10
- "lstrip": false,
11
- "normalized": true,
12
- "rstrip": false,
13
- "single_word": false
14
- },
15
- "eos_token": {
16
- "content": "</s>",
17
- "lstrip": false,
18
- "normalized": true,
19
- "rstrip": false,
20
- "single_word": false
21
- },
22
- "pad_token": "</s>",
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
+ "▁<PRE>",
4
+ "▁<MID>",
5
+ "▁<SUF>",
6
+ "▁<EOT>",
7
+ "▁<PRE>",
8
+ "▁<MID>",
9
+ "▁<SUF>",
10
+ "▁<EOT>",
11
  "▁<PRE>",
12
  "▁<MID>",
13
  "▁<SUF>",
14
  "▁<EOT>"
15
  ],
16
+ "bos_token": "<s>",
17
+ "eos_token": "</s>",
18
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
  }
tokenizer.json CHANGED
@@ -9,7 +9,7 @@
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
- "normalized": true,
13
  "special": true
14
  },
15
  {
@@ -18,7 +18,7 @@
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
- "normalized": true,
22
  "special": true
23
  },
24
  {
@@ -34,8 +34,8 @@
34
  "id": 32000,
35
  "content": "▁<PRE>",
36
  "single_word": false,
37
- "lstrip": false,
38
- "rstrip": false,
39
  "normalized": false,
40
  "special": true
41
  },
@@ -43,8 +43,8 @@
43
  "id": 32001,
44
  "content": "▁<MID>",
45
  "single_word": false,
46
- "lstrip": false,
47
- "rstrip": false,
48
  "normalized": false,
49
  "special": true
50
  },
@@ -52,8 +52,8 @@
52
  "id": 32002,
53
  "content": "▁<SUF>",
54
  "single_word": false,
55
- "lstrip": false,
56
- "rstrip": false,
57
  "normalized": false,
58
  "special": true
59
  },
@@ -61,8 +61,8 @@
61
  "id": 32003,
62
  "content": "▁<EOT>",
63
  "single_word": false,
64
- "lstrip": false,
65
- "rstrip": false,
66
  "normalized": false,
67
  "special": true
68
  }
 
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
+ "normalized": false,
13
  "special": true
14
  },
15
  {
 
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
+ "normalized": false,
22
  "special": true
23
  },
24
  {
 
34
  "id": 32000,
35
  "content": "▁<PRE>",
36
  "single_word": false,
37
+ "lstrip": true,
38
+ "rstrip": true,
39
  "normalized": false,
40
  "special": true
41
  },
 
43
  "id": 32001,
44
  "content": "▁<MID>",
45
  "single_word": false,
46
+ "lstrip": true,
47
+ "rstrip": true,
48
  "normalized": false,
49
  "special": true
50
  },
 
52
  "id": 32002,
53
  "content": "▁<SUF>",
54
  "single_word": false,
55
+ "lstrip": true,
56
+ "rstrip": true,
57
  "normalized": false,
58
  "special": true
59
  },
 
61
  "id": 32003,
62
  "content": "▁<EOT>",
63
  "single_word": false,
64
+ "lstrip": true,
65
+ "rstrip": true,
66
  "normalized": false,
67
  "special": true
68
  }
tokenizer_config.json CHANGED
@@ -1,4 +1,62 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "additional_special_tokens": [
3
  "▁<PRE>",
4
  "▁<MID>",
@@ -13,23 +71,9 @@
13
  "▁<SUF>",
14
  "▁<EOT>"
15
  ],
16
- "bos_token": {
17
- "__type": "AddedToken",
18
- "content": "<s>",
19
- "lstrip": false,
20
- "normalized": true,
21
- "rstrip": false,
22
- "single_word": false
23
- },
24
  "clean_up_tokenization_spaces": false,
25
- "eos_token": {
26
- "__type": "AddedToken",
27
- "content": "</s>",
28
- "lstrip": false,
29
- "normalized": true,
30
- "rstrip": false,
31
- "single_word": false
32
- },
33
  "eot_token": "▁<EOT>",
34
  "fill_token": "<FILL_ME>",
35
  "legacy": null,
@@ -40,13 +84,6 @@
40
  "sp_model_kwargs": {},
41
  "suffix_token": "▁<SUF>",
42
  "tokenizer_class": "CodeLlamaTokenizer",
43
- "unk_token": {
44
- "__type": "AddedToken",
45
- "content": "<unk>",
46
- "lstrip": false,
47
- "normalized": true,
48
- "rstrip": false,
49
- "single_word": false
50
- },
51
  "use_default_system_prompt": false
52
  }
 
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
+ "32000": {
28
+ "content": "▁<PRE>",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32001": {
36
+ "content": "▁<MID>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "32002": {
44
+ "content": "▁<SUF>",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32003": {
52
+ "content": "▁<EOT>",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
  "additional_special_tokens": [
61
  "▁<PRE>",
62
  "▁<MID>",
 
71
  "▁<SUF>",
72
  "▁<EOT>"
73
  ],
74
+ "bos_token": "<s>",
 
 
 
 
 
 
 
75
  "clean_up_tokenization_spaces": false,
76
+ "eos_token": "</s>",
 
 
 
 
 
 
 
77
  "eot_token": "▁<EOT>",
78
  "fill_token": "<FILL_ME>",
79
  "legacy": null,
 
84
  "sp_model_kwargs": {},
85
  "suffix_token": "▁<SUF>",
86
  "tokenizer_class": "CodeLlamaTokenizer",
87
+ "unk_token": "<unk>",
 
 
 
 
 
 
 
88
  "use_default_system_prompt": false
89
  }