bjoernp commited on
Commit
a4c5fcb
1 Parent(s): 7c343a5

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +1 -7
  2. tokenizer.json +7 -7
  3. tokenizer_config.json +93 -24
special_tokens_map.json CHANGED
@@ -9,11 +9,5 @@
9
  "mask_token": "<MASK>",
10
  "pad_token": "<PAD>",
11
  "sep_token": "<SEP>",
12
- "unk_token": {
13
- "content": "<unk>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false
18
- }
19
  }
 
9
  "mask_token": "<MASK>",
10
  "pad_token": "<PAD>",
11
  "sep_token": "<SEP>",
12
+ "unk_token": "<unk>"
 
 
 
 
 
 
13
  }
tokenizer.json CHANGED
@@ -116,7 +116,7 @@
116
  "single": [
117
  {
118
  "SpecialToken": {
119
- "id": "<s>",
120
  "type_id": 0
121
  }
122
  },
@@ -130,7 +130,7 @@
130
  "pair": [
131
  {
132
  "SpecialToken": {
133
- "id": "<s>",
134
  "type_id": 0
135
  }
136
  },
@@ -142,7 +142,7 @@
142
  },
143
  {
144
  "SpecialToken": {
145
- "id": "<s>",
146
  "type_id": 1
147
  }
148
  },
@@ -154,13 +154,13 @@
154
  }
155
  ],
156
  "special_tokens": {
157
- "<s>": {
158
- "id": "<s>",
159
  "ids": [
160
- 1
161
  ],
162
  "tokens": [
163
- "<s>"
164
  ]
165
  }
166
  }
 
116
  "single": [
117
  {
118
  "SpecialToken": {
119
+ "id": "<|im_start|>",
120
  "type_id": 0
121
  }
122
  },
 
130
  "pair": [
131
  {
132
  "SpecialToken": {
133
+ "id": "<|im_start|>",
134
  "type_id": 0
135
  }
136
  },
 
142
  },
143
  {
144
  "SpecialToken": {
145
+ "id": "<|im_start|>",
146
  "type_id": 1
147
  }
148
  },
 
154
  }
155
  ],
156
  "special_tokens": {
157
+ "<|im_start|>": {
158
+ "id": "<|im_start|>",
159
  "ids": [
160
+ 32005
161
  ],
162
  "tokens": [
163
+ "<|im_start|>"
164
  ]
165
  }
166
  }
tokenizer_config.json CHANGED
@@ -1,34 +1,103 @@
1
  {
2
- "bos_token": {
3
- "__type": "AddedToken",
4
- "content": "<s>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  },
 
 
 
 
 
 
10
  "clean_up_tokenization_spaces": false,
11
- "eos_token": {
12
- "__type": "AddedToken",
13
- "content": "</s>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false
18
- },
19
  "legacy": true,
 
20
  "model_max_length": 1000000000000000019884624838656,
21
- "pad_token": null,
22
  "padding_side": "right",
 
23
  "sp_model_kwargs": {},
24
  "tokenizer_class": "LlamaTokenizer",
25
- "unk_token": {
26
- "__type": "AddedToken",
27
- "content": "<unk>",
28
- "lstrip": false,
29
- "normalized": false,
30
- "rstrip": false,
31
- "single_word": false
32
- },
33
  "use_default_system_prompt": false
34
  }
 
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": "<CLS>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32001": {
36
+ "content": "<SEP>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "32002": {
44
+ "content": "<EOD>",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "32003": {
52
+ "content": "<MASK>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "32004": {
60
+ "content": "<PAD>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "32005": {
68
+ "content": "<|im_start|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "32006": {
76
+ "content": "<|im_end|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ }
83
  },
84
+ "additional_special_tokens": [
85
+ "<|im_start|>",
86
+ "<|im_end|>"
87
+ ],
88
+ "bos_token": "<|im_start|>",
89
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
90
  "clean_up_tokenization_spaces": false,
91
+ "cls_token": "<CLS>",
92
+ "eos_token": "<|im_end|>",
 
 
 
 
 
 
93
  "legacy": true,
94
+ "mask_token": "<MASK>",
95
  "model_max_length": 1000000000000000019884624838656,
96
+ "pad_token": "<PAD>",
97
  "padding_side": "right",
98
+ "sep_token": "<SEP>",
99
  "sp_model_kwargs": {},
100
  "tokenizer_class": "LlamaTokenizer",
101
+ "unk_token": "<unk>",
 
 
 
 
 
 
 
102
  "use_default_system_prompt": false
103
  }