NotShrirang commited on
Commit
a48e542
1 Parent(s): 1bb64da

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +6 -8
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +33 -21
special_tokens_map.json CHANGED
@@ -1,11 +1,9 @@
1
  {
2
- "additional_special_tokens": [
3
- "<unk>",
4
- "<s>",
5
- "</s>"
6
- ],
7
- "bos_token": "<s>",
8
- "eos_token": "</s>",
9
- "pad_token": "</s>",
10
  "unk_token": "<unk>"
11
  }
 
1
  {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "[SEP]",
 
 
8
  "unk_token": "<unk>"
9
  }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
- "content": "<unk>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
@@ -9,7 +9,7 @@
9
  "special": true
10
  },
11
  "1": {
12
- "content": "<s>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
@@ -17,30 +17,42 @@
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
  },
28
- "additional_special_tokens": [
29
- "<unk>",
30
- "<s>",
31
- "</s>"
32
- ],
33
- "bos_token": "<s>",
34
- "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
35
- "clean_up_tokenization_spaces": false,
36
- "eos_token": "</s>",
37
- "legacy": true,
38
- "model_max_length": 1000000000000000019884624838656,
39
- "pad_token": "</s>",
40
- "sp_model_kwargs": {},
41
- "spaces_between_special_tokens": false,
42
  "tokenizer_class": "AlbertTokenizer",
43
- "truncation_side": "left",
44
- "unk_token": "<unk>",
45
- "use_default_system_prompt": true
46
- }
 
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "<pad>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
 
9
  "special": true
10
  },
11
  "1": {
12
+ "content": "<unk>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
 
17
  "special": true
18
  },
19
  "2": {
20
+ "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
  }
43
  },
44
+ "additional_special_tokens": [],
45
+ "bos_token": "[CLS]",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "[CLS]",
48
+ "do_lower_case": true,
49
+ "eos_token": "[SEP]",
50
+ "keep_accents": false,
51
+ "mask_token": "[MASK]",
52
+ "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "remove_space": true,
55
+ "sep_token": "[SEP]",
 
 
56
  "tokenizer_class": "AlbertTokenizer",
57
+ "unk_token": "<unk>"
58
+ }