Ashegh-Sad-Warrior commited on
Commit
87671b7
1 Parent(s): 4075874

Upload tokenizer

Browse files
Files changed (6) hide show
  1. README.md +1 -1
  2. merges.txt +0 -0
  3. special_tokens_map.json +4 -5
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +10 -45
  6. vocab.json +0 -0
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
- license: apache-2.0
3
  base_model: distilbert-base-uncased
 
4
  tags:
5
  - generated_from_trainer
6
  model-index:
 
1
  ---
 
2
  base_model: distilbert-base-uncased
3
+ license: apache-2.0
4
  tags:
5
  - generated_from_trainer
6
  model-index:
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,7 +1,6 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
7
  }
 
1
  {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
 
6
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,55 +1,20 @@
1
  {
 
2
  "added_tokens_decoder": {
3
- "0": {
4
- "content": "[PAD]",
5
  "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "100": {
12
- "content": "[UNK]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "101": {
20
- "content": "[CLS]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "102": {
28
- "content": "[SEP]",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "103": {
36
- "content": "[MASK]",
37
- "lstrip": false,
38
- "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
  }
43
  },
 
44
  "clean_up_tokenization_spaces": true,
45
- "cls_token": "[CLS]",
46
- "do_lower_case": true,
47
- "mask_token": "[MASK]",
48
- "model_max_length": 512,
49
- "pad_token": "[PAD]",
50
- "sep_token": "[SEP]",
51
- "strip_accents": null,
52
- "tokenize_chinese_chars": true,
53
- "tokenizer_class": "DistilBertTokenizer",
54
- "unk_token": "[UNK]"
55
  }
 
1
  {
2
+ "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
  "lstrip": false,
7
+ "normalized": true,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  }
12
  },
13
+ "bos_token": "<|endoftext|>",
14
  "clean_up_tokenization_spaces": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1024,
17
+ "pad_token": "<|endoftext|>",
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
 
 
 
 
 
20
  }
vocab.json ADDED
The diff for this file is too large to render. See raw diff