Hugging Face's logo

nroggendorff
/
dictionary

Transformers
Inference Endpoints
Model card Files Community
nroggendorff commited on
Commit
2db1964
•
1 Parent(s): e26184e

Upload tokenizer

Browse files
Files changed (5) hide show
  1. added_tokens.json +1 -5
  2. merges.txt +1 -0
  3. special_tokens_map.json +21 -5
  4. tokenizer_config.json +12 -47
  5. vocab.json +0 -0
added_tokens.json CHANGED
@@ -1,7 +1,3 @@
1
  {
2
- "[CLS]": 4,
3
- "[MASK]": 5,
4
- "[PAD]": 3,
5
- "[SEP]": 2,
6
- "[UNK]": 1
7
  }
 
1
  {
2
+ "<|endoftext|>": 123916
 
 
 
 
3
  }
merges.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ #version: 0.2
special_tokens_map.json CHANGED
@@ -1,7 +1,23 @@
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": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
  }
tokenizer_config.json CHANGED
@@ -1,58 +1,23 @@
1
  {
 
 
2
  "added_tokens_decoder": {
3
- "1": {
4
- "content": "[UNK]",
5
  "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "2": {
12
- "content": "[SEP]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "3": {
20
- "content": "[PAD]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "4": {
28
- "content": "[CLS]",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "5": {
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_basic_tokenize": true,
47
- "do_lower_case": true,
48
- "mask_token": "[MASK]",
49
  "model_max_length": 1000000000000000019884624838656,
50
- "never_split": null,
51
- "pad_token": "[PAD]",
52
- "sep_token": "[SEP]",
53
- "strip_accents": null,
54
- "tokenize_chinese_chars": true,
55
- "tokenizer_class": "BertTokenizer",
56
  "tokenizer_file": null,
57
- "unk_token": "[UNK]"
58
  }
 
1
  {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
  "added_tokens_decoder": {
5
+ "123916": {
6
+ "content": "<|endoftext|>",
7
  "lstrip": false,
8
+ "normalized": true,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
12
  }
13
  },
14
+ "bos_token": "<|endoftext|>",
15
+ "clean_up_tokenization_spaces": false,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
 
18
  "model_max_length": 1000000000000000019884624838656,
19
+ "pad_token": null,
20
+ "tokenizer_class": "GPT2Tokenizer",
 
 
 
 
21
  "tokenizer_file": null,
22
+ "unk_token": "<|endoftext|>"
23
  }
vocab.json ADDED
The diff for this file is too large to render. See raw diff