Thouph commited on
Commit
9feda42
·
1 Parent(s): 3a4585c

Upload 5 files

Browse files
Files changed (5) hide show
  1. merges.txt +0 -0
  2. special_tokens_map.json +22 -3
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +29 -5
  5. vocab.json +0 -0
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,5 +1,24 @@
1
  {
2
- "bos_token": "<|endoftext|>",
3
- "eos_token": "<|endoftext|>",
4
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
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
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,9 +1,33 @@
1
  {
2
  "add_prefix_space": false,
3
- "bos_token": "<|endoftext|>",
 
 
 
 
 
 
 
4
  "clean_up_tokenization_spaces": true,
5
- "eos_token": "<|endoftext|>",
6
- "model_max_length": 1024,
7
- "tokenizer_class": "GPT2Tokenizer",
8
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  }
 
1
  {
2
  "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
  "clean_up_tokenization_spaces": true,
12
+ "do_lower_case": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 77,
23
+ "pad_token": "<|endoftext|>",
24
+ "tokenizer_class": "CLIPTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
  }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff