gblong1 commited on
Commit
090f4e9
1 Parent(s): d776808

Adding missing files.

Browse files
Files changed (3) hide show
  1. merges.txt +0 -0
  2. special_tokens_map.json +9 -3
  3. tokenizer_config.json +20 -23
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -9,15 +9,21 @@
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
  }
 
9
  "eos_token": {
10
  "content": "<|endoftext|>",
11
  "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
  "rstrip": false,
21
  "single_word": false
22
  },
 
23
  "unk_token": {
24
  "content": "<|endoftext|>",
25
  "lstrip": false,
26
+ "normalized": false,
27
  "rstrip": false,
28
  "single_word": false
29
  }
tokenizer_config.json CHANGED
@@ -1,33 +1,30 @@
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
  }
 
1
  {
2
  "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "49406": {
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "49407": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
  },
21
+ "bos_token": "<|startoftext|>",
22
  "clean_up_tokenization_spaces": true,
23
  "do_lower_case": true,
24
+ "eos_token": "<|endoftext|>",
 
 
 
 
 
 
 
25
  "errors": "replace",
26
  "model_max_length": 77,
27
  "pad_token": "<|endoftext|>",
28
  "tokenizer_class": "CLIPTokenizer",
29
+ "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
30
  }