patrickvonplaten commited on
Commit
746a432
1 Parent(s): 8c7a358

correct tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +24 -1
  2. tokenizer_config.json +33 -33
special_tokens_map.json CHANGED
@@ -1 +1,24 @@
1
- {"bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|endoftext|>"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "single_word": false,
5
+ "lstrip": false,
6
+ "rstrip": false,
7
+ "normalized": true
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "single_word": false,
12
+ "lstrip": false,
13
+ "rstrip": false,
14
+ "normalized": true
15
+ },
16
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": true
22
+ },
23
+ "pad_token": "!"
24
+ }
tokenizer_config.json CHANGED
@@ -1,34 +1,34 @@
1
  {
2
- "unk_token": {
3
- "content": "<|endoftext|>",
4
- "single_word": false,
5
- "lstrip": false,
6
- "rstrip": false,
7
- "normalized": true,
8
- "__type": "AddedToken"
9
- },
10
- "bos_token": {
11
- "content": "<|startoftext|>",
12
- "single_word": false,
13
- "lstrip": false,
14
- "rstrip": false,
15
- "normalized": true,
16
- "__type": "AddedToken"
17
- },
18
- "eos_token": {
19
- "content": "<|endoftext|>",
20
- "single_word": false,
21
- "lstrip": false,
22
- "rstrip": false,
23
- "normalized": true,
24
- "__type": "AddedToken"
25
- },
26
- "pad_token": "<|endoftext|>",
27
- "add_prefix_space": false,
28
- "errors": "replace",
29
- "do_lower_case": true,
30
- "name_or_path": "openai/clip-vit-base-patch32",
31
- "model_max_length": 77,
32
- "special_tokens_map_file": "./special_tokens_map.json",
33
- "tokenizer_class": "CLIPTokenizer"
34
- }
 
1
  {
2
+ "unk_token": {
3
+ "content": "<|endoftext|>",
4
+ "single_word": false,
5
+ "lstrip": false,
6
+ "rstrip": false,
7
+ "normalized": true,
8
+ "__type": "AddedToken"
9
+ },
10
+ "bos_token": {
11
+ "content": "<|startoftext|>",
12
+ "single_word": false,
13
+ "lstrip": false,
14
+ "rstrip": false,
15
+ "normalized": true,
16
+ "__type": "AddedToken"
17
+ },
18
+ "eos_token": {
19
+ "content": "<|endoftext|>",
20
+ "single_word": false,
21
+ "lstrip": false,
22
+ "rstrip": false,
23
+ "normalized": true,
24
+ "__type": "AddedToken"
25
+ },
26
+ "pad_token": "!",
27
+ "add_prefix_space": false,
28
+ "errors": "replace",
29
+ "do_lower_case": true,
30
+ "name_or_path": "openai/clip-vit-base-patch32",
31
+ "model_max_length": 77,
32
+ "special_tokens_map_file": "./special_tokens_map.json",
33
+ "tokenizer_class": "CLIPTokenizer"
34
+ }