kamilakesbi commited on
Commit
9856a45
1 Parent(s): b5b17b1

Upload processor

Browse files
Files changed (5) hide show
  1. merges.txt +0 -0
  2. special_tokens_map.json +12 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +29 -0
  5. vocab.json +0 -0
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": {
5
+ "content": "!",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "unk_token": "<|endoftext|>"
12
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "!",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50256": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "bos_token": "<|endoftext|>",
22
+ "clean_up_tokenization_spaces": true,
23
+ "eos_token": "<|endoftext|>",
24
+ "model_max_length": 1024,
25
+ "pad_token": "!",
26
+ "processor_class": "MSClapProcessor",
27
+ "tokenizer_class": "GPT2Tokenizer",
28
+ "unk_token": "<|endoftext|>"
29
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff