UltimoUno commited on
Commit
38498cf
1 Parent(s): c2a360d

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +17 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +32 -0
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin▁of▁sentence|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end▁of▁sentence|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|end▁of▁sentence|>"
17
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "100000": {
6
+ "content": "<|begin▁of▁sentence|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "100001": {
14
+ "content": "<|end▁of▁sentence|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ }
21
+ },
22
+ "bos_token": "<|begin▁of▁sentence|>",
23
+ "clean_up_tokenization_spaces": false,
24
+ "eos_token": "<|end▁of▁sentence|>",
25
+ "legacy": true,
26
+ "model_max_length": 4096,
27
+ "pad_token": "<|end▁of▁sentence|>",
28
+ "sp_model_kwargs": {},
29
+ "tokenizer_class": "LlamaTokenizer",
30
+ "unk_token": null,
31
+ "use_default_system_prompt": false
32
+ }