skeskinen commited on
Commit
7a99667
1 Parent(s): 2cb9900

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +22 -1
  2. tokenizer_config.json +29 -4
special_tokens_map.json CHANGED
@@ -1,3 +1,24 @@
1
  {
2
- "pad_token": "<s>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
  }
tokenizer_config.json CHANGED
@@ -1,8 +1,33 @@
1
  {
2
- "bos_token": "",
3
- "eos_token": "",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  "model_max_length": 1000000000000000019884624838656,
5
- "special_tokens_map_file": "/home/santtu/.cache/huggingface/hub/models--aleksickx--llama-7b-hf/snapshots/d7d132438caf5e95800f35dfc46cf82c2be9b365/special_tokens_map.json",
 
6
  "tokenizer_class": "LlamaTokenizer",
7
- "unk_token": ""
 
 
 
 
 
 
 
8
  }
 
1
  {
2
+ "add_bos_token": true,
3
+ "add_eos_token": true,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
  "model_max_length": 1000000000000000019884624838656,
22
+ "pad_token": null,
23
+ "sp_model_kwargs": {},
24
  "tokenizer_class": "LlamaTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
  }