Tamnemtf commited on
Commit
13defc7
·
verified ·
1 Parent(s): b6e64a7

Upload tokenizer

Browse files
special_tokens_map.json CHANGED
@@ -2,14 +2,14 @@
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
  },
@@ -17,7 +17,7 @@
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
20
- "normalized": true,
21
  "rstrip": false,
22
  "single_word": false
23
  }
 
2
  "bos_token": {
3
  "content": "<s>",
4
  "lstrip": false,
5
+ "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
  "content": "</s>",
11
  "lstrip": false,
12
+ "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
 
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
20
+ "normalized": false,
21
  "rstrip": false,
22
  "single_word": false
23
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json CHANGED
@@ -3,7 +3,7 @@
3
  "0": {
4
  "content": "<unk>",
5
  "lstrip": false,
6
- "normalized": true,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
@@ -11,7 +11,7 @@
11
  "1": {
12
  "content": "<s>",
13
  "lstrip": false,
14
- "normalized": true,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
@@ -19,7 +19,7 @@
19
  "2": {
20
  "content": "</s>",
21
  "lstrip": false,
22
- "normalized": true,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
@@ -31,9 +31,10 @@
31
  "legacy": false,
32
  "model_max_length": 1000000000000000019884624838656,
33
  "pad_token": "</s>",
 
34
  "sp_model_kwargs": {},
 
35
  "tokenizer_class": "LlamaTokenizer",
36
  "unk_token": "<unk>",
37
- "use_default_system_prompt": false,
38
- "use_fast": true
39
  }
 
3
  "0": {
4
  "content": "<unk>",
5
  "lstrip": false,
6
+ "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
 
11
  "1": {
12
  "content": "<s>",
13
  "lstrip": false,
14
+ "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
 
19
  "2": {
20
  "content": "</s>",
21
  "lstrip": false,
22
+ "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
 
31
  "legacy": false,
32
  "model_max_length": 1000000000000000019884624838656,
33
  "pad_token": "</s>",
34
+ "padding_side": "right",
35
  "sp_model_kwargs": {},
36
+ "spaces_between_special_tokens": false,
37
  "tokenizer_class": "LlamaTokenizer",
38
  "unk_token": "<unk>",
39
+ "use_default_system_prompt": false
 
40
  }