ArthurZ HF staff commited on
Commit
bc5f121
1 Parent(s): fda6940

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +3 -3
  2. tokenizer_config.json +9 -3
tokenizer.json CHANGED
@@ -9,7 +9,7 @@
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
- "normalized": false,
13
  "special": true
14
  },
15
  {
@@ -18,7 +18,7 @@
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
- "normalized": false,
22
  "special": true
23
  },
24
  {
@@ -27,7 +27,7 @@
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
30
- "normalized": false,
31
  "special": true
32
  }
33
  ],
 
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
+ "normalized": true,
13
  "special": true
14
  },
15
  {
 
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
+ "normalized": true,
22
  "special": true
23
  },
24
  {
 
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
30
+ "normalized": true,
31
  "special": true
32
  }
33
  ],
tokenizer_config.json CHANGED
@@ -1,6 +1,5 @@
1
  {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
  "bos_token": {
5
  "__type": "AddedToken",
6
  "content": "<s>",
@@ -18,10 +17,16 @@
18
  "rstrip": false,
19
  "single_word": false
20
  },
 
 
21
  "legacy": null,
 
22
  "model_max_length": 1000000000000000019884624838656,
23
  "pad_token": null,
 
24
  "sp_model_kwargs": {},
 
 
25
  "tokenizer_class": "CodeLlamaTokenizer",
26
  "unk_token": {
27
  "__type": "AddedToken",
@@ -30,5 +35,6 @@
30
  "normalized": true,
31
  "rstrip": false,
32
  "single_word": false
33
- }
 
34
  }
 
1
  {
2
+ "additional_special_tokens": [],
 
3
  "bos_token": {
4
  "__type": "AddedToken",
5
  "content": "<s>",
 
17
  "rstrip": false,
18
  "single_word": false
19
  },
20
+ "eot_token": null,
21
+ "fill_token": "<FILL_ME>",
22
  "legacy": null,
23
+ "middle_token": null,
24
  "model_max_length": 1000000000000000019884624838656,
25
  "pad_token": null,
26
+ "prefix_token": null,
27
  "sp_model_kwargs": {},
28
+ "suffix_first": false,
29
+ "suffix_token": null,
30
  "tokenizer_class": "CodeLlamaTokenizer",
31
  "unk_token": {
32
  "__type": "AddedToken",
 
35
  "normalized": true,
36
  "rstrip": false,
37
  "single_word": false
38
+ },
39
+ "use_default_system_prompt": false
40
  }