ArthurZ HF staff commited on
Commit
acb500d
1 Parent(s): a2e1e63

Upload tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "|ENDOFTEXT|",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "unk_token": {
10
+ "content": "<unk>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:407d001d18582959881b30ff39b660d4bd5ee50957d03f57daeeb3059e9db54c
3
+ size 6128796
tokenizer_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "|ENDOFTEXT|",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": null,
14
+ "legacy": null,
15
+ "model_max_length": 1000000000000000019884624838656,
16
+ "pad_token": null,
17
+ "sp_model_kwargs": {},
18
+ "spaces_between_special_tokens": false,
19
+ "tokenizer_class": "LlamaTokenizer",
20
+ "unk_token": {
21
+ "__type": "AddedToken",
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "use_default_system_prompt": true
29
+ }