kkatiz commited on
Commit
6250d67
1 Parent(s): 2bb1c6e

Upload tokenizer

Browse files
.gitattributes CHANGED
@@ -5,3 +5,4 @@ model-00004-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
5
  model-00005-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
6
  model-00006-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
7
  model-00007-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
 
 
5
  model-00005-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
6
  model-00006-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
7
  model-00007-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text
8
+ tokenizer.model filter=lfs diff=lfs merge=lfs -text
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<|padding|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05234874580b169d3ba5a59b004b655ddba73fc9ea5493451053374629d9295d
3
+ size 4569957
tokenizer_config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<|endofline|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<|padding|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ }
37
+ },
38
+ "auto_map": {
39
+ "AutoTokenizer": [
40
+ "aisingapore/sea-lion-7b-instruct--tokenization_SEA_BPE.SEABPETokenizer",
41
+ null
42
+ ]
43
+ },
44
+ "bos_token": null,
45
+ "clean_up_tokenization_spaces": false,
46
+ "eos_token": "<|endoftext|>",
47
+ "legacy": true,
48
+ "model_max_length": 1000000000000000019884624838656,
49
+ "pad_token": "<|padding|>",
50
+ "sp_model_kwargs": {},
51
+ "tokenizer_class": "SEABPETokenizer",
52
+ "unk_token": "<unk>"
53
+ }