Hugging Face's logo

ocisd4
/
openllama_tokenizer_ext_zh

Model card Files
xet
 Community
samleeasus commited on
Commit
9def049
·
1 Parent(s): fb7167d

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +3 -3
  2. tokenizer.model +2 -2
  3. tokenizer_config.json +4 -11
special_tokens_map.json CHANGED
@@ -1,19 +1,19 @@
1
  {
2
  "bos_token": {
3
- "content": "<|bos|>",
4
  "lstrip": false,
5
  "normalized": true,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
- "content": "<|eos|>",
11
  "lstrip": false,
12
  "normalized": true,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": "<|ctx|>",
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
 
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": "<|pad|>",
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
tokenizer.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:707b7199a4a7bcf18c01be43e2ba1709a4366dca255d54dc36ec432816766b30
3
- size 780938
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92a4b32f17afc26c60e42accff53f43c3ce9b137b06fdd198e4ca7d3a129930f
3
+ size 827706
tokenizer_config.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "add_bos_token": true,
3
- "add_eos_token": true,
4
  "bos_token": {
5
  "__type": "AddedToken",
6
- "content": "<|bos|>",
7
  "lstrip": false,
8
  "normalized": true,
9
  "rstrip": false,
@@ -12,21 +12,14 @@
12
  "clean_up_tokenization_spaces": false,
13
  "eos_token": {
14
  "__type": "AddedToken",
15
- "content": "<|eos|>",
16
  "lstrip": false,
17
  "normalized": true,
18
  "rstrip": false,
19
  "single_word": false
20
  },
21
  "model_max_length": 1000000000000000019884624838656,
22
- "pad_token": {
23
- "__type": "AddedToken",
24
- "content": "<|pad|>",
25
- "lstrip": false,
26
- "normalized": true,
27
- "rstrip": false,
28
- "single_word": false
29
- },
30
  "sp_model_kwargs": {},
31
  "tokenizer_class": "LlamaTokenizer",
32
  "unk_token": {
 
1
  {
2
  "add_bos_token": true,
3
+ "add_eos_token": false,
4
  "bos_token": {
5
  "__type": "AddedToken",
6
+ "content": "<s>",
7
  "lstrip": false,
8
  "normalized": true,
9
  "rstrip": false,
 
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": {