Hugging Face's logo

kaijie-qin
/
llama-2-7b-paul

PEFT
Model card Files Community
kaijie-qin commited on
Commit
0873486
•
1 Parent(s): a322913

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +3 -3
  2. tokenizer.json +3 -8
  3. tokenizer_config.json +4 -3
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
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 1024,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
@@ -23,7 +18,7 @@
23
  "single_word": false,
24
  "lstrip": false,
25
  "rstrip": false,
26
- "normalized": true,
27
  "special": true
28
  },
29
  {
@@ -32,7 +27,7 @@
32
  "single_word": false,
33
  "lstrip": false,
34
  "rstrip": false,
35
- "normalized": true,
36
  "special": true
37
  },
38
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
 
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
+ "normalized": false,
22
  "special": true
23
  },
24
  {
 
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
30
+ "normalized": false,
31
  "special": true
32
  },
33
  {
tokenizer_config.json CHANGED
@@ -3,7 +3,7 @@
3
  "__type": "AddedToken",
4
  "content": "<s>",
5
  "lstrip": false,
6
- "normalized": true,
7
  "rstrip": false,
8
  "single_word": false
9
  },
@@ -12,20 +12,21 @@
12
  "__type": "AddedToken",
13
  "content": "</s>",
14
  "lstrip": false,
15
- "normalized": true,
16
  "rstrip": false,
17
  "single_word": false
18
  },
19
  "legacy": false,
20
  "model_max_length": 1000000000000000019884624838656,
21
  "pad_token": null,
 
22
  "sp_model_kwargs": {},
23
  "tokenizer_class": "LlamaTokenizer",
24
  "unk_token": {
25
  "__type": "AddedToken",
26
  "content": "<unk>",
27
  "lstrip": false,
28
- "normalized": true,
29
  "rstrip": false,
30
  "single_word": false
31
  }
 
3
  "__type": "AddedToken",
4
  "content": "<s>",
5
  "lstrip": false,
6
+ "normalized": false,
7
  "rstrip": false,
8
  "single_word": false
9
  },
 
12
  "__type": "AddedToken",
13
  "content": "</s>",
14
  "lstrip": false,
15
+ "normalized": false,
16
  "rstrip": false,
17
  "single_word": false
18
  },
19
  "legacy": false,
20
  "model_max_length": 1000000000000000019884624838656,
21
  "pad_token": null,
22
+ "padding_side": "right",
23
  "sp_model_kwargs": {},
24
  "tokenizer_class": "LlamaTokenizer",
25
  "unk_token": {
26
  "__type": "AddedToken",
27
  "content": "<unk>",
28
  "lstrip": false,
29
+ "normalized": false,
30
  "rstrip": false,
31
  "single_word": false
32
  }