Hugging Face's logo

poteminr
/
llama2-conll2003

PEFT
Model card Files
xet
Community
poteminr commited on
Commit
c7be97c
·
1 Parent(s): b5de909

Upload 5 files

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +21 -3
  2. tokenizer.json +13 -4
  3. tokenizer_config.json +23 -31
special_tokens_map.json CHANGED
@@ -1,7 +1,25 @@
1
  {
2
- "bos_token": "<s>",
3
- "eos_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
4
  "pad_token": "<unk>",
5
  "sep_token": "<s>",
6
- "unk_token": "<unk>"
 
 
 
 
 
 
7
  }
 
1
  {
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
+ },
16
  "pad_token": "<unk>",
17
  "sep_token": "<s>",
18
+ "unk_token": {
19
+ "content": "<unk>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ }
25
  }
tokenizer.json CHANGED
@@ -12,8 +12,8 @@
12
  "id": 0,
13
  "content": "<unk>",
14
  "single_word": false,
15
- "lstrip": true,
16
- "rstrip": true,
17
  "normalized": false,
18
  "special": true
19
  },
@@ -21,8 +21,8 @@
21
  "id": 1,
22
  "content": "<s>",
23
  "single_word": false,
24
- "lstrip": true,
25
- "rstrip": true,
26
  "normalized": false,
27
  "special": true
28
  },
@@ -34,6 +34,15 @@
34
  "rstrip": false,
35
  "normalized": false,
36
  "special": true
 
 
 
 
 
 
 
 
 
37
  }
38
  ],
39
  "normalizer": {
 
12
  "id": 0,
13
  "content": "<unk>",
14
  "single_word": false,
15
+ "lstrip": false,
16
+ "rstrip": false,
17
  "normalized": false,
18
  "special": true
19
  },
 
21
  "id": 1,
22
  "content": "<s>",
23
  "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
  "normalized": false,
27
  "special": true
28
  },
 
34
  "rstrip": false,
35
  "normalized": false,
36
  "special": true
37
+ },
38
+ {
39
+ "id": 32000,
40
+ "content": "<pad>",
41
+ "single_word": false,
42
+ "lstrip": false,
43
+ "rstrip": false,
44
+ "normalized": true,
45
+ "special": false
46
  }
47
  ],
48
  "normalizer": {
tokenizer_config.json CHANGED
@@ -1,40 +1,32 @@
1
  {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "<unk>",
5
- "lstrip": true,
6
- "normalized": false,
7
- "rstrip": true,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "1": {
12
- "content": "<s>",
13
- "lstrip": true,
14
- "normalized": false,
15
- "rstrip": true,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "2": {
20
- "content": "</s>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- }
27
  },
28
- "additional_special_tokens": [],
29
- "bos_token": "<s>",
30
  "clean_up_tokenization_spaces": false,
31
- "eos_token": "</s>",
 
 
 
 
 
 
 
32
  "legacy": false,
33
  "model_max_length": 1000000000000000019884624838656,
34
  "pad_token": null,
35
- "padding_side": "right",
36
  "sp_model_kwargs": {},
37
  "tokenizer_class": "LlamaTokenizer",
38
- "unk_token": "<unk>",
39
- "use_default_system_prompt": true
 
 
 
 
 
 
40
  }
 
1
  {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  },
 
 
10
  "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
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
  "sp_model_kwargs": {},
23
  "tokenizer_class": "LlamaTokenizer",
24
+ "unk_token": {
25
+ "__type": "AddedToken",
26
+ "content": "<unk>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
  }