Hugging Face's logo

zphudzz
/
phu-ner-model

Safetensors
Vietnamese
gemma
Model card Files Community
zphudzz commited on
Commit
ec81316
·
verified ·
1 Parent(s): 347502e

Upload tokenizer_config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +69 -70
tokenizer_config.json CHANGED
@@ -1,72 +1,71 @@
1
  {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "added_tokens_decoder": {
5
- "0": {
6
- "content": "<pad>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  },
13
- "1": {
14
- "content": "<eos>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "2": {
22
- "content": "<bos>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- },
29
- "3": {
30
- "content": "<unk>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "106": {
38
- "content": "<start_of_turn>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "107": {
46
- "content": "<end_of_turn>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": true
52
- }
53
- },
54
- "additional_special_tokens": [
55
- "<start_of_turn>",
56
- "<end_of_turn>"
57
- ],
58
- "bos_token": "<bos>",
59
- "chat_template": "{{ '<bos>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<start_of_turn>user\n' + content + '<end_of_turn>\n<start_of_turn>model\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<end_of_turn>\n' }}{% endif %}{% endfor %}",
60
- "clean_up_tokenization_spaces": false,
61
- "eos_token": "<eos>",
62
- "legacy": null,
63
- "model_max_length": 1000000000000000019884624838656,
64
- "pad_token": "<pad>",
65
- "padding_side": "left",
66
- "sp_model_kwargs": {},
67
- "spaces_between_special_tokens": false,
68
- "split_special_tokens": false,
69
- "tokenizer_class": "GemmaTokenizer",
70
- "unk_token": "<unk>",
71
- "use_default_system_prompt": false
72
- }
 
1
  {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<bos>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "106": {
38
+ "content": "<start_of_turn>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "107": {
46
+ "content": "<end_of_turn>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ }
53
  },
54
+ "additional_special_tokens": [
55
+ "<start_of_turn>",
56
+ "<end_of_turn>"
57
+ ],
58
+ "bos_token": "<bos>",
59
+ "clean_up_tokenization_spaces": false,
60
+ "eos_token": "<eos>",
61
+ "legacy": null,
62
+ "model_max_length": 1000000000000000019884624838656,
63
+ "pad_token": "<pad>",
64
+ "padding_side": "right",
65
+ "sp_model_kwargs": {},
66
+ "spaces_between_special_tokens": false,
67
+ "split_special_tokens": false,
68
+ "tokenizer_class": "GemmaTokenizer",
69
+ "unk_token": "<unk>",
70
+ "use_default_system_prompt": false
71
+ }