Hugging Face's logo

Snowflake
/
snowflake-arctic-instruct

Text Generation
Transformers
Safetensors
arctic
snowflake
Mixture of Experts
conversational
custom_code
Model card Files Community
18
tomaarsen HF staff commited on
Commit
f9281b7
•
1 Parent(s): ecca7ac

Revert extraneous tokenizer config changes

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +60 -39
tokenizer_config.json CHANGED
@@ -1,42 +1,63 @@
1
  {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "added_tokens_decoder": {
5
- "0": {
6
- "content": "<unk>",
7
- "lstrip": false,
8
- "normalized": true,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "1": {
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": true,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "2": {
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": true,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- }
29
  },
30
- "auto_map": {
31
- "AutoTokenizer": ["tokenization_arctic.ArcticTokenizer", null]
 
 
 
 
 
32
  },
33
- "bos_token": "<s>",
34
- "clean_up_tokenization_spaces": false,
35
- "eos_token": "</s>",
36
- "model_max_length": 4096,
37
- "pad_token": null,
38
- "sp_model_kwargs": {},
39
- "tokenizer_class": "ArcticTokenizer",
40
- "unk_token": "<unk>",
41
- "use_default_system_prompt": false
42
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
  },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "31998": {
30
+ "content": "<|im_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "31999": {
38
+ "content": "<|im_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ }
45
+ },
46
+ "additional_special_tokens": [
47
+ "<s>",
48
+ "</s>"
49
+ ],
50
+ "auto_map": {
51
+ "AutoTokenizer": ["tokenization_arctic.ArcticTokenizer", null]
52
+ },
53
+ "bos_token": "<|im_start|>",
54
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
55
+ "clean_up_tokenization_spaces": false,
56
+ "eos_token": "<|im_end|>",
57
+ "model_max_length": 4096,
58
+ "pad_token": null,
59
+ "sp_model_kwargs": {},
60
+ "tokenizer_class": "ArcticTokenizer",
61
+ "unk_token": "<unk>",
62
+ "use_default_system_prompt": false
63
+ }