Hugging Face's logo

microsoft
/
Orca-2-13b

Text Generation
Transformers
PyTorch
llama
orca
orca2
microsoft
Inference Endpoints
text-generation-inference
Model card Files Community
25

Upload tokenizer

#10
by Rocketknight1 HF staff - opened
base: refs/heads/main
←
from: refs/pr/10
Discussion Files changed
+93479
-25
Files changed (3) hide show
  1. special_tokens_map.json +7 -1
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +54 -24
special_tokens_map.json CHANGED
@@ -13,7 +13,13 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": "[PAD]",
 
 
 
 
 
 
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
  "unk_token": {
24
  "content": "<unk>",
25
  "lstrip": false,
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,37 +1,67 @@
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": false,
9
- "rstrip": false,
10
- "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  },
 
 
12
  "clean_up_tokenization_spaces": false,
13
- "eos_token": {
14
- "__type": "AddedToken",
15
- "content": "</s>",
16
- "lstrip": false,
17
- "normalized": false,
18
- "rstrip": false,
19
- "single_word": false
20
- },
21
  "legacy": false,
22
  "model_max_length": 4096,
23
- "pad_token": null,
24
  "padding_side": "right",
25
  "sp_model_kwargs": {},
26
  "spaces_between_special_tokens": false,
27
  "tokenizer_class": "LlamaTokenizer",
28
- "unk_token": {
29
- "__type": "AddedToken",
30
- "content": "<unk>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false
35
- },
36
  "use_default_system_prompt": true
37
  }
 
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": false,
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
+ "32000": {
30
+ "content": "[PAD]",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|im_start|>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "32002": {
46
+ "content": "<|im_end|>",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ }
53
  },
54
+ "bos_token": "<s>",
55
+ "chat_template": "{{ bos_token }} {% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
56
  "clean_up_tokenization_spaces": false,
57
+ "eos_token": "</s>",
 
 
 
 
 
 
 
58
  "legacy": false,
59
  "model_max_length": 4096,
60
+ "pad_token": "[PAD]",
61
  "padding_side": "right",
62
  "sp_model_kwargs": {},
63
  "spaces_between_special_tokens": false,
64
  "tokenizer_class": "LlamaTokenizer",
65
+ "unk_token": "<unk>",
 
 
 
 
 
 
 
66
  "use_default_system_prompt": true
67
  }