Hugging Face's logo

julep-ai-archive
/
samantha-1-tokenizer

Model card Files Community
diwank commited on
Commit
2baf777
•
1 Parent(s): e124a42

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +10 -0
  2. special_tokens_map.json +77 -6
  3. tokenizer.model +3 -0
  4. tokenizer_config.json +32 -7
added_tokens.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|behavior_anthropoid|>": 32002,
3
+ "<|behavior_mechanoid|>": 32003,
4
+ "<|im_end|>": 32001,
5
+ "<|im_start|>": 32000,
6
+ "<|safety_benign|>": 32005,
7
+ "<|safety_bold|>": 32006,
8
+ "<|safety_conservative|>": 32004,
9
+ "<|safety_unrestricted|>": 32007
10
+ }
special_tokens_map.json CHANGED
@@ -1,10 +1,81 @@
1
  {
2
  "additional_special_tokens": [
3
- "<|im_start|>",
4
- "<|im_end|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  ],
6
- "bos_token": "<|endoftext|>",
7
- "eos_token": "<|endoftext|>",
8
- "pad_token": "<|endoftext|>",
9
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  }
 
1
  {
2
  "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_start|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|im_end|>",
12
+ "lstrip": true,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<|behavior_anthropoid|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<|behavior_mechanoid|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<|safety_conservative|>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "<|safety_benign|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<|safety_bold|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "<|safety_unrestricted|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ }
59
  ],
60
+ "bos_token": {
61
+ "content": "<s>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false
66
+ },
67
+ "eos_token": {
68
+ "content": "</s>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false
73
+ },
74
+ "unk_token": {
75
+ "content": "<unk>",
76
+ "lstrip": false,
77
+ "normalized": false,
78
+ "rstrip": false,
79
+ "single_word": false
80
+ }
81
  }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json CHANGED
@@ -1,9 +1,34 @@
1
  {
2
- "add_prefix_space": false,
3
- "bos_token": "<|endoftext|>",
4
- "clean_up_tokenization_spaces": true,
5
- "eos_token": "<|endoftext|>",
6
- "model_max_length": 8192,
7
- "tokenizer_class": "GPTNeoXTokenizer",
8
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  }
 
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": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
+ "sp_model_kwargs": {},
25
+ "tokenizer_class": "LlamaTokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
  }