Hugging Face's logo

UNSAFE
/
praxis-8192

Model card Files Community
Vectorrent commited on
Commit
de97abe
·
verified ·
1 Parent(s): a22627c

Upload 3 files

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +6 -20
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +12 -30
special_tokens_map.json CHANGED
@@ -1,28 +1,14 @@
1
  {
2
  "additional_special_tokens": [
3
  {
4
- "content": "[CTX]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false
9
  },
10
  {
11
- "content": "[XTC]",
12
- "lstrip": false,
13
- "normalized": false,
14
- "rstrip": false,
15
- "single_word": false
16
- },
17
- {
18
- "content": "[CAT]",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- },
24
- {
25
- "content": "[TAC]",
26
  "lstrip": false,
27
  "normalized": false,
28
  "rstrip": false,
@@ -30,28 +16,28 @@
30
  }
31
  ],
32
  "bos_token": {
33
- "content": "[BOS]",
34
  "lstrip": false,
35
  "normalized": false,
36
  "rstrip": false,
37
  "single_word": false
38
  },
39
  "eos_token": {
40
- "content": "[EOS]",
41
  "lstrip": false,
42
  "normalized": false,
43
  "rstrip": false,
44
  "single_word": false
45
  },
46
  "pad_token": {
47
- "content": "[PAD]",
48
  "lstrip": false,
49
  "normalized": false,
50
  "rstrip": false,
51
  "single_word": false
52
  },
53
  "unk_token": {
54
- "content": "[UNK]",
55
  "lstrip": false,
56
  "normalized": false,
57
  "rstrip": false,
 
1
  {
2
  "additional_special_tokens": [
3
  {
4
+ "content": "<|im_start|>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false
9
  },
10
  {
11
+ "content": "<|im_end|>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  "lstrip": false,
13
  "normalized": false,
14
  "rstrip": false,
 
16
  }
17
  ],
18
  "bos_token": {
19
+ "content": "<|bos|>",
20
  "lstrip": false,
21
  "normalized": false,
22
  "rstrip": false,
23
  "single_word": false
24
  },
25
  "eos_token": {
26
+ "content": "<|eos|>",
27
  "lstrip": false,
28
  "normalized": false,
29
  "rstrip": false,
30
  "single_word": false
31
  },
32
  "pad_token": {
33
+ "content": "<|pad|>",
34
  "lstrip": false,
35
  "normalized": false,
36
  "rstrip": false,
37
  "single_word": false
38
  },
39
  "unk_token": {
40
+ "content": "<|unk|>",
41
  "lstrip": false,
42
  "normalized": false,
43
  "rstrip": false,
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
- "content": "[UNK]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
@@ -9,7 +9,7 @@
9
  "special": true
10
  },
11
  "1": {
12
- "content": "[PAD]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
@@ -17,7 +17,7 @@
17
  "special": true
18
  },
19
  "2": {
20
- "content": "[BOS]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
@@ -25,7 +25,7 @@
25
  "special": true
26
  },
27
  "3": {
28
- "content": "[EOS]",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
@@ -33,7 +33,7 @@
33
  "special": true
34
  },
35
  "4": {
36
- "content": "[CTX]",
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
@@ -41,23 +41,7 @@
41
  "special": true
42
  },
43
  "5": {
44
- "content": "[XTC]",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "6": {
52
- "content": "[CAT]",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
- },
59
- "7": {
60
- "content": "[TAC]",
61
  "lstrip": false,
62
  "normalized": false,
63
  "rstrip": false,
@@ -66,16 +50,14 @@
66
  }
67
  },
68
  "additional_special_tokens": [
69
- "[CTX]",
70
- "[XTC]",
71
- "[CAT]",
72
- "[TAC]"
73
  ],
74
- "bos_token": "[BOS]",
75
  "clean_up_tokenization_spaces": false,
76
- "eos_token": "[EOS]",
77
  "model_max_length": 1000000000000000019884624838656,
78
- "pad_token": "[PAD]",
79
  "tokenizer_class": "PreTrainedTokenizerFast",
80
- "unk_token": "[UNK]"
81
  }
 
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "<|unk|>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
 
9
  "special": true
10
  },
11
  "1": {
12
+ "content": "<|pad|>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
 
17
  "special": true
18
  },
19
  "2": {
20
+ "content": "<|bos|>",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
 
25
  "special": true
26
  },
27
  "3": {
28
+ "content": "<|eos|>",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
 
33
  "special": true
34
  },
35
  "4": {
36
+ "content": "<|im_start|>",
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
 
41
  "special": true
42
  },
43
  "5": {
44
+ "content": "<|im_end|>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
  "lstrip": false,
46
  "normalized": false,
47
  "rstrip": false,
 
50
  }
51
  },
52
  "additional_special_tokens": [
53
+ "<|im_start|>",
54
+ "<|im_end|>"
 
 
55
  ],
56
+ "bos_token": "<|bos|>",
57
  "clean_up_tokenization_spaces": false,
58
+ "eos_token": "<|eos|>",
59
  "model_max_length": 1000000000000000019884624838656,
60
+ "pad_token": "<|pad|>",
61
  "tokenizer_class": "PreTrainedTokenizerFast",
62
+ "unk_token": "<|unk|>"
63
  }