Hugging Face's logo

UNSAFE
/
praxis-4096

Model card Files Community
Vectorrent commited on
Commit
6f49b6b
·
verified ·
1 Parent(s): e07b871

Upload 3 files

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +3 -40
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +8 -54
special_tokens_map.json CHANGED
@@ -1,57 +1,20 @@
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,
29
- "single_word": false
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
  "bos_token": {
3
+ "content": "<|im_start|>",
4
  "lstrip": false,
5
  "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
+ "content": "<|im_end|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "pad_token": {
17
+ "content": "<|endoftext|>",
 
 
 
 
 
 
 
18
  "lstrip": false,
19
  "normalized": false,
20
  "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,
@@ -17,47 +17,7 @@
17
  "special": true
18
  },
19
  "2": {
20
- "content": "[BOS]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "3": {
28
- "content": "[EOS]",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "4": {
36
- "content": "[CTX]",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
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,
@@ -65,17 +25,11 @@
65
  "special": true
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": "<|endoftext|>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
 
9
  "special": true
10
  },
11
  "1": {
12
+ "content": "<|im_start|>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
 
17
  "special": true
18
  },
19
  "2": {
20
+ "content": "<|im_end|>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
 
25
  "special": true
26
  }
27
  },
28
+ "bos_token": "<|im_start|>",
 
 
 
 
 
 
29
  "clean_up_tokenization_spaces": false,
30
+ "eos_token": "<|im_end|>",
31
+ "extra_special_tokens": {},
32
  "model_max_length": 1000000000000000019884624838656,
33
+ "pad_token": "<|endoftext|>",
34
+ "tokenizer_class": "PreTrainedTokenizerFast"
 
35
  }