Hugging Face's logo

UNSAFE
/
praxis-2048

Model card Files Community
Vectorrent commited on
Commit
8fbe13c
·
verified ·
1 Parent(s): b1cc346

Upload 3 files

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +3 -10
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +9 -17
special_tokens_map.json CHANGED
@@ -1,27 +1,20 @@
1
  {
2
  "bos_token": {
3
- "content": "[BOS]",
4
  "lstrip": false,
5
  "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
- "content": "[EOS]",
11
  "lstrip": false,
12
  "normalized": 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,
26
  "normalized": false,
27
  "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,
@@ -17,15 +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,
@@ -33,11 +25,11 @@
33
  "special": true
34
  }
35
  },
36
- "bos_token": "[BOS]",
37
- "clean_up_tokenization_spaces": true,
38
- "eos_token": "[EOS]",
 
39
  "model_max_length": 1000000000000000019884624838656,
40
- "pad_token": "[PAD]",
41
- "tokenizer_class": "PreTrainedTokenizerFast",
42
- "unk_token": "[UNK]"
43
  }
 
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
  }