Hugging Face's logo

LeroyDyer
/
SpydazWebAI_QuietStar_Project

Text Generation
Transformers
Safetensors
GGUF
English
mistral
mergekit
Merge
unsloth
Cyber-Series
custom_code
text-generation-inference
Inference Endpoints
Model card Files Community
LeroyDyer commited on
Commit
89e9a7c
•
1 Parent(s): 86002a1

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +4 -0
  2. special_tokens_map.json +38 -3
  3. tokenizer.json +18 -0
  4. tokenizer_config.json +23 -3
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|endthought|>": 32001,
3
+ "<|startthought|>": 32000
4
+ }
special_tokens_map.json CHANGED
@@ -1,5 +1,40 @@
1
  {
2
- "bos_token": "<s>",
3
- "eos_token": "</s>",
4
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|startthought|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|endthought|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": {
19
+ "content": "<s>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "eos_token": {
26
+ "content": "</s>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "pad_token": "</s>",
33
+ "unk_token": {
34
+ "content": "<unk>",
35
+ "lstrip": false,
36
+ "normalized": false,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ }
40
  }
tokenizer.json CHANGED
@@ -29,6 +29,24 @@
29
  "rstrip": false,
30
  "normalized": false,
31
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32
  }
33
  ],
34
  "normalizer": {
 
29
  "rstrip": false,
30
  "normalized": false,
31
  "special": true
32
+ },
33
+ {
34
+ "id": 32000,
35
+ "content": "<|startthought|>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 32001,
44
+ "content": "<|endthought|>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
  }
51
  ],
52
  "normalizer": {
tokenizer_config.json CHANGED
@@ -25,15 +25,35 @@
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  }
29
  },
30
- "additional_special_tokens": [],
 
 
 
31
  "bos_token": "<s>",
32
  "clean_up_tokenization_spaces": false,
33
  "eos_token": "</s>",
34
  "legacy": true,
35
- "model_max_length": 1000000000000000019884624838656,
36
- "pad_token": null,
 
37
  "sp_model_kwargs": {},
38
  "spaces_between_special_tokens": false,
39
  "tokenizer_class": "LlamaTokenizer",
 
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<|startthought|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|endthought|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
  }
45
  },
46
+ "additional_special_tokens": [
47
+ "<|startthought|>",
48
+ "<|endthought|>"
49
+ ],
50
  "bos_token": "<s>",
51
  "clean_up_tokenization_spaces": false,
52
  "eos_token": "</s>",
53
  "legacy": true,
54
+ "model_max_length": 32768,
55
+ "pad_token": "</s>",
56
+ "padding_side": "right",
57
  "sp_model_kwargs": {},
58
  "spaces_between_special_tokens": false,
59
  "tokenizer_class": "LlamaTokenizer",