Hugging Face's logo

AoiKazama
/
Kinoe-7B

Text Generation
Transformers
PyTorch
Safetensors
kinoe
custom_code
Model card Files Community
1
AoiKazama commited on
Commit
96c0f27
•
1 Parent(s): 45ea409

Add Tokenizer

Browse files
Files changed (5) hide show
  1. generation_config.json +6 -0
  2. special_tokens_map.json +9 -10
  3. tokenizer.json +0 -0
  4. tokenizer.model +3 -0
  5. tokenizer_config.json +14 -56
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": 2,
4
+ "max_new_tokens": 50,
5
+ "transformers_version": "4.40.1"
6
+ }
special_tokens_map.json CHANGED
@@ -1,21 +1,20 @@
1
  {
2
- "additional_special_tokens": [
3
- "</s|LLM-jp>"
4
- ],
5
  "bos_token": {
6
- "content": "<s|LLM-jp>",
 
 
 
 
 
 
 
7
  "lstrip": false,
8
  "normalized": false,
9
  "rstrip": false,
10
  "single_word": false
11
  },
12
- "cls_token": "<CLS|LLM-jp>",
13
- "eos_token": "<EOD|LLM-jp>",
14
- "mask_token": "<mask|LLM-jp>",
15
- "pad_token": "<pad|LLM-jp>",
16
- "sep_token": "<SEP|LLM-jp>",
17
  "unk_token": {
18
- "content": "<unk|LLM-jp>",
19
  "lstrip": false,
20
  "normalized": false,
21
  "rstrip": false,
 
1
  {
 
 
 
2
  "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
 
 
 
 
 
16
  "unk_token": {
17
+ "content": "<unk>",
18
  "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b2e129181c6e0dfb48d6698e03dae881d4fb93ef5e587559e043b627b7b06e9
3
+ size 943852
tokenizer_config.json CHANGED
@@ -1,7 +1,10 @@
1
  {
 
 
 
2
  "added_tokens_decoder": {
3
  "0": {
4
- "content": "<unk|LLM-jp>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
@@ -9,7 +12,7 @@
9
  "special": true
10
  },
11
  "1": {
12
- "content": "<s|LLM-jp>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
@@ -17,47 +20,7 @@
17
  "special": true
18
  },
19
  "2": {
20
- "content": "</s|LLM-jp>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "55392": {
28
- "content": "<EOD|LLM-jp>",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "55393": {
36
- "content": "<SEP|LLM-jp>",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- },
43
- "55394": {
44
- "content": "<pad|LLM-jp>",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "55395": {
52
- "content": "<CLS|LLM-jp>",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
- },
59
- "55396": {
60
- "content": "<mask|LLM-jp>",
61
  "lstrip": false,
62
  "normalized": false,
63
  "rstrip": false,
@@ -65,20 +28,15 @@
65
  "special": true
66
  }
67
  },
68
- "additional_special_tokens": [
69
- "</s|LLM-jp>"
70
- ],
71
- "bos_token": "<s|LLM-jp>",
72
  "clean_up_tokenization_spaces": false,
73
- "cls_token": "<CLS|LLM-jp>",
74
- "eod_token": "<EOD|LLM-jp>",
75
- "eos_token": "<EOD|LLM-jp>",
76
- "extra_ids": 0,
77
- "mask_token": "<mask|LLM-jp>",
78
  "model_max_length": 1000000000000000019884624838656,
79
- "pad_token": "<pad|LLM-jp>",
80
- "sep_token": "<SEP|LLM-jp>",
81
  "sp_model_kwargs": {},
82
- "tokenizer_class": "PreTrainedTokenizerFast",
83
- "unk_token": "<unk|LLM-jp>"
 
 
84
  }
 
1
  {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
  "added_tokens_decoder": {
6
  "0": {
7
+ "content": "<unk>",
8
  "lstrip": false,
9
  "normalized": false,
10
  "rstrip": false,
 
12
  "special": true
13
  },
14
  "1": {
15
+ "content": "<s>",
16
  "lstrip": false,
17
  "normalized": false,
18
  "rstrip": false,
 
20
  "special": true
21
  },
22
  "2": {
23
+ "content": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24
  "lstrip": false,
25
  "normalized": false,
26
  "rstrip": false,
 
28
  "special": true
29
  }
30
  },
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",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
  }