Hugging Face's logo

nrohan09
/
merged_16bit

Text Generation
Transformers
PyTorch
Safetensors
English
mistral
text-generation-inference
unsloth
trl
sft
conversational
Inference Endpoints
Model card Files Community
nrohan09 commited on
Commit
b51d195
•
1 Parent(s): 00e8758

Upload tokenizer

Browse files
Files changed (5) hide show
  1. added_tokens.json +13 -0
  2. special_tokens_map.json +3 -3
  3. tokenizer.json +0 -0
  4. tokenizer.model +2 -2
  5. tokenizer_config.json +93 -6
added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 32001,
3
+ "<|endoftext|>": 32000,
4
+ "<|end|>": 32007,
5
+ "<|placeholder1|>": 32002,
6
+ "<|placeholder2|>": 32003,
7
+ "<|placeholder3|>": 32004,
8
+ "<|placeholder4|>": 32005,
9
+ "<|placeholder5|>": 32008,
10
+ "<|placeholder6|>": 32009,
11
+ "<|system|>": 32006,
12
+ "<|user|>": 32010
13
+ }
special_tokens_map.json CHANGED
@@ -7,17 +7,17 @@
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
  "pad_token": {
17
- "content": "<unk>",
18
  "lstrip": false,
19
  "normalized": false,
20
- "rstrip": false,
21
  "single_word": false
22
  },
23
  "unk_token": {
 
7
  "single_word": false
8
  },
9
  "eos_token": {
10
+ "content": "<|endoftext|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "pad_token": {
17
+ "content": "<|placeholder6|>",
18
  "lstrip": false,
19
  "normalized": false,
20
+ "rstrip": true,
21
  "single_word": false
22
  },
23
  "unk_token": {
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
- size 493443
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json CHANGED
@@ -22,21 +22,108 @@
22
  "content": "</s>",
23
  "lstrip": false,
24
  "normalized": false,
 
 
 
 
 
 
 
 
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": 32768,
36
- "pad_token": "<unk>",
37
  "padding_side": "left",
38
  "sp_model_kwargs": {},
39
- "spaces_between_special_tokens": false,
40
  "tokenizer_class": "LlamaTokenizer",
41
  "unk_token": "<unk>",
42
  "use_default_system_prompt": false
 
22
  "content": "</s>",
23
  "lstrip": false,
24
  "normalized": false,
25
+ "rstrip": true,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "32000": {
30
+ "content": "<|endoftext|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
  "rstrip": false,
34
  "single_word": false,
35
  "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|assistant|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": true,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<|placeholder1|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": true,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "<|placeholder2|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": true,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "32004": {
62
+ "content": "<|placeholder3|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": true,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "32005": {
70
+ "content": "<|placeholder4|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": true,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "32006": {
78
+ "content": "<|system|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": true,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "32007": {
86
+ "content": "<|end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": true,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "32008": {
94
+ "content": "<|placeholder5|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": true,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "32009": {
102
+ "content": "<|placeholder6|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": true,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "32010": {
110
+ "content": "<|user|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": true,
114
+ "single_word": false,
115
+ "special": true
116
  }
117
  },
 
118
  "bos_token": "<s>",
119
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
120
  "clean_up_tokenization_spaces": false,
121
+ "eos_token": "<|endoftext|>",
122
+ "legacy": false,
123
+ "model_max_length": 4096,
124
+ "pad_token": "<|placeholder6|>",
125
  "padding_side": "left",
126
  "sp_model_kwargs": {},
 
127
  "tokenizer_class": "LlamaTokenizer",
128
  "unk_token": "<unk>",
129
  "use_default_system_prompt": false