Hugging Face's logo

NeuraCraft
/
Lance-AI

Text Generation
Transformers
Safetensors
PyTorch
lance_ai
gpt
causal-lm
lance-ai
conversational
custom_code
Model card Files
xet
 Community
NeuraCraft commited on
Commit
ab4f8c8
·
1 Parent(s): b5843e3

Upload tokenizer

Browse files
Files changed (5) hide show
  1. merges.txt +0 -0
  2. special_tokens_map.json +45 -4
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +183 -7
  5. vocab.json +0 -0
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,12 +1,53 @@
1
  {
2
- "bos_token": "<|endoftext|>",
3
- "eos_token": "<|endoftext|>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  "pad_token": {
5
- "content": "[PAD]",
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
9
  "single_word": false
10
  },
11
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
12
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|fim_prefix|>",
5
+ "<|fim_middle|>",
6
+ "<|fim_suffix|>",
7
+ "<|endofprompt|>",
8
+ "<|_unuse_missing_100256|>",
9
+ "<|_unuse_missing_100261|>",
10
+ "<|_unuse_missing_100262|>",
11
+ "<|_unuse_missing_100263|>",
12
+ "<|_unuse_missing_100264|>",
13
+ "<|_unuse_missing_100265|>",
14
+ "<|_unuse_missing_100266|>",
15
+ "<|_unuse_missing_100267|>",
16
+ "<|_unuse_missing_100268|>",
17
+ "<|_unuse_missing_100269|>",
18
+ "<|_unuse_missing_100270|>",
19
+ "<|_unuse_missing_100271|>",
20
+ "<|_unuse_missing_100272|>",
21
+ "<|_unuse_missing_100273|>",
22
+ "<|_unuse_missing_100274|>",
23
+ "<|_unuse_missing_100275|>"
24
+ ],
25
+ "bos_token": {
26
+ "content": "<|endoftext|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "eos_token": {
33
+ "content": "<|endoftext|>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
  "pad_token": {
40
+ "content": "<|endoftext|>",
41
  "lstrip": false,
42
  "normalized": false,
43
  "rstrip": false,
44
  "single_word": false
45
  },
46
+ "unk_token": {
47
+ "content": "<|endoftext|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ }
53
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,16 +1,168 @@
1
  {
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
- "50256": {
 
 
 
 
 
 
 
 
5
  "content": "<|endoftext|>",
6
  "lstrip": false,
7
- "normalized": true,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
- "50257": {
13
- "content": "[PAD]",
14
  "lstrip": false,
15
  "normalized": false,
16
  "rstrip": false,
@@ -18,12 +170,36 @@
18
  "special": true
19
  }
20
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  "bos_token": "<|endoftext|>",
22
- "clean_up_tokenization_spaces": false,
 
23
  "eos_token": "<|endoftext|>",
24
  "extra_special_tokens": {},
25
- "model_max_length": 1024,
26
- "pad_token": "[PAD]",
27
  "tokenizer_class": "GPT2Tokenizer",
28
  "unk_token": "<|endoftext|>"
29
  }
 
1
  {
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
+ "100256": {
5
+ "content": "<|_unuse_missing_100256|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "100257": {
13
  "content": "<|endoftext|>",
14
  "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "100258": {
21
+ "content": "<|fim_prefix|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "100259": {
29
+ "content": "<|fim_middle|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "100260": {
37
+ "content": "<|fim_suffix|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "100261": {
45
+ "content": "<|_unuse_missing_100261|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "100262": {
53
+ "content": "<|_unuse_missing_100262|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "100263": {
61
+ "content": "<|_unuse_missing_100263|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "100264": {
69
+ "content": "<|_unuse_missing_100264|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "100265": {
77
+ "content": "<|_unuse_missing_100265|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "100266": {
85
+ "content": "<|_unuse_missing_100266|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "100267": {
93
+ "content": "<|_unuse_missing_100267|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "100268": {
101
+ "content": "<|_unuse_missing_100268|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "100269": {
109
+ "content": "<|_unuse_missing_100269|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "100270": {
117
+ "content": "<|_unuse_missing_100270|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "100271": {
125
+ "content": "<|_unuse_missing_100271|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "100272": {
133
+ "content": "<|_unuse_missing_100272|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "100273": {
141
+ "content": "<|_unuse_missing_100273|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "100274": {
149
+ "content": "<|_unuse_missing_100274|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "100275": {
157
+ "content": "<|_unuse_missing_100275|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
  "rstrip": false,
161
  "single_word": false,
162
  "special": true
163
  },
164
+ "100276": {
165
+ "content": "<|endofprompt|>",
166
  "lstrip": false,
167
  "normalized": false,
168
  "rstrip": false,
 
170
  "special": true
171
  }
172
  },
173
+ "additional_special_tokens": [
174
+ "<|endoftext|>",
175
+ "<|fim_prefix|>",
176
+ "<|fim_middle|>",
177
+ "<|fim_suffix|>",
178
+ "<|endofprompt|>",
179
+ "<|_unuse_missing_100256|>",
180
+ "<|_unuse_missing_100261|>",
181
+ "<|_unuse_missing_100262|>",
182
+ "<|_unuse_missing_100263|>",
183
+ "<|_unuse_missing_100264|>",
184
+ "<|_unuse_missing_100265|>",
185
+ "<|_unuse_missing_100266|>",
186
+ "<|_unuse_missing_100267|>",
187
+ "<|_unuse_missing_100268|>",
188
+ "<|_unuse_missing_100269|>",
189
+ "<|_unuse_missing_100270|>",
190
+ "<|_unuse_missing_100271|>",
191
+ "<|_unuse_missing_100272|>",
192
+ "<|_unuse_missing_100273|>",
193
+ "<|_unuse_missing_100274|>",
194
+ "<|_unuse_missing_100275|>"
195
+ ],
196
  "bos_token": "<|endoftext|>",
197
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
198
+ "clean_up_tokenization_spaces": true,
199
  "eos_token": "<|endoftext|>",
200
  "extra_special_tokens": {},
201
+ "model_max_length": 1000000000000000019884624838656,
202
+ "pad_token": "<|endoftext|>",
203
  "tokenizer_class": "GPT2Tokenizer",
204
  "unk_token": "<|endoftext|>"
205
  }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff