Abhaykoul commited on
Commit
3f29dd1
1 Parent(s): 3bcf9f2

Upload 2 files

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +11 -22
  2. tokenizer_config.json +211 -22
special_tokens_map.json CHANGED
@@ -6,31 +6,20 @@
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false
 
 
 
 
 
 
 
9
  }
10
  ],
11
- "bos_token": {
12
- "content": "<|startoftext|>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false
17
- },
18
- "eos_token": {
19
- "content": "<|im_end|>",
20
- "lstrip": false,
21
- "normalized": false,
22
- "rstrip": false,
23
- "single_word": false
24
- },
25
- "pad_token": {
26
- "content": "<unk>",
27
- "lstrip": false,
28
- "normalized": false,
29
- "rstrip": false,
30
- "single_word": false
31
- },
32
  "unk_token": {
33
- "content": "<unk>",
34
  "lstrip": false,
35
  "normalized": false,
36
  "rstrip": false,
 
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false
9
+ },
10
+ {
11
+ "content": "<|im_end|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
  }
17
  ],
18
+ "bos_token": "<|im_start|>",
19
+ "eos_token": "<|im_end|>",
20
+ "pad_token": "<|im_end|>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  "unk_token": {
22
+ "content": "<|endoftext|>",
23
  "lstrip": false,
24
  "normalized": false,
25
  "rstrip": false,
tokenizer_config.json CHANGED
@@ -1,9 +1,10 @@
1
  {
2
  "add_bos_token": false,
3
  "add_eos_token": false,
 
4
  "added_tokens_decoder": {
5
  "0": {
6
- "content": "<unk>",
7
  "lstrip": false,
8
  "normalized": false,
9
  "rstrip": false,
@@ -11,22 +12,206 @@
11
  "special": true
12
  },
13
  "1": {
14
- "content": "<|startoftext|>",
15
  "lstrip": false,
16
  "normalized": false,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
20
  },
21
- "2": {
22
- "content": "<|endoftext|>",
23
  "lstrip": false,
24
- "normalized": false,
25
  "rstrip": false,
26
  "single_word": false,
27
- "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  },
29
- "6": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30
  "content": "<|im_start|>",
31
  "lstrip": false,
32
  "normalized": false,
@@ -34,29 +219,33 @@
34
  "single_word": false,
35
  "special": true
36
  },
37
- "7": {
38
  "content": "<|im_end|>",
39
  "lstrip": false,
40
  "normalized": false,
41
  "rstrip": false,
42
  "single_word": false,
43
  "special": true
 
 
 
 
 
 
 
 
44
  }
45
  },
46
  "additional_special_tokens": [
47
- "<|im_start|>"
 
48
  ],
49
- "bos_token": "<|startoftext|>",
50
- "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\\n' + system_message + '<|im_end|>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
51
- "clean_up_tokenization_spaces": false,
52
  "eos_token": "<|im_end|>",
53
- "legacy": true,
54
- "model_max_length": 4096,
55
- "pad_token": "<unk>",
56
- "padding_side": "right",
57
- "sp_model_kwargs": {},
58
- "split_special_tokens": false,
59
- "tokenizer_class": "LlamaTokenizer",
60
- "unk_token": "<unk>",
61
- "use_default_system_prompt": false
62
- }
 
1
  {
2
  "add_bos_token": false,
3
  "add_eos_token": false,
4
+ "add_prefix_space": false,
5
  "added_tokens_decoder": {
6
  "0": {
7
+ "content": "<|endoftext|>",
8
  "lstrip": false,
9
  "normalized": false,
10
  "rstrip": false,
 
12
  "special": true
13
  },
14
  "1": {
15
+ "content": "<|padding|>",
16
  "lstrip": false,
17
  "normalized": false,
18
  "rstrip": false,
19
  "single_word": false,
20
  "special": true
21
  },
22
+ "50254": {
23
+ "content": " ",
24
  "lstrip": false,
25
+ "normalized": true,
26
  "rstrip": false,
27
  "single_word": false,
28
+ "special": false
29
+ },
30
+ "50255": {
31
+ "content": " ",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "50256": {
39
+ "content": " ",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "50257": {
47
+ "content": " ",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "50258": {
55
+ "content": " ",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "50259": {
63
+ "content": " ",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "50260": {
71
+ "content": " ",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "50261": {
79
+ "content": " ",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "50262": {
87
+ "content": " ",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "50263": {
95
+ "content": " ",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "50264": {
103
+ "content": " ",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "50265": {
111
+ "content": " ",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "50266": {
119
+ "content": " ",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "50267": {
127
+ "content": " ",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "50268": {
135
+ "content": " ",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "50269": {
143
+ "content": " ",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
  },
150
+ "50270": {
151
+ "content": " ",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "50271": {
159
+ "content": " ",
160
+ "lstrip": false,
161
+ "normalized": true,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "50272": {
167
+ "content": " ",
168
+ "lstrip": false,
169
+ "normalized": true,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "50273": {
175
+ "content": " ",
176
+ "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "50274": {
183
+ "content": " ",
184
+ "lstrip": false,
185
+ "normalized": true,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "50275": {
191
+ "content": " ",
192
+ "lstrip": false,
193
+ "normalized": true,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "50276": {
199
+ "content": " ",
200
+ "lstrip": false,
201
+ "normalized": true,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "50277": {
207
+ "content": "<|pad|>",
208
+ "lstrip": false,
209
+ "normalized": true,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": false
213
+ },
214
+ "50278": {
215
  "content": "<|im_start|>",
216
  "lstrip": false,
217
  "normalized": false,
 
219
  "single_word": false,
220
  "special": true
221
  },
222
+ "50279": {
223
  "content": "<|im_end|>",
224
  "lstrip": false,
225
  "normalized": false,
226
  "rstrip": false,
227
  "single_word": false,
228
  "special": true
229
+ },
230
+ "50280": {
231
+ "content": "[PAD]",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": true
237
  }
238
  },
239
  "additional_special_tokens": [
240
+ "<|im_start|>",
241
+ "<|im_end|>"
242
  ],
243
+ "bos_token": "<|im_start|>",
244
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
245
+ "clean_up_tokenization_spaces": true,
246
  "eos_token": "<|im_end|>",
247
+ "model_max_length": 1000000000000000019884624838656,
248
+ "pad_token": "<|im_end|>",
249
+ "tokenizer_class": "GPTNeoXTokenizer",
250
+ "unk_token": "<|endoftext|>"
251
+ }