birgermoell commited on
Commit
f23e1e1
1 Parent(s): 2675f75

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +14 -19
  2. tokenizer.json +0 -18
  3. tokenizer_config.json +3 -24
special_tokens_map.json CHANGED
@@ -1,21 +1,16 @@
1
  {
2
- "additional_special_tokens": [
3
- {
4
- "content": "<|im_start|>",
5
- "lstrip": 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
  }
 
1
  {
2
+ "eos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<|padding|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
 
 
 
 
 
16
  }
tokenizer.json CHANGED
@@ -254,24 +254,6 @@
254
  "rstrip": false,
255
  "normalized": false,
256
  "special": true
257
- },
258
- {
259
- "id": 50280,
260
- "content": "<|im_start|>",
261
- "single_word": false,
262
- "lstrip": false,
263
- "rstrip": false,
264
- "normalized": false,
265
- "special": true
266
- },
267
- {
268
- "id": 50281,
269
- "content": "<|im_end|>",
270
- "single_word": false,
271
- "lstrip": false,
272
- "rstrip": false,
273
- "normalized": false,
274
- "special": true
275
  }
276
  ],
277
  "normalizer": {
 
254
  "rstrip": false,
255
  "normalized": false,
256
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
257
  }
258
  ],
259
  "normalizer": {
tokenizer_config.json CHANGED
@@ -226,34 +226,13 @@
226
  "rstrip": false,
227
  "single_word": false,
228
  "special": true
229
- },
230
- "50280": {
231
- "content": "<|im_start|>",
232
- "lstrip": false,
233
- "normalized": false,
234
- "rstrip": false,
235
- "single_word": false,
236
- "special": true
237
- },
238
- "50281": {
239
- "content": "<|im_end|>",
240
- "lstrip": false,
241
- "normalized": false,
242
- "rstrip": false,
243
- "single_word": false,
244
- "special": true
245
  }
246
  },
247
- "additional_special_tokens": [
248
- "<|im_start|>",
249
- "<|im_end|>"
250
- ],
251
- "bos_token": "<|im_start|>",
252
- "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 %}",
253
  "clean_up_tokenization_spaces": true,
254
- "eos_token": "<|im_end|>",
255
  "model_max_length": 1000000000000000019884624838656,
256
- "pad_token": "<|im_end|>",
257
  "tokenizer_class": "GPTNeoXTokenizer",
258
  "unk_token": null
259
  }
 
226
  "rstrip": false,
227
  "single_word": false,
228
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
229
  }
230
  },
231
+ "bos_token": null,
 
 
 
 
 
232
  "clean_up_tokenization_spaces": true,
233
+ "eos_token": "<|endoftext|>",
234
  "model_max_length": 1000000000000000019884624838656,
235
+ "pad_token": "<|padding|>",
236
  "tokenizer_class": "GPTNeoXTokenizer",
237
  "unk_token": null
238
  }