bovely commited on
Commit
0bac72e
1 Parent(s): dc0d4e1

Upload 2 files

Browse files
Files changed (2) hide show
  1. tokenizer.json +19 -1
  2. tokenizer_config.json +16 -0
tokenizer.json CHANGED
@@ -5,7 +5,7 @@
5
  "strategy": "BatchLongest",
6
  "direction": "Right",
7
  "pad_to_multiple_of": null,
8
- "pad_id": 128255,
9
  "pad_type_id": 0,
10
  "pad_token": "<|im_end|>"
11
  },
@@ -2313,6 +2313,24 @@
2313
  "rstrip": false,
2314
  "normalized": false,
2315
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2316
  }
2317
  ],
2318
  "normalizer": null,
 
5
  "strategy": "BatchLongest",
6
  "direction": "Right",
7
  "pad_to_multiple_of": null,
8
+ "pad_id": 128257,
9
  "pad_type_id": 0,
10
  "pad_token": "<|im_end|>"
11
  },
 
2313
  "rstrip": false,
2314
  "normalized": false,
2315
  "special": true
2316
+ },
2317
+ {
2318
+ "id": 128256,
2319
+ "content": "<|im_start|>",
2320
+ "single_word": false,
2321
+ "lstrip": false,
2322
+ "rstrip": false,
2323
+ "normalized": false,
2324
+ "special": true
2325
+ },
2326
+ {
2327
+ "id": 128257,
2328
+ "content": "<|im_end|>",
2329
+ "single_word": false,
2330
+ "lstrip": false,
2331
+ "rstrip": false,
2332
+ "normalized": false,
2333
+ "special": true
2334
  }
2335
  ],
2336
  "normalizer": null,
tokenizer_config.json CHANGED
@@ -2047,6 +2047,22 @@
2047
  "rstrip": false,
2048
  "single_word": false,
2049
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2050
  }
2051
  },
2052
  "additional_special_tokens": [
 
2047
  "rstrip": false,
2048
  "single_word": false,
2049
  "special": true
2050
+ },
2051
+ "128256": {
2052
+ "content": "<|im_start|>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ },
2059
+ "128257": {
2060
+ "content": "<|im_end|>",
2061
+ "lstrip": false,
2062
+ "normalized": false,
2063
+ "rstrip": false,
2064
+ "single_word": false,
2065
+ "special": true
2066
  }
2067
  },
2068
  "additional_special_tokens": [