Rudra-ai commited on
Commit
4374c5b
1 Parent(s): 1ef1430

Upload tokenizer

Browse files
special_tokens_map.json CHANGED
@@ -12,12 +12,5 @@
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
- },
16
- "pad_token": {
17
- "content": "[PAD]",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
  }
23
  }
 
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
 
 
 
 
 
 
 
15
  }
16
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8485b8900f2ef3a891091dbe5ef0edc56f6922c0a23c7dfbb4baf64854f7de4
3
- size 17210102
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
tokenizer_config.json CHANGED
@@ -2047,14 +2047,6 @@
2047
  "rstrip": false,
2048
  "single_word": false,
2049
  "special": true
2050
- },
2051
- "128256": {
2052
- "content": "[PAD]",
2053
- "lstrip": false,
2054
- "normalized": false,
2055
- "rstrip": false,
2056
- "single_word": false,
2057
- "special": true
2058
  }
2059
  },
2060
  "bos_token": "<|begin_of_text|>",
@@ -2066,7 +2058,5 @@
2066
  "attention_mask"
2067
  ],
2068
  "model_max_length": 131072,
2069
- "pad_token": "[PAD]",
2070
- "padding_side": "left",
2071
  "tokenizer_class": "PreTrainedTokenizerFast"
2072
  }
 
2047
  "rstrip": false,
2048
  "single_word": false,
2049
  "special": true
 
 
 
 
 
 
 
 
2050
  }
2051
  },
2052
  "bos_token": "<|begin_of_text|>",
 
2058
  "attention_mask"
2059
  ],
2060
  "model_max_length": 131072,
 
 
2061
  "tokenizer_class": "PreTrainedTokenizerFast"
2062
  }