baiges commited on
Commit
3a1cd51
1 Parent(s): 9706aa0

Upload folder using huggingface_hub

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +4 -21
  2. tokenizer_config.json +4 -4
special_tokens_map.json CHANGED
@@ -1,23 +1,6 @@
1
  {
2
- "bos_token": {
3
- "content": "<|endoftext|>",
4
- "lstrip": false,
5
- "normalized": true,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "<|endoftext|>",
11
- "lstrip": false,
12
- "normalized": true,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "unk_token": {
17
- "content": "<|endoftext|>",
18
- "lstrip": false,
19
- "normalized": true,
20
- "rstrip": false,
21
- "single_word": false
22
- }
23
  }
 
1
  {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  }
tokenizer_config.json CHANGED
@@ -11,12 +11,12 @@
11
  "special": true
12
  }
13
  },
14
- "bos_token": "<|endoftext|>",
15
  "clean_up_tokenization_spaces": true,
16
- "eos_token": "<|endoftext|>",
17
  "errors": "replace",
18
  "model_max_length": 1000000000000000019884624838656,
19
- "pad_token": null,
20
  "tokenizer_class": "GPT2Tokenizer",
21
- "unk_token": "<|endoftext|>"
22
  }
 
11
  "special": true
12
  }
13
  },
14
+ "bos_token": "<s>",
15
  "clean_up_tokenization_spaces": true,
16
+ "eos_token": "</s>",
17
  "errors": "replace",
18
  "model_max_length": 1000000000000000019884624838656,
19
+ "pad_token": "<pad>",
20
  "tokenizer_class": "GPT2Tokenizer",
21
+ "unk_token": "<unk>"
22
  }