Hugging Face's logo

clam004
/
oct30_test2

Text Generation
Transformers
PyTorch
gpt_neo
Model card Files
xet
 Community
1
clam004 commited on
Commit
6a8406b
·
1 Parent(s): e768b66

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +0 -3
  2. tokenizer.json +1 -1
  3. tokenizer_config.json +2 -4
special_tokens_map.json CHANGED
@@ -1,7 +1,4 @@
1
  {
2
- "additional_special_tokens": [
3
- "<|endoftext|>"
4
- ],
5
  "bos_token": "<|endoftext|>",
6
  "eos_token": "<|endoftext|>",
7
  "pad_token": "<|endoftext|>",
 
1
  {
 
 
 
2
  "bos_token": "<|endoftext|>",
3
  "eos_token": "<|endoftext|>",
4
  "pad_token": "<|endoftext|>",
tokenizer.json CHANGED
@@ -9,7 +9,7 @@
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
- "normalized": false,
13
  "special": true
14
  }
15
  ],
 
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
+ "normalized": true,
13
  "special": true
14
  }
15
  ],
tokenizer_config.json CHANGED
@@ -5,15 +5,13 @@
5
  "50256": {
6
  "content": "<|endoftext|>",
7
  "lstrip": false,
8
- "normalized": false,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
12
  }
13
  },
14
- "additional_special_tokens": [
15
- "<|endoftext|>"
16
- ],
17
  "bos_token": "<|endoftext|>",
18
  "clean_up_tokenization_spaces": true,
19
  "eos_token": "<|endoftext|>",
 
5
  "50256": {
6
  "content": "<|endoftext|>",
7
  "lstrip": false,
8
+ "normalized": true,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
12
  }
13
  },
14
+ "additional_special_tokens": [],
 
 
15
  "bos_token": "<|endoftext|>",
16
  "clean_up_tokenization_spaces": true,
17
  "eos_token": "<|endoftext|>",