Torrchy commited on
Commit
3e16997
·
verified ·
1 Parent(s): 935af9e

Upload folder using huggingface_hub

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +7 -1
  2. tokenizer_config.json +7 -0
special_tokens_map.json CHANGED
@@ -13,7 +13,13 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": "<|endoftext|>",
 
 
 
 
 
 
17
  "unk_token": {
18
  "content": "<|endoftext|>",
19
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
  "unk_token": {
24
  "content": "<|endoftext|>",
25
  "lstrip": false,
tokenizer_config.json CHANGED
@@ -15,8 +15,15 @@
15
  "clean_up_tokenization_spaces": true,
16
  "eos_token": "<|endoftext|>",
17
  "errors": "replace",
 
18
  "model_max_length": 2048,
 
19
  "pad_token": "<|endoftext|>",
 
 
 
20
  "tokenizer_class": "GPT2Tokenizer",
 
 
21
  "unk_token": "<|endoftext|>"
22
  }
 
15
  "clean_up_tokenization_spaces": true,
16
  "eos_token": "<|endoftext|>",
17
  "errors": "replace",
18
+ "max_length": 512,
19
  "model_max_length": 2048,
20
+ "pad_to_multiple_of": null,
21
  "pad_token": "<|endoftext|>",
22
+ "pad_token_type_id": 0,
23
+ "padding_side": "right",
24
+ "stride": 0,
25
  "tokenizer_class": "GPT2Tokenizer",
26
+ "truncation_side": "right",
27
+ "truncation_strategy": "longest_first",
28
  "unk_token": "<|endoftext|>"
29
  }