UnderstandLing commited on
Commit
1732e2f
1 Parent(s): 1720a09

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +1 -1
  2. tokenizer_config.json +2 -2
special_tokens_map.json CHANGED
@@ -13,7 +13,7 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": "<unk>",
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "<|endoftext|>",
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
tokenizer_config.json CHANGED
@@ -121,8 +121,8 @@
121
  "eos_token": "<|endoftext|>",
122
  "legacy": false,
123
  "model_max_length": 131072,
124
- "pad_token": "<unk>",
125
- "padding_side": "left",
126
  "sp_model_kwargs": {},
127
  "tokenizer_class": "LlamaTokenizer",
128
  "unk_token": "<unk>",
 
121
  "eos_token": "<|endoftext|>",
122
  "legacy": false,
123
  "model_max_length": 131072,
124
+ "pad_token": "<|endoftext|>",
125
+ "padding_side": "right",
126
  "sp_model_kwargs": {},
127
  "tokenizer_class": "LlamaTokenizer",
128
  "unk_token": "<unk>",