cenkersisman commited on
Commit
f1bbc8d
1 Parent(s): d2751d4

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "(A)": 52005,
3
+ "[CLS]": 52002,
4
+ "[EOS]": 52000,
5
+ "[PAD]": 52001,
6
+ "[Q]": 52004,
7
+ "[SEP]": 52003,
8
+ "[UNK]": 52006
9
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[Q]",
4
+ "(A)"
5
+ ],
6
+ "bos_token": "[EOS]",
7
+ "cls_token": "[CLS]",
8
+ "eos_token": "[EOS]",
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "unk_token": "[UNK]"
12
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 1024,
7
+ "tokenizer_class": "GPT2Tokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff