Moreno La Quatra commited on
Commit
16fd9d9
1 Parent(s): d77cb9b

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "[END]": 50258,
3
+ "[PAD]": 50259,
4
+ "[START]": 50257
5
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[START]",
3
+ "eos_token": "[END]",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "[START]",
4
+ "eos_token": "[END]",
5
+ "model_max_length": 1024,
6
+ "name_or_path": "distilgpt2",
7
+ "pad_token": "[PAD]",
8
+ "special_tokens_map_file": null,
9
+ "tokenizer_class": "GPT2Tokenizer",
10
+ "unk_token": "<|endoftext|>"
11
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff