santyzenith commited on
Commit
a87cadf
1 Parent(s): 7ba68a0

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<EF>": 50258,
3
+ "<SF>": 50257,
4
+ "<|endoftext|>": 0
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": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
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 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "50257": {
14
+ "content": "<SF>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": false
20
+ },
21
+ "50258": {
22
+ "content": "<EF>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": false
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<|endoftext|>",
32
+ "clean_up_tokenization_spaces": true,
33
+ "eos_token": "<|endoftext|>",
34
+ "errors": "replace",
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "<|endoftext|>",
37
+ "tokenizer_class": "GPT2Tokenizer",
38
+ "unk_token": "<|endoftext|>"
39
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff