Milana commited on
Commit
4715d9c
1 Parent(s): 9992139

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 50257,
3
+ "[PAD]": 50264,
4
+ "[e:artist]": 50261,
5
+ "[e:lyrics]": 50263,
6
+ "[e:song_name]": 50262,
7
+ "[s:artist]": 50258,
8
+ "[s:lyrics]": 50260,
9
+ "[s:song_name]": 50259
10
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[s:artist]",
4
+ "[s:song_name]",
5
+ "[s:lyrics]",
6
+ "[e:artist]",
7
+ "[e:song_name]",
8
+ "[e:lyrics]"
9
+ ],
10
+ "bos_token": {
11
+ "content": "<|endoftext|>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "eos_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": "[PAD]",
25
+ "unk_token": {
26
+ "content": "<|endoftext|>",
27
+ "lstrip": false,
28
+ "normalized": true,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "name_or_path": "sberbank-ai/rugpt3small_based_on_gpt2",
22
+ "pad_token": null,
23
+ "special_tokens_map_file": null,
24
+ "tokenizer_class": "GPT2Tokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff