nicholasKluge commited on
Commit
134ecfb
1 Parent(s): e1a518c

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|endofcompletion|>": 50266,
3
+ "<|endofinstruction|>": 50268,
4
+ "<|pad|>": 50269,
5
+ "<|startofinstruction|>": 50265,
6
+ "<|unk|>": 50267
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startofinstruction|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endofcompletion|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|pad|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": "<|endofinstruction|>",
24
+ "unk_token": {
25
+ "content": "<|unk|>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50265": {
6
+ "content": "<|startofinstruction|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "50266": {
14
+ "content": "<|endofcompletion|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "50267": {
22
+ "content": "<|unk|>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "50268": {
30
+ "content": "<|endofinstruction|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "50269": {
38
+ "content": "<|pad|>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ }
45
+ },
46
+ "bos_token": "<|startofinstruction|>",
47
+ "clean_up_tokenization_spaces": true,
48
+ "eos_token": "<|endofcompletion|>",
49
+ "errors": "replace",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "<|pad|>",
52
+ "sep_token": "<|endofinstruction|>",
53
+ "tokenizer_class": "GPT2Tokenizer",
54
+ "unk_token": "<|unk|>"
55
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff