SummerSigh commited on
Commit
b57d9bf
1 Parent(s): 14e113c

Upload tokenizer

Browse files
Files changed (5) hide show
  1. merges.txt +0 -0
  2. special_tokens_map.json +27 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +33 -0
  5. vocab.json +0 -0
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>"
4
+ ],
5
+ "bos_token": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "pad_token": "<|endoftext|>",
20
+ "unk_token": {
21
+ "content": "<|endoftext|>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ }
27
+ }
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_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "errors": "replace",
20
+ "model_max_length": 1000000000000000019884624838656,
21
+ "pad_token": "<|endoftext|>",
22
+ "special_tokens_map_file": "/root/.cache/huggingface/hub/models--xhyi--PT_GPTNEO350_ATG/snapshots/56ab08aaa6802d0f830d42c352d5d536be72811d/special_tokens_map.json",
23
+ "tokenizer_class": "GPT2Tokenizer",
24
+ "unk_token": {
25
+ "__type": "AddedToken",
26
+ "content": "<|endoftext|>",
27
+ "lstrip": false,
28
+ "normalized": true,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "verbose": false
33
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff