theformatisvalid commited on
Commit
7cc2359
·
verified ·
1 Parent(s): 1f7d560

Upload 12 files

Browse files
src/tokenizers/bpe_v15k_f2/special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "unk_token": "<UNK>"
3
+ }
src/tokenizers/bpe_v15k_f2/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
src/tokenizers/bpe_v15k_f2/tokenizer_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<UNK>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<NUM>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<URL>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<EMAIL>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "unk_token": "<UNK>",
37
+ "cls_token": null,
38
+ "sep_token": null,
39
+ "mask_token": null,
40
+ "model_max_length": 512
41
+ }
src/tokenizers/bpe_v8k_f2/special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "unk_token": "<UNK>"
3
+ }
src/tokenizers/bpe_v8k_f2/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
src/tokenizers/bpe_v8k_f2/tokenizer_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "unk_token": "<UNK>",
3
+ "cls_token": null,
4
+ "sep_token": null,
5
+ "mask_token": null,
6
+ "model_max_length": 512
7
+ }
src/tokenizers/bpe_v8k_f3/special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "unk_token": "<UNK>"
3
+ }
src/tokenizers/bpe_v8k_f3/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
src/tokenizers/bpe_v8k_f3/tokenizer_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "unk_token": "<UNK>",
3
+ "cls_token": null,
4
+ "sep_token": null,
5
+ "mask_token": null,
6
+ "model_max_length": 512
7
+ }
src/tokenizers/bpe_v8k_f4/special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "unk_token": "<UNK>"
3
+ }
src/tokenizers/bpe_v8k_f4/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
src/tokenizers/bpe_v8k_f4/tokenizer_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "unk_token": "<UNK>",
3
+ "cls_token": null,
4
+ "sep_token": null,
5
+ "mask_token": null,
6
+ "model_max_length": 512
7
+ }