Upload tokenizer
Browse files- added_tokens.json +5 -0
- special_tokens_map.json +15 -0
- spiece.model +3 -0
- tokenizer_config.json +23 -0
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[CLS]": 32000,
|
3 |
+
"[MASK]": 32002,
|
4 |
+
"[SEP]": 32001
|
5 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "[MASK]",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "[SEP]",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22d10b5fb5208564d1b801bb1878ba1d21c7536dc5e4bd0cf46bbe7aaa8561f8
|
3 |
+
size 834480
|
tokenizer_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"cls_token": "[CLS]",
|
5 |
+
"do_lower_case": true,
|
6 |
+
"eos_token": "[SEP]",
|
7 |
+
"keep_accents": true,
|
8 |
+
"mask_token": {
|
9 |
+
"__type": "AddedToken",
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": true,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"model_max_length": 1000000000000000019884624838656,
|
17 |
+
"pad_token": "<pad>",
|
18 |
+
"remove_space": false,
|
19 |
+
"sep_token": "[SEP]",
|
20 |
+
"sp_model_kwargs": {},
|
21 |
+
"tokenizer_class": "AlbertTokenizer",
|
22 |
+
"unk_token": "<unk>"
|
23 |
+
}
|