Commit
•
d342f99
1
Parent(s):
92d29a2
add tokenizer
Browse files- added_tokens.json +7 -0
- special_tokens_map.json +9 -0
- tokenizer_config.json +17 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[BOS]": 30003,
|
3 |
+
"[BSEP]": 30000,
|
4 |
+
"[EOS]": 30004,
|
5 |
+
"[FSEP]": 30001,
|
6 |
+
"[SOB]": 30002
|
7 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[BOS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[EOS]",
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"unk_token": "[UNK]"
|
9 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": false,
|
5 |
+
"full_tokenizer_file": null,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"name_or_path": "/content/drive/MyDrive/CaMelBERTSharedmeter2poem2",
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"special_tokens_map_file": null,
|
12 |
+
"strip_accents": null,
|
13 |
+
"tokenize_chinese_chars": true,
|
14 |
+
"tokenizer_class": "BertTokenizer",
|
15 |
+
"tokenizer_file": null,
|
16 |
+
"unk_token": "[UNK]"
|
17 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|