paragon-analytics
commited on
Commit
•
f5950dd
1
Parent(s):
a6d154a
Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +4 -3
- vocab.txt +0 -0
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,14 +1,15 @@
|
|
1 |
{
|
2 |
"cls_token": "[CLS]",
|
3 |
-
"
|
|
|
4 |
"mask_token": "[MASK]",
|
5 |
"model_max_length": 512,
|
6 |
-
"name_or_path": "
|
7 |
"pad_token": "[PAD]",
|
8 |
"sep_token": "[SEP]",
|
9 |
"special_tokens_map_file": null,
|
10 |
"strip_accents": null,
|
11 |
"tokenize_chinese_chars": true,
|
12 |
-
"tokenizer_class": "
|
13 |
"unk_token": "[UNK]"
|
14 |
}
|
|
|
1 |
{
|
2 |
"cls_token": "[CLS]",
|
3 |
+
"cuda": 0,
|
4 |
+
"do_lower_case": true,
|
5 |
"mask_token": "[MASK]",
|
6 |
"model_max_length": 512,
|
7 |
+
"name_or_path": "d4data/biomedical-ner-all",
|
8 |
"pad_token": "[PAD]",
|
9 |
"sep_token": "[SEP]",
|
10 |
"special_tokens_map_file": null,
|
11 |
"strip_accents": null,
|
12 |
"tokenize_chinese_chars": true,
|
13 |
+
"tokenizer_class": "DistilBertTokenizer",
|
14 |
"unk_token": "[UNK]"
|
15 |
}
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|