Commit
•
3fbd2a4
1
Parent(s):
1c901b3
Upload 6 files
Browse files- pytorch_model.bin +1 -1
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2 -1
- vocab.txt +0 -0
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 267854321
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8d458eda97109ca65d3410bbc9a3f58e5690d9ea3fde545caaff65face40335
|
| 3 |
size 267854321
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,11 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"clean_up_tokenization_spaces": true,
|
| 3 |
"cls_token": "[CLS]",
|
| 4 |
"do_lower_case": true,
|
| 5 |
"mask_token": "[MASK]",
|
| 6 |
"model_max_length": 512,
|
|
|
|
| 7 |
"pad_token": "[PAD]",
|
| 8 |
"sep_token": "[SEP]",
|
|
|
|
| 9 |
"strip_accents": null,
|
| 10 |
"tokenize_chinese_chars": true,
|
| 11 |
"tokenizer_class": "DistilBertTokenizer",
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"cls_token": "[CLS]",
|
| 3 |
"do_lower_case": true,
|
| 4 |
"mask_token": "[MASK]",
|
| 5 |
"model_max_length": 512,
|
| 6 |
+
"name_or_path": "distilbert-base-uncased",
|
| 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": "DistilBertTokenizer",
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|