Upload tokenizer
Browse files- tokenizer.json +7 -5
- tokenizer_config.json +1 -1
tokenizer.json
CHANGED
@@ -1,12 +1,14 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
4 |
"direction": "Right",
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
|
|
8 |
},
|
9 |
-
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
12 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": {
|
5 |
+
"strategy": "BatchLongest",
|
6 |
"direction": "Right",
|
7 |
+
"pad_to_multiple_of": null,
|
8 |
+
"pad_id": 1,
|
9 |
+
"pad_type_id": 0,
|
10 |
+
"pad_token": "<pad>"
|
11 |
},
|
|
|
12 |
"added_tokens": [
|
13 |
{
|
14 |
"id": 0,
|
tokenizer_config.json
CHANGED
@@ -5,6 +5,6 @@
|
|
5 |
"mask_token": "<mask>",
|
6 |
"model_max_length": 512,
|
7 |
"pad_token": "<pad>",
|
8 |
-
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--new5558--HoogBERTa/snapshots/
|
9 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
10 |
}
|
|
|
5 |
"mask_token": "<mask>",
|
6 |
"model_max_length": 512,
|
7 |
"pad_token": "<pad>",
|
8 |
+
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--new5558--HoogBERTa/snapshots/76ab6e47ce08d0ad7ad7ba2bf0f5d0aa1e86ddb6/special_tokens_map.json",
|
9 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
10 |
}
|