add tokenizer
Browse files- added_tokens.json +3 -1
- special_tokens_map.json +8 -1
- tokenizer.json +1 -1
- tokenizer_config.json +11 -1
added_tokens.json
CHANGED
@@ -1 +1,3 @@
|
|
1 |
-
{
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<hl>": 250100
|
3 |
+
}
|
special_tokens_map.json
CHANGED
@@ -1 +1,8 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<hl>"
|
4 |
+
],
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"unk_token": "<unk>"
|
8 |
+
}
|
tokenizer.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 16315302
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff0d2a9b1e74c78117caaf355264121c1391aef3c28f883e132e87710411e3cf
|
3 |
size 16315302
|
tokenizer_config.json
CHANGED
@@ -1 +1,11 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": null,
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"extra_ids": 0,
|
5 |
+
"name_or_path": "mt5-base-ruquad-qg",
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sp_model_kwargs": {},
|
8 |
+
"special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
|
9 |
+
"tokenizer_class": "T5Tokenizer",
|
10 |
+
"unk_token": "<unk>"
|
11 |
+
}
|