Upload tokenizer
Browse files- tokenizer.json +16 -2
- tokenizer_config.json +1 -1
tokenizer.json
CHANGED
@@ -1,7 +1,21 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 32,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
+
"padding": {
|
10 |
+
"strategy": {
|
11 |
+
"Fixed": 32
|
12 |
+
},
|
13 |
+
"direction": "Right",
|
14 |
+
"pad_to_multiple_of": null,
|
15 |
+
"pad_id": 0,
|
16 |
+
"pad_type_id": 0,
|
17 |
+
"pad_token": "<pad>"
|
18 |
+
},
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|
tokenizer_config.json
CHANGED
@@ -6,7 +6,7 @@
|
|
6 |
"name_or_path": "lmqg_output/trimmed_qg/mt5-small-trimmed-ru-120000-ruquad-qg/best_model",
|
7 |
"pad_token": "<pad>",
|
8 |
"sp_model_kwargs": {},
|
9 |
-
"special_tokens_map_file": "/home/
|
10 |
"tokenizer_class": "T5Tokenizer",
|
11 |
"unk_token": "<unk>"
|
12 |
}
|
|
|
6 |
"name_or_path": "lmqg_output/trimmed_qg/mt5-small-trimmed-ru-120000-ruquad-qg/best_model",
|
7 |
"pad_token": "<pad>",
|
8 |
"sp_model_kwargs": {},
|
9 |
+
"special_tokens_map_file": "/home/c.c2042013/.cache/huggingface/hub/models--google--mt5-small/snapshots/38f23af8ec210eb6c376d40e9c56bd25a80f195d/special_tokens_map.json",
|
10 |
"tokenizer_class": "T5Tokenizer",
|
11 |
"unk_token": "<unk>"
|
12 |
}
|