Upload tokenizer
Browse files- .gitattributes +1 -0
- added_tokens.json +25 -0
- special_tokens_map.json +9 -0
- spm.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +16 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"Abschlagsänderung": 250109,
|
3 |
+
"An- und Ummeldungen": 250111,
|
4 |
+
"Beschwerdemanagement": 250104,
|
5 |
+
"Energieausweis": 250117,
|
6 |
+
"Energieeffizienz und Beratung": 250123,
|
7 |
+
"Fernwärme": 250119,
|
8 |
+
"Informationen zu Baumaßnahmen": 250115,
|
9 |
+
"Kontaktdatenänderung": 250110,
|
10 |
+
"Notfallkontakte": 250113,
|
11 |
+
"Photovoltaik": 250122,
|
12 |
+
"Rechnungsanfragen": 250105,
|
13 |
+
"Sperrmüll": 250121,
|
14 |
+
"Strassenentsorgung": 250120,
|
15 |
+
"Störungsmeldungen und Auskünfte": 250102,
|
16 |
+
"Tarifinformationen": 250106,
|
17 |
+
"Tarifwechsel": 250107,
|
18 |
+
"Technischer Support": 250103,
|
19 |
+
"Thermographie": 250118,
|
20 |
+
"Umwelt- und Nachhaltigkeitsinitiativen": 250114,
|
21 |
+
"Vertragsangelegenheiten": 250108,
|
22 |
+
"Zählerstände übermitteln": 250116,
|
23 |
+
"[MASK]": 250101,
|
24 |
+
"Öffnungszeiten": 250112
|
25 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"unk_token": "[UNK]"
|
9 |
+
}
|
spm.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
|
3 |
+
size 4305025
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0cca807d85c12109c5cc59e521c41dc3adfb1b03f698bd1d3e163d890f3c12d
|
3 |
+
size 16320811
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"cls_token": "[CLS]",
|
5 |
+
"do_lower_case": false,
|
6 |
+
"eos_token": "[SEP]",
|
7 |
+
"mask_token": "[MASK]",
|
8 |
+
"model_max_length": 512,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"sp_model_kwargs": {},
|
12 |
+
"split_by_punct": false,
|
13 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
14 |
+
"unk_token": "[UNK]",
|
15 |
+
"vocab_type": "spm"
|
16 |
+
}
|