Commit
•
a838e2a
1
Parent(s):
828c4e4
Upload tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +5 -0
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
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 3 |
+
"special_tokens_map_file": "cache/hub/models--ai4bharat--IndicBERTv2-MLM-only/snapshots/51eb711a4c4b29949298b3f46971b5e1a0fd963f/special_tokens_map.json",
|
| 4 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 5 |
+
}
|