Upload tokenizer
Browse files- special_tokens_map.json +14 -2
- tokenizer_config.json +1 -0
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,16 @@
|
|
| 1 |
{
|
| 2 |
-
"pad_token":
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"pad_token": {
|
| 3 |
+
"content": "फ",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"unk_token": {
|
| 10 |
+
"content": "<unk>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
}
|
| 16 |
}
|
tokenizer_config.json
CHANGED
|
@@ -19,6 +19,7 @@
|
|
| 19 |
}
|
| 20 |
},
|
| 21 |
"clean_up_tokenization_spaces": true,
|
|
|
|
| 22 |
"is_uroman": false,
|
| 23 |
"language": "hin",
|
| 24 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 19 |
}
|
| 20 |
},
|
| 21 |
"clean_up_tokenization_spaces": true,
|
| 22 |
+
"extra_special_tokens": {},
|
| 23 |
"is_uroman": false,
|
| 24 |
"language": "hin",
|
| 25 |
"model_max_length": 1000000000000000019884624838656,
|