Initial commit
Browse files- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +1 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|"}
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"ी": 0, "ल": 1, "ऊ": 2, "र": 3, "त": 4, "ठ": 5, "उ": 6, "ह": 7, "ब": 8, "ृ": 9, "ि": 10, "ऐ": 11, "फ": 12, "घ": 13, "च": 14, "ञ": 15, "ऋ": 16, "ज": 17, "झ": 19, "श": 20, "ङ": 21, "म": 22, "य": 23, "ो": 24, "ढ": 25, "": 26, "इ": 27, "न": 28, "थ": 29, "औ": 30, "ओ": 31, "ै": 32, "ए": 33, "ँ": 34, "ध": 35, "ं": 36, "ट": 37, "ख": 38, "ड": 39, "ा": 40, "आ": 41, "व": 42, "द": 43, "ग": 44, "ष": 45, "अ": 46, "ई": 47, "ॠ": 48, "स": 49, "ू": 50, "े": 51, "्": 52, "प": 53, "ु": 54, "छ": 55, "ः": 56, "ौ": 57, "ण": 58, "भ": 59, "": 60, "क": 61, "८": 62, "|": 18, "[UNK]": 63, "[PAD]": 64}
|