config tokenizer
Browse files- tokenizer_config.json +15 -0
tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "bpe",
|
| 3 |
+
"tokenizer_type": "bpe",
|
| 4 |
+
"unk_token": "[UNK]",
|
| 5 |
+
"bos_token": "[CLS]",
|
| 6 |
+
"eos_token": "[SEP]",
|
| 7 |
+
"pad_token": "[PAD]",
|
| 8 |
+
"mask_token": "[MASK]",
|
| 9 |
+
"normalizer_type": "Sequence",
|
| 10 |
+
"normalizers": ["NFKC", "Lowercase"],
|
| 11 |
+
"pre_tokenizer_type": "Sequence",
|
| 12 |
+
"pre_tokenizers": ["Whitespace", "Digits", "Punctuation"],
|
| 13 |
+
"vocab_size": 3000
|
| 14 |
+
}
|
| 15 |
+
|