Add vocab file and tokenizer_config.json
Browse files- sentencepiece.bpe.model +0 -0
- sentencepiece.bpe.vocab +0 -0
- tokenizer_config.json +14 -0
sentencepiece.bpe.model
ADDED
|
Binary file (905 kB). View file
|
|
|
sentencepiece.bpe.vocab
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"unk_token": "<unk>",
|
| 5 |
+
"sep_token": "</s>",
|
| 6 |
+
"cls_token": "<s>",
|
| 7 |
+
"pad_token": "<pad>",
|
| 8 |
+
"mask_token": "<mask>",
|
| 9 |
+
"additional_special_tokens": [
|
| 10 |
+
"<s>NOTUSED",
|
| 11 |
+
"</s>NOTUSED",
|
| 12 |
+
"<th_roberta_space_token>"
|
| 13 |
+
]
|
| 14 |
+
}
|