Upload tokenizer
Browse files- sentencepiece.bpe.model +3 -0
- tokenizer_config.json +1 -0
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
| 3 |
+
size 5069051
|
tokenizer_config.json
CHANGED
|
@@ -45,6 +45,7 @@
|
|
| 45 |
"clean_up_tokenization_spaces": false,
|
| 46 |
"cls_token": "<s>",
|
| 47 |
"eos_token": "</s>",
|
|
|
|
| 48 |
"mask_token": "<mask>",
|
| 49 |
"model_max_length": 512,
|
| 50 |
"pad_token": "<pad>",
|
|
|
|
| 45 |
"clean_up_tokenization_spaces": false,
|
| 46 |
"cls_token": "<s>",
|
| 47 |
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
"mask_token": "<mask>",
|
| 50 |
"model_max_length": 512,
|
| 51 |
"pad_token": "<pad>",
|