Commit
•
c5f6aa7
1
Parent(s):
fc756e8
add tokenizer
Browse files- added_tokens.json +0 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -1
- tokenizer_config.json +1 -0
added_tokens.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
| 3 |
+
size 5069051
|
special_tokens_map.json
CHANGED
|
@@ -5,7 +5,7 @@
|
|
| 5 |
"mask_token": {
|
| 6 |
"content": "<mask>",
|
| 7 |
"lstrip": true,
|
| 8 |
-
"normalized":
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
|
|
|
| 5 |
"mask_token": {
|
| 6 |
"content": "<mask>",
|
| 7 |
"lstrip": true,
|
| 8 |
+
"normalized": true,
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
tokenizer_config.json
CHANGED
|
@@ -14,6 +14,7 @@
|
|
| 14 |
"name_or_path": "xlm-roberta-base",
|
| 15 |
"pad_token": "<pad>",
|
| 16 |
"sep_token": "</s>",
|
|
|
|
| 17 |
"special_tokens_map_file": null,
|
| 18 |
"tokenizer_class": "XLMRobertaTokenizer",
|
| 19 |
"unk_token": "<unk>"
|
|
|
|
| 14 |
"name_or_path": "xlm-roberta-base",
|
| 15 |
"pad_token": "<pad>",
|
| 16 |
"sep_token": "</s>",
|
| 17 |
+
"sp_model_kwargs": {},
|
| 18 |
"special_tokens_map_file": null,
|
| 19 |
"tokenizer_class": "XLMRobertaTokenizer",
|
| 20 |
"unk_token": "<unk>"
|