add tokenizer
Browse files- special_tokens_map.json +1 -1
- tokenizer.json +0 -0
- tokenizer_config.json +0 -1
special_tokens_map.json
CHANGED
|
@@ -9,7 +9,7 @@
|
|
| 9 |
"mask_token": {
|
| 10 |
"content": "<mask>",
|
| 11 |
"lstrip": true,
|
| 12 |
-
"normalized":
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
|
|
|
| 9 |
"mask_token": {
|
| 10 |
"content": "<mask>",
|
| 11 |
"lstrip": true,
|
| 12 |
+
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -18,7 +18,6 @@
|
|
| 18 |
"name_or_path": "camembert-base",
|
| 19 |
"pad_token": "<pad>",
|
| 20 |
"sep_token": "</s>",
|
| 21 |
-
"sp_model_kwargs": {},
|
| 22 |
"special_tokens_map_file": null,
|
| 23 |
"tokenizer_class": "CamembertTokenizer",
|
| 24 |
"unk_token": "<unk>"
|
|
|
|
| 18 |
"name_or_path": "camembert-base",
|
| 19 |
"pad_token": "<pad>",
|
| 20 |
"sep_token": "</s>",
|
|
|
|
| 21 |
"special_tokens_map_file": null,
|
| 22 |
"tokenizer_class": "CamembertTokenizer",
|
| 23 |
"unk_token": "<unk>"
|