tokenizer v2- include normalization discussed with Bengali community
Browse files- special_tokens_map.json +1 -1
- tokenizer.json +0 -0
- tokenizer_config.json +2 -2
special_tokens_map.json
CHANGED
|
@@ -8,7 +8,7 @@
|
|
| 8 |
"mask_token": {
|
| 9 |
"content": "[MASK]",
|
| 10 |
"single_word": false,
|
| 11 |
-
"lstrip":
|
| 12 |
"rstrip": false,
|
| 13 |
"normalized": false
|
| 14 |
}
|
| 8 |
"mask_token": {
|
| 9 |
"content": "[MASK]",
|
| 10 |
"single_word": false,
|
| 11 |
+
"lstrip": true,
|
| 12 |
"rstrip": false,
|
| 13 |
"normalized": false
|
| 14 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
tokenizer_config.json
CHANGED
|
@@ -8,9 +8,9 @@
|
|
| 8 |
"mask_token": {
|
| 9 |
"content": "[MASK]",
|
| 10 |
"single_word": false,
|
| 11 |
-
"lstrip":
|
| 12 |
"rstrip": false,
|
| 13 |
-
"normalized":
|
| 14 |
"__type": "AddedToken"
|
| 15 |
},
|
| 16 |
"model_max_length": 512,
|
| 8 |
"mask_token": {
|
| 9 |
"content": "[MASK]",
|
| 10 |
"single_word": false,
|
| 11 |
+
"lstrip": true,
|
| 12 |
"rstrip": false,
|
| 13 |
+
"normalized": true,
|
| 14 |
"__type": "AddedToken"
|
| 15 |
},
|
| 16 |
"model_max_length": 512,
|