Upload tokenizer
Browse files- tokenizer.json +2 -2
- tokenizer_config.json +44 -10
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f59925fcb90c92b894cb93e51bb9b4a6105c5c249fe54ce1c704420ac39b81af
|
| 3 |
+
size 17082756
|
tokenizer_config.json
CHANGED
|
@@ -1,20 +1,54 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": "<s>",
|
|
|
|
| 3 |
"cls_token": "<s>",
|
| 4 |
"eos_token": "</s>",
|
| 5 |
-
"mask_token":
|
| 6 |
-
"__type": "AddedToken",
|
| 7 |
-
"content": "<mask>",
|
| 8 |
-
"lstrip": true,
|
| 9 |
-
"normalized": true,
|
| 10 |
-
"rstrip": false,
|
| 11 |
-
"single_word": false
|
| 12 |
-
},
|
| 13 |
"model_max_length": 512,
|
| 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>"
|
| 20 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"250001": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
"cls_token": "<s>",
|
| 47 |
"eos_token": "</s>",
|
| 48 |
+
"mask_token": "<mask>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
"model_max_length": 512,
|
|
|
|
| 50 |
"pad_token": "<pad>",
|
| 51 |
"sep_token": "</s>",
|
|
|
|
| 52 |
"tokenizer_class": "XLMRobertaTokenizer",
|
| 53 |
"unk_token": "<unk>"
|
| 54 |
}
|