Commit
•
58f6656
1
Parent(s):
b0189d4
Upload tokenizer
Browse files- special_tokens_map.json +42 -6
- tokenizer_config.json +1 -1
- vocab.json +0 -0
special_tokens_map.json
CHANGED
|
@@ -1,7 +1,25 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"mask_token": {
|
| 6 |
"content": "<mask>",
|
| 7 |
"lstrip": true,
|
|
@@ -9,7 +27,25 @@
|
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
| 12 |
-
"pad_token":
|
| 13 |
-
|
| 14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
"mask_token": {
|
| 24 |
"content": "<mask>",
|
| 25 |
"lstrip": true,
|
|
|
|
| 27 |
"rstrip": false,
|
| 28 |
"single_word": false
|
| 29 |
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
}
|
tokenizer_config.json
CHANGED
|
@@ -45,6 +45,7 @@
|
|
| 45 |
"bos_token": "<s>",
|
| 46 |
"clean_up_tokenization_spaces": true,
|
| 47 |
"cls_token": "<s>",
|
|
|
|
| 48 |
"eos_token": "</s>",
|
| 49 |
"errors": "replace",
|
| 50 |
"mask_token": "<mask>",
|
|
@@ -52,6 +53,5 @@
|
|
| 52 |
"pad_token": "<pad>",
|
| 53 |
"sep_token": "</s>",
|
| 54 |
"tokenizer_class": "RobertaTokenizer",
|
| 55 |
-
"trim_offsets": true,
|
| 56 |
"unk_token": "<unk>"
|
| 57 |
}
|
|
|
|
| 45 |
"bos_token": "<s>",
|
| 46 |
"clean_up_tokenization_spaces": true,
|
| 47 |
"cls_token": "<s>",
|
| 48 |
+
"do_lower_case": true,
|
| 49 |
"eos_token": "</s>",
|
| 50 |
"errors": "replace",
|
| 51 |
"mask_token": "<mask>",
|
|
|
|
| 53 |
"pad_token": "<pad>",
|
| 54 |
"sep_token": "</s>",
|
| 55 |
"tokenizer_class": "RobertaTokenizer",
|
|
|
|
| 56 |
"unk_token": "<unk>"
|
| 57 |
}
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|