Commit
路
44eefde
1
Parent(s):
4cde656
Upload 2 files
Browse files- tokenizer_config.json +1 -66
- vocab.json +0 -0
tokenizer_config.json
CHANGED
|
@@ -1,66 +1 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"bos_token": {
|
| 4 |
-
"__type": "AddedToken",
|
| 5 |
-
"content": "<s>",
|
| 6 |
-
"lstrip": false,
|
| 7 |
-
"normalized": true,
|
| 8 |
-
"rstrip": false,
|
| 9 |
-
"single_word": false
|
| 10 |
-
},
|
| 11 |
-
"clean_up_tokenization_spaces": true,
|
| 12 |
-
"cls_token": {
|
| 13 |
-
"__type": "AddedToken",
|
| 14 |
-
"content": "<s>",
|
| 15 |
-
"lstrip": false,
|
| 16 |
-
"normalized": true,
|
| 17 |
-
"rstrip": false,
|
| 18 |
-
"single_word": false
|
| 19 |
-
},
|
| 20 |
-
"do_lower_case": false,
|
| 21 |
-
"eos_token": {
|
| 22 |
-
"__type": "AddedToken",
|
| 23 |
-
"content": "</s>",
|
| 24 |
-
"lstrip": false,
|
| 25 |
-
"normalized": true,
|
| 26 |
-
"rstrip": false,
|
| 27 |
-
"single_word": false
|
| 28 |
-
},
|
| 29 |
-
"errors": "replace",
|
| 30 |
-
"full_tokenizer_file": null,
|
| 31 |
-
"mask_token": {
|
| 32 |
-
"__type": "AddedToken",
|
| 33 |
-
"content": "<mask>",
|
| 34 |
-
"lstrip": true,
|
| 35 |
-
"normalized": true,
|
| 36 |
-
"rstrip": false,
|
| 37 |
-
"single_word": false
|
| 38 |
-
},
|
| 39 |
-
"model_max_length": 512,
|
| 40 |
-
"pad_token": {
|
| 41 |
-
"__type": "AddedToken",
|
| 42 |
-
"content": "<pad>",
|
| 43 |
-
"lstrip": false,
|
| 44 |
-
"normalized": true,
|
| 45 |
-
"rstrip": false,
|
| 46 |
-
"single_word": false
|
| 47 |
-
},
|
| 48 |
-
"sep_token": {
|
| 49 |
-
"__type": "AddedToken",
|
| 50 |
-
"content": "</s>",
|
| 51 |
-
"lstrip": false,
|
| 52 |
-
"normalized": true,
|
| 53 |
-
"rstrip": false,
|
| 54 |
-
"single_word": false
|
| 55 |
-
},
|
| 56 |
-
"tokenizer_class": "RobertaTokenizer",
|
| 57 |
-
"trim_offsets": true,
|
| 58 |
-
"unk_token": {
|
| 59 |
-
"__type": "AddedToken",
|
| 60 |
-
"content": "<unk>",
|
| 61 |
-
"lstrip": false,
|
| 62 |
-
"normalized": true,
|
| 63 |
-
"rstrip": false,
|
| 64 |
-
"single_word": false
|
| 65 |
-
}
|
| 66 |
-
}
|
|
|
|
| 1 |
+
{"do_lower_case": false, "model_max_length": 512, "full_tokenizer_file": null}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|