Upload tokenizer
Browse files- merges.txt +0 -0
- special_tokens_map.json +13 -5
- tokenizer.json +0 -0
- tokenizer_config.json +11 -9
- vocab.json +0 -0
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
CHANGED
|
@@ -1,7 +1,15 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,13 +1,15 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"clean_up_tokenization_spaces": true,
|
| 3 |
-
"cls_token": "
|
| 4 |
-
"
|
| 5 |
-
"
|
|
|
|
| 6 |
"model_max_length": 512,
|
| 7 |
-
"pad_token": "
|
| 8 |
-
"sep_token": "
|
| 9 |
-
"
|
| 10 |
-
"
|
| 11 |
-
"
|
| 12 |
-
"unk_token": "[UNK]"
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"cls_token": "<s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"mask_token": "<mask>",
|
| 9 |
"model_max_length": 512,
|
| 10 |
+
"pad_token": "<pad>",
|
| 11 |
+
"sep_token": "</s>",
|
| 12 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 13 |
+
"trim_offsets": true,
|
| 14 |
+
"unk_token": "<unk>"
|
|
|
|
| 15 |
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|