Delete tokenizer
Browse files- tokenizer/merges.txt +0 -0
- tokenizer/special_tokens_map.json +0 -15
- tokenizer/tokenizer.json +0 -0
- tokenizer/tokenizer_config.json +0 -20
- tokenizer/vocab.json +0 -0
tokenizer/merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer/special_tokens_map.json
DELETED
|
@@ -1,15 +0,0 @@
|
|
| 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/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer/tokenizer_config.json
DELETED
|
@@ -1,20 +0,0 @@
|
|
| 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 |
-
"max_length": null,
|
| 10 |
-
"model_max_length": 512,
|
| 11 |
-
"pad_to_multiple_of": null,
|
| 12 |
-
"pad_token": "<pad>",
|
| 13 |
-
"pad_token_type_id": 0,
|
| 14 |
-
"padding_side": "right",
|
| 15 |
-
"processor_class": "ClapProcessor",
|
| 16 |
-
"sep_token": "</s>",
|
| 17 |
-
"tokenizer_class": "RobertaTokenizer",
|
| 18 |
-
"trim_offsets": true,
|
| 19 |
-
"unk_token": "<unk>"
|
| 20 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|