Upload tokenizer
Browse files- special_tokens_map.json +1 -1
- tokenizer_config.json +2 -3
special_tokens_map.json
CHANGED
|
@@ -14,7 +14,7 @@
|
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"mask_token": {
|
| 17 |
-
"content": "<
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
|
|
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"mask_token": {
|
| 17 |
+
"content": "<mask>",
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"0": {
|
| 5 |
"content": "<s>",
|
|
@@ -3005,9 +3004,9 @@
|
|
| 3005 |
"bos_token": "</s>",
|
| 3006 |
"clean_up_tokenization_spaces": true,
|
| 3007 |
"eos_token": "</s>",
|
| 3008 |
-
"mask_token": "<
|
| 3009 |
"model_max_length": 1000000000000000019884624838656,
|
| 3010 |
"pad_token": "<pad>",
|
| 3011 |
-
"tokenizer_class": "
|
| 3012 |
"unk_token": "<unk>"
|
| 3013 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
"content": "<s>",
|
|
|
|
| 3004 |
"bos_token": "</s>",
|
| 3005 |
"clean_up_tokenization_spaces": true,
|
| 3006 |
"eos_token": "</s>",
|
| 3007 |
+
"mask_token": "<mask>",
|
| 3008 |
"model_max_length": 1000000000000000019884624838656,
|
| 3009 |
"pad_token": "<pad>",
|
| 3010 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 3011 |
"unk_token": "<unk>"
|
| 3012 |
}
|