Upload tokenizer
Browse files- tokenizer.json +1 -0
- tokenizer_config.json +1 -0
tokenizer.json
CHANGED
|
@@ -128,6 +128,7 @@
|
|
| 128 |
"continuing_subword_prefix": null,
|
| 129 |
"end_of_word_suffix": "</w>",
|
| 130 |
"fuse_unk": false,
|
|
|
|
| 131 |
"vocab": {
|
| 132 |
"<s>": 0,
|
| 133 |
"<pad>": 1,
|
|
|
|
| 128 |
"continuing_subword_prefix": null,
|
| 129 |
"end_of_word_suffix": "</w>",
|
| 130 |
"fuse_unk": false,
|
| 131 |
+
"byte_fallback": false,
|
| 132 |
"vocab": {
|
| 133 |
"<s>": 0,
|
| 134 |
"<pad>": 1,
|
tokenizer_config.json
CHANGED
|
@@ -5,5 +5,6 @@
|
|
| 5 |
"mask_token": "<mask>",
|
| 6 |
"model_max_length": 512,
|
| 7 |
"pad_token": "<pad>",
|
|
|
|
| 8 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 9 |
}
|
|
|
|
| 5 |
"mask_token": "<mask>",
|
| 6 |
"model_max_length": 512,
|
| 7 |
"pad_token": "<pad>",
|
| 8 |
+
"special_tokens_map_file": "data/converted_model_mlm_huggingface/special_tokens_map.json",
|
| 9 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 10 |
}
|