add tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"cls_token": "[CLS]", "mask_token": "[MASK]", "model_max_length": 512, "pad_token": "[PAD]", "padding_side": "right", "sep_token": "[SEP]", "truncation_side": "right", "unk_token": "[UNK]", "special_tokens_map_file": "/home/jovyan/.cache/huggingface/transformers/9ca1788577741882be5baba9cf98ecfa7602c7fd73aefcaf473746da083c1ed6.7da70648c6cb9951e284c9685f9ba7ae083dd59ed1d6d84bdfc0584a4ea94b6d", "name_or_path": "Vlasta/DNA_Sentencepiece_vocab_10000_max_tokenlen_45", "tokenizer_class": "PreTrainedTokenizerFast"}
|