add tokenizer
Browse files- added_tokens.json +0 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "/home/daniel/.cache/huggingface/transformers/75be22d7750034989358861e325977feda47740e1c3f8a4dc1cb73570aad843e.2b9a196704f2f183fe3f4b48d6e662dba8203fdcb3346bfa896831378edf6f97", "name_or_path": "bert-large-cased", "tokenizer_class": "BertTokenizer"}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|