add tokenizer
Browse files- added_tokens.json +1 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"[QRY]": 30920, "[SAL]": 30922, "[CLF]": 30919, "[RGN]": 30921}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "additional_special_tokens": ["[CLF]", "[QRY]", "[RGN]", "[SAL]"]}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "special_tokens_map.json", "name_or_path": "../../phantasm/phantasm_new/lightning_logs/full_run/scincl_ctrl/checkpoints//tokenizer", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|