Commit
•
f8e5bba
1
Parent(s):
cdaf4b4
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 |
+
{"bos_token": "[CLS]", "eos_token": "[SEP]", "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 |
+
{"do_lower_case": true, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "max_len": 512, "special_tokens_map_file": "/root/.cache/huggingface/transformers/ca4f508cee2d258f5dafd36de94f1ceb6c8305e928410fa9365892fa88fa0fde.623993453f3f6b9f6ad831899812f482e5cde100e664124feb3a6446d69a26bf", "name_or_path": "/content/gdrive/MyDrive/Colab_Notebooks/Master_Project/Saved_models/ALBERT", "sp_model_kwargs": {}, "tokenizer_class": "AlbertTokenizer"}
|