add tokenizer
Browse files- special_tokens_map.json +1 -0
- spiece.model +3 -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": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eedf777f037d8bc9ca0115cca50c7d18569292613c3a23a861fc5a6eff89b961
|
| 3 |
+
size 321482
|
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"}, "sp_model_kwargs": {}, "model_max_length": 256, "special_tokens_map_file": "/root/.cache/huggingface/transformers/e0f085d5ba6003dd56d84de7485216c332f557b7c0eb99b00ebeddbf6e91c106.15ed5b79b197b4fcc5f3f80b2ee89a5a3ad708dbd076575cd22cffd9e1a56284", "name_or_path": "hf-internal-testing/tiny-albert", "tokenizer_class": "AlbertTokenizer"}
|