Commit
·
acb3b68
1
Parent(s):
a866c08
add tokenizer
Browse files- dict.txt +0 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
dict.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e63e0e8f2d912f8ebf14402e66c2afef07b078099b953efb690d18c6c00af23a
|
| 3 |
+
size 1027111
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/Users/hieunguyen/Coding/learning/masked-language-model/huggingmodel/uncased", "tokenizer_class": "BartphoTokenizer"}
|