Commit
•
87274fe
1
Parent(s):
eecfd03
Upload tokenizer
Browse files- README.md +4 -5
- special_tokens_map.json +1 -15
- tokenizer.json +0 -0
- tokenizer_config.json +3 -18
README.md
CHANGED
|
@@ -1,13 +1,12 @@
|
|
| 1 |
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
datasets:
|
| 4 |
- hieunguyen1053/binhvq-news-corpus
|
| 5 |
language:
|
| 6 |
- vi
|
| 7 |
library_name: transformers
|
|
|
|
| 8 |
pipeline_tag: fill-mask
|
| 9 |
-
|
| 10 |
widget:
|
| 11 |
-
- text:
|
| 12 |
-
example_title:
|
| 13 |
-
---
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
datasets:
|
| 3 |
- hieunguyen1053/binhvq-news-corpus
|
| 4 |
language:
|
| 5 |
- vi
|
| 6 |
library_name: transformers
|
| 7 |
+
license: apache-2.0
|
| 8 |
pipeline_tag: fill-mask
|
|
|
|
| 9 |
widget:
|
| 10 |
+
- text: tôi là <mask> viên trường đại học tôn đức thắng
|
| 11 |
+
example_title: Example 1
|
| 12 |
+
---
|
special_tokens_map.json
CHANGED
|
@@ -1,15 +1 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token": "<s>",
|
| 3 |
-
"cls_token": "<s>",
|
| 4 |
-
"eos_token": "</s>",
|
| 5 |
-
"mask_token": {
|
| 6 |
-
"content": "<mask>",
|
| 7 |
-
"lstrip": true,
|
| 8 |
-
"normalized": true,
|
| 9 |
-
"rstrip": false,
|
| 10 |
-
"single_word": false
|
| 11 |
-
},
|
| 12 |
-
"pad_token": "<pad>",
|
| 13 |
-
"sep_token": "</s>",
|
| 14 |
-
"unk_token": "<unk>"
|
| 15 |
-
}
|
|
|
|
| 1 |
+
{}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,21 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"eos_token": "</s>",
|
| 5 |
-
"mask_token": {
|
| 6 |
-
"__type": "AddedToken",
|
| 7 |
-
"content": "<mask>",
|
| 8 |
-
"lstrip": true,
|
| 9 |
-
"normalized": true,
|
| 10 |
-
"rstrip": false,
|
| 11 |
-
"single_word": false
|
| 12 |
-
},
|
| 13 |
"model_max_length": 1000000000000000019884624838656,
|
| 14 |
-
"
|
| 15 |
-
"pad_token": "<pad>",
|
| 16 |
-
"sep_token": "</s>",
|
| 17 |
-
"sp_model_kwargs": {},
|
| 18 |
-
"special_tokens_map_file": null,
|
| 19 |
-
"tokenizer_class": "BartphoTokenizer",
|
| 20 |
-
"unk_token": "<unk>"
|
| 21 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"added_tokens_decoder": {},
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"model_max_length": 1000000000000000019884624838656,
|
| 5 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
}
|