KoichiYasuoka
commited on
Commit
•
2618a53
1
Parent(s):
1a96437
initial release
Browse files
README.md
CHANGED
@@ -1,3 +1,26 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- "th"
|
4 |
+
tags:
|
5 |
+
- "thai"
|
6 |
+
- "masked-lm"
|
7 |
+
- "wikipedia"
|
8 |
+
license: "apache-2.0"
|
9 |
+
pipeline_tag: "fill-mask"
|
10 |
+
mask_token: "<mask>"
|
11 |
+
---
|
12 |
+
|
13 |
+
# roberta-base-thai-char
|
14 |
+
|
15 |
+
## Model Description
|
16 |
+
|
17 |
+
This is a RoBERTa model pre-trained on Thai Wikipedia texts with character-wise embeddings to use BertTokenizerFast. You can fine-tune `roberta-base-thai-char` for downstream tasks, such as [POS-tagging](https://huggingface.co/KoichiYasuoka/roberta-base-thai-char-upos), dependency-parsing, and so on.
|
18 |
+
|
19 |
+
## How to Use
|
20 |
+
|
21 |
+
```py
|
22 |
+
from transformers import AutoTokenizer,AutoModelForMaskedLM
|
23 |
+
tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/roberta-base-thai-char")
|
24 |
+
model=AutoModelForMaskedLM.from_pretrained("KoichiYasuoka/roberta-base-thai-char")
|
25 |
+
```
|
26 |
+
|