Commit
•
92a4e96
1
Parent(s):
f8c585f
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- bo
|
| 5 |
+
tags:
|
| 6 |
+
- tibetan,tokenization,sentencepiece
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
# marpa-tokenizer
|
| 10 |
+
|
| 11 |
+
> A LlamaTokenizer with support to tokenize Tibetan text.
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
Example:
|
| 15 |
+
|
| 16 |
+
```sh
|
| 17 |
+
['▁རྒྱལ་ཡོངས་', '▁ཀྱི་', '▁དོ་ཁུར་', '▁དང་', '▁འཛམ་གླིང་', '▁ཡོངས་', '▁ཀྱི་', '▁དོ་སྣང་', '▁ཁྲོད', '▁།']
|
| 18 |
+
['▁我们', '认为', '下面', '这些', '真理', '是不', '言', '而', '喻', '的']
|
| 19 |
+
```
|