Update README.md
Browse files
README.md
CHANGED
|
@@ -1,21 +1,13 @@
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
-
|
| 4 |
-
|
| 5 |
license: apache-2.0
|
| 6 |
library_name: tokenizers
|
| 7 |
-
datasets:
|
| 8 |
-
- AdaMLLab/AraMix
|
| 9 |
-
- HuggingFaceFW/fineweb-2
|
| 10 |
-
- HuggingFaceFW/fineweb
|
| 11 |
tags:
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
- bpe
|
| 16 |
-
- byte-level
|
| 17 |
-
- multilingual
|
| 18 |
-
- saudi-arabia
|
| 19 |
---
|
| 20 |
|
| 21 |
# SamAI-Tokenizer
|
|
@@ -234,4 +226,4 @@ source-corpus or benchmark documents are redistributed here.
|
|
| 234 |
version = {1.0.0},
|
| 235 |
url = {https://huggingface.co/Samai-sa/SamAI-Tokenizer}
|
| 236 |
}
|
| 237 |
-
```
|
|
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
+
- ar
|
| 4 |
+
- en
|
| 5 |
license: apache-2.0
|
| 6 |
library_name: tokenizers
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
tags:
|
| 8 |
+
- tokenizer
|
| 9 |
+
- arabic
|
| 10 |
+
- arabic-nlp
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
# SamAI-Tokenizer
|
|
|
|
| 226 |
version = {1.0.0},
|
| 227 |
url = {https://huggingface.co/Samai-sa/SamAI-Tokenizer}
|
| 228 |
}
|
| 229 |
+
```
|