Update README.md
#1
by
Hailay
- opened
README.md
CHANGED
|
@@ -3,8 +3,17 @@ license: apache-2.0
|
|
| 3 |
language:
|
| 4 |
- ti
|
| 5 |
- am
|
|
|
|
| 6 |
---
|
| 7 |
|Model|Vocabulary Size|
|
| 8 |
|---|---|
|
| 9 |
|XLM-Roberta|250002|
|
| 10 |
-
|EXLMR|280147|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
language:
|
| 4 |
- ti
|
| 5 |
- am
|
| 6 |
+
- ar
|
| 7 |
---
|
| 8 |
|Model|Vocabulary Size|
|
| 9 |
|---|---|
|
| 10 |
|XLM-Roberta|250002|
|
| 11 |
+
|EXLMR|280147|
|
| 12 |
+
|
| 13 |
+
Model Card
|
| 14 |
+
|
| 15 |
+
The EXLMR model is a multilingual transformer that expands the XLM-RoBERTa tokenizer by adding vocabulary for low-resource languages such as Tigrinya and Amharic. It solves issues like out-of-vocabulary words and over-tokenization, enhancing the model's ability to represent languages written in the Ge'ez script. The model can be fine-tuned for various multilingual tasks, including sentiment analysis, question answering, named entity recognition, and paraphrase detection. These improvements make EXLMR highly effective for low-resource languages, while still supporting a broad range of languages with strong overall performance.
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|