Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Sindhi-BERT-base
|
| 2 |
|
| 3 |
The first BERT-style language model trained **from scratch** on Sindhi text, using a custom Sindhi BPE tokenizer with 32,000 pure Sindhi tokens.
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- sd
|
| 4 |
+
license: mit
|
| 5 |
+
tags:
|
| 6 |
+
- sindhi
|
| 7 |
+
- bert
|
| 8 |
+
- masked-language-modeling
|
| 9 |
+
- from-scratch
|
| 10 |
+
- nlp
|
| 11 |
+
model-index:
|
| 12 |
+
- name: sindhi-bert-base
|
| 13 |
+
results:
|
| 14 |
+
- task:
|
| 15 |
+
type: fill-mask
|
| 16 |
+
name: Masked Language Modeling
|
| 17 |
+
metrics:
|
| 18 |
+
- type: perplexity
|
| 19 |
+
value: 28.46
|
| 20 |
+
name: Perplexity (Session 3)
|
| 21 |
+
---
|
| 22 |
+
|
| 23 |
# Sindhi-BERT-base
|
| 24 |
|
| 25 |
The first BERT-style language model trained **from scratch** on Sindhi text, using a custom Sindhi BPE tokenizer with 32,000 pure Sindhi tokens.
|