Upload README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- he
|
| 4 |
+
- en
|
| 5 |
+
license: apache-2.0
|
| 6 |
+
tags:
|
| 7 |
+
- hebrew
|
| 8 |
+
- dint-transformer
|
| 9 |
+
- differential-attention
|
| 10 |
+
- pretrained
|
| 11 |
+
- text-generation
|
| 12 |
+
- from-scratch
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# Hebrew DINT Transformer
|
| 16 |
+
|
| 17 |
+
The first Hebrew LLM built from scratch using DINT (Differential + Integral) Transformer architecture.
|
| 18 |
+
|
| 19 |
+
Based on arxiv:2501.17486 (DINT) + arxiv:2410.05258 (DIFF Transformer).
|
| 20 |
+
|
| 21 |
+
Trained on HeDC4, Hebrew Wikipedia, Project Ben-Yehuda, and more Hebrew corpora.
|