Update README.md
Browse files
README.md
CHANGED
|
@@ -16,6 +16,8 @@ base_model: nvidia/nemotron-3-nano-30b-base
|
|
| 16 |
pipeline_tag: text-generation
|
| 17 |
---
|
| 18 |
|
|
|
|
|
|
|
| 19 |
# 🛡️ HEBATRON: Hebrew-Specialized Mamba2-MoE
|
| 20 |
|
| 21 |
HEBATRON is a state-of-the-art, high-performance language model specialized for the Hebrew language. Developed through a collaboration between **PwC Israel**, **MAFAT**, and **AWS**, it introduces a unique hybrid architecture combining **Mamba2** and **Mixture-of-Experts (MoE)**.
|
|
|
|
| 16 |
pipeline_tag: text-generation
|
| 17 |
---
|
| 18 |
|
| 19 |
+
|
| 20 |
+
|
| 21 |
# 🛡️ HEBATRON: Hebrew-Specialized Mamba2-MoE
|
| 22 |
|
| 23 |
HEBATRON is a state-of-the-art, high-performance language model specialized for the Hebrew language. Developed through a collaboration between **PwC Israel**, **MAFAT**, and **AWS**, it introduces a unique hybrid architecture combining **Mamba2** and **Mixture-of-Experts (MoE)**.
|