Update README.md
Browse files
README.md
CHANGED
|
@@ -15,7 +15,7 @@ library_name: transformers
|
|
| 15 |
|
| 16 |
<p align="center">
|
| 17 |
<br>
|
| 18 |
-
<span style="font-size: 60px; font-weight: bold;">Mi:dm 2.0
|
| 19 |
</br>
|
| 20 |
</p>
|
| 21 |
|
|
@@ -62,11 +62,11 @@ library_name: transformers
|
|
| 62 |
|
| 63 |
Mi:dm 2.0 is released in two versions:
|
| 64 |
|
| 65 |
-
- **Mi:dm 2.0
|
| 66 |
An 11.5B parameter dense model designed to balance model size and performance.
|
| 67 |
It extends an 8B-scale model by applying the Depth-up Scaling (DuS) method, making it suitable for real-world applications that require both performance and versatility.
|
| 68 |
|
| 69 |
-
- **Mi:dm 2.0
|
| 70 |
A lightweight 2.3B parameter dense model optimized for on-device environments and systems with limited GPU resources.
|
| 71 |
It was derived from the Base model through pruning and distillation to enable compact deployment.
|
| 72 |
|
|
|
|
| 15 |
|
| 16 |
<p align="center">
|
| 17 |
<br>
|
| 18 |
+
<span style="font-size: 60px; font-weight: bold;">Mi:dm 2.0 Base</span>
|
| 19 |
</br>
|
| 20 |
</p>
|
| 21 |
|
|
|
|
| 62 |
|
| 63 |
Mi:dm 2.0 is released in two versions:
|
| 64 |
|
| 65 |
+
- **Mi:dm 2.0 Base**
|
| 66 |
An 11.5B parameter dense model designed to balance model size and performance.
|
| 67 |
It extends an 8B-scale model by applying the Depth-up Scaling (DuS) method, making it suitable for real-world applications that require both performance and versatility.
|
| 68 |
|
| 69 |
+
- **Mi:dm 2.0 Mini**
|
| 70 |
A lightweight 2.3B parameter dense model optimized for on-device environments and systems with limited GPU resources.
|
| 71 |
It was derived from the Base model through pruning and distillation to enable compact deployment.
|
| 72 |
|