Update README.md
Browse files
README.md
CHANGED
@@ -13,7 +13,7 @@ library_name: transformers
|
|
13 |
|
14 |
<p align="center">
|
15 |
<br>
|
16 |
-
<span style="font-size: 60px; font-weight: bold;">Mi:dm 2.0
|
17 |
</br>
|
18 |
</p>
|
19 |
<p align="center">
|
@@ -59,11 +59,11 @@ library_name: transformers
|
|
59 |
|
60 |
Mi:dm 2.0 is released in two versions:
|
61 |
|
62 |
-
- **Mi:dm 2.0
|
63 |
An 11.5B parameter dense model designed to balance model size and performance.
|
64 |
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.
|
65 |
|
66 |
-
- **Mi:dm 2.0
|
67 |
A lightweight 2.3B parameter dense model optimized for on-device environments and systems with limited GPU resources.
|
68 |
It was derived from the Base model through pruning and distillation to enable compact deployment.
|
69 |
|
|
|
13 |
|
14 |
<p align="center">
|
15 |
<br>
|
16 |
+
<span style="font-size: 60px; font-weight: bold;">Mi:dm 2.0 Mini</span>
|
17 |
</br>
|
18 |
</p>
|
19 |
<p align="center">
|
|
|
59 |
|
60 |
Mi:dm 2.0 is released in two versions:
|
61 |
|
62 |
+
- **Mi:dm 2.0 Base**
|
63 |
An 11.5B parameter dense model designed to balance model size and performance.
|
64 |
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.
|
65 |
|
66 |
+
- **Mi:dm 2.0 Mini**
|
67 |
A lightweight 2.3B parameter dense model optimized for on-device environments and systems with limited GPU resources.
|
68 |
It was derived from the Base model through pruning and distillation to enable compact deployment.
|
69 |
|