Update README.md
Browse files
README.md
CHANGED
@@ -70,7 +70,7 @@ print(response)
|
|
70 |
The MoLA-LM architecture consists of:
|
71 |
|
72 |
1. **Base Model**: Qwen/Qwen3-4B-Thinking-2507
|
73 |
-
2. **Router Network**: Frozen encoder as Sentence transformer + decoder as
|
74 |
3. **LoRA Adapters**: 9 task-specific fine-tuned adapters
|
75 |
4. **Dynamic Switching**: Automatic adapter application based on input
|
76 |
|
|
|
70 |
The MoLA-LM architecture consists of:
|
71 |
|
72 |
1. **Base Model**: Qwen/Qwen3-4B-Thinking-2507
|
73 |
+
2. **Router Network**: Frozen encoder as Sentence transformer + decoder as MLP for adapter selection
|
74 |
3. **LoRA Adapters**: 9 task-specific fine-tuned adapters
|
75 |
4. **Dynamic Switching**: Automatic adapter application based on input
|
76 |
|