Update README.md
Browse files
README.md
CHANGED
@@ -28,4 +28,11 @@ Invalid output length: 7, Testing length: 1319 , **Accuracy: 0.580**
|
|
28 |
## Comparison
|
29 |
The official report **accuracy is 0.665** by fine-tuning the whole LLaMA 2 7B model for 3 epochs.
|
30 |
|
31 |
-
**Note**: The LoRA adapter is being used for future research purposes.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
## Comparison
|
29 |
The official report **accuracy is 0.665** by fine-tuning the whole LLaMA 2 7B model for 3 epochs.
|
30 |
|
31 |
+
**Note**: The LoRA adapter is being used for future research purposes.
|
32 |
+
|
33 |
+
# 🚀 Adapter Usage
|
34 |
+
```python
|
35 |
+
# Load the Pre-trained LoRA Adapter
|
36 |
+
model.load_adapter("shuyuej/metamath_lora_qkv_llama2_7b")
|
37 |
+
model.enable_adapters()
|
38 |
+
```
|