Update README.md
Browse files
README.md
CHANGED
|
@@ -45,6 +45,12 @@ Significant improvements over the base model on QED evaluation metrics:
|
|
| 45 |
|
| 46 |
*Results based on 0.5 F1 overlap threshold, non-strict matching*
|
| 47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
## Usage
|
| 49 |
|
| 50 |
The model expects input in a specific format and outputs structured JSON:
|
|
|
|
| 45 |
|
| 46 |
*Results based on 0.5 F1 overlap threshold, non-strict matching*
|
| 47 |
|
| 48 |
+
## Training Code & Methodology
|
| 49 |
+
|
| 50 |
+
This model was trained using our comprehensive QED fine-tuning framework available on GitHub:
|
| 51 |
+
|
| 52 |
+
**🔗 [QED Fine-Tuning Framework](https://github.com/denisrize/QED-LLM-ExplanationGeneration/tree/main)**
|
| 53 |
+
|
| 54 |
## Usage
|
| 55 |
|
| 56 |
The model expects input in a specific format and outputs structured JSON:
|