Update README.md
Browse files
README.md
CHANGED
|
@@ -41,7 +41,6 @@ The model underwent a fine-tuning process utilizing a combination of QLoRA and P
|
|
| 41 |
- **Additional Settings:**
|
| 42 |
- Gradient checkpointing and a maximum gradient norm of 0.3
|
| 43 |
- Sequences grouped by length for training efficiency
|
| 44 |
-
- Batch size, maximum input, and target length optimized for each specific task and model
|
| 45 |
- PEFT adapters merged into the baseline models for enhanced performance
|
| 46 |
|
| 47 |
## Evaluation Results
|
|
|
|
| 41 |
- **Additional Settings:**
|
| 42 |
- Gradient checkpointing and a maximum gradient norm of 0.3
|
| 43 |
- Sequences grouped by length for training efficiency
|
|
|
|
| 44 |
- PEFT adapters merged into the baseline models for enhanced performance
|
| 45 |
|
| 46 |
## Evaluation Results
|