Update README.md
Browse files
README.md
CHANGED
|
@@ -114,6 +114,9 @@ Standard text preprocessing and tokenization methods were applied.
|
|
| 114 |
- **Optimizer:** AdamW
|
| 115 |
- Details on learning rate, batch size, epochs/steps are not provided for this base model release.
|
| 116 |
|
|
|
|
|
|
|
|
|
|
| 117 |
## Evaluation
|
| 118 |
|
| 119 |
Initial evaluations were conducted on internal validation splits derived from the training data. Due to the limited size of the initial data and the potential for overfitting, these results should be considered preliminary. **The definitive performance characteristics of this architecture are best assessed after fine-tuning with a suitable dataset.**
|
|
|
|
| 114 |
- **Optimizer:** AdamW
|
| 115 |
- Details on learning rate, batch size, epochs/steps are not provided for this base model release.
|
| 116 |
|
| 117 |
+
## Developed by
|
| 118 |
+
- **Abhinav TJ** - Founder,CEO
|
| 119 |
+
|
| 120 |
## Evaluation
|
| 121 |
|
| 122 |
Initial evaluations were conducted on internal validation splits derived from the training data. Due to the limited size of the initial data and the potential for overfitting, these results should be considered preliminary. **The definitive performance characteristics of this architecture are best assessed after fine-tuning with a suitable dataset.**
|