Update README.md
Browse files
README.md
CHANGED
|
@@ -67,7 +67,7 @@ The dataset was generated by crawling the https://quantum-journal.org/ site, and
|
|
| 67 |
|
| 68 |
### Training Procedure
|
| 69 |
|
| 70 |
-
Various training procedures were explored alongside multiple models.
|
| 71 |
|
| 72 |
Over time, several models and fine-tuning approaches were tested as the base model. The best performance was achieved with [Llama 3.1 70B Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct) and qLoRA, but the training duration was extensive, and optimizing hyperparameters proved to be highly challenging.
|
| 73 |
|
|
|
|
| 67 |
|
| 68 |
### Training Procedure
|
| 69 |
|
| 70 |
+
Various training procedures were explored alongside multiple models, however, all of them were parameter efficient.
|
| 71 |
|
| 72 |
Over time, several models and fine-tuning approaches were tested as the base model. The best performance was achieved with [Llama 3.1 70B Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct) and qLoRA, but the training duration was extensive, and optimizing hyperparameters proved to be highly challenging.
|
| 73 |
|