Update README.md
Browse files
README.md
CHANGED
|
@@ -66,7 +66,7 @@ The data was tokenized using the [EleutherAI/gpt-neox-20b](https://huggingface.c
|
|
| 66 |
|
| 67 |
### Fine-Tuning
|
| 68 |
|
| 69 |
-
|
| 70 |
|
| 71 |
## Training Configuration
|
| 72 |
|
|
|
|
| 66 |
|
| 67 |
### Fine-Tuning
|
| 68 |
|
| 69 |
+
We fine tuned this model on the [databricks-dolly-15k dataset](https://github.com/databrickslabs/dolly/tree/master/data) released by Databricks, following the same hyperparameters found in their [train_dolly.py](https://github.com/databrickslabs/dolly/blob/master/train_dolly.py) script.
|
| 70 |
|
| 71 |
## Training Configuration
|
| 72 |
|