Update README.md
Browse files
README.md
CHANGED
|
@@ -23,7 +23,7 @@ Colibri_8b_v0.1 is a conversational model for cybersecurity fine-tuned from the
|
|
| 23 |
|
| 24 |
We derived our training dataset by creating Q/A pairs from a huge amount of cybersecurity related texts.
|
| 25 |
|
| 26 |
-
> v0.1 trained using around
|
| 27 |
|
| 28 |
This model is using ChatML prompt template format.
|
| 29 |
|
|
|
|
| 23 |
|
| 24 |
We derived our training dataset by creating Q/A pairs from a huge amount of cybersecurity related texts.
|
| 25 |
|
| 26 |
+
> v0.1 trained for 3 epochs using around 35k Q/A pairs FFT on all parameters using a single A100 80gb for 3 hours.
|
| 27 |
|
| 28 |
This model is using ChatML prompt template format.
|
| 29 |
|