Update README.md
Browse files
README.md
CHANGED
@@ -26,7 +26,7 @@ I modified the dataset for uncensoring, deduping, cleaning, and quality.
|
|
26 |
I added Jon Durbin's excellent Airoboros dataset to increase creativity.
|
27 |
|
28 |
## Training
|
29 |
-
It took
|
30 |
|
31 |
Prompt format:
|
32 |
This model (and all my future releases) use [ChatML](https://github.com/openai/openai-python/blob/main/chatml.md) prompt format.
|
|
|
26 |
I added Jon Durbin's excellent Airoboros dataset to increase creativity.
|
27 |
|
28 |
## Training
|
29 |
+
It took 4 days to train 3 epochs on 4x A100s.
|
30 |
|
31 |
Prompt format:
|
32 |
This model (and all my future releases) use [ChatML](https://github.com/openai/openai-python/blob/main/chatml.md) prompt format.
|