Update README.md
Browse files
README.md
CHANGED
|
@@ -46,7 +46,7 @@ I added Jon Durbin's excellent Airoboros dataset to increase creativity.
|
|
| 46 |
I added a curated subset of Samantha (sans identity and relationship stuff) and WizardLM data to train it for multi-turn conversation.
|
| 47 |
|
| 48 |
## Training
|
| 49 |
-
It took
|
| 50 |
|
| 51 |
Prompt format:
|
| 52 |
This model (and all my future releases) use [ChatML](https://github.com/openai/openai-python/blob/main/chatml.md) prompt format.
|
|
|
|
| 46 |
I added a curated subset of Samantha (sans identity and relationship stuff) and WizardLM data to train it for multi-turn conversation.
|
| 47 |
|
| 48 |
## Training
|
| 49 |
+
It took 3 days to train 3 epochs on 4x A100s using qLoRA and Axolotl
|
| 50 |
|
| 51 |
Prompt format:
|
| 52 |
This model (and all my future releases) use [ChatML](https://github.com/openai/openai-python/blob/main/chatml.md) prompt format.
|