Update README.md
Browse files
README.md
CHANGED
|
@@ -32,7 +32,7 @@ The base model has 8k context, and the qLoRA fine-tuning was with 8k sequence le
|
|
| 32 |
|
| 33 |
It took 2.5 days on 8xH100 node provided by Crusoe Cloud
|
| 34 |
|
| 35 |
-
This model
|
| 36 |
|
| 37 |
example:
|
| 38 |
|
|
|
|
| 32 |
|
| 33 |
It took 2.5 days on 8xH100 node provided by Crusoe Cloud
|
| 34 |
|
| 35 |
+
This model uses ChatML prompt template format.
|
| 36 |
|
| 37 |
example:
|
| 38 |
|