Update README.md
Browse files
README.md
CHANGED
|
@@ -18,6 +18,8 @@ Llama-3.1-Centaur-70B is a foundation model of cognition model that can predict
|
|
| 18 |
|
| 19 |
### Usage:
|
| 20 |
|
|
|
|
|
|
|
| 21 |
This is the low-rank adapter which runs with unsloth on a single 80GB GPU.
|
| 22 |
|
| 23 |
```python
|
|
|
|
| 18 |
|
| 19 |
### Usage:
|
| 20 |
|
| 21 |
+
Note that Centaur is trained on a data set in which human choices are encapsuled by "<<" and ">>" tokens. For optimal performance, it is recommended to adjust prompts accordingly.
|
| 22 |
+
|
| 23 |
This is the low-rank adapter which runs with unsloth on a single 80GB GPU.
|
| 24 |
|
| 25 |
```python
|