Update README.md
Browse files
README.md
CHANGED
|
@@ -11,7 +11,8 @@ license: cc-by-nc-sa-4.0
|
|
| 11 |
- Trained on additional tokens
|
| 12 |
- Improved mix of subject matter model was trained on
|
| 13 |
- Trained for 1.5M additional tokens
|
| 14 |
-
|
|
|
|
| 15 |
# Model Rationale
|
| 16 |
|
| 17 |
Llama 3 is a strong base model with strong world understanding and creativity. Additional instruct finetuning trades that world understanding and creativity for instruction following that Llama doesn't require in order to adhere to most forms of roleplay.
|
|
|
|
| 11 |
- Trained on additional tokens
|
| 12 |
- Improved mix of subject matter model was trained on
|
| 13 |
- Trained for 1.5M additional tokens
|
| 14 |
+
- Additional training on DPO dataset
|
| 15 |
+
|
| 16 |
# Model Rationale
|
| 17 |
|
| 18 |
Llama 3 is a strong base model with strong world understanding and creativity. Additional instruct finetuning trades that world understanding and creativity for instruction following that Llama doesn't require in order to adhere to most forms of roleplay.
|