Commit
•
b2dbbb4
1
Parent(s):
d80480a
Update README.md
Browse files
README.md
CHANGED
|
@@ -31,6 +31,9 @@ DPO Trained on the Neural-DPO dataset.
|
|
| 31 |
Trained on the Neural-DPO
|
| 32 |
This model excels at character roleplay, also with the ability of responding accurately to a wide variety of complex questions.
|
| 33 |
|
|
|
|
|
|
|
|
|
|
| 34 |
```yaml
|
| 35 |
base_model: mistralai/Mistral-7B-v0.1
|
| 36 |
model_type: AutoModelForCausalLM
|
|
|
|
| 31 |
Trained on the Neural-DPO
|
| 32 |
This model excels at character roleplay, also with the ability of responding accurately to a wide variety of complex questions.
|
| 33 |
|
| 34 |
+
|
| 35 |
+
## Training Params
|
| 36 |
+
|
| 37 |
```yaml
|
| 38 |
base_model: mistralai/Mistral-7B-v0.1
|
| 39 |
model_type: AutoModelForCausalLM
|