Update README.md
Browse files
README.md
CHANGED
|
@@ -32,7 +32,6 @@ Cat1.0 is a fine-tuned version of **Llama-3-1-8b base model**, optimized for rol
|
|
| 32 |
|
| 33 |
To achieve optimal performance with this model, I recommend the following settings:
|
| 34 |
|
| 35 |
-
- **Minimum Probability (`min_p`)**: `0.05`
|
| 36 |
- **Temperature**: `1.1` or higher
|
| 37 |
|
| 38 |
> **Note**: Due to the nature of the fine-tuning, setting the temperature to `1.1` or higher helps prevent the model from repeating itself and encourages more creative and coherent responses.
|
|
@@ -78,23 +77,22 @@ Natalie: Good, how are things going with you, Ryan?
|
|
| 78 |
Ryan: Great, I'm just doing just great.
|
| 79 |
```
|
| 80 |
|
| 81 |
-
### Text Generation Example
|
| 82 |
-
|
| 83 |
-
|
| 84 |
-
|
| 85 |
## Model Capabilities
|
| 86 |
|
| 87 |
Below are some examples showcasing the model's performance in various roleplay scenarios:
|
| 88 |
|
| 89 |
### Roleplay Examples
|
| 90 |
|
| 91 |
-
|
| 92 |
|
| 93 |
|
| 94 |
-
|
| 97 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 98 |
## Limitations and Tips
|
| 99 |
|
| 100 |
While this model excels in chat and roleplaying scenarios, it isn't perfect. If you notice the model repeating itself or providing less coherent responses:
|
|
|
|
| 32 |
|
| 33 |
To achieve optimal performance with this model, I recommend the following settings:
|
| 34 |
|
|
|
|
| 35 |
- **Temperature**: `1.1` or higher
|
| 36 |
|
| 37 |
> **Note**: Due to the nature of the fine-tuning, setting the temperature to `1.1` or higher helps prevent the model from repeating itself and encourages more creative and coherent responses.
|
|
|
|
| 77 |
Ryan: Great, I'm just doing just great.
|
| 78 |
```
|
| 79 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
## Model Capabilities
|
| 81 |
|
| 82 |
Below are some examples showcasing the model's performance in various roleplay scenarios:
|
| 83 |
|
| 84 |
### Roleplay Examples
|
| 85 |
|
|
|
|
| 86 |
|
| 87 |
|
| 88 |
+
|
| 89 |
|
| 90 |
|
| 91 |
|
| 92 |
+
### Text Generation Example
|
| 93 |
+
|
| 94 |
+
|
| 95 |
+
|
| 96 |
## Limitations and Tips
|
| 97 |
|
| 98 |
While this model excels in chat and roleplaying scenarios, it isn't perfect. If you notice the model repeating itself or providing less coherent responses:
|