Commit
•
ba1b016
1
Parent(s):
452ff6e
Update README.md
Browse files
README.md
CHANGED
|
@@ -39,6 +39,25 @@ These models CAN and WILL produce X rated or harmful content, due to being heavi
|
|
| 39 |
|
| 40 |
This Model has a Very good knowledge base and understands anatomy decently, Plus this Model is VERY versitle and is great for General assistant work, RP and ERP, RPG RPs and much more.
|
| 41 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
### Merge Method
|
| 43 |
|
| 44 |
This model was merged using the [ties](https://arxiv.org/abs/2306.01708) merge method using [TheBloke/Llama-2-13B-fp16](https://huggingface.co/TheBloke/Llama-2-13B-fp16) as a base.
|
|
|
|
| 39 |
|
| 40 |
This Model has a Very good knowledge base and understands anatomy decently, Plus this Model is VERY versitle and is great for General assistant work, RP and ERP, RPG RPs and much more.
|
| 41 |
|
| 42 |
+
## Model Use:
|
| 43 |
+
|
| 44 |
+
This model is very good... WITH THE RIGHT SETTINGS.
|
| 45 |
+
I personally use microstat mixed with dynamic temp with epsion cut off and eta cut off.
|
| 46 |
+
```
|
| 47 |
+
Optimal Settings (so far)
|
| 48 |
+
|
| 49 |
+
Microstat Mode: 2
|
| 50 |
+
tau: 2.95
|
| 51 |
+
eta: 0.05
|
| 52 |
+
|
| 53 |
+
Dynamic Temp
|
| 54 |
+
min: 0.25
|
| 55 |
+
max: 1.8
|
| 56 |
+
|
| 57 |
+
Cut offs
|
| 58 |
+
epsilon: 3
|
| 59 |
+
eta: 3
|
| 60 |
+
```
|
| 61 |
### Merge Method
|
| 62 |
|
| 63 |
This model was merged using the [ties](https://arxiv.org/abs/2306.01708) merge method using [TheBloke/Llama-2-13B-fp16](https://huggingface.co/TheBloke/Llama-2-13B-fp16) as a base.
|