Update README.md
Browse files
README.md
CHANGED
|
@@ -23,6 +23,18 @@ using [NurtureAI/Meta-Llama-3-8B-Instruct-32k](https://huggingface.co/NurtureAI/
|
|
| 23 |
- Strong at instruction following.
|
| 24 |
- Supports ChatML and Llama-3 Context Templates.
|
| 25 |
***
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
### GGUF
|
| 27 |
|
| 28 |
[mradermacher](https://huggingface.co/mradermacher): [L3-Inca-8B-v0.5-GGUF](https://huggingface.co/mradermacher/L3-Inca-8B-v0.5-GGUF)
|
|
|
|
| 23 |
- Strong at instruction following.
|
| 24 |
- Supports ChatML and Llama-3 Context Templates.
|
| 25 |
***
|
| 26 |
+
Recommend Preset Settings:
|
| 27 |
+
```
|
| 28 |
+
Temperature: 1.17
|
| 29 |
+
Top K: 40
|
| 30 |
+
Top P: 0.95
|
| 31 |
+
Min P: 0.075
|
| 32 |
+
Rep Pen: 1.05
|
| 33 |
+
Rep Pen Range: 2048
|
| 34 |
+
Frequency Pen: 0.50
|
| 35 |
+
Presence Pen: 0.15
|
| 36 |
+
```
|
| 37 |
+
***
|
| 38 |
### GGUF
|
| 39 |
|
| 40 |
[mradermacher](https://huggingface.co/mradermacher): [L3-Inca-8B-v0.5-GGUF](https://huggingface.co/mradermacher/L3-Inca-8B-v0.5-GGUF)
|