Update README.md
Browse files
README.md
CHANGED
|
@@ -24,6 +24,13 @@ using [NurtureAI/Meta-Llama-3-8B-Instruct-32k](https://huggingface.co/NurtureAI/
|
|
| 24 |
> UPDATE:
|
| 25 |
> Changed the merging method from **model_stock** to **ties** and made Stheno have the most weight and density.
|
| 26 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
### Configuration
|
| 28 |
```yaml
|
| 29 |
models:
|
|
|
|
| 24 |
> UPDATE:
|
| 25 |
> Changed the merging method from **model_stock** to **ties** and made Stheno have the most weight and density.
|
| 26 |
|
| 27 |
+
***
|
| 28 |
+
### GGUF
|
| 29 |
+
Static:
|
| 30 |
+
[mradermacher](https://huggingface.co/mradermacher): [L3-Inca-8B-v0.8-GGUF](https://huggingface.co/mradermacher/L3-Inca-8B-v0.8-GGUF)
|
| 31 |
+
Imatrix:
|
| 32 |
+
[mradermacher](https://huggingface.co/mradermacher): [L3-Inca-8B-v0.8-i1-GGUF](https://huggingface.co/mradermacher/L3-Inca-8B-v0.8-i1-GGUF)
|
| 33 |
+
|
| 34 |
### Configuration
|
| 35 |
```yaml
|
| 36 |
models:
|