Update README.md
Browse files
README.md
CHANGED
|
@@ -5,4 +5,14 @@ base_model: Felladrin/Minueza-32M-Base
|
|
| 5 |
|
| 6 |
GGUF version of [Felladrin/Minueza-32M-Base](https://huggingface.co/Felladrin/Minueza-32M-Base).
|
| 7 |
|
| 8 |
-
It was not possible to quantize the model after converting it to F16/F32 GGUF, so only those versions are available, being F32 the recommended one for having better precision.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
|
| 6 |
GGUF version of [Felladrin/Minueza-32M-Base](https://huggingface.co/Felladrin/Minueza-32M-Base).
|
| 7 |
|
| 8 |
+
It was not possible to quantize the model after converting it to F16/F32 GGUF, so only those versions are available, being F32 the recommended one for having better precision.
|
| 9 |
+
|
| 10 |
+
## Recommended Inference Parameters
|
| 11 |
+
|
| 12 |
+
```
|
| 13 |
+
temp 0.4
|
| 14 |
+
min-p 0.1
|
| 15 |
+
top_p 1
|
| 16 |
+
top_k 0
|
| 17 |
+
repeat_penalty 1.0
|
| 18 |
+
```
|