Commit
•
7559a1a
1
Parent(s):
432f01e
Update README.md
Browse files
README.md
CHANGED
|
@@ -18,6 +18,13 @@ inference: false
|
|
| 18 |
# Llama.cpp version: b2343
|
| 19 |
---
|
| 20 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
## GGUF-Imatrix quantizations for [ChaoticNeutrals/Eris_Remix_7B](https://huggingface.co/ChaoticNeutrals/Eris_Remix_7B/).
|
| 22 |
|
| 23 |
All credits belong to the author.
|
|
|
|
| 18 |
# Llama.cpp version: b2343
|
| 19 |
---
|
| 20 |
|
| 21 |
+
```python
|
| 22 |
+
quantization_options = [
|
| 23 |
+
"Q4_K_M", "Q4_K_S", "IQ4_NL", "IQ4_XS", "Q5_K_M",
|
| 24 |
+
"Q5_K_S", "Q6_K", "Q8_0", "IQ3_M", "IQ3_S", "IQ3_XS", "IQ3_XXS"
|
| 25 |
+
]
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
## GGUF-Imatrix quantizations for [ChaoticNeutrals/Eris_Remix_7B](https://huggingface.co/ChaoticNeutrals/Eris_Remix_7B/).
|
| 29 |
|
| 30 |
All credits belong to the author.
|