Commit
•
ef234f8
1
Parent(s):
16a5ccd
add GGUF (#5)
Browse files- add GGUF (b0fda0538be68eab718816c71c8a0c64aa83f619)
README.md
CHANGED
|
@@ -133,6 +133,9 @@ This model is a fine-tuned version of [NousResearch/Nous-Hermes-2-Mixtral-8x7B-S
|
|
| 133 |
It achieves the following results on the evaluation set:
|
| 134 |
- Loss: 0.4559
|
| 135 |
|
|
|
|
|
|
|
|
|
|
| 136 |
## How to use
|
| 137 |
|
| 138 |
**PEFT**
|
|
|
|
| 133 |
It achieves the following results on the evaluation set:
|
| 134 |
- Loss: 0.4559
|
| 135 |
|
| 136 |
+
## GGUF and Quantized models
|
| 137 |
+
- https://huggingface.co/MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow-GGUF
|
| 138 |
+
|
| 139 |
## How to use
|
| 140 |
|
| 141 |
**PEFT**
|