Update README.md
Browse files
README.md
CHANGED
|
@@ -15,6 +15,8 @@ Since 7B models tend to be less capable all-rounders, more emphasis was put on i
|
|
| 15 |
|
| 16 |
In technical terms, the Hermes-2 core starts at 90% strength before fading away completely at the 12th layer level, where Stable Beluga (and Kimiko) handle the more intricate linguistic aspects.
|
| 17 |
|
|
|
|
|
|
|
| 18 |
## Prompt Format
|
| 19 |
|
| 20 |
Due to its Hermes-2 core this model works best with Alpaca formatting, so for optimal model performance, use:
|
|
|
|
| 15 |
|
| 16 |
In technical terms, the Hermes-2 core starts at 90% strength before fading away completely at the 12th layer level, where Stable Beluga (and Kimiko) handle the more intricate linguistic aspects.
|
| 17 |
|
| 18 |
+
Quantized models are available from TheBloke: [GGML](https://huggingface.co/TheBloke/MythoLogic-Mini-7b-GGML) - [GPTQ](https://huggingface.co/TheBloke/MythoLogic-Mini-7b-GPTQ) (You're the best!)
|
| 19 |
+
|
| 20 |
## Prompt Format
|
| 21 |
|
| 22 |
Due to its Hermes-2 core this model works best with Alpaca formatting, so for optimal model performance, use:
|