Update README.md
Browse files
README.md
CHANGED
|
@@ -22,6 +22,10 @@ The choice was fully intentional. I briefly considered a FFT but for this partic
|
|
| 22 |
- Use the templates in [Quant-Cartel/Recommended-Settings](https://huggingface.co/Quant-Cartel/Recommended-Settings) under the `SorcererLM`-folder.
|
| 23 |
- Or Vicuna 1.1 and a sane context template. It's somewhat sensitive to samplers, I'd recommend Temperature 1, MinP 0.05 and a dash of DRY but YMMV. Shorter prompts seem to work better, too.
|
| 24 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
## Quantized Versions
|
| 26 |
|
| 27 |
- [iMat GGUFs](https://huggingface.co/Quant-Cartel/SorcererLM-8x22b-iMat-GGUF)
|
|
|
|
| 22 |
- Use the templates in [Quant-Cartel/Recommended-Settings](https://huggingface.co/Quant-Cartel/Recommended-Settings) under the `SorcererLM`-folder.
|
| 23 |
- Or Vicuna 1.1 and a sane context template. It's somewhat sensitive to samplers, I'd recommend Temperature 1, MinP 0.05 and a dash of DRY but YMMV. Shorter prompts seem to work better, too.
|
| 24 |
|
| 25 |
+
## Control Vectors
|
| 26 |
+
|
| 27 |
+
[gghfez](https://huggingface.co/gghfez/) has trained control vectors for this model, available [here (gghfez/Sorcerer_creative-writing-control-vectors)](https://huggingface.co/gghfez/Sorcerer_creative-writing-control-vectors)
|
| 28 |
+
|
| 29 |
## Quantized Versions
|
| 30 |
|
| 31 |
- [iMat GGUFs](https://huggingface.co/Quant-Cartel/SorcererLM-8x22b-iMat-GGUF)
|