Update README.md

README.md

@@ -21,6 +21,8 @@ The goal was a merge model more varied in its outputs, a goal which inherently h
 
 Sampler settings: Tested lightly with temperature=0.7 and minP=0.01. For greater creativity, boost temperature.
 
+Prompts: Alpaca format natively supported, although ChatML was used during testing.
+
 Download options:
 * [full weights](https://huggingface.co/grimjim/fireblossom-32K-7B)
 * [Q8_0 GGUF](https://huggingface.co/grimjim/fireblossom-32K-7B-GGUF)