Update README.md

README.md

@@ -1 +1,11 @@
-4-bit GPTQ quantization of [VicUnlocked-alpaca-30b](https://huggingface.co/Aeala/VicUnlocked-alpaca-30b)
+4-bit GPTQ quantization of [VicUnlocked-alpaca-30b](https://huggingface.co/Aeala/VicUnlocked-alpaca-30b)
+
+**Important Note**: While this is trained on a cleaned ShareGPT dataset like Vicuna used, this was trained in the *Alpaca* format, so prompting should be something like:
+
+```
+### Instruction:
+
+<prompt> (without the <>)
+
+### Response:
+```