Update README.md

README.md

@@ -10,10 +10,31 @@ datasets:
 
 [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) trained with some of [teknium/openhermes](https://huggingface.co/datasets/teknium/openhermes), in Alpaca format.
 
+<br />
+<br />
 
+# Prompt Format
 
+Both the default Mistral-Instruct tags and Alpaca are fine, so either:
+```
+<s>[INST] {sys_prompt} {instruction} [/INST] 
+```
+
+```
+{sys_prompt}
+
+### Instruction:
+{instruction}
+
+### Response:
+
+```
+The tokenizer defaults to Mistral-style.
+
+<br />
+<br />
 
-## 💻 Usage
+# Usage
 
 ```python
 from transformers import AutoTokenizer