Update README.md

README.md

@@ -34,6 +34,24 @@ GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/gger
 * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/airoboros-13B-1.1-GGML)
 * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/airoboros-13B-1.1-fp16)
 
+## Prompt example
+
+Please see the base Airoboros model README below, or by [going to the original model](https://huggingface.co/jondurbin/airoboros-13b-gpt4-1.1), for more details.
+```
+BEGININPUT
+BEGINCONTEXT
+url: https://some.web.site/123
+date: 2023-06-01
+... other metdata ...
+ENDCONTEXT
+[insert your text blocks here]
+ENDINPUT
+[add as many other blocks, in the exact same format]
+BEGININSTRUCTION
+[insert your instruction(s).  The model was tuned with single questions, paragraph format, lists, etc.]
+ENDINSTRUCTION
+```
+
 <!-- compatibility_ggml start -->
 ## Compatibility