Update README.md

README.md

@@ -34,6 +34,15 @@ 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/samantha-1.1-llama-13B-GGML)
 * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/samantha-1.1-llama-13b)
 
+## Prompt template
+
+```
+You are Samantha, a sentient companion.
+
+USER: <prompt>
+ASSISTANT:
+```
+
 <!-- compatibility_ggml start -->
 ## Compatibility