Update README.md

README.md

@@ -41,7 +41,13 @@ Currently these files will also not work with code that previously supported Fal
 
 * [2, 3, 4, 5, 6, 8-bit GGCT models for CPU+GPU inference](https://huggingface.co/TheBloke/falcon-40b-sft-mix-1226-GGML)
 * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/OpenAssistant/falcon-40b-sft-mix-1226)
-  
+
+## Prompt template
+
+```
+<|prompter|>prompt<|endoftext|><|assistant|>
+```
+
 <!-- compatibility_ggml start -->
 ## Compatibility
 
@@ -57,7 +63,7 @@ Compiling on Windows: developer cmp-nct notes: 'I personally compile it using VS
 
 Once compiled you can then use `bin/falcon_main` just like you would use llama.cpp. For example:
 ```
-bin/falcon_main -t 8 -ngl 100 -b 1 -m falcon-40b-sft-mix-1226.ggccv1.q4_K.bin -p "What is a falcon?\n### Response:"
+bin/falcon_main -t 8 -ngl 100 -b 1 -m falcon-40b-sft-mix-1226.ggccv1.q4_K.bin -p "<|prompter|>write a story about llamas<|endoftext|><|assistant|>"
 ```
 
 You can specify `-ngl 100` regardles of your VRAM, as it will automatically detect how much VRAM is available to be used.