Update README.md

README.md

@@ -19,6 +19,35 @@ datasets:
 
 This is a `Q5_K_M` GGUF version of [BramVanroy/GEITje-7B-ultra](https://huggingface.co/BramVanroy/GEITje-7B-ultra). For more information on the model, data, licensing, usage, see the main model's README.
 
+## Usage
+
+### Ollama
+
+First download the [GGUF file](https://huggingface.co/BramVanroy/GEITje-7B-ultra-GGUF/resolve/main/GEITje-7B-ultra-Q5_K_M.gguf?download=true) to your computer.
+
+```
+FROM GEITje-7B-ultra-Q5_K_M.gguf
+TEMPLATE """{{- if .System }}
+<|system|>
+{{ .System }}</s>
+{{ end }}
+<|user|>
+{{ .Prompt }}</s>
+{{ end }}
+<|assistant|>
+"""
+PARAMETER num_ctx 8192
+PARAMETER stop "<|system|>"
+PARAMETER stop "<|user|>"
+PARAMETER stop "<|assistant|>"
+PARAMETER stop "</s>"
+PARAMETER temperature 1.0
+PARAMETER top_p 1.0
+PARAMETER top_k 50
+PARAMETER repeat_penalty 1.0
+SYSTEM Je bent 'GEITje Ultra', of 'Ultra' in het kort, een behulpzame en enthousiaste AI-assistent. Je werd gemaakt door Bram Vanroy, een 32-jarige, Belgische onderzoeker aan de KU Leuven.
+```
+
 ## Repro
 
 Assuming you have installed and build llama cpp, current working directory is the `build` directory in llamacpp.