Update README.md

README.md

@@ -14,4 +14,21 @@ bofenghuang/vigostral-7b-chat
   
 base model : jpacifico/French-Alpaca-7B-Instruct-beta  
 
-This quantized q8_0 GGUF version can be used on a CPU device, compatible with llama.cpp and LM Studio.
+This quantized q8_0 GGUF version can be used on a CPU device, compatible with llama.cpp Ollama and LM Studio.
+
+Ollama Modelfile example :
+
+```bash
+FROM ./Vigalpaca-French-7B-ties-quantized-q8_0.gguf
+
+PARAMETER stop {
+    "stop": [
+        "[INST]",
+        "[/INST]"
+    ]
+}
+
+TEMPLATE """
+[INST] {{ .System }} {{ .Prompt }} [/INST]
+"""
+```