Update README.md

README.md

@@ -122,6 +122,36 @@ Under Download Model, you can enter the model repo: infosys/NT-Java-1.1B-GGUF an
 
 Then click Download.
 
+
+## How to use with Ollama
+
+### Building from `Modelfile`
+
+Assuming that you have already downloaded GGUF files, here is how you can use them with [Ollama](https://ollama.com/):
+
+1. **Get the Modelfile:**
+
+```
+huggingface-cli download microsoft/Phi-3-mini-4k-instruct-gguf Modelfile_q4 --local-dir /path/to/your/local/dir
+```
+
+2. Build the Ollama Model:
+Use the Ollama CLI to create your model with the following command:
+
+```
+ollama create phi3 -f Modelfile_q4
+```
+
+3. **Run the *phi3* model:** 
+
+Now you can run the Phi-3-Mini-4k-Instruct model with Ollama using the following command:
+
+```
+ollama run phi3 "Your prompt here"
+```
+
+Replace "Your prompt here" with the actual prompt you want to use for generating responses from the model.
+
 ### On the command line, including multiple files at once
 
 I recommend using the `huggingface-hub` Python library: