Skip to content

Latest commit

 

History

History
34 lines (23 loc) · 1.01 KB

README.md

File metadata and controls

34 lines (23 loc) · 1.01 KB

Prerequisites

Before you begin, ensure you have the following prerequisites:

  • .NET 10 SDK or later
  • Docker installed and running on your machine
  • An Ollama model downloaded into Ollama

To download and start Ollama on Docker using CPU, run the following command in your terminal.

docker run -d -v "c:\temp\ollama:/root/.ollama" -p 11434:11434 --name ollama ollama/ollama

To download and start Ollama on Docker using GPU, run the following command in your terminal.

docker run -d --gpus=all -v "c:\temp\ollama:/root/.ollama" -p 11434:11434 --name ollama ollama/ollama

After the container has started, launch a Terminal window for the docker container, e.g. if using docker desktop, choose Open in Terminal from actions.

From this terminal download the required models, e.g. here we are downloading the phi3 model.

ollama pull gpt-oss

Set the following environment variables:

$env:OLLAMA_ENDPOINT="http://localhost:11434"
$env:OLLAMA_MODEL_NAME="gpt-oss"