Ollama

Demonstration Environment

Development Board: Jetson Nano

SD (TF) Card: 64GB

xxxxxxxxxx
Recommended for models with 4B parameters or less

Ollama is an open-source tool designed to simplify the deployment and operation of large language models, allowing users to use high-quality language models in a local environment.

Large Language Models (LLMs)

Large Language Models (LLMs) are a type of advanced text generation system based on artificial intelligence technology. Their main feature is their ability to learn and understand human language using large amounts of training data and generate natural and fluent text.

Ollama Installation

This tutorial demonstrates how to install Ollama on a Jetson Nano using a script.

Script Installation

Note: Failure to pull the Ollama file is normal. You can try multiple times or use a proxy to pull the file. You will need to search online for proxy setup instructions.

xxxxxxxxxx
sudo apt install curl
curl -fsSL https://ollama.com/install.sh | sh

Using Ollama

Type "ollama" in the terminal to see the following prompt:

Ollama Uninstall

• Removing the service

xxxxxxxxxx
sudo systemctl stop ollama
sudo systemctl disable ollama
sudo rm /etc/systemd/system/ollama.service

• Removing files

xxxxxxxxxx
sudo rm $(which ollama)

• Removing the model and service user and group

xxxxxxxxxx
sudo rm -r /usr/share/ollama
sudo userdel ollama
sudo groupdel ollama

References

Ollama

Official Website: https://ollama.com/

GitHub: https://github.com/ollama/ollama