Ever fantasized about embarking on an adventurous journey with your very own chat-GPT-style model? Open-source Large Language Models (LLMs) are at your disposal for exploration. In this guide, I'll guide you through setting up a playground using Gitpod and Ollama, turning your coding dreams into an exciting reality!
Setting Things Up:
Create a GitHub Playground:
Start your coding adventure by creating a new repository on GitHub. Consider it your coding playground where you can freely experiment with a variety of cool stuff.
Unlock Gitpod's Magic:
Open this repository in Gitpod by adding gitpod.io# to the beginning of your GitHub repository link. Witness as Gitpod works its magic, setting up a ready-to-use coding space just for your explorations.
Embarking on the Exploration:
Install Ollama:
With Gitpod ready, infuse your coding space with the magic of Ollama by entering this command in the terminal:
curl https://ollama.ai/install.sh | sh
Set the Ollama Stage:
Make your model accessible by typing the following commands in the terminal:
ollama
ollama serve
Choosing Your Adventure Companion:
Navigate to Ollama's library (https://github.com/jmorganca/ollama#model-library) and choose a model. These models are like adventurous chat buddies, capable of understanding and generating language. For this exploration, let's go with the starling-lm model.
ollama run starling-lm
Witness the magic unfold as your new language companion eagerly joins in on the exploration! Feel free to experiment with different prompts, ask intriguing questions, or weave captivating tales. The possibilities are as vast as your imagination.
Top comments (0)