In recent months, I’ve delved deep into the world of Chat GPT, and what an exciting journey it’s been. While navigating this landscape, I’ve come to a profound realization – putting all your faith in a single company’s proprietary solutions might not always be the wisest choice. This epiphany led me on a quest to explore alternatives, and my research unveiled a treasure trove of open-source language models like Llama 2 and Mistral that not only offer incredible capabilities but can also be effortlessly run on your local machine, all without costing you a dime.
Now, let’s dive into the heart of the matter: how to install one of these models.
Begin with the Basics
Start by installing Ollama, your gateway to these incredible models.
Select the model of Your Choice
From the Ollama platform, select the model you’re eager to try. Simply enter ollama run mistral, and let the magic unfold. Should the model not be already installed, it will automatically initiate the download.
Ask Away
With the model at your fingertips, there’s no need for extensive training or complex setups. Just start typing your questions or prompts, and watch the model generate responses.
If you’re looking for an uncensored language model, you can try dolphin-mixtral. This model has all the censorship removed, so please use it responsibly.
Bonus section
If you are a fan of vim. I recommend you to check out gen.nvim. This is a nice plugin for integrating llm to you text editor. Example of how it looks like can be seen below.