There’s been a lot of talk comparing Llama 2 and GPT-3.5. So, I made a site to let the models fight it out. Each round, pick the output you like better.<p>All open-source, and built with Elixir/Phoenix LiveView:
<a href="https://github.com/cbh123/llmboxing">https://github.com/cbh123/llmboxing</a>