I want to like Ollama, but I wish it didn't obfuscate the actual directives (full prompt) that it sends to the underlying model. Ollama uses a custom templatizing script in its Modelfiles to translate user input into the format that a specific model expects ([INST], etc), but it can be difficult to tell if it's working as expected because it won't show up in the logs at all.

Other than that it's a great project - very easy to get started and has a solid API implementation. I've got it running on both a Win 10 + WSL2 docker and on a Mac M1.