alt Hacker NewsThis is an interesting project and in some ways similar to an idea I had. My idea was actually just to aggregate primary texts (whatever public domain versions are available) for a wide range of philosophical and spiritual work and provide an easy way to include it as context in straight-forward LLM calls.
I've skimmed this announcement, your github repo and your site and it isn't clear to me, are these custom models? Are they fine-tuned from some base model? e.g. do you have 30 separate models?
We have no custom models and no fine tuning. It is the base model, Qwen3 235B for the free tier and we recommend Qwen3.6 27B for the local mode. So the figures are data, not weights. We have instruction files for every figure and additional voice profiles for the councils. The work was put into the iterations to improve the instructions. It is possible to fetch them from the CDN, for example: https://media.agoracosmica.org/instructions/jung/free_conver...
I like your primary texts idea. For our case we tried to keep the instructions lean to have them around 4k tokens, so that it also works in local mode for users with limited context.