HN user
Definitely! We’re working on a benchmark in the coming weeks, and although we don't have data to support against qwen8b if you do try it out please let us know your experience in how it compares.
We have two models: a cloud version that we released ~1.5 mos. ago and now the local model which took us a bit more time to release. The credits only apply to the cloud version. With our cloud version, you start off with 5,000 free credits and can purchase add-on credits. You can also bring your own API keys if you want to use a commercial cloud model. For local, none of that applies. Thanks for the comment, and we need to update that page to avoid confusion.
Hey everyone, made a local LLM, configured for Home Assistant called Selora AI.
Specs: qwen3_17b_base.Q6_K.gguf selora-v047-answer.f16.gguf selora-v047-automation.f16.gguf selora-v047-clarification.f16.gguf selora-v047-command.f16.gguf
The full base model and LoRA adapters are only 3.5GB
Capabilities include configuring for smart home setup to help with answers, clarifications, commands, and creating automations in Home Assistant. The models with the LoRA adapters were made with lean scripted data made specifically for Home Assistant. A lot of work was put into this, feel free to give it a try and happy for any feedback!
That's interesting, did you find that gamification attracts users that are not actually wanting to learn a language or what do you mean?
Congrats on launch! I like how simple the layout is and you can get right to value. Any difference between an AI transcript and a transcript provided by the show itself or something like PodScripts? Also, I see the red icon next to pod eps does that indicate an AI transcript was created for this ep and not others?