flan-alpaca VS alpaca-electron

If you have enough task or domain specific training data, the model size becomes less important. For example, you can take an instruction tuned smaller model like FlanT5 and fine tune for your specific case: https://github.com/declare-lab/flan-alpaca

Hi, you can try Flan-Alpaca here which does not have such restrictions: https://github.com/declare-lab/flan-alpaca

I've been following open source LLMs for a while and at first glance this doesn't seem too powerful compared to other open models, Flan-Alpaca[0] is licensed under Apache 2.0, and it seems to perform much better. Although I'm not sure about the legalities about that licensing, since it's basically Flan-T5 fine-tuned using the Alpaca dataset (which is under a Non-Commercial license).

Nonetheless, it's exciting to see all these open models popping up, and I hope that a LLM equivalent to Stable Diffusion comes sooner than later.

[0]: https://github.com/declare-lab/flan-alpaca

Someone's already taking care of that - Flan-Alpaca

I think this might be exactly what you're looking for https://github.com/declare-lab/flan-alpaca

I sympathize. There are some efforts here and there but it's not something that resonates with the enthusiast crowd much. An abandoned example here: ItsPi3141/alpaca-electron

Look up troublechute on youtube. Or alpaca electron

I recently tried alpaca electron with the 7b model. I am surprised how well this runs on my own hardware with very little CPU and RAM consumption.

Here's alpaca running in electron. Not exactly one click but close.

https://github.com/ItsPi3141/alpaca-electron