secondbrain
secondbrain copied to clipboard
juliooa
Multi-platform desktop app to download and run Large Language Models(LLM) locally in your computer.
I think this because any AVX on my 2xprocessor 24thread computer....? I use with the appimage linux.
LammaCPP introduced metal support, for M1/M2 blazing fast inference for GGML's.
Hi Julio, When do you expect to have finish the "Query your documents" function? This function looks like a very attractive proposition of your product, given that I can find...
For example, if the MBT model had MPT selected, and I swap over to Wizard-Vicuna while choosing Llamma, the MBT model will select llama as the default setting.
When multiple models are enabled, their activation icons turn orange, and de-selection isn't possible. Rebooting the app will default to the most recently activated model.
When selecting "MBT" for Wizard-Vicuna 7b, this error happens. Selecting Llamma works fine.
I downloaded Wizard-Vicuna 7b uncensored, and the app gave a number of notifications. I think they were for the...?variants?, such as MPT, GPT, and so forth.
Title, but with a twist: It now works. It was only when I didn't have a model activated that the 404 was happening.
As said below: (Wizard-Vicuna 13b Uncensored) > Yes, my local model has Wi-Fi capabilities built into its hardware so it can connect to the internet wirelessly via any available network...
As said on the tin. I tried to activate a model, Wizard-Vicuna 7b Uncensored, and got this error.