nokirunner
nokirunner
### What is the issue? On Windows with version 0.1.33 assembling two models creates a path error. Version 0.1.32 works correctly. You can manifest the bug by assembling this model:...
for convenience and fluidity as nice copilot: - Remember last model selected when invoking the side panel to chat. - Refresh the focus on the updatet web page. (for example...
It would be nice to add LLava to recognize images in web pages so that it works together with RAG models.. LLava is however a textual AI model so it...
When the bot completes a response, especially if it was long, at least 30 seconds and sometimes even a minute pass before i can copy the text into the clipboard...
llamafile as LLM server for Mantella mod and Skyrim, is working nice but there is a little problem.
[Mantella mod](https://github.com/art-from-the-machine/Mantella) introduces the possibility of talking to[ Skyrim NPCs](https://www.nexusmods.com/skyrimspecialedition/mods/98631), revolutionizing the way of playing this RPG, making it a unique experience ever seen. Officially the author of the mod...
Mixed models like llama3 + llava are capable of doing superior things, such as recognizing an image of a screenshot and reconstructing it in html-type programming for example if required.....
At the moment the process of loading the embedding for rag or summarizing a web page is a bit slow, it would be useful to allow the LLM to notify...
Currently when the sidebar is invoked it emerges globally and the way it works is confusing. It does not matter if we navigate through the other tab pages of the...
Unfortunately koboldcpp with cuda crashes on my pc because my processor doesn't support avx2, while the other "blas" are too slow. So as an alternative i use [llamafile](https://github.com/Mozilla-Ocho/llamafile/), is working...
I'm back! ... it's the right time to add the reflection function.. You already know what I mean.. get inspiration from here: https://github.com/antibitcoin/ReflectionAnyLLM I know it's a piece of cake...