nokirunner

I'm using Windows, I don't have WSL, and with windows native ollama, bun works with Edge, even if I have to refresh every time.. With brave it seems to not...

with hermes 2 pro 7b it seems to work best, even if the code it generates is not usable due to some syntax errors.. I have this similar error with...

> Not likely. You are basically asking if it is possible to create a system prompt for a much smaller model to behave like GPT-4. > > If it was...

@ARajgor with the[ "codeqwen"](https://ollama.com/library/codeqwen) model (It works with other models too) devika performed the tasks but instead of giving me the code it gave me the example in the agent...

I had the same error the first time I tried creating my own model from gguf. Then I tried this other modified version that someone else created, and it worked....

This of transforming the names of the .gguf files into hash names is a terrible method, the llm models are large and take up a lot of space at a...

@jmorganca on windows, native ollama v.1.38 the images are interpreted only for the first one, the subsequent ones are given a description of the first one.

It seemed strange to me that i couldn't close the sidepannel, mystery solved, in brave browser it doesn't appear. 

... just for fun .. 👍 with as rag: mxbai-embed-large 👯 😄     

Bravo! step by step it begins to be a practical application