Fine-Tune Any LLM, Convert to GGUF, And Deploy Using Ollama

[@chukypedro818]

insightful, thanks for this video

[@BoeroBoy]

Love this. If you add the -ngl option to llama-server it will offload GGML layers to GPU though - as run here you're only using CPU for your test.

[@Baxate]

Very detailed work, great work Ishan and the Brev Team!

[@GabFelix-kv3fq]

Hello! Great tutorial! I can't seem to find this launchable/notebook on gguf and ollama in the console brev website, is it still available or was this taken down? Wanting to do some tinkering on this as well.