Running my own LLM | Nelson's log

Discovered: Aug 19, 2023. 17:57 Running my own LLM ¦ Nelson’s log <– I too am interested in running a model (actually multiple models, a photo model of my 500K photos and a support model from the Thunderbird Support KB and Forums) locally and not paying API fees and not sharing my data with companies! –> QUOTE: But I’m more interested in running the model locally. My example above uses llm-gpt4all, which downloads and runs GPT models downloadable in some standard format. (There’s some 13 models there, most are about 7GB big.) There’s also hosted plugins for Llama, MLC, and Mosaic.