Learnings from fine-tuning LLM on my Telegram messages

Re:Learnings from fine-tuning LLM on my Telegram messages by siquick on Monday November 27, 2023 @04:12PM (#38438370)

Excuse the ignorance but are you using these instances to fine tune a “fresh install” of a model, and then when you’ve finished fine tuning it do you download the whole model from the instance for use somewhere else?

[ Parent | on HN ]

Re:Learnings from fine-tuning LLM on my Telegram messages by furiousteabag on Monday November 27, 2023 @10:53PM (#38442126)

First I download the weights of the base pre-trained model to the VM instance. Then I upload my data there. Afterward, I fine-tune either LoRA or full and when training finishes, from the VM instance I download the adapters in case of LoRA and full weights in case of full fine-tune and run inference on a way less expensive instance (usually 3090).

[ Parent | on HN ]