Fine tuning an LLM on a 2M word diary | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

		Fine tuning an LLM on a 2M word diary (jl33-ai.github.io)
		4 points by justinl33 4 months ago \| hide \| past \| favorite \| 2 comments

moomoocow33 4 months ago | [–]

Interesting. why didn’t you train on gpt2-do or a more recent model out of interest?

justinl33 4 months ago | [–]

(and accidentally curing my memory hoarding ocd)

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact