A simulation of me: fine-tuning an LLM on 240k text messages

Re:A simulation of me: fine-tuning an LLM on 240k text messages by orenlindsey on Thursday January 04, 2024 @06:03PM (#38873533)

I wanted to do this myself but I don't have enough messages yet. Also, I wish the author shared some more technical information on how to do it.

[ Parent | on HN ]

Re:A simulation of me: fine-tuning an LLM on 240k text messages by speps on Thursday January 04, 2024 @09:24PM (#38874965)

This repo, albeit "old" in regards to how much progress there's been in LLMs, has great simple tutorials right there eg. fine-tuning GPT2 with Shakespeare: https://github.com/karpathy/nanoGPT

[ Parent | on HN ]

Re:A simulation of me: fine-tuning an LLM on 240k text messages by szmerdi on Thursday January 04, 2024 @10:31PM (#38875391)

Similar project with enough technical details: https://asmirnov.xyz/doppelganger

[ Parent | on HN ]

Re:A simulation of me: fine-tuning an LLM on 240k text messages by valray on Friday January 05, 2024 @01:13AM (#38876264)

Alexander Smirnov's article was discussed on HN: https://news.ycombinator.com/item?id=38434914

[ Parent | on HN ]